Path planning problem in mobile robotics can be solved in several ways. Often used are probabilistic roadmaps and potential field algorithm. However, adding nonholonomic constraints into part planning algorithm can be difficult for those methods. Therefore the rapidly exploring random trees (RRT) algorithm was examined and paper illustrates its usability in path planning task for both legged (walking) and wheeled mobile robots. The method proved to be capable of coping with limiting constraints and at the same time it is very fast, enabling its use in real time path recalculation when used with localization algorithm. and Obsahuje seznam literatury
This paper is concentrated on a reactive sensor - based omnidirectional motion mode in in-door robot surrounding. A high accuracy dead - reckogning and obstacle avoidance of the robot is acquired. The method supposes the use of odometer robot means. The model assumes that the wheel distance measurement errors are random zero means white noise. Algorithms developed will be implemented within a generic SW architecture and used on ‘OMR III‘ experimental robot. and Obsahuje seznam literatury
The mobile robot path planning involves finding the shortest and least difficult path from a start to a goal position in a given environment without collisions with known obstacles.
The main idea of case-based reasoning (CBR) is a presumption that similar tasks probably also have similar solutions. New tasks are solved by adapting old proved solutions of similar tasks to new conditions. Tasks and their solutions (cases) are stored in a case base.
The focal point of this paper is the proposition of a path planning method based on CBR combined with graph algorithms in the environment represented by a rectangular grid. On the basis of the experimental results obtained, it is possible to say that case-based reasoning can significantly save computation costs, particularly in large environments. and Obsahuje seznam literatury