Dissertations / Theses on the topic 'Moving obstacles'

Dans le contexte des applications de perception pour le véhicule à conduite déléguée, l’intérêt pour les approches d’apprentissage automatique a continuellement augmenté pendant cette dernière décennie. Cependant, lorsque ces approches doivent être discriminatives, elle nécessitent généralement d’apprendre sur des données manuellement annotées. L’annotation manuelle a un coût non négligeable, tandis que les données non annotées peuvent être facilement obtenues dans le contexte d’un véhicule autonome équipé de capteurs. Il se trouve qu’une catégorie de stratégies d’apprentissage, dite d’apprentissage faiblement supervisé, permet d’exploiter des données partiellement labélisées. Ainsi, nous avons pour objectif dans cette thèse de réduire autant que possible le besoin de labélisation manuelle en proposant des techniques d’apprentissage faiblement supervisées
In the context of autonomous vehicle perception, the interest of the research community for deep learning approaches has continuously grown since the last decade. This can be explained by the fact that deep learning techniques provide nowadays state-of-the-art prediction performances for several computer vision challenges. More specifically, deep learning techniques can provide rich semantic information concerning the complex visual patterns encountered in autonomous driving scenarios. However, such approaches require, as their name implies, to learn on data. In particular, state-of-the-art prediction performances on discriminative tasks often demand hand labeled data of the target application domain. Hand labeling has a significant cost, while, conversely, unlabeled data can be easily obtained in the autonomous driving context. It turns out that a category of learning strategies, referred to as weakly supervised learning, enables to exploit partially labeled data. Therefore, we aim in this thesis at reducing as much as possible the hand labeling requirement by proposing weakly supervised learning techniques.We start by presenting a type of learning methods which are self-supervised. They consist of substituting hand-labels by upstream techniques able to automatically generate exploitable training labels. Self-supervised learning (SSL) techniques have proven their usefulness in the past for offroad obstacles avoidance and path planning through changing environments. However, SSL techniques still leave the door open for detection, segmentation, and classification of static potentially moving obstacles.Consequently, we propose in this thesis three novel weakly supervised learning methods with the final goal to deal with such road users through an SSL framework. The first two proposed contributions of this work aim at dealing with partially labeled image classification datasets, such that the labeling effort can be only focused on our class of interest, the positive class. Then, we propose an approach which deals with training data containing a high fraction of wrong labels, referred to as noisy labels. Next, we demonstrate the potential of such weakly supervised strategies for detection and segmentation of potentially moving obstacles

Cette thèse présente une étude théorique et numérique des écoulements non-stationnaires autour des ailes battantes des insectes. Une méthode numérique est développée pour modéliser des écoulements visqueux incompressibles autour d’obstacles mobiles. La condition de non-glissement sur les parois est imposée par la méthode de pénalisation. Le problème est discrétisé par une méthode pseudo-spectrale Fourier. Une approche originale est proposée pour l’interpolation de l’interface entre le fluide et le solide, basée sur la discrétisation spectrale. Le code de calcul est adapté aux architectures massivement parallèles. La méthode développée est utilisée pour examiner le mécanisme de Lighthill–Weis-Fogh, un mouvement qui permet d’augmenter la portance engendrée au début de chaque cycle de battement d’ailes. Cependant, cette étude commence par un développement non-visqueux. On s’intéresse particulièrement au changement topologique du domaine fluide, au moment où les ailes se touchent et puis se séparent. Le scénario bidimensionnel non-visqueux proposé par Lighthill est confirmé par un calcul directe, qui montre une possibilité d’engendrer un mouvement circulatoire dans un fluide non-visqueux. Ensuite, les effets visqueux sont considérés. Notamment, on établit que les contraintes visqueuses contrôlent l’établissement de l’écoulement dans l’espace entre les deux ailes après leur séparation. Au voisinage des bords de fuite le nombre de Reynolds est localement très faible, et l’écoulement est bien décrit par des solutions auto-similaires de l’équation de Stokes. Ensuite, des effets tridimensionnels sont considérés. Les simulations numériques sont effectuées avec deux valeurs du nombre de Reynolds, 128 et 1400, typique pour des différentes tailles des insectes. Au début d’un cycle de battement, l’approximation bidimensionnelle est justifiée ; peu de temps après, le caractère tridimensionnel de l’écoulement commence à jouer un rôle important en faisant retarder le décrochage des tourbillons. Enfin, quelques résultats sur le couplage du mouvement du fluide et du solide sont présentés. On considère la chute libre des plaques sous la force de gravite. Les simulations numérique à Re = 10, 100 et 1000 montre l’effet stabilisant de la viscosité
The dissertation presents theoretical and numerical studies of unsteady flows relevant to insect flapping flight. Much emphasis is put on the development of a numerical method for modelling incompressible viscous flows past multiple moving solid obstacles. The Navier–Stokes equations are solved using a Fourier pseudo-spectral discretization. Solid obstacles are modelled with the volume penalization method. An original approach is proposed for interpolation of the time-dependent penalization mask function, which takes advantage of the spectral discretization. Both two- and three-dimensional solvers have been developed, which differ in some implementation aspects. Notably, the three-dimensional code is adapted for massively parallel computers. The newly-developed numerical method is employed in a study of the Lighthill–Weis- Fogh mechanism, an unsteady aerodynamic mechanism used by some insects. That study begins, however, with the inviscid fluid model first considered by Lighthill. A transition from fling to sweep is analysed, when the connectivity of the domain changes. Then, modifications due to viscosity are explored. Important viscous effects are found near the trailing edges. The flow field near the hinge, observed in numerical simulations, is explained theoretically by local analysis of the Stokes equation. The importance of the three-dimensional effects is assessed. Numerical simulations are performed at two different values of the Reynolds number, Re = 128 and 1400, typical for insects of different size. The flow during fling is shown to be in reasonable agreement with the two-dimensional approximation. After the wings move apart, three-dimensional effects become essential. The penalization model has been extended to solve the problem of solid bodies falling through a fluid. Numerical simulations at Re = 10, 100 and 1000 have shown that decreasing Re has a stabilizing effect on the free fall dynamics

In this thesis, four robots will be used to implement a collision-free trajectory planning/replanning algorithm. The existence of a chained form transformation so that the robot's model can be control in canonical form will be analyzed and proved. A trajectory generation for obstacles avoidance will be derived, simulated, and implemented. A specific PC based control algorithm will be developed. Chapter two describes two wheels differential drive robot modeling and existence of controllable canonical chained form. Chapter 3 describes criterion for avoiding dynamic objects, a feasible collision-free trajectory parameterization, and solution to steering velocity. Chapter 4 describes robot implementation, pc wireless interface, and strategy to send and receive information wirelessly. The main robot will be moving in a dynamically changing environment using canonical chained form. The other three robots will be used as moving obstacles that will move with known piecewise constant velocities, and therefore, with known trajectories. Their initial positions are assumed to be known as well. The main robot will receive the command from the computer such as how fast to move and to turn in order to avoid collision. The robot will autonomously travel to the desired destination collision-free.
M.S.E.E.
School of Electrical Engineering and Computer Science
Engineering and Computer Science
Electrical Engineering

Virtual visualization of mobile robot analytical trajectories while avoiding moving obstacles is presented in this thesis as a very helpful technique to properly display and communicate simulation results. Analytical solutions to the path planning problem of mobile robots in the presence of obstacles and a dynamically changing environment have been presented in the current robotics and controls literature. These techniques have been demonstrated using two-dimensional graphical representation of simulation results. In this thesis, the analytical solution published by Dr. Zhihua Qu in December 2004 is used and simulated using a virtual visualization tool called VRML.
M.S.E.E.
School of Electrical Engineering and Computer Science
Engineering and Computer Science
Electrical Engineering MSEE

This thesis presents a 3D reconstruction approach to the detection of static obstacles from a single rear view parking camera. Corner features are tracked to estimate the vehicle’s motion and to perform multiview triangulation in order to reconstruct the scene. We model the camera motion as planar motion and use the knowledge of the camera pose to efficiently solve motion parameters. Based on the observed motion, we selected snapshots from which the scene is reconstructed. These snapshots guarantee a sufficient baseline between the images and result in more robust scene modeling. Multiview triangulation of a feature is performed only if the feature obeys the epipolar constraint. Triangulated features are semantically labelled according to their 3D location. Obstacle features are spatially clustered to reduce false detections. Finally, the distance to the nearest obstacle cluster is reported to the driver.

We introduce a vision system for autonomous navigation of a mobile platform. This system is able to interact with is immediate environment by recognizing obstacles and moving objects and means of a stable representation of external world. This system is made of 3 components : external world representation, obstacles detection and avoidance, behavioral analysis. The main contribution of this work lies in the perceptive representation of the external world, e. G. A representation compared to the final goal of autonomous navigation. This representation is based on the stereovision paradigm and is able to determine in the scene obstacles and moving objects. Our approach returns the depth of any region. The location estimation of regions is precise with respect to navigation requirements and the system is fast enough for real time applications
Nous présentons un système de vision pour la navigation autonome d’une plateforme mobile. Ce système est en mesure d’interagir avec l’espace immédiatement environnant, en reconnaissant les obstacles et les objets en mouvement et en construisant une vision stable du monde extérieur. Le système est composé de trois composants : la représentation dans l’espace environnant ; la détection et l’évitement des obstacles et l’analyse comportementale. La contribution majeure de ce travail concerne la représentation « perceptive » de l’espace, c’est-à-dire une représentation qui est comparée à l’objectif final de la navigation autonome. Cette représentation est basée sur le paradigme de la vision stéréo et elle permet de déterminer dans la scène les obstacles et les objets en mouvement. Notre méthode fournit la profondeur moyenne par région. L’estimation de la position des régions est suffisamment précise pour la navigation et le système est assez rapide pour les applications en temps réel

The Micro Aerial Vehicless (MAVs) are gaining attention in numerous applications asthese platforms are cheap and can do complex maneuvers. Moreover, most of the commer-cially available MAVs are equipped with a mono-camera. Currently, there is an increasinginterest to deploy autonomous mono-camera MAVs with obstacle avoidance capabilitiesin various complex application areas. Some of the application areas have moving obstaclesas well as stationary, which makes it more challenging for collision avoidance schemes.This master thesis set out to investigate the possibility to avoid moving and station-ary obstacles with a single camera as the only sensor gathering information from thesurrounding environment.One concept to perform autonomous obstacle avoidance is to predict the time near-collision based on a Convolution Neural Network (CNN) architecture that uses the videofeed from a mono-camera. In this way, the heading of the MAV is regulated to maximizethe time to a collision, resulting in the avoidance maneuver. Moreover, another interestingperspective is when due to multiple dynamic obstacles in the environment there aremultiple time predictions for different parts of the Field of View (FoV). The method ismaximizing time to a collision by choosing the part with the largest time to collision.However, this is a complicated task and this thesis provides an overview of it whilediscussing the challenges and possible future directions. One of the main reason was thatthe available data set was not reliable and was not provide enough information for theCNN to produce any acceptable predictions.Moreover, this thesis looks into another approach for avoiding collisions, using objectdetection method You Only Lock Once (YOLO) with the mono-camera video feed. YOLOis a state-of-the-art network that can detect objects and produce bounding boxes in real-time. Because of YOLOs high success rate and speed were it chosen to be used in thisthesis. When YOLO detects an obstacle it is telling where in the image the object is,the obstacle pixel coordinates. By utilizing the images FoV and trigonometry can pixelcoordinates be transformed to an angle, assuming the lens does not distort the image.This position information can then be used to avoid obstacles. The method is evaluated insimulation environment Gazebo and experimental verification with commercial availableMAV Parrot Bebop 2. While the obtained results show the efficiency of the method. To bemore specific, the proposed method is capable to avoid dynamic and stationary obstacles.Future works will be the evaluation of this method in more complex environments with multiple dynamic obstacles for autonomous navigation of a team of MAVs. A video ofthe experiments can be viewed at:https://youtu.be/g_zL6eVqgVM.

Micro aerial vehicles and other autonomous systems have the potential to truly transform life as we know it, however much of the potential of autonomous systems remains unrealized because reliable navigation is still an unsolved problem with significant challenges. This dissertation presents solutions to many aspects of autonomous navigation. First, it presents ROSflight, a software and hardware architure that allows for rapid prototyping and experimentation of autonomy algorithms on MAVs with lightweight, efficient flight control. Next, this dissertation presents improvments to the state-of-the-art in optimal control of quadrotors by utilizing the error-state formulation frequently utilized in state estimation. It is shown that performing optimal control directly over the error-state results in a vastly more computationally efficient system than competing methods while also dealing with the non-vector rotation components of the state in a principled way. In addition, real-time robust flight planning is considered with a method to navigate cluttered, potentially unknown scenarios with real-time obstacle avoidance. Robust state estimation is a critical component to reliable operation, and this dissertation focuses on improving the robustness of visual-inertial state estimation in a filtering framework by extending the state-of-the-art to include better modeling and sensor fusion. Further, this dissertation takes concepts from the visual-inertial estimation community and applies it to tightly-coupled GNSS, visual-inertial state estimation. This method is shown to demonstrate significantly more reliable state estimation than visual-inertial or GNSS-inertial state estimation alone in a hardware experiment through a GNSS-GNSS denied transition flying under a building and back out into open sky. Finally, this dissertation explores a novel method to combine measurements from multiple agents into a coherent map. Traditional approaches to this problem attempt to solve for the position of multiple agents at specific times in their trajectories. This dissertation instead attempts to solve this problem in a relative context, resulting in a much more robust approach that is able to handle much greater intial error than traditional approaches.

Pour les véhicules intelligents autonomes ou semi-autonomes, la perception constitue la première tâche fondamentale à accomplir avant la décision et l’action. Grâce à l’analyse des données vidéo, Lidar et radar, elle fournit une représentation spécifique de l’environnement et de son état, à travers l’extraction de propriétés clés issues des données des capteurs. Comparé à d’autres modalités de perception telles que le GPS, les capteurs inertiels ou les capteurs de distance (Lidar, radar, ultrasons), les caméras offrent la plus grande quantité d’informations. Grâce à leur polyvalence, les caméras permettent aux systèmes intelligents d’extraire à la fois des informations contextuelles de haut niveau et de reconstruire des informations géométriques de la scène observée et ce, à haute vitesse et à faible coût. De plus, la technologie de détection passive des caméras permet une faible consommation d’énergie et facilite leur miniaturisation. L’utilisation des caméras n’est toutefois pas triviale et pose un certain nombre de questions théoriques liées à la façon dont ce capteur perçoit son environnement. Dans cette thèse, nous proposons un système de détection d’objets mobiles basé seule- ment sur l’analyse d’images. En effet, dans les environnements observés par un véhicule intelligent, les objets en mouvement représentent des obstacles avec un risque de collision élevé, et ils doivent être détectés de manière fiable et robuste. Nous abordons le problème de la détection d’objets mobiles à partir de l’extraction du contexte local reposant sur une segmentation de la route. Après transformation de l’image couleur en une image invariante à l’illumination, les ombres peuvent alors être supprimées réduisant ainsi leur influence négative sur la détection d’obstacles. Ainsi, à partir d’une sélection automatique de pixels appartenant à la route, une région d’intérêt où les objets en mouvement peuvent apparaître avec un risque de collision élevé, est extraite. Dans cette zone, les pixels appartenant à des objets mobiles sont ensuite identifiés à l’aide d’une approche plan+parallaxe. À cette fin, les pixels potentiellement mobiles et liés à l’effet de parallaxe sont détectés par une méthode de soustraction du fond de l’image; puis trois contraintes géométriques différentes: la contrainte épipolaire, la contrainte de cohérence structurelle et le tenseur trifocal, sont appliquées à ces pixels pour filtrer ceux issus de l’effet de parallaxe. Des équations de vraisemblance sont aussi proposées afin de combiner les différents contraintes d’une manière complémentaire et efficace. Lorsque la stéréovision est disponible, la segmentation de la route et la détection d’obstacles peuvent être affinées en utilisant une segmentation spécifique de la carte de disparité. De plus, dans ce cas, un algorithme de suivi robuste combinant les informations de l’image et la profondeur des pixels a été proposé. Ainsi, si l’une des deux caméras ne fonctionne plus, le système peut donc revenir dans un mode de fonctionnement monoculaire ce qui constitue une propriété importante pour la fiabilité et l’intégrité du système de perception. Les différents algorithmes proposés ont été testés sur des bases de données d’images publiques en réalisant une évaluation par rapport aux approches de l’état de l’art et en se comparant à des données de vérité terrain. Les résultats obtenus sont prometteurs et montrent que les méthodes proposées sont efficaces et robustes pour différents scénarios routiers et les détections s’avèrent fiables notamment dans des situations ambiguës
For autonomous or semi-autonomous intelligent vehicles, perception constitutes the first fundamental task to be performed before decision and action/control. Through the analysis of video, Lidar and radar data, it provides a specific representation of the environment and of its state, by extracting key properties from sensor data with time integration of sensor information. Compared to other perception modalities such as GPS, inertial or range sensors (Lidar, radar, ultrasonic), the cameras offer the greatest amount of information. Thanks to their versatility, cameras allow intelligent systems to achieve both high-level contextual and low-level geometrical information about the observed scene, and this is at high speed and low cost. Furthermore, the passive sensing technology of cameras enables low energy consumption and facilitates small size system integration. The use of cameras is however, not trivial and poses a number of theoretical issues related to how this sensor perceives its environmen. In this thesis, we propose a vision-only system for moving object detection. Indeed,within natural and constrained environments observed by an intelligent vehicle, moving objects represent high risk collision obstacles, and have to be handled robustly. We approach the problem of detecting moving objects by first extracting the local contextusing a color-based road segmentation. After transforming the color image into illuminant invariant image, shadows as well as their negative influence on the detection process can be removed. Hence, according to the feature automatically selected onthe road, a region of interest (ROI), where the moving objects can appear with a high collision risk, is extracted. Within this area, the moving pixels are then identified usin ga plane+parallax approach. To this end, the potential moving and parallax pixels a redetected using a background subtraction method; then three different geometrical constraints : the epipolar constraint, the structural consistency constraint and the trifocaltensor are applied to such potential pixels to filter out parallax ones. Likelihood equations are also introduced to combine the constraints in a complementary and effectiveway. When stereo vision is available, the road segmentation and on-road obstacles detection can be refined by means of the disparity map with geometrical cues. Moreover, in this case, a robust tracking algorithm combining image and depth information has been proposed. If one of the two cameras fails, the system can therefore come back to a monocular operation mode, which is an important feature for perception system reliability and integrity. The different proposed algorithms have been tested on public images data set with anevaluation against state-of-the-art approaches and ground-truth data. The obtained results are promising and show that the proposed methods are effective and robust on the different traffic scenarios and can achieve reliable detections in ambiguous situations

abstract: There has been a vast increase in applications of Unmanned Aerial Vehicles (UAVs) in civilian domains. To operate in the civilian airspace, a UAV must be able to sense and avoid both static and moving obstacles for flight safety. While indoor and low-altitude environments are mainly occupied by static obstacles, risks in space of higher altitude primarily come from moving obstacles such as other aircraft or flying vehicles in the airspace. Therefore, the ability to avoid moving obstacles becomes a necessity for Unmanned Aerial Vehicles. Towards enabling a UAV to autonomously sense and avoid moving obstacles, this thesis makes the following contributions. Initially, an image-based reactive motion planner is developed for a quadrotor to avoid a fast approaching obstacle. Furthermore, A Dubin’s curve based geometry method is developed as a global path planner for a fixed-wing UAV to avoid collisions with aircraft. The image-based method is unable to produce an optimal path and the geometry method uses a simplified UAV model. To compensate these two disadvantages, a series of algorithms built upon the Closed-Loop Rapid Exploratory Random Tree are developed as global path planners to generate collision avoidance paths in real time. The algorithms are validated in Software-In-the-Loop (SITL) and Hardware-In-the-Loop (HIL) simulations using a fixed-wing UAV model and in real flight experiments using quadrotors. It is observed that the algorithm enables a UAV to avoid moving obstacles approaching to it with different directions and speeds.
Dissertation/Thesis
Doctoral Dissertation Computer Science 2015

碩士
長榮大學
職業安全與衛生學系碩士班
98
The railway transportation is quite important, and has integrated into the populace's lives in Taiwan. The crossing where a railway and a road intersect is the region that the road users and the train meet. The railway has brought us convenience, but on the contrary has also caused many traffic accidents each year. Presently the railway in Taiwan spans approximately 1,100 kilometers and has 650 level crossings, which means that approximately every 1.7 kilometers there will be a crossing on the tracks. Therefore, most road users has many chances to pass through the crossings everyday.. According to the statistics 432 accidents occurred at all crossings in Taiwan during 2004-2008 and claimed 132 deaths and 137 wounds, which shows that some citizens have not obeyed the traffic regulations and that the safety protection measures on the crossings still need to be improved. The existing protection devices of crossing include those traditional signs, flash lights, horns , barriers and direction indicators of the approaching trains. These devices only give warmings to the road users but can not do anything about intrusions and temporary stops at the crossing. Among the recently equipped devices emergency buttons need the passers-by to operate manually. In the state of news, people may stall or even forget to operate the buttons, which actually reduces the effect of this device. As matter of fact, there are more hoaxes than real emergency conditions. Other recently developed devices can automatically detect obstacles, which include photoelectric sensors, inductive coils, radar and ultrasonic systems. However, these safety devices have some defects. Such as the blind spots to the photoelectric instrument, the climate and the interference sensitive to the inductive coils, the surrounding interference and the restrictive regulations to the radar signals, as well as the wind disturbance to the ultrasound devices. This study utilizes a 1394 CCD camera and the LabVIEW Graphic programming language to process the images of a railway crossing miniature. The developed system is designed to be a redundant safety measure which is able to detect the existence of obstacles at the crossing, along with the characteristics of moving obstacles. If the crossing is not clear, the system will send alarms immediately to avoid the accident and reduce its severity. Therefore the safety of the crew and passengers on the trains as well as the road users can be further assured.

碩士
國立臺北科技大學
機電整合研究所
96
In this paper, we develop the system of autonomous land vehicles (ALV) by computer vision with artificial intelligent (AI) based on optical flow method. It makes ALV adapted to the complex environment. This system can verify the motion obstacle and estimate its movement, and then making path strategy to avoid collision. Our algorithm of ALV has three parts, image capture system, static object analyzed system, and motion object detection system, respectively. We set ALV navigates at an outdoor environment automatically. In computer vision analyzed, we present a method that use Lucas and Kanade''s Optical flow equation, then we obtain the optical flow map, by using three-dimension histogram (3-D histogram) to gather statistics of our moving object, checking our optical vectors group, separating the optical vectors of obstacle and background, and use morphological process to segment the moving object. We segment them and use first-order linear equation to calculate the relationship between ALV and the motion obstacle. At last, calculate the collision time between the moving object and ALV and makes strategy to avoid collision with obstacle. Finally, our experiment shows the method avoiding collision with moving object efficiently when ALV moving on its way.

碩士
國立臺北科技大學
機電整合研究所
92
In this study, AutoCAD 2002 is used as a working media. Through VBA and 3D solid drawing function inside AutoCAD, an interface software of moving obstacle-avoidance path planning for Mitsubishi Robot RV-E2 is established. First, user needs to input the information which include both start point and end point for end effecter of robot、the dimension of both obstacle and end effecter、the moving speed of both obstacle and robot、the start point of obstacle. Second, We build the 3D solid model of obstacle and robot in the Working space of AutoCAD. Then according to these input data, simulation for the moving motion is made to check if any interference (collision) by using “Interference” command of AutoCAD is happened. All coordinates of trajectory just pass through are recorded. Here we offer an intelligent graph interference theory to determine the best path of obstacle-Avoidance. This non-collision path made by using this moving simulation method is shown on the screen of AutoCAD. Finally, We can transfer the calculated path data through RS-232 to the controller of robot to drive it. The actual moving obstacle-Avoidance motion path and the physical motion path are feedback to the AutoCAD screen immediately for comparison with the theoretical simulation path.

Η παρούσα διπλωματική ασχολείται με την πλοήγηση κινούμενου ρομπότ. Δεδομένου ενός χώρου με εμπόδια και στόχο, ασχολείται με την δημιουργία ενός αλγορίθμου για την οδήγηση του ρομπότ διαμέσου του χώρου στο στόχο, αποφεύγοντας τα εμπόδια κατά την κίνηση. Επικεντρώνεται σε δίτροχα ρομπότ και αναλύει βήμα βήμα την διαδικασία εύρεση μονοπατιού, δημιουργία τροχιάς και έλεγχο του ρομπότ.
The present thesis deals with the navigation of moving robots. Granted an area with obstacles and target, it deals with the creation of an algorithm for guiding the robot through space at target, avoiding obstacles during movement. It focuses on two-wheeled robots and analyzes step by step the process of finding a path, creating the trajectory and controlling the robot.