A Hierarchical Strategy for Learning of Robot Walking Strategies in Natural Terrain Environments

©2007 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other users, including reprinting/ republishing this material for advertising or promotional purposes, creating new collective works for resale or redistribution to servers or lists, or reuse of any...

Full description

Bibliographic Details
Published in:2007 IEEE International Conference on Systems, Man and Cybernetics
Main Authors: Howard, Ayanna M., Parker, Lonnie T.
Other Authors: Georgia Institute of Technology. Human-Automation Systems Lab, Rochester Institute of Technology. Dept. of Electrical Engineering, Georgia Institute of Technology. Center for Robotics and Intelligent Machines
Format: Conference Object
Language:English
Published: Georgia Institute of Technology 2007
Subjects:
Natural terrain environment navigation
Persistent forward locomotion
Robot walking learning strategies
Robot navigation
Antarc*
Antarctica
Online Access:http://hdl.handle.net/1853/38302
https://doi.org/10.1109/ICSMC.2007.4413682
Description
Summary:©2007 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other users, including reprinting/ republishing this material for advertising or promotional purposes, creating new collective works for resale or redistribution to servers or lists, or reuse of any copyrighted components of this work in other works. Presented at the 2007 IEEE International Conference on Systems, Man and Cybernetics, October 7-10, 2007, Montréal. DOI:10.1109/ICSMC.2007.4413682 In this paper, we present a hierarchical methodology that learns new walking gaits autonomously while operating in an uncharted environment, such as on the Mars planetary surface or in the remote Antarctica environment. The focus is to maintain persistent forward locomotion along the body axis, while navigating in natural terrain environments. The hierarchical strategy consists of a finite state machine that models the state of leg orientations coupled with a modified evolutionary algorithm to learn necessary leg movement sequences. Locomotion behavior is assessed by monitoring the robot's progress toward a specified goal location. Details of the methodology are discussed, and experimental results with a six-legged robot are presented.

Similar Items