Title :
Neural network approach to path planning for two dimensional robot motion
Author :
Kozakiewicz, Christopher ; Ejiri, Masakazu
Author_Institution :
Mech. Eng. Res. Lab., Hitachi Ltd., Ibaraki, Japan
Abstract :
A method for robot obstacle avoidance and path planning is proposed. The algorithm is based on a camera image feedback loop utilizing a neural network for image processing. The method can successfully generate collision-free paths in a 2D robot workspace containing randomly-placed polygonal obstacles. The control algorithm is simple and robust and has low computational requirements. Controller simulation implemented on a personal computer can generate collision-free robot paths in real time, requiring approximately 1 sec. per robot move
Keywords :
computerised picture processing; feedback; neural nets; planning (artificial intelligence); position control; robots; 2D robot workspace; camera image feedback loop; collision-free paths; neural network; obstacle avoidance; path planning; robot motion; Cameras; Computational modeling; Computer simulation; Feedback loop; Image processing; Microcomputers; Neural networks; Path planning; Robot vision systems; Robust control;
Conference_Titel :
Intelligent Robots and Systems '91. 'Intelligence for Mechanical Systems, Proceedings IROS '91. IEEE/RSJ International Workshop on
Conference_Location :
Osaka
Print_ISBN :
0-7803-0067-X
DOI :
10.1109/IROS.1991.174585
