Dissertations / Theses: 'Probabilistic Robotics'

1

Chechetka, Anton. "Query-Specific Learning and Inference for Probabilistic Graphical Models." Research Showcase @ CMU, 2011. http://repository.cmu.edu/dissertations/171.

Full text

Abstract:

In numerous real world applications, from sensor networks to computer vision to natural text processing, one needs to reason about the system in question in the face of uncertainty. A key problem in all those settings is to compute the probability distribution over the variables of interest (the query) given the observed values of other random variables (the evidence). Probabilistic graphical models (PGMs) have become the approach of choice for representing and reasoning with high-dimensional probability distributions. However, for most models capable of accurately representing real-life distributions, inference is fundamentally intractable. As a result, optimally balancing the expressive power and inference complexity of the models, as well as designing better approximate inference algorithms, remain important open problems with potential to significantly improve the quality of answers to probabilistic queries. This thesis contributes algorithms for learning and approximate inference in probabilistic graphical models that improve on the state of the art by emphasizing the computational aspects of inference over the representational properties of the models. Our contributions fall into two categories: learning accurate models where exact inference is tractable and speeding up approximate inference by focusing computation on the query variables and only spending as much effort on the remaining parts of the model as needed to answer the query accurately. First, for a case when the set of evidence variables is not known in advance and a single model is needed that can be used to answer any query well, we propose a polynomial time algorithm for learning the structure of tractable graphical models with quality guarantees, including PAC learnability and graceful degradation guarantees. Ours is the first efficient algorithm to provide this type of guarantees. A key theoretical insight of our approach is a tractable upper bound on the mutual information of arbitrarily large sets of random variables that yields exponential speedups over the exact computation. Second, for a setting where the set of evidence variables is known in advance, we propose an approach for learning tractable models that tailors the structure of the model for the particular value of evidence that become known at test time. By avoiding a commitment to a single tractable structure during learning, we are able to expand the representation power of the model without sacrificing efficient exact inference and parameter learning. We provide a general framework that allows one to leverage existing structure learning algorithms for discovering high-quality evidence-specific structures. Empirically, we demonstrate state of the art accuracy on real-life datasets and an order of magnitude speedup. Finally, for applications where the intractable model structure is a given and approximate inference is needed, we propose a principled way to speed up convergence of belief propagation by focusing the computation on the query variables and away from the variables that are of no direct interest to the user. We demonstrate significant speedups over the state of the art on large-scale relational models. Unlike existing approaches, ours does not involve model simplification, and thus has an advantage of converging to the fixed point of the full model. More generally, we argue that the common approach of concentrating on the structure of representation provided by PGMs, and only structuring the computation as representation allows, is suboptimal because of the fundamental computational problems. It is the computation that eventually yields answers to the queries, so directly focusing on structure of computation is a natural direction for improving the quality of the answers. The results of this thesis are a step towards adapting the structure of computation as a foundation of graphical models.

APA, Harvard, Vancouver, ISO, and other styles

2

Li, Yueqiao. "Incremental high quality probabilistic roadmap construction for robot path planning." Thesis, University of Bedfordshire, 2009. http://hdl.handle.net/10547/134950.

Full text

Abstract:

In robotics, path planning refers to the process of establishing paths for robots to move from initial positions to goal positions without colliding into any obstacle within specified environments. Constructing roadmaps and searching for paths in the roadmaps is one of the most commonly used methodologies adopted in path planning. However, most sampling-based path planners focus on improving the speed of constructing roadmaps without taking into account the quality. Therefore, they often produce poor-quality roadmaps. Poor-quality roadmaps can cause problems, such as time-consuming path searches, poor quality path production, and even failure of the searching. This research aims to develop a novel sampling-based path planning algorithm which is able to incrementally construct high-quality roadmaps while answering path queries for robots with many degrees of freedom. A novel K-order surrounding roadmap (KSR) concept is proposed in this research based on a thorough investigation into the criteria of high-quality roadmaps, including the criteria themselves and the relationships between them. A KSR contains K useful cycles. There exist a value T for which we can say, with confidence, that the KSR is a high quality roadmap when K=T. A new sampling-based path planning algorithm, known as the KSR path planner that is able to construct a roadmap incrementally while answering path queries, is also developed. The KSR path planner can be employed to answer path queries without requiring any pre-processing. The planner grows trees from the initial and goal III configurations of a path query and connects these two trees to obtain a path. The path planner retains useful vertices of the trees and uses these to construct the roadmap and adds useful cycles to the existing roadmap in order to improve the quality. The roadmap constructed can be used to answer further queries. With the KSR path planner algorithm, there is no need to calculate the value of K to construct a high quality roadmap in advance. The quality of the roadmap improves as the KSR path planner answer queries until the roadmap is able to answer any path queries and no further useful cycles can be added into the roadmap. If the number of path queries is infinite, a high quality KSR can be constructed. The novelty of this KSR path planner is twofold. Firstly, it employs a vertex category classifier to understand local environments where roadmap vertices reside. The classifier is developed using a decision tree method. The classifier is able to classify vertices in a roadmap based on the region information stored in the vertices and their neighbours within a certain distance. The region information stored in the vertices is obtained while the edges connecting the vertices are added to the roadmap. Therefore, employing the vertex category classifier does not require much additional execution time. Secondly, the KSR path planner selects suitable developed strategies to prune the existing roadmap and add useful cycles according to the identified local environments where the vertices reside to improve the quality of the existing roadmap. Experimental results show that the KSR path planner can construct a roadmap and improve the quality of the roadmap incrementally while answering path queries until the roadmap can answer all the path queries without any pre-processing stage. The roadmap constructed by the KSR path planner then achieves better quality than the roadmaps constructed by Reconfigurable Random Forest (RRF) path planner and traditional probabilistic roadmap (PRM) path planner.

APA, Harvard, Vancouver, ISO, and other styles

3

Lewis, Amy Jeannette. "Surveying Underwater Shipwrecks with Probabilistic Roadmaps." DigitalCommons@CalPoly, 2019. https://digitalcommons.calpoly.edu/theses/2059.

Full text

Abstract:

Almost two thirds of the Earth's surface is covered in ocean, and yet, only about 5% of it is mapped. There are an unknown amount of sunken ships, planes, and other artifacts hidden below the sea. Extensive search via boat and a sonar tow fish following a standard lawnmower pattern is used to identify sites of interest. Then, if a site has been determined to potentially be historically significant, the most common next step is a survey by either a human dive team or remotely operated vehicle. These are time consuming, error prone, and potentially dangerous options, but autonomous underwater vehicles (AUVs) are a possible solution. This thesis introduces a system for automatically generating paths for AUVs to survey and map shipwrecks. Most AUVs include software to set a lawnmower path for a given region of ocean, and individualized paths can be set via specifying GPS encoded nodes for the AUV to pass through. This thesis presents an algorithm for generating an individualized path that permits the AUV, equipped with a camera to "see" all sides of a region of interest (i.e. a shipwreck). This allows the region of interest to be completely documented. Photogrammetry can then be used to reconstruct a three-dimensional model, but a path is needed to do so. Paths are generated by a probabilistic roadmap algorithm that uses a rapidly-exploring random tree to quickly cover the volume of exploration space and generate small maps with good coverage. The roadmap is constructed out of nodes, each having its own weight. The weight of a given node is calculated using an objective function which measures an approximate view coverage by casting rays from the virtual view and intersecting them with the region of interest. In addition, the weight of a node is increased if this node allows the AUV to see a new side of the region of interest. In each iteration of the algorithm, a node to expand off of is selected based off its location in space or its high weight, a new node with a given amount of freedom is generated, and then added to the roadmap. The algorithm has degrees of freedom in position, pitch, and yaw as well as the objective function to encourage the path to see all sides of the region of interest. Once all sides of the region of interest have been viewed, a path is determined to be complete. The algorithm was tested in a virtual world where the virtual camera acted as the AUV. All of the images collected from our automatically generated path were used to create 3D models and point clouds using photogrammetry. To measure the effectiveness of our paths versus the pre-packaged lawnmower paths, the 3D models and point clouds created from our algorithm were compared to those generated from running a standard lawnmower pattern. The paths generated by our algorithm captured images that could be used in a 3D reconstruction which were more detailed and showed better coverage of the region of interest than those from the lawnmower pattern.

APA, Harvard, Vancouver, ISO, and other styles

4

Cummins, Mark. "Probabilistic localization and mapping in appearance space." Thesis, University of Oxford, 2009. http://ora.ox.ac.uk/objects/uuid:a34370f2-a2a9-40b5-9a2d-1c8c616ff07a.

Full text

Abstract:

This thesis is concerned with the problem of place recognition for mobile robots. How can a robot determine its location from an image or sequence of images, without any prior knowledge of its position, even in a world where many places look identical? We outline a new probabilistic approach to the problem, which we call Fast Appearance Based Mapping or FAB-MAP. Our map of the environment consists of a set of discrete locations, each with an associated appearance model. For every observation collected by the robot, we compute a probability distribution over the map, and either create a new location or update our belief about the appearance of an existing location. The technique can be seen as a new type of SLAM algorithm, where the appearance of locations (rather than their position) is subject to estimation. Unlike existing SLAM systems, our appearance based technique does not rely on keeping track of the robot in any metric coordinate system. Thus it is applicable even when informative observations are available only intermittently. Solutions to the loop closure detection problem, the kidnapped robot problem and the multi-session mapping problem arise as special cases of our general approach. Abstract Our probabilistic model introduces several technical advances. The model incorporates correlations between visual features in a novel way, which is shown to improve system performance. Additionally, we explicitly compute an approximation to the partition function in our Bayesian formulation, which provides a natural probabilistic measure of when a new observation should be assigned to a location not already present in the map. The technique is applicable even in visually repetitive environments where many places look the same. Abstract Finally, we define two distinct approximate inference procedures for the model. The first of these is based on concentration inequalities and has general applicability beyond the problem considered in this thesis. The second approach, built on inverted index techniques, is tailored to our specific problem of place recognition, but achieves extreme efficiency, allowing us to apply FAB-MAP to navigation problems on the largest scale. The thesis concludes with a visual SLAM experiment on a trajectory 1,000 km long. The system successfully detects loop closures with close to 100% precision and requires average inference time of only 25 ms by the end of the trajectory.

APA, Harvard, Vancouver, ISO, and other styles

5

Dondrup, Christian. "Human-robot spatial interaction using probabilistic qualitative representations." Thesis, University of Lincoln, 2016. http://eprints.lincoln.ac.uk/28665/.

Full text

Abstract:

Current human-aware navigation approaches use a predominantly metric representation of the interaction which makes them susceptible to changes in the environment. In order to accomplish reliable navigation in ever-changing human populated environments, the presented work aims to abstract from the underlying metric representation by using Qualitative Spatial Relations (QSR), namely the Qualitative Trajectory Calculus (QTC), for Human-Robot Spatial Interaction (HRSI). So far, this form of representing HRSI has been used to analyse different types of interactions online. This work extends this representation to be able to classify the interaction type online using incrementally updated QTC state chains, create a belief about the state of the world, and transform this high-level descriptor into low-level movement commands. By using QSRs the system becomes invariant to change in the environment, which is essential for any form of long-term deployment of a robot, but most importantly also allows the transfer of knowledge between similar encounters in different environments to facilitate interaction learning. To create a robust qualitative representation of the interaction, the essence of the movement of the human in relation to the robot and vice-versa is encoded in two new variants of QTC especially designed for HRSI and evaluated in several user studies. To enable interaction learning and facilitate reasoning, they are employed in a probabilistic framework using Hidden Markov Models (HMMs) for online classiffication and evaluation of their appropriateness for the task of human-aware navigation. In order to create a system for an autonomous robot, a perception pipeline for the detection and tracking of humans in the vicinity of the robot is described which serves as an enabling technology to create incrementally updated QTC state chains in real-time using the robot's sensors. Using this framework, the abstraction and generalisability of the QTC based framework is tested by using data from a different study for the classiffication of automatically generated state chains which shows the benefits of using such a highlevel description language. The detriment of using qualitative states to encode interaction is the severe loss of information that would be necessary to generate behaviour from it. To overcome this issue, so-called Velocity Costmaps are introduced which restrict the sampling space of a reactive local planner to only allow the generation of trajectories that correspond to the desired QTC state. This results in a exible and agile behaviour I generation that is able to produce inherently safe paths. In order to classify the current interaction type online and predict the current state for action selection, the HMMs are evolved into a particle filter especially designed to work with QSRs of any kind. This online belief generation is the basis for a exible action selection process that is based on data acquired using Learning from Demonstration (LfD) to encode human judgement into the used model. Thereby, the generated behaviour is not only sociable but also legible and ensures a high experienced comfort as shown in the experiments conducted. LfD itself is a rather underused approach when it comes to human-aware navigation but is facilitated by the qualitative model and allows exploitation of expert knowledge for model generation. Hence, the presented work bridges the gap between the speed and exibility of a sampling based reactive approach by using the particle filter and fast action selection, and the legibility of deliberative planners by using high-level information based on expert knowledge about the unfolding of an interaction.

APA, Harvard, Vancouver, ISO, and other styles

6

Hoffmann, Jan. "Reactive probabilistic belief modeling for mobile robots." Doctoral thesis, Humboldt-Universität zu Berlin, Mathematisch-Naturwissenschaftliche Fakultät II, 2008. http://dx.doi.org/10.18452/15731.

Full text

Abstract:

Trotz der Entwicklungen der letzten Jahre kommt es in der Robotik immer noch vor, dass mobile Roboter scheinbar sinnlose Handlungen ausführen. Der Grund für dieses Verhalten ist oftmals, dass sich das interne Weltbild des Roboters stark von der tatsächlichen Situation, in der sich der Roboter befindet, unterscheidet. Die darauf basierende Robotersteuerung wählt infolge dieser Diskrepanz scheinbar sinnlose Handlungen aus. Eine wichtige Ursache von Lokalisierungsfehlern stellen Kollisionen des Roboters mit anderen Robotern oder seiner Umwelt dar. Mit Hilfe eines Hindernismodells wird der Roboter in die Lage versetzt, Hindernisse zu erkennen, sich ihre Position zu merken und Kollisionen zu vermeiden. Ferner wird in dieser Arbeit eine Erweiterung der Bewegungsmodellierung beschrieben, die die Bewegung in Mobilitätszustände untergliedert, die jeweils ein eigenes Bewegungsmodell besitzen und die mit Hilfe von Propriozeption unterschieden werden können. Mit Hilfe der Servo-Motoren des Roboters lässt sich eine Art Propriozeption erzielen: der momentan gewünschte, angesteuerte Gelenkwinkel wird mit dem tatsächlich erreichten, im Servo-Motor gemessenen Winkel verglichen. Dieser "Sinn" erlaubt eine bessere Beschreibung der Roboterbewegung. Verbesserung des Sensormodells wird das bisher wenig untersuchte Konzept der Negativinformation, d.h. das Ausbleiben einer erwarteten Messung, genutzt. Bestehende Lokalisierungsansätze nutzen diese Information nicht, da es viele Gründe für ein Ausbleiben einer erwarteten Messung gibt. Eine genaue Modellierung des Sensors ermöglicht es jedoch, Negativinformation nutzbar zu machen. Eine Weltmodellierung, die Negativinformation verarbeiten kann, ermöglicht eine Lokalisierung des Roboters in Situationen, in denen einzig auf Landmarken basierende Ansätze scheitern.
Despite the dramatic advancements in the field of robotics, robots still tend to exhibit erratic behavior when facing unexpected situations, causing them, for example, to run into walls. This is mainly the result of the robot''s internal world model no longer being an accurate description of the environment and the robot''s localization within the environment. The key challenge explored in this dissertation is the creation of an internal world model for mobile robots that is more robust and accurate in situations where existing approaches exhibit a tendency to fail. First, means to avoid a major source of localization error - collisions - are investigated. Efficient collision avoidance is achieved by creating a model of free space in the direct vicinity of the robot. The model is based on camera images and serves as a short term memory, enabling the robot to avoid obstacles that are out of sight. It allows the robot to efficiently circumnavigate obstacles. The motion model of the robot is enhanced by integrating proprioceptive information. Since the robot lacks sensors dedicated to proprioception, information about the current state and configuration of the robot''s body is generated by comparing control commands and actual motion of individual joints. This enables the robot to detect collisions with other robots or obstacles and is used as additional information for modeling locomotion. In the context of sensing, the notion of negative information is introduced. Negative information marks the ascertained absence of an expected observation in feature-based localization. This information is not used in previous work on localization because of the several reasons for a sensor to miss a feature, even if the object lies within its sensing range. This information can, however, be put to good use by carefully modeling the sensor. Integrating negative information allows the robot to localize in situations where it cannot do so based on landmark observation alone.

APA, Harvard, Vancouver, ISO, and other styles

7

Zhai, Menghua. "Deep Probabilistic Models for Camera Geo-Calibration." UKnowledge, 2018. https://uknowledge.uky.edu/cs_etds/74.

Full text

Abstract:

The ultimate goal of image understanding is to transfer visual images into numerical or symbolic descriptions of the scene that are helpful for decision making. Knowing when, where, and in which direction a picture was taken, the task of geo-calibration makes it possible to use imagery to understand the world and how it changes in time. Current models for geo-calibration are mostly deterministic, which in many cases fails to model the inherent uncertainties when the image content is ambiguous. Furthermore, without a proper modeling of the uncertainty, subsequent processing can yield overly confident predictions. To address these limitations, we propose a probabilistic model for camera geo-calibration using deep neural networks. While our primary contribution is geo-calibration, we also show that learning to geo-calibrate a camera allows us to implicitly learn to understand the content of the scene.

APA, Harvard, Vancouver, ISO, and other styles

8

Fasel, Ian Robert. "Learning real-time object detectors probabilistic generative approaches /." Connect to a 24 p. preview or request complete full text in PDF format. Access restricted to UC campuses, 2006. http://wwwlib.umi.com/cr/ucsd/fullcit?p3216357.

Full text

Abstract:

Thesis (Ph. D.)--University of California, San Diego, 2006.
Title from first page of PDF file (viewed July 24, 2006). Available via ProQuest Digital Dissertations. Vita. Includes bibliographical references (p. 87-91).

APA, Harvard, Vancouver, ISO, and other styles

9

Soysal, Onur. "A Systematic Study Of Probabilistic Aggregation Strategies In Swarm Robotic Systems." Master's thesis, METU, 2005. http://etd.lib.metu.edu.tr/upload/12606460/index.pdf.

Full text

Abstract:

In this study, a systematic analysis of probabilistic aggregation strategies in swarm robotic systems is presented. A generic aggregation behavior is proposed as a combination of four basic behaviors: obstacle avoidance, approach, repel, and wait. The latter three basic behaviors are combined using a three-state finite state machine with two probabilistic transitions among them. Two different metrics were used to compare performance of strategies. Through systematic experiments, how the aggregation performance, as measured by these two metrics, change 1) with transition probabilities, 2) with number of simulation steps, and 3) with arena size, is studied.

APA, Harvard, Vancouver, ISO, and other styles

10

Peynot, Thierry. "Selection et controle de modes de deplacement pour un robot mobile autonome en environnements naturels." Thesis, Institut National Polytechnique de Toulouse, 2006. http://ethesis.inp-toulouse.fr/archive/00000395/.

Full text

Abstract:

Autonomous navigation and locomotion of a mobile robot in natural environments remain a rather open issue. Several functionalities are required to complete the usual perception/decision/action cycle. They can be divided in two main categories : navigation (perception and decision about the movement) and locomotion (movement execution). In order to be able to face the large range of possible situations in natural environments, it is essential to make use of various kinds of complementary functionalities, defining various navigation and locomotion modes. Indeed, a number of navigation and locomotion approaches have been proposed in the literature for the last years, but none can pretend being able to achieve autonomous navigation and locomotion in every situation. Thus, it seems relevant to endow an outdoor mobile robot with several complementary navigation and locomotion modes. Accordingly, the robot must also have means to select the most appropriate mode to apply. This thesis proposes the development of such a navigation/locomotion mode selection system, based on two types of data: an observation of the context to determine in what kind of situation the robot has to achieve its movement and an evaluation of the behavior of the current mode, made by monitors which influence the transitions towards other modes when the behavior of the current one is considered as non satisfying. Hence, this document introduces a probabilistic framework for the estimation of the mode to be applied, some navigation and locomotion modes used, a qualitative terrain representation method (based on the evaluation of a difficulty computed from the placement of the robot's structure on a digital elevation map), and monitors that check the behavior of the modes used (evaluation of rolling locomotion efficiency, robot's attitude and configuration watching. . .). Some experimental results obtained with those elements integrated on board two different outdoor robots are presented and discussed.

APA, Harvard, Vancouver, ISO, and other styles

11

Lavis, Benjamin Mark Mechanical &amp Manufacturing Engineering Faculty of Engineering UNSW. "Spatially reconfigurable and non-parametric representation of dynamic bayesian beliefs." Publisher:University of New South Wales. Mechanical & Manufacturing Engineering, 2008. http://handle.unsw.edu.au/1959.4/41468.

Full text

Abstract:

This thesis presents a means for representing and computing beliefs in the form of arbitrary probability density functions with a guarantee for the ongoing validity of such beliefs over indefinte time frames. The foremost aspect of this proposal is the introduction of a general, theoretical, solution to the guaranteed state estimation problem from within the recursive Bayesian estimation framework. The solution presented here determines the minimum space required, at each stage of the estimation process, to represent the belief with limited, or no, loss of information. Beyond this purely theoretical aspect, a number of numerical techniques, capable of determining the required space and performing the appropriate spatial reconfiguration, whilst also computing and representing the belief functions, are developed. This includes a new, hybrid particle-element approach to recursive Bayesian estimation. The advantage of spatial reconfiguration as presented here is that it ensures that the belief functions consider all plausible states of the target system, without altering the recursive Bayesian estimation equations used to form those beliefs. Furthermore, spatial reconfiguration as proposed in this dissertation enhances the estimation process since it allows computational resources to be concentrated on only those states considered plausible. Autonomous maritime search and rescue is used as a focus application throughout this dissertation since the searching-and-tracking requirements of the problem involve uncertainty, the use of arbitrary belief functions and dynamic target systems. Nevertheless, the theoretical development in this dissertation has been kept general and independent of an application, and as such the theory and techniques presented here may be applied to any problem involving dynamic Bayesian beliefs. A number of numerical experiments and simulations show the efficacy of the proposed spatially reconfigurable representations, not only in ensuring the validity of the belief functions over indefinite time frames, but also in reducing computation time and improving the accuracy of function approximation. Improvements of an order of magnitude were achieved when compared with traditional, spatially static representations.

APA, Harvard, Vancouver, ISO, and other styles

12

McNeil, Joshua G. "Autonomous Fire Suppression Using Feedback Control for Robotic Firefighting." Diss., Virginia Tech, 2016. http://hdl.handle.net/10919/64784.

Full text

Abstract:

There is an increasing demand for robotics in dangerous and extreme conditions to limit human exposure and risk. An area in which robots are being considered as a support tool is in firefighting operations to reduce the number of firefighter injuries and deaths. One such application is to increase firefighting performance through localized fire suppression. This research focused on developing an autonomous suppression system for use on a mobile robotic platform. This included a real-time close proximity fire suppression approach, appropriate feature selection and probabilistic classification of water leaks and sprays, real-time trajectory estimation, and a feedback controller for error correction in longer-range firefighting. The close proximity suppression algorithm uses IR fire detection IR stereo processing to localize a fire. Feedback of the fire size and fire target was used to manipulate the nozzle for effective placement of the suppressant onto the fire and experimentally validated with tests in high and low visibility environments. To improve performance of autonomous suppression and for inspection tasks, identification of water sprays and leaks is a critical component. Bayesian classification was used to identify the features associated with water leaks and sprays in thermal images. Appropriate first and second order features were selected by using a multi-objective genetic algorithm optimization. Four textural features were selected as a method of discriminating water sprays and leaks from other non-water, high motion objects. Water classification was implemented into a real-time suppression system as a method of determining the yaw and pitch angle of a water nozzle. Estimation of the angle orientation provided an error estimate between the current path and desired nozzle orientation. A proportional-integral (PI) controller was used to correct for forced errors in fire targeting and performance and response was shown through indoor and outdoor suppression tests with wood-crib fires. The autonomous suppression algorithm was demonstrated through fire testing to be at least three times faster compared with suppression by an operator using tele-operation.
Ph. D.

APA, Harvard, Vancouver, ISO, and other styles

13

Ramos, Fabio Tozeto. "Recognising, Representing and Mapping Natural Features in Unstructured Environments." Australian Centre for Field Robotics, Department of Aerospace, Mechanical and Mechatronic Engineering, 2008. http://hdl.handle.net/2123/2322.

Full text

Abstract:

Doctor of Philosophy (PhD)
This thesis addresses the problem of building statistical models for multi-sensor perception in unstructured outdoor environments. The perception problem is divided into three distinct tasks: recognition, representation and association. Recognition is cast as a statistical classification problem where inputs are images or a combination of images and ranging information. Given the complexity and variability of natural environments, this thesis investigates the use of Bayesian statistics and supervised dimensionality reduction to incorporate prior information and fuse sensory data. A compact probabilistic representation of natural objects is essential for many problems in field robotics. This thesis presents techniques for combining non-linear dimensionality reduction with parametric learning through Expectation Maximisation to build general representations of natural features. Once created these models need to be rapidly processed to account for incoming information. To this end, techniques for efficient probabilistic inference are proposed. The robustness of localisation and mapping algorithms is directly related to reliable data association. Conventional algorithms employ only geometric information which can become inconsistent for large trajectories. A new data association algorithm incorporating visual and geometric information is proposed to improve the reliability of this task. The method uses a compact probabilistic representation of objects to fuse visual and geometric information for the association decision. The main contributions of this thesis are: 1) a stochastic representation of objects through non-linear dimensionality reduction; 2) a landmark recognition system using a visual and ranging sensors; 3) a data association algorithm combining appearance and position properties; 4) a real-time algorithm for detection and segmentation of natural objects from few training images and 5) a real-time place recognition system combining dimensionality reduction and Bayesian learning. The theoretical contributions of this thesis are demonstrated with a series of experiments in unstructured environments. In particular, the combination of recognition, representation and association algorithms is applied to the Simultaneous Localisation and Mapping problem (SLAM) to close large loops in outdoor trajectories, proving the benefits of the proposed methodology.

APA, Harvard, Vancouver, ISO, and other styles

14

Toro, Walter Mauricio Mayor. "Navegação robótica relacional baseada em web considerando incerteza na percepção." Universidade de São Paulo, 2014. http://www.teses.usp.br/teses/disponiveis/3/3139/tde-26082015-165514/.

Full text

Abstract:

Quando um robô autônomo tenta resolver as tarefas de navegação dentro de um ambiente real interno usando relações qualitativas, vários problemas aparecem tais como observação parcial do ambiente e percepção incerta. Isso ocorre porque os sensores do robô não proporcionam informação suficiente para perceber completamente as situações do ambiente, além de incorporarem ruído no processo. A web semântica dota o robô autônomo com a habilidade de obter conhecimento de senso comum extraído da web, conhecimento este que os sensores do robô não podem proporcionar. Porém, nem sempre é fácil levar efetivamente estes recursos semânticos da web ao uso prático. Neste trabalho, foi examinado o uso de recursos semânticos da web na navegação robótica; mais especificamente, em uma navegação qualitativa onde o raciocínio incerto desempenha um papel significativo. Nós avaliamos o uso de uma representação relacional; particularmente, na combinação da informação semântica web e dos dados de baixo nível proporcionados pelos sensores, permitindo uma descrição de objetos e das relações entre os mesmos. Esta representação também permite o uso de abstração e generalização das situações do ambiente. Este trabalho propõe a arquitetura Web-based Relational Robotic Architecture (WRRA )para navegação robótica que combina os dados de baixo nível dos sensores do robô e os recursos web semânticos existentes baseados em lógica descritiva probabilística, como aprendizagem e planejamento relacional probabilístico. Neste trabalho, mostramos os benefícios desta arquitetura em um robô simulado, apresentando um estudo de caso sobre como os recursos semânticos podem ser usados para lidar com a incerteza da localização e o mapeamento em um problema prático.
When an autonomous robot attempts to solve navigation tasks in a qualitative relational way within a real indoor environments, several problems appear such as partial observation of the environment, and uncertain perception, since the robots sensors do not provide enough information to perceive completely the environment situations, besides the sensors incorporate noise in the process. The semantic web information endows the autonomous robot with the ability to obtain common sense knowledge from the web that the robot\'s sensors cannot provide. However, it is not always easy to effectively bring these semantic web resources into practical use. In this work, we examine the use of semantic web resources in robot navigation; more specifically, in qualitative navigation where uncertain reasoning plays a significant role. We evaluate the use of a relational representation; particularly, in the combination of the semantic web and the low-level data sensor information, which allows a description of relationships among objects. This representation also allows the use of abstraction and generalization of the environment situations. This work proposes the framework Web-based Relational Robotic Architecture WRRA for robot navigation that connects the low-level data from robot\'s sensors and existing semantic web resources based on probabilistic description logics, with probabilistic relational learning and planning. We show the benefits of this framework in a simulated robot, presenting a case study on how semantic web resources can be used to face location and mapping uncertain in a practical problem.

APA, Harvard, Vancouver, ISO, and other styles

15

Lancaster, Joseph Paul Jr. "Predicting the behavior of robotic swarms in discrete simulation." Diss., Kansas State University, 2015. http://hdl.handle.net/2097/18980.

Full text

Abstract:

Doctor of Philosophy
Department of Computing and Information Sciences
David Gustafson
We use probabilistic graphs to predict the location of swarms over 100 steps in simulations in grid worlds. One graph can be used to make predictions for worlds of different dimensions. The worlds are constructed from a single 5x5 square pattern, each square of which may be either unoccupied or occupied by an obstacle or a target. Simulated robots move through the worlds avoiding the obstacles and tagging the targets. The interactions between the robots and the robots and the environment lead to behavior that, even in deterministic simulations, can be difficult to anticipate. The graphs capture the local rate and direction of swarm movement through the pattern. The graphs are used to create a transition matrix, which along with an occupancy matrix, can be used to predict the occupancy in the patterns in the 100 steps using 100 matrix multiplications. In the future, the graphs could be used to predict the movement of physical swarms though patterned environments such as city blocks in applications such as disaster response search and rescue. The predictions could assist in the design and deployment of such swarms and help rule out undesirable behavior.

APA, Harvard, Vancouver, ISO, and other styles

16

Ohnheiser, Jan. "Vizualizace plánování cesty pro neholonomní objekty." Master's thesis, Vysoké učení technické v Brně. Fakulta informačních technologií, 2013. http://www.nusl.cz/ntk/nusl-236161.

Full text

Abstract:

This work deals with the path finding for nonholonomic robots using probabilistic algorithms. The theoretical part analyzes the general problem of finding routes. Subsequently, the work will focus on probabilistic algorithms. The practical part describes design of the applet and web sites that demonstrate probabilistic algorithms to user-specified objects.

APA, Harvard, Vancouver, ISO, and other styles

17

Ranganathan, Ananth. "Probabilistic topological maps." Diss., Atlanta, Ga. : Georgia Institute of Technology, 2008. http://hdl.handle.net/1853/22643.

Full text

Abstract:

Thesis (Ph. D.)--Computing, Georgia Institute of Technology, 2008.
Committee Chair: Dellaert, Frank; Committee Member: Balch, Tucker; Committee Member: Christensen, Henrik; Committee Member: Kuipers, Benjamin; Committee Member: Rehg, Jim.

APA, Harvard, Vancouver, ISO, and other styles

18

Corrêa, Fabiano Rogério. "Mapeamento semântico com aprendizado estatístico relacional para representação de conhecimento em robótica móvel." Universidade de São Paulo, 2009. http://www.teses.usp.br/teses/disponiveis/3/3152/tde-13072009-165912/.

Full text

Abstract:

A maior parte dos mapas empregados em tarefas de navegação por robôs móveis representam apenas informações espaciais do ambiente. Outros tipos de informações, que poderiam ser obtidos dos sensores do robô e incorporados à representação, são desprezados. Hoje em dia é comum um robô móvel conter sensores de distância e um sistema de visão, o que permitiria a princípio usá-lo na realização de tarefas complexas e gerais de maneira autônoma, dada uma representação adequada e um meio de extrair diretamente dos sensores o conhecimento necessário. Uma representação possível nesse contexto consiste no acréscimo de informação semântica aos mapas métricos, como por exemplo a segmentação do ambiente seguida da rotulação de cada uma de suas partes. O presente trabalho propõe uma maneira de estruturar a informação espacial criando um mapa semântico do ambiente que representa, além de obstáculos, um vínculo entre estes e as imagens segmentadas correspondentes obtidas por um sistema de visão omnidirecional. A representação é implementada por uma descrição relacional do domínio, que quando instanciada gera um campo aleatório condicionado, onde são realizadas as inferências. Modelos que combinam probabilidade e lógica de primeira ordem são mais expressivos e adequados para estruturar informações espaciais em semânticas.
Most maps used in navigational tasks by mobile robots represent only environmental spatial information. Other kinds of information, that might be obtained from the sensors of the robot and incorporated in the representation, are negleted. Nowadays it is common for mobile robots to have distance sensors and a vision system, which could in principle be used to accomplish complex and general tasks in an autonomously manner, given an adequate representation and a way to extract directly from the sensors the necessary knowledge. A possible representation in this context consists of the addition of semantic information to metric maps, as for example the environment segmentation followed by an attribution of labels to them. This work proposes a way to structure the spatial information in order to create a semantic map representing, beyond obstacles, an anchoring between them and the correspondent segmented images obtained by an omnidirectional vision system. The representation is implemented by a domains relational description that, when instantiated, produces a conditional random field, which supports the inferences. Models that combine probability and firstorder logic are more expressive and adequate to structure spatial in semantic information.

APA, Harvard, Vancouver, ISO, and other styles

19

Fracasso, Paulo Thiago. "Análise de técnicas para amostragem e seleção de vértices no planejamento probabilístico de mapa de rotas." Universidade de São Paulo, 2008. http://www.teses.usp.br/teses/disponiveis/3/3141/tde-30052008-132218/.

Full text

Abstract:

O planejamento probabilístico de mapa de rotas tem se mostrado uma poderosa ferramenta para o planejamento de caminhos para robôs móveis, devido a sua eficiência computacional, simplicidade de implementação e escalabilidade em diferentes problemas. Este método de planejamento possui duas fases. Na fase de construção, um mapa de rotas é gerado de forma iterativa e incremental, e armazenado na forma de um grafo G, cujos vértices são configurações livres, amostradas no espaço de configurações do robô e cujas arestas correspondem a caminhos livres de colisão entre tais configurações. Na fase de questionamento, dadas quaisquer configurações de origem e destino, \'alfa\' e \'beta\' respectivamente, o planejador conecta \'alfa\' e \'beta\' à G inserindo arestas que correspondem a caminhos livres de colisão, para então procurar por um caminho entre \'alfa\' e \'beta\' em G. Neste trabalho o foco reside principalmente na fase de construção do mapa de rotas. O objetivo aqui consiste em efetuar uma análise comparativa de diversas combinações de diferentes técnicas de amostragem das configurações livres e de diferentes técnicas de seleção de vértices em G, todas implementadas em um único sistema e aplicadas aos mesmos cenários. Os resultados propiciam um valioso auxílio aos usuários do planejamento probabilístico de mapas de rotas na decisão da melhor combinação para suas aplicações.
The probabilistic roadmap planning has emerged as a powerful framework for path planning of mobile robots due to its computational efficiency, implementation simplicity, and scalability in different problems. This planning method proceeds in two phases. In the construction phase a roadmap is incrementally constructed and stored as a graph G whose nodes are free configurations sampled on the robot\'s configuration space and whose edges correspond to collision-free paths between these configurations. In the query phase, given any start and goal configurations, \'alfa\' and \'beta\' respectively, the planner first connects \'alfa\' and \'beta\' to G by adding edges that correspond to collision-free paths, and then searches for a path in G between \'alfa\' and \'beta\'. In this work, we address mainly the roadmap construction phase. The goal here is to provide a comparative analysis of a number of combinations of different techniques for sampling free configurations and different node adding techniques, all implemented in a single system and applied to the same test workspace. Results help probabilistic roadmap planning users to choose the best combination for their applications.

APA, Harvard, Vancouver, ISO, and other styles

20

Warraich, Daud Sana Mechanical &amp Manufacturing Engineering Faculty of Engineering UNSW. "Ultrasonic stochastic localization of hidden discontinuities in composites using multimodal probability beliefs." Publisher:University of New South Wales. Mechanical & Manufacturing Engineering, 2009. http://handle.unsw.edu.au/1959.4/43719.

Full text

Abstract:

This thesis presents a technique used to stochastically estimate the location of hidden discontinuities in carbon fiber composite materials. Composites pose a challenge to signal processing because speckle noise, as a result of reflections from impregnated laminas, masks useful information and impedes detection of hidden discontinuities. Although digital signal processing techniques have been exploited to lessen speckle noise and help to localize discontinuities, uncertainty in ultrasonic wave propagation and broadband frequency based inspections of composites still make it a difficult task. The technique proposed in this thesis estimates the location of hidden discontinuities stochastically in one- and two-dimensions based on statistical data of A-Scans and C-Scans. Multiple experiments have been performed on carbon fiber reinforced plastics including artificial delaminations and porosity at different depths in the thickness of material. A probabilistic approach, which precisely localizes discontinuities in high and low amplitude signals, has been used to present this method. Compared to conventional techniques the proposed technique offers a more reliable package, with the ability to detect discontinuities in signals with lower intensities by utilizing the repetitive amplitudes in multiple sensor observations obtained from one-dimensional A-Scans or two-dimensional C-Scan data sets. The thesis presents the methodology encompassing the proposed technique and the implementation of a system to process real ultrasonic signals and images for effective discontinuity detection and localization.

APA, Harvard, Vancouver, ISO, and other styles

21

ARAÚJO, Rafael Pereira de. "Probabilistic analysis applied to robots." Universidade Federal de Pernambuco, 2016. https://repositorio.ufpe.br/handle/123456789/20827.

Full text

Abstract:

Submitted by Fabio Sobreira Campos da Costa (fabio.sobreira@ufpe.br) on 2017-08-23T12:48:01Z No. of bitstreams: 2 license_rdf: 811 bytes, checksum: e39d27027a6cc9cb039ad269a5db8e34 (MD5) dissertacao_mestrado_rafael_araujo.pdf: 1319314 bytes, checksum: 15854b595d618c609a911b95573a01ad (MD5)
Made available in DSpace on 2017-08-23T12:48:01Z (GMT). No. of bitstreams: 2 license_rdf: 811 bytes, checksum: e39d27027a6cc9cb039ad269a5db8e34 (MD5) dissertacao_mestrado_rafael_araujo.pdf: 1319314 bytes, checksum: 15854b595d618c609a911b95573a01ad (MD5) Previous issue date: 2016-09-15
Robots are increasingly being used in industry and starting their way to our homes as well. Nonetheless, the most frequently used techniques to analyze robots motion are based on simulations or statistical experiments made from filming robots’ movements. In this work we propose an alternative way of performing such analysis by using Probabilistic Model Checking with the language and tool PRISM. With PRISM we can perform simulations as well as check exhaustively whether a robot motion planning satisfies specific Probabilistic Temporal formulas. Therefore we can measure energy consumption, time to complete missions, etc., and all of these in terms of specific motion planning algorithms. As consequence we can also determine if an algorithm is superior to another in certain metrics. Furthermore, to ease the use of our work, we hide the PRISM syntax by proposing a more user-friendly DSL. As a consequence, we created a translator from the DSL to PRISM by implementing the translation rules and also, a preliminary investigation about its relative completeness by using the grammatical elements generation tool LGen. We illustrate those ideas with motion planning algorithms for home cleaning robots.
Robôs estão sendo cada vez mais utilizados na indústria e entrando em nossas casas também. No entanto, as técnicas mais frequentemente utilizadas para analisar a movimentação dos robôs são baseadas em simulações ou experimentos estatísticos realizados a partir da filmagem do movimento dos robôs. Neste trabalho, nós propomos uma maneira alternativa de realizar tais análises com a utilização da técnica de Verificação de Modelos Probabilísticos com a linguagem e ferramenta PRISM. Com PRISM, podemos, tanto realizar simulações quanto verificar exaustivamente se um planejamento de movimentação do robô satisfaz fórmulas Probabilísticas Temporais específicas. Portanto, podemos medir o consumo de energia, tempo necessário para completar missões, etc. e tudo isso em termos de algoritmos específicos de planejamento de movimentação. Como consequência, podemos, também, determinar se um algoritmo é superior a outro em relação a certas métricas. Além disso, para facilitar o uso do nosso trabalho, escondemos a sintaxe do PRISM propondo uma DSL amigável ao usuário. Em consequência, criamos um tradutor da DSL em PRISM através da implementação de regras de tradução bem como fizemos uma investigação preliminar sobre sua completude relativa usando a ferramenta de geração de elementos gramaticais LGen. Ilustramos as idéias com algoritmos de planejamento de movimentação para robôs de limpeza de casas.

APA, Harvard, Vancouver, ISO, and other styles

22

Pereira, Valquiria Fenelon. "Interpretação de imagens com raciocínio espacial qualitativo probabilístico." Universidade de São Paulo, 2014. http://www.teses.usp.br/teses/disponiveis/3/3152/tde-23122014-141015/.

Full text

Abstract:

Um sistema artificial pode usar raciocínio espacial qualitativo para inferir informações sobre seu ambiente tridimensional a partir de imagens bidimensionais. Inferências realizadas com base em raciocínio espacial qualitativo devem ser capazes de lidar com incertezas. Neste trabalho investigamos a utilização de técnicas probabilísticas para tornar o raciocínio espacial qualitativo mais robusto a incertezas e aplicável a agentes móveis em ambientes reais. Investigamos uma formalização de raciocínio espacial com lógica de descrição probabilística em um subdomínio de tráfego. Desenvolvemos também um método que combina raciocínio espacial qualitativo com um filtro Bayesiano para desenvolver dois sistemas que foram aplicados na auto localização de um robô móvel. Executamos dois experimentos de auto localização; um utilizando a teoria de relações qualitativas percebíveis sobre sombra com filtro Bayesiano; e outro utilizando o cálculo de oclusão de regiões e o cálculo de direção com filtro Bayesiano. Ambos os sistemas obtiveram resultados positivos onde somente o raciocínio espacial qualitativo não foi capaz de inferir a localização do robô. Os experimentos com dados reais mostraram robustez aos ruídos e à informação parcial.
An artificial system can use qualitative spatial reasoning to obtain information about its tridimensional environment, from bi-dimensional images. Inferences produced by qualitative spatial reasoning must be able to deal with uncertainty. This work investigates the use of probabilistic techniques to make qualitative spatial reasoning more robust against uncertainty, and better applicable to mobile agents in real environments. The work investigates a formalization of spatial reasoning using probabilistic description logics in a traffic domain. Additionally, a method is presented that combines qualitative spatial reasoning with a Bayesian filter, to develop two systems that are applied to self-localization of mobile robots. Two experiments are described; one using the theory of perceptual qualitative relations about shadows; the other using occlusion calculus and direction calculus. Both systems are combined with a Bayesian filter producing positive results in situations where qualitative spatial reasoning alone cannot infer robot location. Experiments with real data show robustness to noise and partial information.

APA, Harvard, Vancouver, ISO, and other styles

23

Xia, Victoria(Victoria F. ). "Learning of probabilistic transition models for robotic actions via templates." Thesis, Massachusetts Institute of Technology, 2018. https://hdl.handle.net/1721.1/121497.

Full text

Abstract:

This electronic version was submitted by the student author. The certified thesis is available in the Institute Archives and Special Collections.
Thesis: M. Eng., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2018
Cataloged from student-submitted PDF version of thesis.
Includes bibliographical references (pages 71-72).
In this work we present templates as an approach for learning probabilistic transition models for actions. By constructing templates via a greedy procedure for building up lists of deictic references that select relevant objects to pass to a predictor, we learn compact representations for a transition model whose training time and performance do not suffer from the presence of additional objects in more complex scenes. We present various algorithms for simultaneously separating training data into corresponding templates and learning template parameters, through the use of clustering-based approaches for initial assignment of samples to templates, followed by EM-like methods to further separate the data and train templates. We evaluate templates on variants of a simulated, 3D table-top pushing task involving stacks of objects. In comparing our approach to a baseline that considers all objects in the scene, we find that the templates approach is more data-efficient in terms of impact of number of training samples on performance.
by Victoria Xia.
M. Eng.
M.Eng. Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science

APA, Harvard, Vancouver, ISO, and other styles

24

Guo, Mingming. "User-Centric Privacy Preservation in Mobile and Location-Aware Applications." FIU Digital Commons, 2018. https://digitalcommons.fiu.edu/etd/3674.

Full text

Abstract:

The mobile and wireless community has brought a significant growth of location-aware devices including smart phones, connected vehicles and IoT devices. The combination of location-aware sensing, data processing and wireless communication in these devices leads to the rapid development of mobile and location-aware applications. Meanwhile, user privacy is becoming an indispensable concern. These mobile and location-aware applications, which collect data from mobile sensors carried by users or vehicles, return valuable data collection services (e.g., health condition monitoring, traffic monitoring, and natural disaster forecasting) in real time. The sequential spatial-temporal data queries sent by users provide their location trajectory information. The location trajectory information not only contains users’ movement patterns, but also reveals sensitive attributes such as users’ personal habits, preferences, as well as home and work addresses. By exploring this type of information, the attackers can extract and sell user profile data, decrease subscribed data services, and even jeopardize personal safety. This research spans from the realization that user privacy is lost along with the popular usage of emerging location-aware applications. The outcome seeks to relive user location and trajectory privacy problems. First, we develop a pseudonym-based anonymity zone generation scheme against a strong adversary model in continuous location-based services. Based on a geometric transformation algorithm, this scheme generates distributed anonymity zones with personalized privacy parameters to conceal users’ real location trajectories. Second, based on the historical query data analysis, we introduce a query-feature-based probabilistic inference attack, and propose query-aware randomized algorithms to preserve user privacy by distorting the probabilistic inference conducted by attackers. Finally, we develop a privacy-aware mobile sensing mechanism to help vehicular users reduce the number of queries to be sent to the adversarial servers. In this mechanism, mobile vehicular users can selectively query nearby nodes in a peer-to-peer way for privacy protection in vehicular networks.

APA, Harvard, Vancouver, ISO, and other styles

25

Glover, Jared Marshall. "Probabilistic procrustean models for shape recognition with an application to robotic grasping." Thesis, Massachusetts Institute of Technology, 2008. http://hdl.handle.net/1721.1/44380.

Full text

Abstract:

Thesis (S.M.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 2008.
Includes bibliographical references (p. 92-98).
Robot manipulators largely rely on complete knowledge of object geometry in order to plan their motion and compute successful grasps. If an object is fully in view, the object geometry can be inferred from sensor data and a grasp computed directly. If the object is occluded by other entities in the scene, manipulations based on the visible part of the object may fail; to compensate, object recognition is often used to identify the location of the object and compute the grasp from a prior model. However, new instances of a known class of objects may vary from the prior model, and known objects may appear in novel configurations if they are not perfectly rigid. As a result, manipulation can pose a substantial modeling challenge when objects are not fully in view. In this thesis, we will attempt to model the shapes of objects in a way that is robust to both deformations and occlusions. In addition, we will develop a model that allows us to recover the hidden parts of occluded objects (shape completion), and which maintains information about the object boundary for use in robotic grasp planning. Our approach will be data-driven and generative, and we will base our probabilistic models on Kendall's Procrustean theory of shape.
by Jared Marshall Glover.
S.M.

APA, Harvard, Vancouver, ISO, and other styles

26

Schmitt, Thorsten. "Vision-based probabilistic state estimation for cooperating autonomous robots." [S.l. : s.n.], 2004. http://deposit.ddb.de/cgi-bin/dokserv?idn=97442997X.

Full text

APA, Harvard, Vancouver, ISO, and other styles

27

Norlander, Arvid. "Improved Sensor Planning in Binaural Probabilistic Active SoundLocalisation for Robots." Thesis, Örebro universitet, Institutionen för naturvetenskap och teknik, 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:oru:diva-84180.

Full text

Abstract:

Sensor planning in the field of active robot sound localisation is an important topic that has potential applications for robots interacting with crowds, search and rescue and more, though the field is currently at the level of basic research. This thesis presents novel improvements that theoretically increase the accuracy of the predictions used in probabilistic sensor planning for sound localisation. In particular two novel improvements are made: First, N-step ahead sensor planning using dierential entropy with a full Gaussian Mixture Model (GMM) is developed and compared with only approximating the prediction with a single Gaussian. The results indicate a modest increase in short-term performance when using a full GMM, but worse or comparable performance in the long term. Secondly, the eect of dierent observation models for the predictions are evaluated to determine the optimal choice. The result of this is surprising, showing that the simplest model performs the best.

APA, Harvard, Vancouver, ISO, and other styles

28

Paiva, mendes Ellon. "Study on the Use of Vision and Laser Range Sensors with Graphical Models for the SLAM Problem." Thesis, Toulouse, INSA, 2017. http://www.theses.fr/2017ISAT0016/document.

Full text

Abstract:

La capacité des robots mobiles à se localiser précisément par rapport à leur environnement est indispensable à leur autonomie. Pour ce faire, les robots exploitent les données acquises par des capteurs qui observent leur état interne, tels que centrales inertielles ou l’odométrie, et les données acquises par des capteurs qui observent l’environnement, telles que les caméras et les Lidars. L’exploitation de ces derniers capteurs a suscité le développement de solutions qui estiment conjointement la position du robot et la position des éléments dans l'environnement, appelées SLAM (Simultaneous Localization and Mapping). Pour gérer le bruit des données provenant des capteurs, les solutions pour le SLAM sont mises en œuvre dans un contexte probabiliste. Les premiers développements étaient basés sur le filtre de Kalman étendu, mais des développements plus récents utilisent des modèles graphiques probabilistes pour modéliser le problème d’estimation et de le résoudre grâce à techniques d’optimisation. Cette thèse exploite cette dernière approche et propose deux techniques distinctes pour les véhicules terrestres autonomes: une utilisant la vision monoculaire, l’autre un Lidar. L’absence d’information de profondeur dans les images obtenues par une caméra a mené à l’utilisation de paramétrisations spécifiques pour les points de repères qui isolent la profondeur inconnue dans une variable, concentrant la grande incertitude sur la profondeur dans un seul paramètre. Une de ces paramétrisations, nommé paramétrisation pour l’angle de parallaxe (ou PAP, Parallax Angle Parametrization), a été introduite dans le contexte du problème d’ajustement de faisceaux, qui traite l’ensemble des données en une seule étape d’optimisation globale. Nous présentons comment exploiter cette paramétrisation dans une approche incrémentale de SLAM à base de modèles graphiques, qui intègre également les mesures de mouvement du robot. Les Lidars peuvent être utilisés pour construire des solutions d’odométrie grâce à un recalage séquentiel des nuages de points acquis le long de la trajectoire. Nous définissons une couche basée sur les modèles graphiques au dessus d’une telle couche d’odométrie, qui utilise l’algorithme ICP (Iterative Closest Points). Des repères clefs (keyframes) sont définis le long de la trajectoire du robot, et les résultats de l’algorithme ICP sont utilisés pour construire un graphe de poses, exploité pour résoudre un problème d’optimisation qui permet la correction de l’ensemble de la trajectoire du robot et de la carte de l’environnement à suite des fermetures de boucle.Après une introduction à la théorie des modèles graphiques appliquée au problème de SLAM, le manuscrit présente ces deux approches. Des résultats simulés et expérimentaux illustrent les développements tout au long du manuscrit, en utilisant des jeux des données classiques et obtenus au laboratoire
A strong requirement to deploy autonomous mobile robots is their capacity to localize themselves with a certain precision in relation to their environment. Localization exploits data gathered by sensors that either observe the inner states of the robot, like acceleration and speed, or the environment, like cameras and Light Detection And Ranging (LIDAR) sensors. The use of environment sensors has triggered the development of localization solutions that jointly estimate the robot position and the position of elements in the environment, referred to as Simultaneous Localization and Mapping (SLAM) approaches. To handle the noise inherent of the data coming from the sensors, SLAM solutions are implemented in a probabilistic framework. First developments were based on Extended Kalman Filters, while a more recent developments use probabilistic graphical models to model the estimation problem and solve it through optimization. This thesis exploits the latter approach to develop two distinct techniques for autonomous ground vehicles: oneusing monocular vision, the other one using LIDAR. The lack of depth information in camera images has fostered the use of specific landmark parametrizations that isolate the unknown depth in one variable, concentrating its large uncertainty into a single parameter. One of these parametrizations, named Parallax Angle Parametrization, was originally introduced in the context of the Bundle Adjustment problem, that processes all the gathered data in a single global optimization step. We present how to exploit this parametrization in an incremental graph-based SLAM approach in which robot motion measures are also incorporated. LIDAR sensors can be used to build odometry-like solutions for localization by sequentially registering the point clouds acquired along a robot trajectory. We define a graphical model layer on top of a LIDAR odometry layer, that uses the Iterative Closest Points (ICP) algorithm as registration technique. Reference frames are defined along the robot trajectory, and ICP results are used to build a pose graph, used to solve an optimization problem that enables the correction of the robot trajectory and the environment map upon loop closures. After an introduction to the theory of graphical models applied to SLAM problem, the manuscript depicts these two approaches. Simulated and experimental results illustrate the developments throughout the manuscript, using classic and in-house datasets

APA, Harvard, Vancouver, ISO, and other styles

29

Drouard, Vincent. "Localisation et suivi de visages à partir d'images et de sons : une approche Bayésienne temporelle et commumative." Thesis, Université Grenoble Alpes (ComUE), 2017. http://www.theses.fr/2017GREAM094/document.

Full text

Abstract:

Dans cette thèse, nous abordons le problème de l’estimation de pose de visage dans le contexte des interactions homme-robot. Nous abordons la résolution de cette tâche à l’aide d’une approche en deux étapes. Tout d’abord en nous inspirant de [Deleforge 15], nous proposons une nouvelle façon d’estimer la pose d’un visage, en apprenant un lien entre deux espaces, l’espace des paramètres de pose et un espace de grande dimension représentant les observations perçues par une caméra. L’apprentissage de ce lien se fait à l’aide d’une approche probabiliste, utilisant un mélange de regressions affines. Par rapport aux méthodes d’estimation de pose de visage déjà existantes, nous incorporons de nouvelles informations à l’espace des paramètres de pose, ces additions sont nécessaires afin de pouvoir prendre en compte la diversité des observations, comme les differents visages et expressions mais aussi lesdécalages entre les positions des visages détectés et leurs positions réelles, cela permet d’avoir une méthode robuste aux conditions réelles. Les évaluations ont montrées que cette méthode permettait d’avoir de meilleurs résultats que les méthodes de regression standard et des résultats similaires aux méthodes de l’état de l’art qui pour certaines utilisent plus d’informations, comme la profondeur, pour estimer la pose. Dans un second temps, nous développons un modèle temporel qui utilise les capacités des traqueurs pour combiner l’information du présent avec celle du passé. Le but à travers cela est de produire une estimation de la pose plus lisse dans le temps, mais aussi de corriger les oscillations entre deux estimations consécutives indépendantes. Le modèle proposé intègre le précédent modèle de régression dans une structure de filtrage de Kalman. Cette extension fait partie de la famille des modèles dynamiques commutatifs et garde tous les avantages du mélange de regressionsaffines précédent. Globalement, le modèle temporel proposé permet d’obtenir des estimations de pose plus précises et plus lisses sur une vidéo. Le modèle dynamique commutatif donne de meilleurs résultats qu’un modèle de suivi utilsant un filtre de Kalman standard. Bien qu’appliqué à l’estimation de pose de visage le modèle presenté dans cette thèse est très général et peut être utilisé pour résoudre d’autres problèmes de régressions et de suivis
In this thesis, we address the well-known problem of head-pose estimationin the context of human-robot interaction (HRI). We accomplish this taskin a two step approach. First, we focus on the estimation of the head pose from visual features. We design features that could represent the face under different orientations and various resolutions in the image. The resulting is a high-dimensional representation of a face from an RGB image. Inspired from [Deleforge 15] we propose to solve the head-pose estimation problem by building a link between the head-pose parameters and the high-dimensional features perceived by a camera. This link is learned using a high-to-low probabilistic regression built using probabilistic mixture of affine transformations. With respect to classic head-pose estimation methods we extend the head-pose parameters by adding some variables to take into account variety in the observations (e.g. misaligned face bounding-box), to obtain a robust method under realistic conditions. Evaluation of the methods shows that our approach achieve better results than classic regression methods and similar results thanstate of the art methods in head pose that use additional cues to estimate the head pose (e.g depth information). Secondly, we propose a temporal model by using tracker ability to combine information from both the present and the past. Our aim through this is to give a smoother estimation output, and to correct oscillations between two consecutives independent observations. The proposed approach embeds the previous regression into a temporal filtering framework. This extention is part of the family of switching dynamic models and keeps all the advantages of the mixture of affine regressions used. Overall the proposed tracker gives a more accurate and smoother estimation of the head pose on a video sequence. In addition, the proposed switching dynamic model gives better results than standard tracking models such as Kalman filter. While being applied to the head-pose estimation problem the methodology presented in this thesis is really general and can be used to solve various regression and tracking problems, e.g. we applied it to the tracking of a sound source in an image

APA, Harvard, Vancouver, ISO, and other styles

30

Bordallo, Micó Alejandro. "Intention prediction for interactive navigation in distributed robotic systems." Thesis, University of Edinburgh, 2017. http://hdl.handle.net/1842/28802.

Full text

Abstract:

Modern applications of mobile robots require them to have the ability to safely and effectively navigate in human environments. New challenges arise when these robots must plan their motion in a human-aware fashion. Current methods addressing this problem have focused mainly on the activity forecasting aspect, aiming at improving predictions without considering the active nature of the interaction, i.e. the robot’s effect on the environment and consequent issues such as reciprocity. Furthermore, many methods rely on computationally expensive offline training of predictive models that may not be well suited to rapidly evolving dynamic environments. This thesis presents a novel approach for enabling autonomous robots to navigate socially in environments with humans. Following formulations of the inverse planning problem, agents reason about the intentions of other agents and make predictions about their future interactive motion. A technique is proposed to implement counterfactual reasoning over a parametrised set of light-weight reciprocal motion models, thus making it more tractable to maintain beliefs over the future trajectories of other agents towards plausible goals. The speed of inference and the effectiveness of the algorithms is demonstrated via physical robot experiments, where computationally constrained robots navigate amongst humans in a distributed multi-sensor setup, able to infer other agents’ intentions as fast as 100ms after the first observation. While intention inference is a key aspect of successful human-robot interaction, executing any task requires planning that takes into account the predicted goals and trajectories of other agents, e.g., pedestrians. It is well known that robots demonstrate unwanted behaviours, such as freezing or becoming sluggishly responsive, when placed in dynamic and cluttered environments, due to the way in which safety margins according to simple heuristics end up covering the entire feasible space of motion. The presented approach makes more refined predictions about future movement, which enables robots to find collision-free paths quickly and efficiently. This thesis describes a novel technique for generating "interactive costmaps", a representation of the planner’s costs and rewards across time and space, providing an autonomous robot with the information required to navigate socially given the estimate of other agents’ intentions. This multi-layered costmap deters the robot from obstructing while encouraging social navigation respectful of other agents’ activity. Results show that this approach minimises collisions and near-collisions, minimises travel times for agents, and importantly offers the same computational cost as the most common costmap alternatives for navigation. A key part of the practical deployment of such technologies is their ease of implementation and configuration. Since every use case and environment is different and distinct, the presented methods use online adaptation to learn parameters of the navigating agents during runtime. Furthermore, this thesis includes a novel technique for allocating tasks in distributed robotics systems, where a tool is provided to maximise the performance on any distributed setup by automatic parameter tuning. All of these methods are implemented in ROS and distributed as open-source. The ultimate aim is to provide an accessible and efficient framework that may be seamlessly deployed on modern robots, enabling widespread use of intention prediction for interactive navigation in distributed robotic systems.

APA, Harvard, Vancouver, ISO, and other styles

31

Jaillet, Léonard. "Méthodes probabilistes pour la planification réactive de mouvements." Phd thesis, Université Paul Sabatier - Toulouse III, 2005. http://tel.archives-ouvertes.fr/tel-00011515.

Full text

Abstract:

Les techniques de planification de mouvement actuelles sont maintenant capables de résoudre des problèmes mettant en jeu des mécanismes complexes plongés au sein d'environnements encombrés. Néanmoins, l'adaptation de ces planificateurs à des scènes comprenant à la fois des obstacles statiques et des obstacles mobiles s'est avérée limitée jusqu'ici. Une des raisons en est le coût associé à la mise à jour des structures de données qui sont précalculées pour capturer la connexité de l'espace libre. Notre contribution principale concerne la proposition d'un nouveau planificateur capable de traiter des problèmes comprenant à la fois obstacles statiques et obstacles mobiles. Ce planificateur hybride combine deux grandes familles de techniques. D'une part les techniques dites PRM, initialement conçues pour résoudre des problèmes à requêtes multiples et que nous avons étendu à des problèmes de scènes dynamiques. D'autre part, de nouvelles techniques de diffusion, alors que celles-ci sont généralement dédiées aux problèmes simple requête ne nécessitant aucune opération de prétraitement. Les principaux développements accompagnant la construction de ce planificateur sont les suivants : - La proposition d'une architecture originale pour le planificateur dédié aux environnements changeants. Cette architecture inclut notamment plusieurs mécanismes dits d' "évaluation paresseuse" qui permettent de minimiser les test de collision et ainsi d'assurer de bonnes performances. - Le développement d'une nouvelle méthode de diffusion permettant de reconnecter localement certaines portions du réseau invalidées par la présence des obstacles mobiles. Cette méthode, appelée RRT à Domaine Dynamique correspond en fait une extension des planificateur bien connus à bases de RRTs. Un des intérêt propre à notre approche est d'équilibrer automatiquement deux comportements propres au planificateur : l'exploration vers des régions encore inconnues et l'affinage du modèle des régions de l'espac e déjà explorées. - Deux méthodes originales de création de réseaux cycliques qui servent à initialiser notre planificateur. La première assume que les obstacles mobiles sont confinés dans une région donnée, pour construire un réseau adapté aux différents types de changements de position possibles. La seconde est une méthode qui construit des réseaux appelés "réseaux de rétraction". A l'aide d'une structure de donnée de faible taille, cette structure parvient à capturer les différentes variétés de chemins de l'espace, à travers notamment chacune des classes d'homotopie de l'espace libre. Toutes ces méthodes sont implémentées au sein de la plate-forme de travail Move3D développée au LAAS-CNRS et sont évaluées sur différents types de systèmes mécaniques plongés au sein d'environnements 3D.

APA, Harvard, Vancouver, ISO, and other styles

32

Terán, Espinoza Antonio. "Probabilistic and learning approaches through concurrent parameter estimation and adaptive control for in-space robotic assembly." Thesis, Massachusetts Institute of Technology, 2017. http://hdl.handle.net/1721.1/112480.

Full text

Abstract:

Thesis: S.M., Massachusetts Institute of Technology, Department of Aeronautics and Astronautics, 2017.
Cataloged from PDF version of thesis.
Includes bibliographical references (pages 143-148).
Autonomous and multi-agent space operations within the context of in-space robotic servicing, assembly, and debris removal have received particular attention from both research and industry communities. The presence of uncertainties and unknown system parameters amongst these missions is prevalent, as they primarily deal with unknown or uncooperative target objects, e.g., asteroids or unresponsive, unsupervised tumbling spacecraft. To lower the inherent risk associated with these types of operations, possessing an accurate knowledge of the aforementioned characteristics is essential. In order to achieve this, approaches that employ a unified framework between parameter estimation and learning methodologies through a Composite Adaptation (CA) structure are presented. Furthermore, to evaluate the likelihood of mission success or objective completion, a probabilistic approach upon the system's operations is introduced; by employing probability distributions to model the control system's response and pairing these with the analysis of objectives' requirements and agents' characteristics, the calculation of on-board feasibility and performance assessments is presented. A formulation for the estimator and the controllers is developed, and results for the adaptive approach are demonstrated through hardware implementation using MIT's Synchronized Position Hold Engage Reorient Experimental Satellites (SPHERES) ground testing facilities. On-orbit test session data is analyzed, and further improvements upon the initial learning approach are verified through simulations.
by Antonio Terán Espinoza.
S.M.

APA, Harvard, Vancouver, ISO, and other styles

33

Vasudevan, Shrihari. "Spatial cognition for mobile robots : a hierarchical probabilistic concept-oriented representation of space." Zürich : ETH, 2008. http://e-collection.ethbib.ethz.ch/show?type=diss&nr=17612.

Full text

APA, Harvard, Vancouver, ISO, and other styles

34

Gordeski, Valerie. "Topological mapping for limited sensing mobile robots using the Probabilistic Gap Navigation Tree." Thesis, Massachusetts Institute of Technology, 2008. http://hdl.handle.net/1721.1/46108.

Full text

Abstract:

Thesis (M. Eng.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 2008.
Includes bibliographical references (p. 75-78).
This thesis proposes a novel structure for robotic navigation with minimal sensing abilities called the Probabilistic Gap Navigation Tree (PGNT). In this navigation approach, we create a topological map of the environment based on a previously created Gap Navigation Tree (GNT) [40]. The "gap" in the gap navigation algorithm represents a discontinuity in the robotic field of vision. The robot is able to use the gaps to represent its world as a tree structure (GNT), in which each vertex corresponds to a gap. Ideally, the robot navigates in the world by following the tree branches to its desired goal. However, due to the sensor uncertainty, the robot may detect discontinuities when there are none present, and vice versa. The Probabilistic Gap Navigation Tree compensates for the measurement noise by sampling from a distribution of the gap navigation trees to obtain the most likely tree given the sensor measurements, similar to the particle filtering algorithm used in Monte Carlo localization. Therefore, the PGNT allows navigation in an unknown environment using a realistic range finder, as opposed to the ideal sensor model assumed previously. We demonstrate the ability to build a PGNT in a simulated environment.
by Valerie Gordeski.
M.Eng.

APA, Harvard, Vancouver, ISO, and other styles

35

Rose-Andrieux, Raphaël. "Modèle probabiliste hérarchique de la locomotion bipède." Thesis, Paris Sciences et Lettres (ComUE), 2016. http://www.theses.fr/2016PSLEE031/document.

Full text

Abstract:

Les robots humanoïdes ont toujours fasciné car leur potentiel d’application est considérable. En effet, si un robot avait les mêmes caractéristiques sensori-motrices et morphologiques qu’un homme, il pourrait théoriquement réaliser les mêmes tâches. Cependant, un premier obstacle au développement de ces robots est la stabilité d’une posture bipède. Lors d’une marche bipède, la marge d’erreur est très faible et les décisions doivent être prises rapidement avec une information souvent incomplète et incertaine. L’incertitude a de multiples sources comme des capteurs imparfaits, un modèle simplifié du monde ou encore une mécanique imprécise.Dans cette thèse, nous partons d’un contrôle de la marche par gestion des points d’appuis. L’idée est d’affiner le choix des points d’appuis en intégrant dans notre modèle les incertitudes que l’on vient d’évoquer. Pour cela, nous allons utiliser un modèle probabiliste Bayésien. A l’aide d’une distribution de probabilité, on peut exprimer simultanément une estimation, et l’incertitude associée à celle-ci. Le cadre théorique des probabilités Bayésiennes permet de définir les variables, et de les intégrer de manière rigoureuse dans un modèle global.Un autre avantage de ce modèle probabiliste est que notre objectif est aussi décrit sous la forme d’une distribution de probabilité. Il est donc possible de s’en servir pour exprimer à la fois un objectif déterministe, et une tolérance autour de celui-ci. Cela va nous permettre de fusionner facilement plusieurs objectifs et de les adapter automatiquement en fonction des contraintes extérieures. De plus, la sortie du modèle étant elle aussi une distribution de probabilité, ce type de modèle s’intègre parfaitement dans un cadre hiérarchique : l’entrée du modèle vient du niveau au-dessus et sa sortie est donnée en objectif niveau en dessous.Dans ce travail, nous allons d’abord explorer une technique de maintien de l’équilibre et la comparer aux résultats d’une expérience préliminaire sur l’homme. Nous allons ensuite étendre cette technique pour créer une stratégie de marche. Autour de cette stratégie, nous allons construire un modèle probabiliste Bayésien. Ce modèle sera finalement implémenté en simulation pour pouvoir quantifier son intérêt dans les différentes situations évoquées plus haut : intégration des incertitudes, fusion d’objectifs et hiérarchie
Humanoid robots have always fascinated due to the vast possibilities they encompass.Indeed, a robot with the same sensorimotor features as a human could theoretically carry out the same tasks. However, a first obstacle in the development of these robots is the stability of a bipedal gait. Bipedal walkers are inherently unstable systems experiencing highly dynamic and uncertain situations. Uncertainty arises from many sources, including intrinsic limitations of a particular model of the world, the noise and perceptual limitations in a robot's sensor measurements, and the internal mechanical imperfection of the system.In this thesis, we focus on foot placement to control the position and velocity of the body's center of mass. We start from a deterministic strategy, and develop a probabilistic strategy around it that includes uncertainties. A probability distribution can express simultaneously an estimation of a variable, and the uncertainty associated. We use a Bayesian model to define relevant variables and integrate them in the global frame.Another benefit of this model is that our objective is also represented as a probability distribution. It can be used to express both a deterministic objective and the tolerance around it. Using this representation one can easily combine multiple objectives and adapt them to external constraints. Moreover, the output of the model is also a probabilistic distribution which fits well in a hierarchical context: the input comes from the level above and the output is given as objective to the lower level.In this work, we will review multiple ways to keep balance and compare them to the results of a preliminary experiment done with humans. We will then extend one strategy to walking using foot placement to keep balance. Finally, we will develop a probabilistic model around that strategy and test it in simulation to measure its benefits in different contexts : integrating uncertainties, fusing multiple objectives and hierarchy

APA, Harvard, Vancouver, ISO, and other styles

36

Toriz, Palacios Alfredo. "Exploration intégrée probabiliste pour robots mobiles évoluant en environnements complexes." Thesis, Montpellier 2, 2012. http://www.theses.fr/2012MON20013/document.

Full text

Abstract:

L'un des défis fondamentaux de la robotique d'aujourd'hui est d'obtenir des cartes robustes en utilisant des mécanismes efficaces pour l'exploration et la modélisation des environnements toujours plus complexes. Ce problème est connu comme celui de la planification, de la localisation et de la cartographie simultanée (SPLAM).Dans cette thèse nous avons développé des outils pour obtenir une stratégie de SPLAM. D'abord, l'exploration est faite par le graphe d'exploration aléatoire (REG) basé sur la création d'une structure de graphe et sur un contrôle de frontières. Ensuite, le problème de localisation et de cartographie simultanée (SLAM) est résolu avec une stratégie topologique basée sur des B-Splines. Pour valider notre stratégie, nous avons créé une autre approche de SPLAM basée sur des outils connus comme le Filtre de Kalman étendu pour le SLAM et sur l'arbre aléatoire (SRT) pour l'exploration. Ces résultats sont comparés avec les résultats de notre stratégie
One of the fundamental challenges of today's robotics is to obtain robust maps using efficient mechanisms for exploring and modeling increasingly complex environments. This is known as simultaneous planning, localization and mapping (SPLAM) problem.Considering this problem, in this thesis we have developed some tools to obtain a SPLAM strategy. First, the exploration is made by the Random Exploration Graph approach (REG) which is based on the creation of a graph structure and on a frontier control. Next, the simultaneous localization and mapping (SLAM) problem is solved using a B-Spline based topologic strategy. To validate our strategy, we have created another SPLAM approach based on well known tools as the Extended Kalman Filter for SLAM and on the Sensor based Random tree (SRT) for the exploration problem. Its results are confronted with the results obtained by our strategy

APA, Harvard, Vancouver, ISO, and other styles

37

Clément, Julien. "Algorithmique probabiliste pour systèmes distribués émergents." Paris 11, 2009. http://www.theses.fr/2009PA112231.

Full text

Abstract:

Les réseaux de capteurs mobiles font leur apparition en informatique depuis plusieurs années. Certaines caractéristiques de ces réseaux sont nouvelles : les capteurs sont petits, avec peu de mémoire, peuvent tomber en panne facilement, sont mobiles. De plus, ces réseaux contiennent parfois plusieurs milliers d'entités. L'enjeu pour l'informatique est de taille. En effet, ces nouvelles propriétés posent un défi pour les concepteurs d'algorithmes que nous sommes. Il est nécessaire de repenser nos méthodes et d'assurer algorithmiquement que ces nouveaux systèmes fonctionneront correctement dans le futur. La difficulté théorique et l’enjeu de ces problèmes en font un sujet de recherche à la fois intéressant et excitant. Le but de cette thèse est de reconsidérer certains algorithmes conçus pour des réseaux classiques afin qu'ils soient performants sur des réseaux émergents. Nous ne nous sommes pas uniquement focalisé sur les réseaux de capteurs mobiles mais aussi sur d'autres systèmes ayant vu le jour ces dernières années. Enfin, nous avons tenté systématiquement d'introduire des probabilités afin de débloquer des impossibilités ou même d'améliorer les performances des algorithmes. Nous avons obtenu différents résultats, sur plusieurs types de réseaux émergents tels que les réseaux pair à pair, les réseaux de robots ou les réseaux de capteurs mobiles pour lesquels nous étendons le modèle des protocoles de population. Enfin, nous proposons un modèle formel permettant de mesurer l’étendue des connexions entre les différents types de réseaux, ou tout du moins entre les modèles les décrivant
Mobile sensor networks have appeared in computer science several years ago. Some of these networks’ characteristics are new: sensors are small, with few memory; they can be corrupted easily and are mobile. Moreover, they may contain thousands of entities. For computer science, the stake is huge. All these new properties are a challenge for us, algorithm creators. It is necessary to adapt our methods and to make sure that from an algorithmic point of view, these new systems will function correctly in the years to come. The theoretical difficulty and the stake of these issues transform them into an interesting and exciting research subject. The goal this thesis is to reconsider some of the algorithms created for classical networks in order to make them performing on these new networks. We did not restrain ourselves to mobile sensor networks and also considered other recent systems. Also, we always introduced probability in order to unblock impossibilities or to improve the performance of the algorithms. We obtained different results on several kinds of new networks as peer to peer networks, robots networks or mobile sensor networks in which we extend the population protocol model. Finally, we introduced a formal model in order to prove that at some level of abstraction, there are very strong connections between the various types of networks, or at least between the models describing them

APA, Harvard, Vancouver, ISO, and other styles

38

Jouandeau, Nicolas. "Algorithmique de la planification de mouvement probabiliste pour un robot mobile." Paris 8, 2004. http://www.theses.fr/2004PA082465.

Full text

Abstract:

Nous étudions dans ce mémoire la planification de mouvement probabiliste incrémentale. Nos travaux se concrétisent par un nouvel algorithme de construction des arbres aléatoires d'exploration rapide et une nouvelle décomposition de l'espace des configurations en cellules irrégulières. Partant d'une synthèse des méthodes de planification incrémentale probabiliste, nos travaux présentent un algorithme de construction accélérant l'exploration de l'espace de recherche. Partant des principales approches d'échantillonnage de l'espace de recherche utilisées dans les méthodes probabilistes, l'analyse des propriétés associées à ces échantillonnages nous conduit à proposer une décomposition de l'espace en cellules irrégulières adaptée à la notion d'accessibilité. Après définition de cette décomposition, ces algorithmes de construction sont évalués comparativement à un échantillonnage uniforme de l'espace de recherche
In this thesis, we are studying incremental probabilistic motion planning. Our studies present a new fast algorithm to expand Rapidly exploring Random Tree (RRT) and a new irregular cell partition based on visibility. Our algorithm improves the existing successful probabilistic path planner called RRT by restricting each expansion step to the first collision free configuration. The analysis of the principal sampling's properties used in probabilistic motion planning leads us to propose a new irregular cell partition based on visibility. This new decomposition is tested in narrow environments and in cluthered ones. Results show that this new algorithm and this new decomposition are two significant componants of RRT methods. The motion planner we developped is implemented for mobile robot, evolving in a static well-known environment

APA, Harvard, Vancouver, ISO, and other styles

39

Jaillet, Léonard. "Méthodes probabilistes pour la planifcation réactive de mouvement." Phd thesis, Université Paul Sabatier - Toulouse III, 2005. http://tel.archives-ouvertes.fr/tel-00853031.

Full text

Abstract:

Malgré le franc succès des techniques de planification de mouvement au cours de ces deux dernières décennies, leur adaptation à des scènes comprenant à la fois des obstacles statiques et des obstacles mobiles s'est avérée limitée jusqu'ici. Une des raisons en est le coût associé à la mise à jour des structures de données précalculées afin de capturer la connexité de l'espace libre. Notre contribution principale concerne la proposition d'un nouveau planificateur capable de traiter ces problèmes d'environnements partiellement dynamiques composés à la fois d'obstacles statiques et d'obstacles mobiles.

APA, Harvard, Vancouver, ISO, and other styles

40

Meyer-Delius, Di Vasto Daniel [Verfasser], and Wolfram [Akademischer Betreuer] Burgard. "Probabilistic modeling of dynamic environments for mobile robots = Wahrscheinlichkeitstheoretische Modellierung dynamischer Umgebungen für mobile Roboter." Freiburg : Universität, 2011. http://d-nb.info/1123464537/34.

Full text

APA, Harvard, Vancouver, ISO, and other styles

41

Ramel, Guy. "Analyse du contexte à l'aide de méthodes probabilistes pour l'interaction hommes-robots /." [S.l.] : [s.n.], 2006. http://library.epfl.ch/theses/?nr=3477.

Full text

APA, Harvard, Vancouver, ISO, and other styles

42

Flandin, Grégory. "Modélisation probabiliste et exploration visuelle autonome pour la reconstruction de scènes inconnues." Phd thesis, Université Rennes 1, 2001. http://tel.archives-ouvertes.fr/tel-00843884.

Full text

Abstract:

inconnues. Il s'agit d'interpréter des informations visuelles et de générer les points de vue qui permettent de construire progressivement une carte de l'environnement. Le problème est décomposé, de façon hiérarchique, en trois fonctionnalités. Dans un premier temps, le système détermine la suite des actions aboutissantàuninventaire de tous les objets de la scène. Cette problématique s'inscrit dans le contexte très général de la recherche d'objets. L'approche que nous présentons est basée sur une description probabiliste de l'occupation de la scène par des objets. La recherche consiste alors à générer une suite d'observations aboutissant à des probabilités proches de 1 aux endroits où se trouve un objet et proches de 0 ailleurs. Nous développons plusieurs stratégies allant dans ce sens. Dans un second temps, l'exploration est focalisée sur chaque objet a˝n d'en améliorer la description. Nous présentons un modèle d'objet basé sur un mélange de modèles stochastique et à erreur bornée permettant de représenter l'enveloppe approchée de l'objet tout en tenant compte des incertitudes de localisation. Nous développons un algorithme d'estimation en ligne de ce modèle et élaborons un processus d'exploration optimale en temps réel basé sur la minimisation de l'incertitude de localisation de l'objet observé. En˝n, la dernière fonction-nalité concerne le suivi des consignes permettant de déplacer la caméra tout en suivant l'objet d'intérêt. Ce problème est résolu par asservissement visuel dont nous étudions les potentialités du point de vue de la coopération caméra globale/caméra locale.

APA, Harvard, Vancouver, ISO, and other styles

43

CANCHUMUNI, SMITH WASHINGTON ARAUCO. "PROBABILISTIC SIMULTANEOUS LOCALIZATION AND MAPPING OF MOBILE ROBOTS IN INDOOR ENVIRONMENTS WITH A LASER RANGE FINDER." PONTIFÍCIA UNIVERSIDADE CATÓLICA DO RIO DE JANEIRO, 2013. http://www.maxwell.vrac.puc-rio.br/Busca_etds.php?strSecao=resultado&nrSeq=23357@1.

Full text

Abstract:

PONTIFÍCIA UNIVERSIDADE CATÓLICA DO RIO DE JANEIRO
COORDENAÇÃO DE APERFEIÇOAMENTO DO PESSOAL DE ENSINO SUPERIOR
PROGRAMA DE EXCELENCIA ACADEMICA
Os Robôs Móveis são cada vez mais inteligentes, para que eles tenham a capacidade de semover livremente no interior deumambiente, evitando obstáculos e sem assistência de um ser humano, precisam possuir um conhecimento prévio do ambiente e de sua localização. Nessa situação, o robô precisa construir um mapa local de seu ambiente durante a execução de sua missão e, simultaneamente, determinar sua localização. Este problema é conhecido como Mapeamento e Localização Simultâneas (SLAM). As soluções típicas para o problema de SLAM utilizam principalmente dois tipos de sensores: (i) odômetros, que fornecem informações de movimento do robô móvel e (ii) sensores de distância, que proporcionam informação da percepção do ambiente. Neste trabalho, apresenta-se uma solução probabilistica para o problema SLAM usando o algoritmo DP-SLAM puramente baseado em medidas de um LRF (Laser Range Finder), com foco em ambientes internos estruturados. Considera-se que o robô móvel está equipado com um único sensor 2DLRF, sem nenhuma informação de odometria, a qual é substituída pela informação obtida da máxima sobreposição de duas leituras consecutivas do sensor LRF, mediante algoritmos de Correspondência de Varreduras (Scan Matching). O algoritmo de Correspondência de Varreduras usado realiza uma Transformada de Distribuições Normais (NDT) para aproximar uma função de sobreposição. Para melhorar o desempenho deste algoritmo e lidar com o LRF de baixo custo, uma reamostragem dos pontos das leituras fornecidas pelo LRF é utilizada, a qual preserva uma maior densidade de pontos da varredura nos locais onde haja características importantes do ambiente. A sobreposição entre duas leituras é otimizada fazendo o uso do algoritmo de Evolução Diferencial (ED). Durante o desenvolvimento deste trabalho, o robô móvel iRobot Create, equipado com o sensor LRF Hokuyo URG-04lx, foi utilizado para coletar dados reais de ambientes internos, e diversos mapas 2D gerados são apresentados como resultados.
The robot to have the ability to move within an environment without the assistance of a human being, it is required to have a knowledge of the environment and its location within it at the same time. In many robotic applications, it is not possible to have an a priori map of the environment. In that situation, the robot needs to build a local map of its environment while executing its mission and, simultaneously, determine its location. A typical solution for the Simultaneous Localization and Mapping (SLAM) problem primarily uses two types of sensors: i) an odometer that provides information of the robot’s movement and ii) a range measurement that provides perception of the environment. In this work, a solution for the SLAM problem is presented using a DP-SLAM algorithm purely based on laser readings, focused on structured indoor environments. It considers that the mobile robot only uses a single 2D Laser Range Finder (LRF), and the odometry sensor is replaced by the information obtained from the overlapping of two consecutive laser scans. The Normal Distributions Transform (NDT) algorithm of the scan matching is used to approximate a function of the map overlapping. To improve the performance of this algorithm and deal with low-quality range data from a compact LRF, a scan point resampling is used to preserve a higher point density of high information features from the scan. An evolution differential algorithm is presented to optimize the overlapping process of two scans. During the development of this work, the mobile robot iRobot Create, assembled with one LRF Hokuyo URG-04LX, is used to collect real data in several indoor environments, generating 2D maps presented as results.

APA, Harvard, Vancouver, ISO, and other styles

44

Solà, Ortega Joan Devy Michel Monin André. "Towards visual localization, mapping and moving objects tracking by a mobile robot a geometric and probabilistic approach /." Toulouse : INP Toulouse, 2007. http://ethesis.inp-toulouse.fr/archive/00000528.

Full text

APA, Harvard, Vancouver, ISO, and other styles

45

Dugas, Olivier. "Localisation relative à six degrés de liberté basée sur les angles et sur le filtrage probabiliste." Master's thesis, Université Laval, 2014. http://hdl.handle.net/20.500.11794/25607.

Full text

Abstract:

Lorsque des robots travaillent en équipe, il est avantageux de permettre à ceux-ci de se localiser mutuellement pour faire, par exemple, de la navigation en formation. La résolution de la localisation relative est d'une importance particulière pour des équipes de robots aériens ou sous-marins lorsque ceux-ci opèrent dans des environnements dépourvus de points de repère. Ce problème se complexifie davantage lorsque le système de localisation permet seulement l'utilisation de caméras légères et bon marché. Cette étude présente une solution analytique au problème de localisation relative à six degrés de liberté basée sur des mesures d'angle. Cette solution est intégrée à des filtres probabilistes pour augmenter sa précision. En utilisant deux robots mutuellement observables possédant chacun deux marqueurs et une caméra colinéaires, nous pouvons retrouver les transformations qui expriment la pose du premier dans le référentiel du second. Notre technique se distingue du fait qu'elle nécessite uniquement la mesure de deux paires d'angles, au lieu d'un mélange de mesures d'angles et de distances. La précision des résultats est vérifiée par des simulations ainsi que par des expérimentations concrètes. Suite à des expérimentations à des distances variant entre 3:0 m et 15:0 m, nous montrons que la position relative est estimée avec moins de 0:5 % d'erreur et que l'erreur moyenne sur l'orientation relative est maintenue sous 2:2 deg. Une généralisation approximative est formulée et simulée pour le cas où la caméra de chaque robot n'est pas colinéaire avec les marqueurs de celui-ci. Au-delà de la précision des caméras, nous montrons qu'un filtre non parfumé de Kalman permet d'adoucir l'erreur sur les estimations de la position relative, et qu'un filtre étendu de Kalman basé sur les quaternions peut faire de même pour l'orientation relative. Cela rend notre solution particulièrement adaptée pour le déploiement de flottes de robots à six degrés de liberté comme des dirigeables.
When a team of robots have to collaborate, it is useful to allow them to localize each other in order to maintain flight formations, for example. The solution of cooperative localization is of particular importance to teams of aerial or underwater robots operating in areas devoid of landmarks. The problem becomes harder if the localization system must be low-cost and lightweight enough that only consumer-grade cameras can be used. This paper presents an analytical solution to the six degrees of freedom cooperative localization problem using bearing only measurements. Probabilistic filters are integrated to this solution to increase it's accuracy. Given two mutually observing robots, each one equipped with a camera and two markers, and given that they each take a picture at the same moment, we can recover the coordinate transformation that expresses the pose of one robot in the frame of reference of the other. The novelty of our approach is the use of two pairs of bearing measurements for the pose estimation instead of using both bearing and range measurements. The accuracy of the results is verified in extensive simulations and in experiments with real hardware. In experiments at distances between 3:0 m and 15:0 m, we show that the relative position is estimated with less than 0:5 % error and that the mean orientation error is kept below 2:2 deg. An approximate generalization is formulated and simulated for the case where each robot's camera is not colinear with the same robot's markers. Passed the precision limit of the cameras, we show that an unscented Kalman filter can soften the error on the relative position estimations, and that an quaternion-based extended Kalman filter can do the same to the error on the relative orientation estimations. This makes our solution particularly well suited for deployment on fleets of inexpensive robots moving in 6 DoF such as blimps.

APA, Harvard, Vancouver, ISO, and other styles

46

Blumer, Benjamin. "Two-handed coordination in robots : by combining two one-handed trajectories based on probabilistic models of taskspace effects." Thesis, University of British Columbia, 2016. http://hdl.handle.net/2429/60226.

Full text

Abstract:

Human environments and tools are commonly designed to be used by two-handed agents. In order for a robot to make use of human tools or to navigate in a human environment it must be able to use two arms. Planning motion for two arms is a difficult task as it requires taking into account a large number of joints and links and involves both temporal and spatial coordination. The work in this thesis addresses these problems by providing a framework to combine two single-arm trajectories to perform a two-armed task. Inspired by results indicating that humans perform better on motor tasks when focusing on the outcome of their movements rather than their joint motions, I propose a solution that considers each trajectory's effect on the taskspace. I develop a novel framework for modifying and combining one-armed trajectories to complete two-armed tasks. The framework is designed to be as general as possible and is agnostic to how the one-armed trajectories were generated and the robot(s) being used. Physical roll-outs of the individual arm trajectories are used to create probabilistic models of their performance in taskspace using Gaussian Mixture Models. This approach allows for error compensation. Trajectories are combined in taskspace in order to achieve the highest probability of success and task performance quality. The framework was tested using two Barrett WAM robots performing the difficult, two-armed task of serving a ping-pong ball. For this demonstration, the trajectories were created using quintic interpolations of joint coordinates. The trajectory combinations are tested for collisions in the robot simulation tool, Gazebo. I demonstrated that the system can successfully choose and execute the highest-probability trajectory combination that is collision-free to achieve a given taskspace goal. The framework achieved timing of the two single-arm trajectories optimal to within 0.0389 seconds -- approximately equal to the time between frames of the 30 Hz camera. The implemented algorithm successfully ranked the likelihood of success for four out of five serving motions. Finally, the framework's ability to perform a higher-level tasks was demonstrated by performing a legal ping-pong serve. These results were achieved despite significant noise in the data.
Applied Science, Faculty of
Graduate

APA, Harvard, Vancouver, ISO, and other styles

47

Sturm, Jürgen [Verfasser], and Wolfram [Akademischer Betreuer] Burgard. "Approaches to probabilistic model learning for mobile manipulation robots = Ansätze zum maschinellen Lernen probabilistischer Modelle für mobile Manipulationsroboter." Freiburg : Universität, 2011. http://d-nb.info/1123460558/34.

Full text

APA, Harvard, Vancouver, ISO, and other styles

48

Sanchez, Lopez Abraham. "Contribution à la planification de mouvements en robotique : approches probabilistes et approches déterministes." Montpellier 2, 2003. http://www.theses.fr/2003MON20038.

Full text

APA, Harvard, Vancouver, ISO, and other styles

49

Brhel, Miroslav. "Řízení pohybu robota pomocí RaspberryPi a kamery." Master's thesis, Vysoké učení technické v Brně. Fakulta informačních technologií, 2015. http://www.nusl.cz/ntk/nusl-234934.

Full text

Abstract:

This Master's Thesis deals with the controlling of robotic car by Raspberry Pi and the ca- mera. Theoretical part describes individual steps of image processing and probabilistic plan- ning for searching path in the work space. In particular, algorithm RRT (Rapidly-exploring Random Tree) is discussed and the balanced bidirectional RRT is further introduced and used for nonholonomic planning in configuration space. Next chapter speaks about propo- sed solution and there is the accurate description of connection Raspberry Pi to the robotic car. Rest of the work provides look at implemetation details and evaluation. In the end, conclusion was given and some improvements were suggested.

APA, Harvard, Vancouver, ISO, and other styles

50

Schmidt-Rohr, Sven R. [Verfasser], and R. [Akademischer Betreuer] Dillmann. "Interactive Learning of Probabilistic Decision Making by Service Robots with Multiple Skill Domains / Sven R. Schmidt-Rohr. Betreuer: R. Dillmann." Karlsruhe : KIT-Bibliothek, 2012. http://d-nb.info/1028567170/34.

Full text

APA, Harvard, Vancouver, ISO, and other styles

Dissertations / Theses on the topic 'Probabilistic Robotics'

Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles