Title :
Acquiring mobile robot behaviors by learning trajectory velocities with multiple FAM matrices
Author :
Ward, Koren ; Zelinsky, Alexander
Author_Institution :
Sch. of Inf. Technol. & Comput. Sci., Wollongong Univ., NSW, Australia
Abstract :
We describe an unsupervised robot learning method which is based on the robot learning a mapping between sensors and trajectory velocities. This enables the robot to acquire object avoidance, wall following and goal seeking behaviors simultaneously without incurring the credit assignment problem. To improve the robot´s perception and behaviors we provide the robot with 7 fuzzy associative matrices (FAMs) so that sensors can be mapped to each trajectory independently. We provide results demonstrating how a mobile robot equipped with 16 sonar sensors is able to achieve improved perception and behaviors by using 7 FAMs to map sensors to trajectories
Keywords :
fuzzy control; matrix algebra; mobile robots; path planning; unsupervised learning; fuzzy associative matrices; goal seeking behavior; mobile robot behaviors; object avoidance; sonar sensors; trajectory velocities; unsupervised robot learning method; wall following; Australia; Computer science; Information science; Information technology; Learning systems; Mobile robots; Orbital robotics; Robot sensing systems; Sonar navigation; Trajectory;
Conference_Titel :
Robotics and Automation, 1998. Proceedings. 1998 IEEE International Conference on
Conference_Location :
Leuven
Print_ISBN :
0-7803-4300-X
DOI :
10.1109/ROBOT.1998.677049