|
|
Visualisation of Path-Finding for Robot
Roubalík, Zbyněk ; Drahanský, Martin (referee) ; Rozman, Jaroslav (advisor)
This thesis deals with methods of path-finding for robot, rather path-finding with Bug algorithms and Potential fields. The thesis descibes individual Bug Algorithms just as theoretical principles of Potential fields and planning paths in this fields. To better demonstration of these algorithms were created java applets. Design, implementation and control over these applets is also described in this thesis.
|
|
|
Visualisation of Path-Planning
Vozák, Petr ; Orság, Filip (referee) ; Rozman, Jaroslav (advisor)
This thesis deals with sampling-based algorithms for nonholonomic (mainly car robot) and flexible robot path planning. Theoretical principles of probabilistic path finding and its implementation detail are discussed here. Java applets for visualization of algorithms and web pages are include on the CD.
|
|
|
Local Navigation of an Autonomous Mobile Robot
Herman, David ; Rozman, Jaroslav (referee) ; Orság, Filip (advisor)
This paper deals with the topic of design of a navigation system for an autonomous mobile robot in a park-like environment. Precisely, designing methods for road detection using available sensoric system, designing a mathematical model for fusion of these data, and suggesting a representation of an environment suitable for planning and local navigation.
|
|
|
Centralised Traffic System Load Evaluation
Zukal, Marek ; Rozman, Jaroslav (referee) ; Janoušek, Vladimír (advisor)
There are statistical data gathered as a part of the operation of the intersections controlled by the traffic light signalling devices. This data concerns characteristics of traffic flows and parameters of the aplied controlling strategy and can be valuable source of information that can be used to improve the controlling strategy or creation of a mathematical model describing the behaviour of the traffic flows. These models are closely studied and used for prediction of the immediate development of the traffic flows based on their current states. This paper is trying to design means to create such models and to work with them.
|
|
|
Telepresence Autonomous Robot for Exploration of Unapproachable Areas
Krkavec, Martin ; Janoušek, Vladimír (referee) ; Rozman, Jaroslav (advisor)
The subject of this master's thesis was to get familiar with a robot developed at the Department of Intelligent Systems of FIT VUT Brno. The goal of this work was to design and then implement hardware and software improvements of the robot so it could be capable of telepresence exploration of a narrow cave using remote control, including autonomous return back to the entrance. Also suggest possible extensions for a further improvement of the robot.
|
|
|
Modern Planning Algorithms
Binko, Petr ; Rozman, Jaroslav (referee) ; Zbořil, František (advisor)
This work describes graphplan, satplan and real-time adaptive A* planning algorithms. Through implementation of these algorithms, functionality and assumed attributes (real-time calculation, parallelism) are tested. These tests take place in nontrivial domains. Graphplan and satplan algorithms were tested in block-world, tire-world and bulldozer domains. Results of these tests were compared and displayed in graphs. Real-time adaptive A* algorithm was tested in tire-world domain. Results of these tests were compared with classic A* algorithm. Advantages and disadvantages of these algorithms are also described in this work.
|
|
|
Robot for Robotour 2010
Kubát, David ; Zbořil, František (referee) ; Rozman, Jaroslav (advisor)
The objective of this master's thesis was to get acquainted with an autonomous outdoor robot competition - The Robotour and further to study the capabilities and information about a robot designed on the DITS FIT Brno VUT. Next part of the project was to study various planning and localization algorithms and to make a proposal of a functional solution, allowing the robot to participate in the competition. To be specific, the goal of this work was to use the acquired knowledge for implementation of an antonomous software so the robot can start in the year 2010 race. The solution also included several related mechanical modifications. The final solution fulfills all the competiton rules and is capable of taking part in this year's plant.
|
|
|
Playing of Nondeterministic Games with Learning
Bukovský, Marek ; Rozman, Jaroslav (referee) ; Zbořil, František (advisor)
The thesis is dedicated to the study and implementation of methods used for learning from the course of playing. The chosen game for this thesis is Backgammon. The algorithm used for training neural networks is called the temporal difference learning with use of eligible traces. This algorithm is also known as TD(lambda). The theoretical part describes algorithms for playing games without learning, introduction to reinforcement learning, temporal difference learning and introduction to artificial neural networks. The practical part deals with application of combination of neural networks and TD(lambda) algorithms.
|
|
|
Optimisation of Exhaust Drains Shape
Navrátil, Dušan ; Rozman, Jaroslav (referee) ; Zbořil, František (advisor)
Multiobjective optimization system of exhaust manifold shapes including initial design has been developed. Space of possible solutions is explored by an evolutionary algorithm. Evaluation of exhaust drains shape comes from drains length and sum of arc angles. Drains mustn't interfere in surrounding parts. System is tested on set of input data originated from practice. Further, performance of proposed evolutionary algorithm is evaluated.
|
|
| |
guest ::
RSS feed.