Rozprawy doktorskie na temat „Collision avoidance”
Kliknij ten link, aby zobaczyć inne rodzaje publikacji na ten temat: Collision avoidance.
Utwórz poprawne odniesienie w stylach APA, MLA, Chicago, Harvard i wielu innych
Sprawdź 50 najlepszych rozpraw doktorskich naukowych na temat „Collision avoidance”.
Przycisk „Dodaj do bibliografii” jest dostępny obok każdej pracy w bibliografii. Użyj go – a my automatycznie utworzymy odniesienie bibliograficzne do wybranej pracy w stylu cytowania, którego potrzebujesz: APA, MLA, Harvard, Chicago, Vancouver itp.
Możesz również pobrać pełny tekst publikacji naukowej w formacie „.pdf” i przeczytać adnotację do pracy online, jeśli odpowiednie parametry są dostępne w metadanych.
Przeglądaj rozprawy doktorskie z różnych dziedzin i twórz odpowiednie bibliografie.
1
Matthews, Neil David. "Visual collision avoidance". Thesis, University of Southampton, 1999. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.287308.
Pełny tekst źródła
2
Perkins, Christopher James. "International collision regulations for automatic collision avoidance". Thesis, University of Plymouth, 1996. http://hdl.handle.net/10026.1/2270.
Pełny tekst źródłaStreszczenie:
This thesis considers the relationship between collision regulations and an automatic collision avoidance system (ACAS). Automation of ship operations is increasingly common. The automation of the collision avoidance task may have merit on grounds of reduced manual workload and the elimination of human error. Work to date by engineers and computer programmers has focused on modelling the requirements of the current collision regulations. This thesis takes a new approach and indicates that legislative change is a necessary precursor to the implementation of a fully automatic collision avoidance system. A descriptive analysis has been used to consider the nature of the collision avoidance problem and the nature of rules as a solution. The importance of coordination between vessels is noted and three requirements for coordination are established. These are a mutual perception of: risk, the strategy to be applied, and the point of manoeuvre. The use of rules to achieve coordination are considered. The analysis indicates that the current collision regulations do not provide the means to coordinate vessels. A review of current and future technology that may be applied to the collision avoidance problem has been made. Several ACAS scenarios are contrived. The compatibility of the scenarios and the current collision regulations is considered. It is noted that both machine sensors and processors affect the ability to comply with the rules. The case is made for judicial recognition of a discrete rule-base for the sake of an ACAS. This leads to the prospect of quantified collision regulations for application by mariners. A novel rule-base to match a pm1icular ACAS scenario has been devised. The rules are simple and brief. They avoid inputs dependent on vision and visibility, and meet all the aforementioned coordination requirements. Their application by mariners to two-vessel open sea, encounters was tested on a navigation simulator. The experimental testing of such a rule-base is unique. Mariners were given experience of applying the rule-base in certain circumstances and asked by questionnaire what their agreeable action would be. This was compared with their usual action. While the number of experiments was small, an indication was given of the impm1ant issues in applying a quantified rule-base. Aspects identified for fm1her study include the testing of rule base elements in isolation, and the use of quantified rules in multi-ship and confined water encounters.
3
Engelhardtsen, Øystein. "3D AUV Collision Avoidance". Thesis, Norwegian University of Science and Technology, Department of Engineering Cybernetics, 2007. http://urn.kb.se/resolve?urn=urn:nbn:no:ntnu:diva-9534.
Pełny tekst źródłaStreszczenie:
An underlying requirement for any Autonomous Underwater Vehicle (AUV) is to navigate through unknown or partly unknown environments while performing certain user specified tasks. The loss of an AUV due to collision is unjustifiable both in terms of cost and replacement time. To prevent such an unfortunate event, one requires a robust and effective Collision Avoidance System (CAS). This paper discusses the collision avoidance problem for the HUGIN AUVs. In the first part, a complete simulator for the HUGIN AUV is implemented in matlab and simulink. This includes a 6 degrees-of-freedom nonlinear AUV model, simulated environment including bottom profile and surface ice, navigation- and guidance functionality and sensor simulators. In the second part a number of well known strategies for the collision avoidance problem is presented with a short analysis of their properties. On the basis of the implemented simulator, a proposed CAS is developed and it’s performance is analyzed. This system is based on simple principles and known collision avoidance strategies, in order to provide effective and robust performance. The proposed system provides feasible solutions during all simulations and the collision avoidance maneuvers are performed in accordance with the specified user demands. The developed simulator and collision avoidance system is expected to provide a suitable framework for further development and possibly a physical implementation on the HUGIN AUVs.
4
Tsoularis, A. "Collision avoidance in unstructured workspaces". Thesis, University of Reading, 1997. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.360766.
Pełny tekst źródła
5
Phan, Long N. 1976. "Collision avoidance via laser rangefinding". Thesis, Massachusetts Institute of Technology, 1999. http://hdl.handle.net/1721.1/80045.
Pełny tekst źródłaStreszczenie:
Thesis (S.M.)--Massachusetts Institute of Technology, Dept. of Mechanical Engineering; and, (S.M.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering, 1999.Includes bibliographical references (leaf 105).
by Long N. Phan.
S.M.
6
Agarwal, Megha, Alisha Bandekar, Ashley Kang, Tyler Martis, Hossein Namazyfard, Alan Yeh, Megha Agarwal i in. "Automotive LiDAR Collision-Avoidance System". Thesis, The University of Arizona, 2017. http://hdl.handle.net/10150/624893.
Pełny tekst źródłaStreszczenie:
The project at hand is an Automotive LiDAR Collision Avoidance System sponsored by
Texas Instruments. The purpose of this project is to design and create a LiDAR system
that utilizes Texas Instruments' technology to avoid forward collisions when mounted on
a remote control car. The team is made up of six seniors from the University of Arizona
of four different engineering disciplines including electrical, mechanical, computer, and
optical engineering. The LiDAR Collision avoidance system is designed and built under a
budget constraint of $4,000 and a non-negotiable completion deadline of May 1, 2017,
otherwise known as Design Day.
7
Jansson, Jonas. "Collision avoidance theory with application to automotive collision mitigation /". Doctoral thesis, Linköping : Dept. of Electrical Enginering, Univ, 2005. http://www.bibl.liu.se/liupubl/disp/disp2005/tek950s.pdf.
Pełny tekst źródła
8
Loe, Øivind Aleksander G. "Collision Avoidance for Unmanned Surface Vehicles". Thesis, Norwegian University of Science and Technology, Department of Engineering Cybernetics, 2008. http://urn.kb.se/resolve?urn=urn:nbn:no:ntnu:diva-8866.
Pełny tekst źródłaStreszczenie:
Considerable progress has been achieved in recent years with respect to autonomous vehicles. A good example is the DARPA Grand Challenge, a competition for autonomous ground vehicles. None of the competing vehicles managed to complete the challenge in 2004, but returning in 2005, a total of five vehicles were successful. Effective collision avoidance is a requirement for autonomous navigation, and even though much progress has been done, it still remains an open problem. The focus of this thesis is on the development of a collision avoidance system for unmanned surface vehicles (USVs), which is compliant with the International Regulations for Avoiding Collisions at Sea (COLREGS). The system is based on a modified version of the Dynamic Window algorithm, taking both acceleration and lateral speeds into account for reactive collision avoidance. Path planning is provided by the Rapidly-Exploring Random Tree (RRT) algorithm, extended to use the A* algorithm as a guide, which significantly increases its efficiency. Extensive simulations have been performed in order to determine the value of the modifications done to the original algorithms, as well as the performance of the total control system. Full-scale experiments have also been carried out in an attempt to verify the results from the simulations. The collision avoidance system performed very well during the simulations, finding near-optimal paths through the environment and evading other vessels in a COLREGS-compliant fashion. In the full-scale experiments, important sensor data was erroneous, resulting in reduced avoidance margins. However, the collision avoidance system still kept the controlled vessel safe, showing significant robustness.
9
Rennæs, Karsten Fernholt. "Wireless Positioning and Collision Avoidance System". Thesis, Norges teknisk-naturvitenskapelige universitet, Institutt for teknisk kybernetikk, 2012. http://urn.kb.se/resolve?urn=urn:nbn:no:ntnu:diva-19205.
Pełny tekst źródłaStreszczenie:
Early in the 1980's Jens G. Balchen wanted to create an autonomous bike, capable of driving without any help from supporting wheels or human interaction. The intriguing idea included a variety of complicated concepts and was at that time almost an impossible task to accomplish. As time progressed and both technology and equipment developed, the possibility of a driverless bike becomes more than just an idea. The Norwegian University of Science and Technology (NTNU) has during the later years dedicated resources, time and effort in making a reality of the concept through the project named CyberBike. Every year, clever solutions are brought to the table, adding more functionality and better designs, bringing the project closer to a complete solution of an autonomous bike.The main focus of this thesis has been to develop a system for the bikes positioning system, as well as collision avoidance. It also includes the communication made from the bike to a potential operator via wireless data transfer. The goal is to make a solution for the bike so that it could travel a given route, while communicating important data back to the observers. The task encompasses gathering the information made available by previous work, defining key areas of improvement and designing and testing a proposed solution. First, the overall design is presented, showing how the two circuit boards made as the solution are connected with possible peripherals. The technical communication challenges pertaining the wireless communication is touched upon and relevant concepts are introduced. Furthermore, the selected microcontroller for the system is presented, giving key pointers in specific areas which might be confusing. Different possible devices are then discussed for the positioning system, the wireless communication and different setups of range sensors. Testing done using the equipment explained in the thesis is presented, showing the results of the system. Improvements to the solution are introduced based on the experience obtained through the work, giving a solid basis for further work relating to the subject.
10
Strömgren, Oliver. "Deep Learning for Autonomous Collision Avoidance". Thesis, Linköpings universitet, Datorseende, 2018. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-147693.
Pełny tekst źródłaStreszczenie:
Deep learning has been rapidly growing in recent years obtaining excellent results for many computer vision applications, such as image classification and object detection. One aspect for the increased popularity of deep learning is that it mitigates the need for hand-crafted features. This thesis work investigates deep learning as a methodology to solve the problem of autonomous collision avoidance for a small robotic car. To accomplish this, transfer learning is used with the VGG16 deep network pre-trained on ImageNet dataset. A dataset has been collected and then used to fine-tune and validate the network offline. The deep network has been used with the robotic car in a real-time manner. The robotic car sends images to an external computer, which is used for running the network. The predictions from the network is sent back to the robotic car which takes actions based on those predictions. The results show that deep learning has great potential in solving the collision avoidance problem.
11
Li, Huiying. "Visual cueing for collision avoidance system". Thesis, Cranfield University, 2012. http://dspace.lib.cranfield.ac.uk/handle/1826/7927.
Pełny tekst źródłaStreszczenie:
The modern Traffic Alert and Collision Avoidance System (TCAS) used
in airlines today is the TCAS II. It provides pilots with both Traffic
Advisory (TA) and Resolution Advisory (RA) which in turn reduces the incidence
of mid-air collisions. It was demonstrated that TCAS could provide
safety and economy benefits for airlines nowadays. However, as the demand
for commercial air travels increases, it exerted a considerable amount of
strain on the current ‘traditional’ TCAS system. This is primarily due to the
increase in competition for airspace. Trajectory-based TCAS systems have
been proposed to overcome the emerging difficulties with collision avoidance.
To date, TCAS systems only provide vertical 2D guidance for the aircraft,
that is to say, that the pilot only receives a ‘Climb’ or ‘Descend’ indicator
with minimalistic visual cues. The following thesis proposes a new visual
cueing method which integrates 3D trajectory path planning for TCAS system.
In general, Head-up Display (HUD) instrumentation provides the pilot with
primary flight display, navigation and guidance information pertaining to
the aircraft’s states. It is especially useful during the critical flight phases,
such as approach, landing and manoeuvring. Furthermore, as the HUD is
located in the direct front field of view, it allows the pilot to keep his her
head up while performing special tasks. It has been demonstrated that the
HUD adds a substantial safety benefit as well as mitigating pilot workload.
Thus a conceptual HUD has been proposed and was used in this project, the
developed TCAS manoeuvre display and conflict alerts were superimposed
on HUD.
A Boeing 747 aircraft model developed in the MATLAB Simulink environment
has been integrated with a 3D trajectory-based TCAS system. Perspective
projection techniques were addressed for TCAS resolution display
and were developed in Java. The resolution display utilizes 3D tunnel-in-thesky
concept as an advanced visual cue. TCAS traffic indications and aural
announcements were implemented using Java and MATLAB respectively.
The HUD concept was designed in the de-cluttered format in accordance
with FAR 25.1321 SAE ARP5288 standards, and was also developed in
Java language. It maximised compatibility with head down display. Finally,
the impact of the developed visual cueing methods were discussed and assessed through scenario trials.
This thesis presents an account of the work done within the scope. It underlines
the main considerations of the design, how scenarios were implemented
and their measurements. The research indicated that tunnel-in-the-sky was
an appropriate display solution for trajectory-based collision avoidance. It
has the advantage of presenting the predictive flight path in an intuitive and
natural way.
12
Coenen, Frans Pierre. "A rule based collision avoidance system". Thesis, Liverpool John Moores University, 1989. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.237820.
Pełny tekst źródła
13
Hsieh, Pin-Chun. "Autonomous robotic wheelchair with collision-avoidance navigation". Texas A&M University, 2008. http://hdl.handle.net/1969.1/86037.
Pełny tekst źródłaStreszczenie:
The objective of this research is to demonstrate a robotic wheelchair moving in an
unknown environment with collision-avoidance navigation. A real-time path-planning
algorithm was implemented by detecting the range to obstacles and by tracking specific
light sources used as beacons. Infrared sensors were used for range sensing, and
light-sensitive resistors were used to track the lights.
To optimize the motion trajectory, it was necessary to modify the original motor
controllers of the electrical wheelchair so that it could turn in a minimum turning radius
of 28.75 cm around its middle point of axle. Then, with these kinematics, the real-time
path planning algorithm of the robotic wheelchair is simplified. In combination with the
newly developed wireless Internet-connection capability, the robotic wheelchair will be
able to navigate in an unknown environment.
The experimental results presented in this thesis include the performance of the control
system, the motion trajectory of the two driving wheels turning in a minimum radius, and the motion trajectory of the real-time path-planning in a real-life testing environment.
These experimental results verified that the robotic wheelchair could move successfully
in an unknown environment with collision-avoidance navigation.
14
Melega, Marco. "Autonomous Collision avoidance for Unmanned aerial systems". Thesis, Cranfield University, 2014. http://dspace.lib.cranfield.ac.uk/handle/1826/9251.
Pełny tekst źródłaStreszczenie:
Unmanned Aerial System (UAS) applications are growing day by day and this will lead Unmanned Aerial Vehicle (UAV) in the close future to share the same airspace of manned aircraft.This implies the need for UAS to define precise safety standards compatible with operations standards for manned aviation. Among these standards the need for a Sense And Avoid (S&A) system to support and, when necessary, sub¬stitute the pilot in the detection and avoidance of hazardous situations (e.g. midair collision, controlled flight into terrain, flight path obstacles, and clouds).
This thesis presents the work come out in the development of a S&A system taking into account collision risks scenarios with multiple moving and fixed threats. The conflict prediction is based on a straight projection of the threats state in the future. The approximations introduced by this approach have the advantage of high update frequency (1 Hz) of the estimated conflict geometry. This solution allows the algorithm to capture the trajectory changes of the threat or ownship. The resolution manoeuvre evaluation is based on a optimisation approach considering step command applied to the heading and altitude autopilots. The optimisation problem takes into account the UAV performances and aims to keep a predefined minimum separation distance between UAV and threats during the resolution manouvre. The Human-Machine Interface (HMI) of this algorithm is then embedded in a partial Ground Control Station (GCS) mock-up with some original concepts for the indication of the flight condition parameters and the indication of the resolution manoeuvre constraints.
Simulations of the S&A algorithm in different critical scenarios are moreover in-cluded to show the algorithm capabilities. Finally, methodology and results of the tests and interviews with pilots regarding the proposed GCS partial layout are covered.
15
Blackwell, Grahame Kenneth. "An expert systems approach to collision avoidance". Thesis, University of Plymouth, 1992. http://hdl.handle.net/10026.1/1773.
Pełny tekst źródła
16
Veldman, Kyle John. "Monocular vision for collision avoidance in vehicles". Thesis, Massachusetts Institute of Technology, 2015. http://hdl.handle.net/1721.1/101478.
Pełny tekst źródłaStreszczenie:
Thesis: S.B., Massachusetts Institute of Technology, Department of Mechanical Engineering, 2015.Cataloged from PDF version of thesis.
Includes bibliographical references (page 21).
An experimental study facilitated by Ford Global Technologies, Inc. on the potential substitution of stereovision systems in car automation with monocular vision systems. The monocular system pairs a camera and passive lens with an active lens. Most active lenses require linear actuating systems to adjust the optical parameters of the system but this experiment employed an Optotune focus tunable lens adjusted by a Lorentz actuator for a much more reliable system. Tests were conducted in a lab environment to capture images of environmental objects at different distances from the system, pass those images through an image processing algorithm operating a high-pass filter to separate in-focus aspects of the image from out-of focus ones. Although the system is in the early phases of testing, monocular vision shows the ability to replace stereovision system. However, additional testing must be done to acclimate the apparatus to environmental factors, minimize the processing speed, and redesign the system for portability.
by Kyle John Veldman.
S.B.
17
Asmar, Dylan M. (Dylan Mitchell). "Airborne collision avoidance in mixed equipage environments". Thesis, Massachusetts Institute of Technology, 2013. http://hdl.handle.net/1721.1/82477.
Pełny tekst źródłaStreszczenie:
Thesis (S.M.)--Massachusetts Institute of Technology, Dept. of Aeronautics and Astronautics, 2013.This electronic version was submitted and approved by the author's academic department as part of an electronic thesis pilot project. The certified thesis is available in the Institute Archives and Special Collections.
"June 2013." Cataloged from department-submitted PDF version of thesis
Includes bibliographical references (p. 93-98).
Over the past few years, research has focused on the use of a computational method known as dynamic programming for producing an optimized decision logic for airborne collision avoidance. There have been a series of technical reports, conference papers, and journal articles summarizing the research, but they have primarily investigated two-aircraft encounters with only one aircraft equipped with a collision avoidance system. This thesis looks at recent research on coordination, interoperability, and multiple-threat encounters. In situations where an aircraft encounters another aircraft with a collision avoidance system, it is important that the resolution advisories provided to the pilots be coordinated so that both aircraft are not instructed to maneuver in the same direction. Interoperability is a related consideration since new collision avoidance systems will be occupying the same airspace as legacy systems. Resolving encounters with multiple intruders poses computational challenges that will be addressed in this thesis. The methodology presented in this thesis results in logic that is safer and performs better than the legacy Traffic Alert and Collision Avoidance System (TCAS). To assess the performance of the system, this thesis uses U.S. airspace encounter models. The results indicate that the proposed methodology can bring significant benefit to the current airspace and can support the need for safe, non-disruptive collision protection as the airspace continues to evolve.
by Dylan M. Asmar.
S.M.
18
Temizer, Selim 1977. "Planning under uncertainty for dynamic collision avoidance". Thesis, Massachusetts Institute of Technology, 2011. http://hdl.handle.net/1721.1/64487.
Pełny tekst źródłaStreszczenie:
Thesis (Ph. D.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 2011.This electronic version was submitted by the student author. The certified thesis is available in the Institute Archives and Special Collections.
Cataloged from student submitted PDF version of thesis.
Includes bibliographical references (p. 157-169).
We approach dynamic collision avoidance problem from the perspective of designing collision avoidance systems for unmanned aerial vehicles. Before unmanned aircraft can fly safely in civil airspace, robust airborne collision avoidance systems must be developed. Instead of hand-crafting a collision avoidance algorithm for every combination of sensor and aircraft configurations, we investigate automatic generation of collision avoidance algorithms given models of aircraft dynamics, sensor performance, and intruder behavior. We first formulate the problem within the Partially Observable Markov Decision Process (POMDP) framework, and use generic MDP/POMDP solvers offline to compute vertical-only avoidance strategies that optimize a cost function to balance flight-plan deviation with risk of collision. We then describe a second framework that performs online planning and allows for 3-D escape maneuvers by starting with possibly dangerous initial flight plans and improving them iteratively. Experimental results with four different sensor modalities and a parametric aircraft performance model demonstrate the suitability of both approaches.
by Selim Temizer.
Ph.D.
19
Barrios, Cesar. "Predicting Trajectory Paths For Collision Avoidance Systems". ScholarWorks @ UVM, 2015. http://scholarworks.uvm.edu/graddis/386.
Pełny tekst źródłaStreszczenie:
This work was motivated by the idea of developing a more encompassing collision avoidance system that supported vehicle to vehicle (V2V) and vehicle to infrastructure (V2I) communications. Current systems are mostly based on line of sight sensors that are used to prevent a collision, but these systems would prevent even more accidents if they could detect possible collisions before both vehicles were in line of sight.
For this research we concentrated mostly on the aspect of improving the prediction of a vehicle's future trajectory, particularly on non-straight paths. Having an accurate prediction of where the vehicle is heading is crucial for the system to reliably determine possible path intersections of more than one vehicle at the same time. We first evaluated the benefits of merging Global Positioning System (GPS) data with the Geographical Information System (GIS) data to correct improbable predicted positions. We then created a new algorithm called the Dead Reckoning with Dynamic Errors (DRWDE) sensor fusion, which can predict future positions at the rate of its fastest sensor, while improving the handling of accumulated error while some of the sensors are offline for a given period of time. The last part of out research consisted in the evaluation of the use of smartphones' built-in sensors to predict a vehicle's trajectory, as a possible intermediate solution for a vehicle to vehicle (V2V) and vehicle to infrastructure (V2I) communications, until all vehicles have all the necessary sensors and communication infrastructure to fully populate this new system.
For the first part of our research, the actual experimental results validated our proposed system, which reduced the position prediction errors during curves to around half of what it would be without the use of GIS data for prediction corrections. The next improvement we worked on was the ability to handle change in noise, depending on unavailable sensor measurements, permitting a flexibility to use any type of sensor and still have the system run at the fastest frequency available. Compared to a more common KF implementation that run at the rate of its slowest sensor (1Hz in our setup), our experimental results showed that our DRWDE (running at 10Hz) yielded more accurate predictions (25-50% improvement) during abrupt changes in the heading of the vehicle. The last part of our research showed that, comparing to results obtained with the vehicle-mounted sensors, some smartphones yield similar prediction errors and can be used to predict a future position.
20
Barceló, Vicens Jaume. "Carrier sense multiple acces with enhanced collision avoidance". Doctoral thesis, Universitat Pompeu Fabra, 2009. http://hdl.handle.net/10803/7553.
Pełny tekst źródłaStreszczenie:
Aquesta tesi suggereix usar un compte enrere determinista després de les transmissions exitoses en les xarxes d'àrea local sense fils. Com que les estacions que han transmès amb èxit en el seu darrer intent no poden col·lisionar entre elles en el seu proper intent, el nombre de col·lisions es redueix. Per tant, anomenem el protocol accés múltiple per detecció de portadora amb evitament de col·lisions millorat. El protocol es modela i es simula en diversos escenaris per a la seva avaluació. S'arriba a la conclusió de que el protocol proposat ofereix un rendiment igual o major que l'existent.This thesis suggests the use of a deterministic backoff after successful transmissions in the MAC protocol of WLANs. Since those stations that successfully transmitted in their last collision attempt cannot collide among them in their next transmission attempt, the number of collisions is reduced. Hence, the protocol is called Carrier Sense Multiple Access with Enhanced Collision Avoidance. The protocol is modelled and simulations are used to assess its performance in a variety of scenarios. It is concluded that the proposed protocol performs always equal or better than the legacy one.
21
Dönmez, Halit Anil. "Collision Avoidance for Virtual Crowds Using Reinforcement Learning". Thesis, KTH, Skolan för datavetenskap och kommunikation (CSC), 2017. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-210560.
Pełny tekst źródłaStreszczenie:
Virtual crowd simulation is being used in a wide variety of applications such as video games, architectural designs and movies. It is important for creators to have a realistic crowd simulator that will be able to generate crowds that displays the behaviours needed. It is important to provide an easy to use tool for crowd generation which is fast and realistic. Reinforcement Learning was proposed for training an agent to display a certain behaviour. In this thesis, a Reinforcement Learning approach was implemented and the generated virtual crowds were evaluated. Q Learning method was selected as the Reinforcement Learning method. Two different versions of the Q Learning method was implemented. These different versions were evaluated with respect to state-of-the-art algorithms: Reciprocal Velocity Obstacles(RVO) and a copy-synthesis approach based on real-data. Evaluation of the crowds was done with a user study. Results from the user study showed that while Reinforcement Learning method is not perceived as real as the real crowds, it was perceived almost as realistic as the crowds generated with RVO. Another result was that, the perception of RVO changes with the changing environment. When only the paths were shown, RVO was perceived as being more natural than when the paths were shown in a setting in real world with pedestrians. It was concluded that using Q Learning for generating virtual crowds is a promising method and can be improved as a substitute for existing methods and in certain scenarios, Q Learning algorithm results with better collision avoidance and more realistic crowd simulation.Virtuell folkmassimulering används i ett brett utbud av applikationersom videospel, arkitektoniska mönster och filmer. Det är viktigt förskaparna att ha en realistisk publik simulator som kommer att kunnagenerera publiken som behövs för att visa de beteenden som behövs. Det är viktigt att tillhandahålla ett lättanvänt verktyg för publikgenereringsom är snabb och realistisk. Förstärkt lärande föreslogs föratt utbilda en agent för att visa ett visst beteende. I denna avhandlingimplementerades en förstärkningslärande metod för att utvärderavirtuella folkmassor. Q Lärandemetod valdes som förstärkningslärningsmetod.Två olika versioner av Q-inlärningsmetoden genomfördes. Dessa olika versioner utvärderades med avseende på toppmodernaalgoritmer: Gensamma hastighetshinder och ett kopieringssyntestillvägagångssättbaserat på realtid. Utvärderingen av publiken gjordesmed en användarstudie. Resultaten från användarstudien visadeatt medan Reinforcement Learning-metoden inte uppfattas som verkligsom den verkliga publiken, uppfattades det nästan lika realistisktsom massorna genererade med Reciprocal Velocity Objects. Ett annatresultat var att uppfattningen av RVO förändras med den föränderligamiljön. När bara stigarna visades upplevdes det mer naturligt än närdet visades i en miljö i riktiga värld med fotgängare. Det drogs slutsatsenatt att använda Q Learning för att generera folkmassor är enlovande metod och kan förbättras som ett ersättare för befintliga metoderoch i vissa scenarier resulterar Q Learning algoritm med bättrekollisionsundvikande och mer realistisk publik simulering.
22
Eidehall, Andreas. "Tracking and threat assessment for automotive collision avoidance". Doctoral thesis, Linköping : Department of Electrical Engineering, Linköpings universitet, 2007. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-8338.
Pełny tekst źródła
23
Herb, Gregory M. "A real-time robot collision avoidance safety system". Thesis, This resource online, 1990. http://scholar.lib.vt.edu/theses/available/etd-06082009-170801/.
Pełny tekst źródła
24
Tan, Chiew Seon. "A collision avoidance system for autonomous underwater vehicles". Thesis, University of Plymouth, 2006. http://hdl.handle.net/10026.1/2258.
Pełny tekst źródłaStreszczenie:
The work in this thesis is concerned with the development of a novel and practical collision avoidance system for autonomous underwater vehicles (AUVs). Synergistically, advanced stochastic motion planning methods, dynamics quantisation approaches, multivariable tracking controller designs, sonar data processing and workspace representation, are combined to enhance significantly the survivability of modern AUVs. The recent proliferation of autonomous AUV deployments for various missions such as seafloor surveying, scientific data gathering and mine hunting has demanded a substantial increase in vehicle autonomy. One matching requirement of such missions is to allow all the AUV to navigate safely in a dynamic and unstructured environment. Therefore, it is vital that a robust and effective collision avoidance system should be forthcoming in order to preserve the structural integrity of the vehicle whilst simultaneously increasing its autonomy. This thesis not only provides a holistic framework but also an arsenal of computational techniques in the design of a collision avoidance system for AUVs. The design of an obstacle avoidance system is first addressed. The core paradigm is the application of the Rapidly-exploring Random Tree (RRT) algorithm and the newly developed version for use as a motion planning tool. Later, this technique is merged with the Manoeuvre Automaton (MA) representation to address the inherent disadvantages of the RRT. A novel multi-node version which can also address time varying final state is suggested. Clearly, the reference trajectory generated by the aforementioned embedded planner must be tracked. Hence, the feasibility of employing the linear quadratic regulator (LQG) and the nonlinear kinematic based state-dependent Ricatti equation (SDRE) controller as trajectory trackers are explored. The obstacle detection module, which comprises of sonar processing and workspace representation submodules, is developed and tested on actual sonar data acquired in a sea-trial via a prototype forward looking sonar (AT500). The sonar processing techniques applied are fundamentally derived from the image processing perspective. Likewise, a novel occupancy grid using nonlinear function is proposed for the workspace representation of the AUV. Results are presented that demonstrate the ability of an AUV to navigate a complex environment. To the author's knowledge, it is the first time the above newly developed methodologies have been applied to an A UV collision avoidance system, and, therefore, it is considered that the work constitutes a contribution of knowledge in this area of work.
25
Sezgin, Umit. "Utilization of manipulator redundancies for collision avoidance strategies". Thesis, King's College London (University of London), 1995. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.283521.
Pełny tekst źródła
26
Sanders, Christopher P. (Christopher Paul) 1973. "Real-time collision avoidance for autonomous air vehicles". Thesis, Massachusetts Institute of Technology, 1998. http://hdl.handle.net/1721.1/50325.
Pełny tekst źródła
27
Leavitt, Joseph William. "Intent-aware collision avoidance for autonomous marine vehicles". Thesis, Massachusetts Institute of Technology, 2010. http://hdl.handle.net/1721.1/111893.
Pełny tekst źródłaStreszczenie:
Thesis: Nav. E., Massachusetts Institute of Technology, Department of Mechanical Engineering, 2017.Thesis: S.M., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2017.
Cataloged from PDF version of thesis.
Includes bibliographical references (pages 259-278).
Applications of autonomous marine vehicles in dynamic and uncertain environments continuously grow as research unveils new enabling technology and academic, commercial, and government entities pursue new marine autonomy concepts. The safe operation of these vehicles in the marine domain, which is currently dominated by human-operated vehicles, demands compliance with collision avoidance protocol, namely the International Regulations for Preventing Collisions at Sea (COLREGS). Strict application of this protocol can lead to a highly constrained motion planning problem, in which it is difficult for a vehicle to identify a safe and efficient motion plan. This thesis proposes a multi-objective optimization-based method for COLREGS-compliant autonomous surface vehicle collision avoidance in which vehicles use shared intent information, in addition to vehicle state information, to identify safe and efficient collision avoidance maneuvers. The proposed method uses intent information to relax certain COLREGS-specified constraints with the goal of providing sufficient maneuvering flexibility to enable improvements in safety and efficiency over a non-intent-aware system. In order to arrive at an intent-aware solution, this thesis explores the concept of intent, including intent formulations for the marine domain, intent communications, and the application of intent to the COLREGS-compliant motion planning problem. Two types of intent information are specifically evaluated: COLREGS mode intent, in which the give-way vessel in an overtaking or crossing scenario communicates its intent to maneuver in a certain direction with respect the stand-on vessel, and discrete trajectory intent in which vehicles communicate projected future positions. Simulations and on-water experiments demonstrate the feasibility of the proposed intent-aware method, as well as improvements in performance, in terms of both vehicle safety and mission efficiency, over a non-intent-aware, COLREGS-compliant collision avoidance method.
by Joseph William Leavitt.
Nav. E.
S.M.
28
Billingsley, Geoffrey O. (Geoffrey Owen) 1975. "Head-up display symbology for ground collision avoidance". Thesis, Massachusetts Institute of Technology, 1999. http://hdl.handle.net/1721.1/50125.
Pełny tekst źródłaStreszczenie:
Thesis (S.M.)--Massachusetts Institute of Technology, Dept. of Aeronautics and Astronautics, 1999.Includes bibliographical references (p. 109-111).
Four predictive ground collision avoidance displays (Break-X, Chevrons, Mountain, and Highway) were tested using a fixed-base T-38 simulator with a projection screen and simulated Head-Up Display (HUD). The Break-X was similar to the conventional military alert except that it remained on the screen until the aircraft was recovered to safety. The Chevron display consisted of two caret symbols (> <) which slid horizontally inward as danger increased, forming an X identical to the break-X. The Mountain display used a single icon which moved upward in the HUD as danger increased, mimicking the motion of the terrain outside. The Highway was a preview display, which consisted of a perspective elevated surface shown at the desired altitude. Twelve subjects flew through a series of Predictive Ground Collision Avoidance System (PGCAS) situations in zero visibility using each display. For about 30 seconds after the alert, they attempted to maintain a set altitude above ground, clear of the terrain but below ground radar threats. Performance metrics were rolling tendency, altitude maintenance, pilot effort, and subjective preference. The Break-X performed more poorly than the other displays in every category. It attracted attention but proved to be impractical for the terrain-following/terrain-avoidance task. Pilots were able to spend only 40% of the flight time between the desired altitudes when given the Break-X, and on average, they crashed every 5 runs. The Chevrons were more useful, although their horizontal motion did not correspond to the outside world. The Chevrons and Mountain averaged only one crash in 12 runs. The vertically moving Mountain had physical analogue, so pilots found it more natural to follow. This enabled them to spend approximately 80% of the time between the altitude limits, while the Chevrons allowed 70%. The better altitude performance from the Mountain came at the cost of higher effort levels, as shown by a significant difference in RMS longitudinal stick movement. However, a false illusion of wings-level produced slightly poorer roll performance from the Mountain. Pilots crashed the least using the Highway, averaging about one crash per 50 runs. It enabled them to fly approximately 90% of the time within the desired altitude layer. The Highway produced the highest objective and subjective ranking, and its predictive nature made it the best display for the task investigated.
by Geoffrey O. Billingsley.
S.M.
29
Leavitt, Joseph William. "Intent-aware collision avoidance for autonomous marine vehicles". Thesis, Massachusetts Institute of Technology, 2017. http://hdl.handle.net/1721.1/111893.
Pełny tekst źródłaStreszczenie:
Thesis: Nav. E., Massachusetts Institute of Technology, Department of Mechanical Engineering, 2017.Thesis: S.M., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2017.
Cataloged from PDF version of thesis.
Includes bibliographical references (pages 259-278).
Applications of autonomous marine vehicles in dynamic and uncertain environments continuously grow as research unveils new enabling technology and academic, commercial, and government entities pursue new marine autonomy concepts. The safe operation of these vehicles in the marine domain, which is currently dominated by human-operated vehicles, demands compliance with collision avoidance protocol, namely the International Regulations for Preventing Collisions at Sea (COLREGS). Strict application of this protocol can lead to a highly constrained motion planning problem, in which it is difficult for a vehicle to identify a safe and efficient motion plan. This thesis proposes a multi-objective optimization-based method for COLREGS-compliant autonomous surface vehicle collision avoidance in which vehicles use shared intent information, in addition to vehicle state information, to identify safe and efficient collision avoidance maneuvers. The proposed method uses intent information to relax certain COLREGS-specified constraints with the goal of providing sufficient maneuvering flexibility to enable improvements in safety and efficiency over a non-intent-aware system. In order to arrive at an intent-aware solution, this thesis explores the concept of intent, including intent formulations for the marine domain, intent communications, and the application of intent to the COLREGS-compliant motion planning problem. Two types of intent information are specifically evaluated: COLREGS mode intent, in which the give-way vessel in an overtaking or crossing scenario communicates its intent to maneuver in a certain direction with respect the stand-on vessel, and discrete trajectory intent in which vehicles communicate projected future positions. Simulations and on-water experiments demonstrate the feasibility of the proposed intent-aware method, as well as improvements in performance, in terms of both vehicle safety and mission efficiency, over a non-intent-aware, COLREGS-compliant collision avoidance method.
by Joseph William Leavitt.
Nav. E.
S.M.
30
Li, Hao. "Decentralized Multi-Agent Collision Avoidance and Reinforcement Learning". The Ohio State University, 2021. http://rave.ohiolink.edu/etdc/view?acc_num=osu1618840664964088.
Pełny tekst źródła
31
Wang, Yu. "Cooperative Transportation of Mobile Manipulators With Collision Avoidance". Thesis, KTH, Reglerteknik, 2018. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-231841.
Pełny tekst źródłaStreszczenie:
In this work, we propose two Nonlinear Model Predictive Control(NMPC) schemes, Decentralized Nonlinear Model Predictive Control(DNMPC) and Centralized Nonlinear Model Predictive Control (CNMPC),for cooperative transportation of an object, which is rigidlygrasped by N agents. We use feedback linearization and model reductionto reduce overall complexity of the model. We also providea mathematical proof for feasibility and convergence of the schemes.Finally, we use simulations and experiments to validate the robustnessand efficiency of the proposed schemes.I det här arbetet föreslår vi två system för icke-linjär model predictivecontrol (NMPC), Decentraliserad icke-linjär MPC (DNMPC) och centraliseradicke-linjär MPC (CNMPC), för kooperativ transport av ettobjekt, som är fast greppad av N agenter . Vi använder feedbacklinjäriseringoch modellreduktion för att minska modellens övergripandekomplexitet. Vi tillhandahåller också ett matematiskt bevis för genomförbarhetoch konvergens av systemen. Slutligen använder vi simuleringaroch experiment för att validera de föreslagna systemens robusthetoch effektivitet.
32
Dravidam, Uttamkumar. "Development of rear-end collision avoidance in automobiles". FIU Digital Commons, 1999. http://digitalcommons.fiu.edu/etd/3084.
Pełny tekst źródłaStreszczenie:
The goal of this work is to develop a Rear-End Collision Avoidance System for automobiles. In order to develop the Rear-end Collision Avoidance System, it is stated that the most important difference from the old practice is the fact that new design approach attempts to completely avoid collision instead of minimizing the damage by over-designing cars. Rear-end collisions are the third highest cause of multiple vehicle fatalities in the U.S. Their cause seems to be a result of poor driver awareness and communication. For example, car brake lights illuminate exactly the same whether the car is slowing, stopping or the driver is simply resting his foot on the pedal. In the development of Rear-End Collision Avoidance System (RECAS), a thorough review of hardware, software, driver/human factors, and current rear-end collision avoidance systems are included. Key sensor technologies are identified and reviewed in an attempt to ease the design effort. The characteristics and capabilities of alternative and emerging sensor technologies are also described and their performance compared. In designing a RECAS the first component is to monitor the distance and speed of the car ahead. If an unsafe condition is detected a warning is issued and the vehicle is decelerated (if necessary). The second component in the design effort utilizes the illumination of independent segments of brake lights corresponding to the stopping condition of the car. This communicates the stopping intensity to the following driver. The RECAS is designed the using the LabVIEW software. The simulation is designed to meet several criteria: System warnings should result in a minimum load on driver attention, and the system should also perform well in a variety of driving conditions.
In order to illustrate and test the proposed RECAS methods, a Java program has been developed. This simulation animates a multi-car, multi-lane highway environment where car speeds are assigned randomly, and the proposed RECAS approaches demonstrate rear-end collision avoidance successfully. The Java simulation is an applet, which is easily accessible through the World Wide Web and also can be tested for different angles of the sensor.
33
Da, Silva Filho José Grimaldo. "Towards natural human-robot collaboration during collision avoidance". Thesis, Université Grenoble Alpes, 2020. http://www.theses.fr/2020GRALM003.
Pełny tekst źródłaStreszczenie:
Ces dernières années, la tendance des robots capables de partager des espaces domestiques ou de travail avec des personnes a connu une croissance importante. Du robot guide à l’aspirateur autonome, ces robots dits "de service" sont de plus en plus intégrés dans la vie quotidienne des profanes.Bien que les progrès des logiciels et du matériel aient permis un comportement plus intelligent et plus autonome des robots, la présence plus répandue des robots parmi les gens pose un nouvel ensemble de défis pour la communauté scientifique. Même si les gens ne sont pas que des obstacles ordinaires, les approches classiques de navigation se sont concentrées sur la garantie d’un mouvement sans collision en supposant que les gens sont soit des obstacles statiques, soit des obstacles en mouvement. Traiter les gens comme des obstacles ordinaires signifie qu’un robot est incapable de tenir compte de la réaction d’une personne au mouvement du robot. Pour cette raison, un mouvement donné d’un robot peut être perçu comme dangereux ou inhabituel, ce qui incite les gens à adopter un mouvement plus prudent pendant qu’ils réfléchissent activement aux intentions du robot. Dans ce contexte, notre travail se concentre sur la manière dont un robot doit se déplacer au milieu des gens, ce qu’on appelle un problème de Mouvement homme-robot. Plus précisément, nous nous concentrons sur la reproduction d’une caractéristique de l’interaction homme-homme lors de la prévention des collisions, à savoir le partage mutuel des adaptations effectuées pour résoudre une collision.Etant donné que les situations d’évitement des collisions entre les personnes sont résolues en coopération, cette thèse modélise la manière dont cette coopération se fait afin qu’un robot puisse reproduire leur comportement. Pour ce faire, des centaines de situations où deux personnes ont des trajectoires de croisement ont été analysées. À partir de ces trajectoires humaines impliquant une tâche d’évitement des collisions, nous avons déterminé comment l’effort total est partagé entre chaque agent en fonction de plusieurs facteurs de l’interaction tels que l’angle de croisement, le temps avant collision ainsi que la vitesse. Pour valider notre approche, une preuve de concept est intégrée dans le framework Robot Operating System (ROS) utilisant une version modifiée de Reciprocal Velocity Objects (RVO) afin de répartir l’effort d’évitement des collisions de façon humanoïde.Bien que la modélisation de la manière dont un robot devrait collaborer avec des personnes ait fourni une base de référence importante pour le comportement d’évitement des collisions, la collaboration pendant une collision pourrait éventuellement engendrer de conséquences négatives. En particulier, pour assurer une collaboration efficace lors de la prévention des collisions, il est nécessaire de prévoir si la personne tentera d’éviter la collision en passant du côté gauche ou du côté droit, c’est-à-dire en prenant une décision de classe homotopie. Cependant, à situation ou cette décision de classe d’homotopie n’est pas cohérente pour les gens, le robot est obligé de tenir compte de la possibilité que les deux agents tentent de se croiser d’un côté ou de l’autre et prennent une décision nuisible à la prévention des collisions.Ainsi, dans cette thèse, nous évaluons également ce qui détermine la frontière qui sépare la décision d’éviter la collision d’un côté ou de l’autre. En faisant une approximation de l’incertitude entourant cette limite, nous avons élaboré une stratégie d’évitement des collisions qui tente de résoudre ce problème. Notre approche est basée sur l’idée que le robot doit planifier son mouvement d’évitement des collisions de telle sorte que, même si les agents, dans un premier temps, choisissent à tort de se croiser sur des côtés différents, le robot et la personne soient capables de percevoirClassical approaches for robot navigation among people have focused on guaranteed collision-free motion with the assumption that people are either static or moving obstacles. However, people are not ordinary obstacles. People react to the presence and the motion of a robot. In this context, a robot that behaves in human-like manner has been shown to reduce overall cognitive effort for nearby people as they do not have to actively think about a robot's intentions while moving on its proximity.Our work is focused on replicating a characteristic of human-human interaction during collision avoidance that is the mutual sharing of effort to avoid a collision. Based on hundreds of situations where two people have crossing trajectories, we determined how total effort is shared between agents depending on several factors of the interaction such as crossing angle and time to collision. As a proof of concept our generated model is integrated into gls{rvo}. For validation, the trajectories generated by our approach are compared to the standard gls{rvo} and to our dataset of people with crossing trajectories.Collaboration during collision avoidance is not without its potential negative consequences. For effective collaboration both agents have to pass each other on the same side. However, whenever the decision of which side collision should be avoided from is not consistent for people, the robot should also account for the risk that both agents will attempt to incorrectly cross each other on different sides. Our work first determines the uncertainty around this decision for people. Based on this, a collision avoidance approach is proposed so that, even if agents initially choose to incorrectly attempt to cross each other on different sides, the robot and the person would be able to perceive the side from which collision should be avoided in their following collision avoidance action. To validate our approach, several distinct scenarios where the crossing side decision is ambiguous are presented alongside collision avoidance trajectories generated by our approach in such scenarios
34
Anantharaman, Gokul Arvind. "Cooperative Collision Avoidance for Connected and Autonomous Vehicles". The Ohio State University, 2018. http://rave.ohiolink.edu/etdc/view?acc_num=osu1543424841946961.
Pełny tekst źródła
35
Patel, Amir. "UAV collision avoidance: a specific acceleration matching approach". Master's thesis, University of Cape Town, 2011. http://hdl.handle.net/11427/11582.
Pełny tekst źródłaStreszczenie:
Includes abstract.Includes bibliographical references.
An increased level of autonomy is required for future Unmanned Aerial Vehicle (UAV) missions. One of the technologies required for this to occur is an adequate sense and avoid system to enable the UAV to detect threat aircraft and take evasive action if required. This thesis investigates a collision avoidance system to satisfy a significant portion of the requirements for sense and avoid. It was hypothesised that a recently published method of UAV guidance, Specific Acceleration Matching (SAM) Control, could address the shortcomings of the current implementations. Additionally, a novel algorithm, the Linear 3D Velocity Guidance Control Algorithm (3DVGC) was developed to address the particular requirements of UAV collision avoidance.
36
Syed, Anees. "Collision prediction and avoidance of satellites in formation". Cincinnati, Ohio : University of Cincinnati, 2004. http://rave.ohiolink.edu/etdc/view?acc%5Fnum=ucin1100034591.
Pełny tekst źródła
37
Humphris, Les. "Software Defined Radio for Maritime Collision Avoidance Applications". Thesis, University of Canterbury. Electrical and Electronic Engineering, 2015. http://hdl.handle.net/10092/11217.
Pełny tekst źródłaStreszczenie:
The design and development of a software defined radio (SDR) receiver prototype has been completed. The goal is to replace the existing automatic identification system (AIS) manufactured by Vesper Marine with a software driven system that reduces costs and provides a high
degree of reconfigurability. One of the key concepts of the SDR is the consideration of directly digitizing the radio frequency (RF) signal using subsampling. This idea arises from the ambition to implement an analog-to-digital converter (ADC) as close to the antenna interface as
practically possible. Thus, majority of the RF processing is encapsulated within in the digital domain. Evaluation of a frequency planning strategy that utilizes a combination of subsampling and oversampling will illustrate how the maritime bandwidth is aliased to a lower frequency. An analog front-end (AFE) board was constructed to implement the frequency planning strategy so that the digitized bandwidth can be streamed into a field programmable gate array (FPGA)
for real-time processing. Research is shown on digital front-end (DFE) techniques that condition the digitized maritime signal for baseband processing. The process of a digital down converter (DDC) is conducted by an FPGA, which acquired the in-phase and quadrature signals. By implementing a digital signal processor (DSP) for baseband processing, demodulation on an AIS test signal is evaluated. The SDR prototype achieved a receiver sensitivity of -113dBm, outperforming the required sensitivity of -107dBm specified in the International Electrotechnical Commission (IEC) 62287-1 standard for AIS applications [1].
38
Rushall, David Aaron 1964. "Efficient heuristics for collision avoidance in three dimensions". Thesis, The University of Arizona, 1989. http://hdl.handle.net/10150/277041.
Pełny tekst źródłaStreszczenie:
This thesis represents a relatively new aspect of computing with regard to robotics. The need for fast, efficient collision avoidance algorithms is growing rapidly. Because conventional methods are complex and require vast amounts of computation, heuristic algorithms are more appealing. The focus of this thesis is the problem of moving a point through three dimensional space while avoiding known polyhedral obstacles. A heuristic algorithm to find shortest (near-optimal) collision-free paths in the presence of polyhedral obstacles, given initial and final positions, is presented. Previous methods for the problem rely on an a priori discretization of the space. The points in the discretization form nodes of a graph, and the collision avoidance problem is then solved by using some shortest path algorithm on the graph. The heuristic suggested here successively adds nodes to a graph, thus keeping the size of the graph manageable. The computational results are extremely encouraging.
39
Mcfadyen, Aaron. "Visual control for automated aircraft collision avoidance systems". Thesis, Queensland University of Technology, 2015. https://eprints.qut.edu.au/81418/1/Aaron_McFadyen_Thesis.pdf.
Pełny tekst źródłaStreszczenie:
This thesis presents a new vision-based decision and control strategy for automated aircraft collision avoidance that can be realistically applied to the See and Avoid problem. The effectiveness of the control strategy positions the research as a major contribution toward realising the simultaneous operation of manned and unmanned aircraft within civilian airspace.
Key developments include novel classical and visual predictive control frameworks, and a performance evaluation technique aligned with existing aviation practise and applicable to autonomous systems. The overall approach is demonstrated through experimental results on a small multirotor unmanned aircraft, and through high fidelity probabilistic simulation studies.
40
Naik, Ankur. "Arc Path Collision Avoidance Algorithm for Autonomous Ground Vehicles". Thesis, Virginia Tech, 2005. http://hdl.handle.net/10919/30969.
Pełny tekst źródłaStreszczenie:
Presented in this thesis is a collision avoidance algorithm designed around an arc path model. The algorithm was designed for use on Virginia Tech robots entered in the 2003 and 2004 Intelligent Ground Vehicle Competition (IGVC) and on our 2004 entry into the DARPA Grand Challenge. The arc path model was used because of the simplicity of the calculations and because it can accurately represent the base kinematics for Ackerman or differentially steered vehicles.
Clothoid curves have been used in the past to create smooth paths with continuously varying curvature, but clothoids are computationally intensive. The circular arc algorithm proposed here is designed with simplicity and versatility in mind. It is readily adaptable to ground vehicles of any size and shape. The algorithm is also designed to run with minimal tuning. The algorithm can be used as a stand alone reactive collision avoidance algorithm in simple scenarios, but it can be better optimized for speed and safety when guided by a global path planner. A complete navigation architecture is presented as an example of how obstacle avoidance can be incorporated in the algorithm.Master of Science
41
Sugiura, Hisashi [Verfasser]. "Real World Collision Avoidance for Humanoid Robots / Hisashi Sugiura". Aachen : Shaker, 2010. http://d-nb.info/1081885483/34.
Pełny tekst źródła
42
Chafye, Nemri. "A collision avoidance algorithm for a cylindrical robot manipulator /". Thesis, McGill University, 1988. http://digitool.Library.McGill.CA:80/R/?func=dbin-jump-full&object_id=61719.
Pełny tekst źródła
43
Alturbeh, Hamid. "Collision avoidance systems for UAS operating in civil airspace". Thesis, Cranfield University, 2014. http://dspace.lib.cranfield.ac.uk/handle/1826/9295.
Pełny tekst źródłaStreszczenie:
Operation of Unmanned Aerial Vehicles (UAVs) in civil airspace is restricted by the aviation
authorities which require full compliance with regulations that apply for manned aircraft.
This thesis proposes control algorithms for a collision avoidance system that can be used
as an advisory system or a guidance system for UAVs that are flying in civil airspace under
visual flight rules. An effective collision avoidance system for the UAV should be able to
perform the different functionalities of the pilot in manned aircraft. Thus, it should be able
to determine, generate, and perform safe avoidance manoeuvres. However, the capability to
generate resolution advisories is crucial for the advisory systems. A decision making system
for collision avoidance is developed based on the rules of the air. The proposed architecture
of the decision making system is engineered to be implementable in both manned aircraft
and UAVs to perform different tasks ranging from collision detection to a safe avoidance
manoeuvre initiation. Avoidance manoeuvres that are compliant with the rules of the air are
proposed based on pilot suggestions for a subset of possible collision scenarios. The avoidance
manoeuvre generation algorithm is augmented with pilot experience by using fuzzy
logic technique to model pilot actions in generating the avoidance manoeuvres. Hence, the
generated avoidance manoeuvres mimic the avoidance manoeuvres of manned aircraft. The
proposed avoidance manoeuvres are parameterized using a geometric approach. An optimal
collision avoidance algorithm is developed for real-time local trajectory planning. Essentially,
a finite-horizon optimal control problem is periodically solved in real-time hence
updating the aircraft trajectory to avoid obstacles and track a predefined trajectory. The optimal
control problem is formulated in output space, and parameterised by using B-splines.
Then the optimal designed outputs are mapped into control inputs of the system by using
the inverse dynamics of a fixed wing aircraft.
44
Kalvå, Andreas. "Collision detection and avoidance system based on computer vision". Thesis, Norges teknisk-naturvitenskapelige universitet, Institutt for teknisk kybernetikk, 2014. http://urn.kb.se/resolve?urn=urn:nbn:no:ntnu:diva-24779.
Pełny tekst źródłaStreszczenie:
A wide selection of stereo matching algorithms have been evaluated for the purpose ofcreating a collision avoidance module. Varying greatly in the accuracy, a few of thealgorithms were fast enough for further use.Two computer vision libraries, OpenCV and MRF, were evaluated for their implementationsof various stereo matching algorithms. In addition OpenCV provides a wide variety offunctions for creating sophisticated computer vision programs and were evaluated onthis basis as well.A stereo camera were constructed using low cost, of-the-shelf web cameras.Two low-power platforms, The Pandaboard and the Beaglebone Black, were evaluated asviable platforms for developing a computer vision module on top. In addition they werecompared to an Intel platform as a reference.Based on the results gathered, a fast, but simple, collision detector could be madeusing the simple block matching algorithm found in OpenCV. A more advanced detectorcould be built using semi-global stereo matching. These were the only implementationsthat were fast enough. The other energy minimization algorithms (Graph cuts and beliefpropagation) did produce good disparity maps, but were too slow for any realisticcollision detector.In order for the low-power platforms to be fast enough, a combination of improvementsmust be used. OpenCV should be compiled with aggressive optimization options enabledwith support for hardware accelerated floating point math. Choice of low-power platformmatters, but it is possible to work around this by reducing the workload.The most effective speedup that enables the low-power platforms were reducing theresolution of the images to be matched. When reducing the size of the sub-problemsenough to align with cache size, considerable speedups were found with littlepenalty in the corresponding disparity map.
45
Lindsay, K. W. "Secondary radar, collision avoidance and ship-to-ship communication". Thesis, Liverpool John Moores University, 1985. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.332121.
Pełny tekst źródła
46
Chen, J. R. "Planning plausible human motions for navigation and collision avoidance". Thesis, University College London (University of London), 2014. http://discovery.ucl.ac.uk/1418044/.
Pełny tekst źródłaStreszczenie:
This thesis investigates the plausibility of computer-generated human motions for navigation and collision avoidance. To navigate a human character through obstacles in an virtual environment, the problem is often tackled by finding the shortest possible path to the destination with smoothest motions available. This is because such solution is regarded as cost-effective and free-flowing in that it implicitly minimises the biomechanical efforts and potentially precludes anomalies such as frequent and sudden change of behaviours, and hence more plausible to human eyes. Previous research addresses this problem in two stages: finding the shortest collision-free path (motion planning) and then fitting motions onto this path accordingly (motion synthesis). This conventional approach is not optimal because the decoupling of these two stages introduces two problems. First, it forces the motion-planning stage to deliberately simplify the collision model to avoid obstacles. Secondly, it over-constrains the motion-synthesis stage to approximate motions to a sub-optimal trajectory. This often results in implausible animations that travel along erratic long paths while making frequent and sudden behaviour changes. In this research, I argue that to provide more plausible navigation and collision avoidance animation, close-proximity interaction with obstacles is crucial. To address this, I propose to combine motion planning and motion synthesis to search for shorter and smoother solutions. The intuition is that by incorporating precise collision detection and avoidance with motion capture database queries, we will be able to plan fine-scale interactions between obstacles and moving crowds. The results demonstrate that my approach can discover shorter paths with steadier behaviour transitions in scene navigation and crowd avoidance. In addition, this thesis attempts to propose a set of metrics that can be used to evaluate the plausibility of computer-generated navigation animations.
47
Kon, Tayfun. "Collision Warning and Avoidance System for Crest Vertical Curves". Master's thesis, Virginia Tech, 1998. http://hdl.handle.net/10919/37169.
Pełny tekst źródłaStreszczenie:
In recent years, State Road Route 114 which is located in
Montgomery County, Virginia, has gained a bad reputation
because of numerous traffic accidents. Most of these
accidents resulted in loss of lives and property. Although
there are many suggestions and proposals designed to prevent
these acidents, to date no actions is taken yet.
The focus of this research is to explore a technology-based,
low cost solution that will lower or eliminate the risk of
accidents on this two-lane rural highway.Master of Science
48
Farahmand, Ashil Sayyed. "Cooperative Decentralized Intersection Collision Avoidance Using Extended Kalman Filtering". Thesis, Virginia Tech, 2008. http://hdl.handle.net/10919/36276.
Pełny tekst źródłaStreszczenie:
Automobile accidents are one of the leading causes of death and claim more than 40,000 lives annually in the US alone. A substantial portion of these accidents occur at road intersections. Stop signs and traffic signals are some of the intersection control devices used to increase safety and prevent collisions. However, these devices themselves can contribute to collisions, are costly, inefficient, and are prone to failure. This thesis proposes an adaptive, decentralized, cooperative collision avoidance (CCA) system that optimizes each vehicle's controls subject to the constraint that no collisions occur. Three major contributions to the field of collision avoidance have resulted from this research. First, a nonlinear 5-state variable vehicle model is expanded from an earlier model developed in [1]. The model accounts for internal engine characteristics and more realistically approximates vehicle behavior in comparison to idealized, linear models. Second, a set of constrained, coupled Extended Kalman Filters (EKF) are used to predict the trajectory of the vehicles approaching an intersection in real-time. The coupled filters support decentralized operation and ensure that the optimization algorithm bases its decisions on good, reliable estimates. Third, a vehicular network based on the new WAVE standard is presented that provides cooperative capabilities by enabling intervehicle communication. The system is simulated against today's common intersection control devices and is shown to be superior in minimizing average vehicle delay.Master of Science
49
Gang, Siqi. "Driver-Monitoring-Camera Based Threat Awareness for Collision Avoidance". Thesis, KTH, Skolan för industriell teknik och management (ITM), 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-263926.
Pełny tekst źródłaStreszczenie:
Since forward collision is one of the most common and dangerous types of traffic accidents, many studies and researches have been conducted to develop forward collision avoidance system. To facilitate the tradeoff between comfort and safety for forward collision avoidance, the driver's state needs to be monitored and estimated. Such support is necessary for Forward Collision Warning (FCW) system given human-involved control. Due to the advances of Driver Monitoring System (DMS), the demand for camera-based driver's state estimation has increased. This master thesis project, conducted at Zenuity AB, investigates a method to estimate driver's awareness based on DMS. The estimation of a driver's awareness is expected to help adapt FCW system based on visual attention when facing the unpredictable braking of the leading vehicle. The project consists of three tasks: gaze estimation, Gaze-to-Object Mapping (GTOM), and awareness estimation. A combined Kalman Filter was developed in gaze estimation for compensation of missing data and outliers and reducing the difference to “ground truth” data. The uncertainty matrix from gaze estimation was utilized to extract a gaze-to-object probability signal in GTOM, while the corresponding fixation duration was also obtained in GTOM. The two extracted new features were used in awareness estimation with two methods: Logistic Regression and two-Hidden Markov Model. The comparison between the two methods reveals whether a complex method is preferred or not. Based on the results of this project, Logistic Regression seems to perform better in driver's state estimation, with 92.0% accuracy and 76.3% True Negative rate. However, further research and improvements on the two-Hidden Markov Model are needed to reach a more comprehensive conclusion. The main contribution of this project is an investigation of an end-to-end method for driver's awareness estimation and thereby an identification of challenges for further studies.Frontkollision (forward collision) är en av de vanligaste och farligaste typerna av trafikolyckor. Många studier och undersökningar har genomförts för att utveckla system för att undvika kollisioner. För att underlätta avvägningar mellan komfort och säkerhet för att undvika Frontkollision måste förarens tillstånd övervakas och skattas. Ett sådant stöd är nödvändigt för Forward Collision Warning (FCW) systemet, som involverar interaktion med människor. Efterfrågan på kamerabaserad uppskattning för föraren har ökat på grund av framsteg Driver Monitoring System (DMS). Det här examensarbete genomfördes på Zenuity AB och undersökte en metod för att skatta förarens medvetenhet baserad på Driver Monitoring System. Uppskattningen av förarens medvetenhet förväntas bidra till att anpassa FCW-systemet. Detta FCW-system är baserat på visuell uppmärksamhet om när oförutsägbar bromsning av det framförvarande fordonet sker. Examensarbetet består av tre uppgifter: blickuppskattning, Gaze-to-Object Mapping (GTOM), och medventenhetsuppskattning. Ett kombinerat Kalman-filter har utvecklats i gaze uppskattning för att kompensera saknade data och outliers samt reducera skillnaden till “ground truth” data. Osäkerhetesmatrisen från gaze uppskattningen användes för att extrahera en gaze-to-object sannolikhetssignal i GTOM. Den motsvarande fixeringsvaraktigheten erhålls också i GTOM. De två extraherade nya egenskaperna användes i medvetenhetsanalys med hjälp av två metoder: logistic regression och two-Hidden Markov Model. Jämförelsen mellan de två metoderna avslöjar om en komplex metod är att föredra eller inte. Resultatet av detta examensarbet visar att logistic regression fungerar bättre i förarens statusuppskattning med 92% noggrannhet och 76.3% True Negative rate. Vidare forskning och förbättringar av den two-hidden Markov modell behövs för att dra en mer omfattande slutsats. Det huvudsakliga bidraget av examensarbetet är en utforskning av en end-to-end metod för att uppskatta förarens medvetenhet och därmed kunna identifiera utmaningar för framtid studie.
50
DE, FILIPPIS LUCA. "Advanced Path Planning and Collision Avoidance Algorithms for UAVs". Doctoral thesis, Politecnico di Torino, 2012. http://hdl.handle.net/11583/2497102.
Pełny tekst źródłaStreszczenie:
The thesis aims to investigate and develop innovative tools to provide autonomous flight capability to a fixed-wing unmanned aircraft. Particularly it contributes to research on path optimization, tra jectory tracking and collision avoidance with two algorithms designed respectively for path planning and navigation. The complete system generates the shortest path from start to target avoiding known obstacles represented on a map, then drives the aircraft to track the optimum path avoiding unpredicted ob jects sensed in flight.
The path planning algorithm, named Kinematic A*, is developed on the basis of graph search algorithms like A* or Theta* and is meant to bridge the gap between path-search logics of these methods and aircraft kinematic constraints. On the other hand the navigation algorithm faces concurring tasks of tra jectory tracking and collision avoidance with Nonlinear Model Predictive Control.
When A* is applied to path planning of unmanned aircrafts any aircraft kinematics is taken into account, then practicability of the path is not guaranteed. Kinematic A* (KA*) generates feasible paths through graph-search logics and basic vehicle characteristics. It includes a simple aircraft kinematic-model to evaluate moving cost between nodes of tridimensional graphs. Movements are constrained with minimum turning radius and maximum rate of climb. Furtermore, separation from obstacles is imposed, defining a volume around the path free from obstacles (tube-type boundaries). Navigation is safe when the tracking error does not exceed this volume.
The path-tracking task aims to link kinematic information related to desired aircraft positions with dynamic behaviors to generate commands that minimize the error between reference and real tra jectory. On the other hand avoid obstacles in flight is one of the
most challenging tasks for autonomous aircrafts and many elements must be taken into account in order to implement an effective collision avoidance maneuver. Second part of the thesis describes a Nonlinear Model Predictive Control (NMPC) application to cope
with collision avoidance and path tracking tasks. First contribution is the development of a navigation system able to match concurring problems: track the optimal path provided with KA* and avoid unpredicted obstacles detected with sensors. Second Contribution is the Sense & Avoid (S&A) technique exploiting spherical camera and visual servoing control logics.