|
|
Expert Systems and Advanced Algorithms in Mobile Robots Path Planning
Abbadi, Ahmad ; Šeda, Miloš (referee) ; Volná,, Eva (referee) ; Matoušek, Radomil (advisor)
Metody plánování pohybu jsou významnou součástí robotiky, resp. mobilních robotických platforem. Technicky je realizace plánování pohybu z globální úrovně převedena do posloupnosti akcí na úrovni specifické robotické platformy a definovaného prostředí, včetně omezení. V rámci této práce byla provedena recenze mnoha metod určených pro plánování cest, přičemž hlavním těžištěm byly metody založené na tzv. rychle rostoucích stromech (RRT), prostorovém rozkladu (CD) a využití fuzzy expertních systémů (FES). Dosažené výsledky, resp. prezentované algoritmy, využívají dostupné informace z pracovního prostoru mobilního robotu a jsou aplikovatelné na řešení globální pohybové trajektorie mobilních robotů, resp. k řešení specifických problémů plánování cest s omezením typu úzké koridory či překážky s proměnnou polohou v čase. V práci jsou představeny nové plánovací postupy využívající výhod algoritmů RRT a CD. Navržené metody jsou navíc efektivně rozšířeny s využitím fuzzy expertního systému, který zlepšuje jejich chování. Práce rovněž prezentuje řešení pro plánovací problémy typu identifikace úzkých koridorů, či významných oblastí prostoru řešení s využitím přístupů na bázi dekompozice prostoru. V řešeních jsou částečně zahrnuty sub-optimalizace nalezených cest založené na zkracování nalezené cesty a vyhlazování cesty, resp. nahrazení trajektorie hladkou křivkou, respektující lépe předpokládanou dynamiku mobilního zařízení. Všechny prezentované metody byly implementovány v prostředí Matlab, které sloužilo k simulačnímu ověření efektivnosti vlastních i převzatých metod a k návrhu prostoru řešení včetně omezení (překážky). Získané výsledky byly vyhodnoceny s využitím statistických přístupů v prostředí Minitab a Matlab.
|
|
|
Autonomous mobile robot motion planning strategy design
Doseděl, Miroslav ; Králík, Jan (referee) ; Věchet, Stanislav (advisor)
This work is concerned with planning the movement of the robot in space and near plants. The main goal is to realize the movement of a robot designed for operation in indoor areas of buildings for watering indoor plants. In the first part of the thesis, existing algorithms for motion planning and obstacle avoidance are presented. In the next part, a search dealing with Framework ROS is written. The individual movements performed by the robot are then described and testing on the real robot is carried out at the end.
|
|
|
Path Planning in 3D Space
Sasýn, Radek ; Zbořil, František (referee) ; Rozman, Jaroslav (advisor)
This work describes path finding among obstacles in 3D space using probabilistic algorithms. Users can create scene in application GUI - define start object, obstacles, goal position and run probabilistic algorithm. The finding path is visualized. The work describes probabilistic algorithm, collision detection and the basics of 3D graphics and shows design and implementation of an application created.
|
|
|
Path Planning in 3D Space
Němec, František ; Samek, Jan (referee) ; Rozman, Jaroslav (advisor)
This paper deals with the problem of object path planning in 3D space. The goal is to create program which allows users to create a scene used for path planning, perform the planning and finally visualize path in the scene. Work is focused on probabilistic algorithms that are described in the theoretical part. The practical part describes the design and implementation of application. Finally, several experiments are performed to compare the performance of different algorithms and demonstrate the functionality of the program.
|
|
|
Navigation of mobile robots
Rozman, Jaroslav ; Matoušek,, Václav (referee) ; Šolc, František (referee) ; Zbořil, František (advisor)
Mobile robotics has been very discussed and wide spread topic recently. This due to the development in the computer technology that allows us to create better and more sophisticated robots. The goal of this effort is to create robots that will be able to autonomously move in the chosen environment. To achieve this goal, it is necessary for the robot to create the map of its environment, where the motion planning will occur. Nowadays, the probabilistic algorithms based on the SLAM algorithm are considered standard in the mapping in these times. This Phd. thesis deals with the proposal of the motion planning of the robot with stereocamera placed on the pan-and-tilt unit. The motion planning is designed with regard to the use of algorithms, which will look for the significant features in the pair of the images. With the use of the triangulation the map, or a model will be created. The benefits of this work can be divided into three parts. In the first one the way of marking the free area, where the robot will plan its motion, is described. The second part describes the motion planning of the robot in this free area. It takes into account the properties of the SLAM algorithm and it tries to plan the exploration in order to create the most precise map. The motion of the pan-and-tilt unit is described in the third part. It takes advantage of the fact that the robot can observe places that are in the different directions than the robot moves. This allows us to observe much bigger space without losing the information about the precision of the movements.
|
|
|
Path Planning in 3D Space
Krčmář, Radim ; Janoušek, Vladimír (referee) ; Rozman, Jaroslav (advisor)
Following thesis presents basics of motion planning, focusing on sampling-based algorithms. System for collision of objects in arbitrary dimensional space is created using linear algebra. Basic options for visualizaton of three-dimensional data are described. Selected algoritms were implemented in haskell and used to pull hedgehog out of the cage (popular disentanglement puzzle in Czech Republic).
|
|
|
Autonomous mobile robot motion planning strategy design
Doseděl, Miroslav ; Králík, Jan (referee) ; Věchet, Stanislav (advisor)
This work is concerned with planning the movement of the robot in space and near plants. The main goal is to realize the movement of a robot designed for operation in indoor areas of buildings for watering indoor plants. In the first part of the thesis, existing algorithms for motion planning and obstacle avoidance are presented. In the next part, a search dealing with Framework ROS is written. The individual movements performed by the robot are then described and testing on the real robot is carried out at the end.
|
|
|
Navigation of mobile robots
Rozman, Jaroslav ; Matoušek,, Václav (referee) ; Šolc, František (referee) ; Zbořil, František (advisor)
Mobile robotics has been very discussed and wide spread topic recently. This due to the development in the computer technology that allows us to create better and more sophisticated robots. The goal of this effort is to create robots that will be able to autonomously move in the chosen environment. To achieve this goal, it is necessary for the robot to create the map of its environment, where the motion planning will occur. Nowadays, the probabilistic algorithms based on the SLAM algorithm are considered standard in the mapping in these times. This Phd. thesis deals with the proposal of the motion planning of the robot with stereocamera placed on the pan-and-tilt unit. The motion planning is designed with regard to the use of algorithms, which will look for the significant features in the pair of the images. With the use of the triangulation the map, or a model will be created. The benefits of this work can be divided into three parts. In the first one the way of marking the free area, where the robot will plan its motion, is described. The second part describes the motion planning of the robot in this free area. It takes into account the properties of the SLAM algorithm and it tries to plan the exploration in order to create the most precise map. The motion of the pan-and-tilt unit is described in the third part. It takes advantage of the fact that the robot can observe places that are in the different directions than the robot moves. This allows us to observe much bigger space without losing the information about the precision of the movements.
|
|
|
Path Planning in 3D Space
Němec, František ; Samek, Jan (referee) ; Rozman, Jaroslav (advisor)
This paper deals with the problem of object path planning in 3D space. The goal is to create program which allows users to create a scene used for path planning, perform the planning and finally visualize path in the scene. Work is focused on probabilistic algorithms that are described in the theoretical part. The practical part describes the design and implementation of application. Finally, several experiments are performed to compare the performance of different algorithms and demonstrate the functionality of the program.
|
|
|
Path Planning in 3D Space
Krčmář, Radim ; Janoušek, Vladimír (referee) ; Rozman, Jaroslav (advisor)
Following thesis presents basics of motion planning, focusing on sampling-based algorithms. System for collision of objects in arbitrary dimensional space is created using linear algebra. Basic options for visualizaton of three-dimensional data are described. Selected algoritms were implemented in haskell and used to pull hedgehog out of the cage (popular disentanglement puzzle in Czech Republic).
|
guest ::
