Autonomous Learning of Stable Quadruped Locomotion

Authors:
Manish Saggar;Thomas D'Silva;Nate Kohl;Peter Stone
Affiliations:
Department of Computer Sciences,;Department of Electrical and Computer Engineering, The University of Texas at Austin,;Department of Computer Sciences,;Department of Computer Sciences,
Venue:
RoboCup 2006: Robot Soccer World Cup X
Year:
2006

Citing 5
Cited 7

Mean Shift: A Robust Approach Toward Feature Space Analysis

IEEE Transactions on Pattern Analysis and Machine Intelligence
Machine learning for fast quadrupedal locomotion

AAAI'04 Proceedings of the 19th national conference on Artifical intelligence
Reliable and precise gait modeling for a quadruped robot

RoboCup 2005
A model-based approach to robot joint control

RoboCup 2004
Evolutionary gait-optimization using a fitness function based on proprioception

RoboCup 2004

MARIOnET: motion acquisition for robots through iterative online evaluative training

Proceedings of the 9th International Conference on Autonomous Agents and Multiagent Systems: volume 1 - Volume 1
Learning powerful kicks on the aibo ERS-7: the quest for a striker

RoboCup 2010
Integrating reinforcement learning with human demonstrations of varying ability

The 10th International Conference on Autonomous Agents and Multiagent Systems - Volume 2
Portable autonomous walk calibration for 4-legged robots

Applied Intelligence
Strategy-Based learning through communication with humans

KES-AMSTA'12 Proceedings of the 6th KES international conference on Agent and Multi-Agent Systems: technologies and applications
Humanoid robots learning to walk faster: from the real world to simulation and back

Proceedings of the 2013 international conference on Autonomous agents and multi-agent systems
A comparison between a communication-based and a data mining-based learning approach for agents

Intelligent Decision Technologies

Quantified Score

Hi-index	0.00

Visualization

Abstract

A fast gait is an essential component of any successful team in the RoboCup 4-legged league. However, quickly moving quadruped robots, including those with learned gaits, often move in such a way so as to cause unsteady camera motions which degrade the robot's visual capabilities. This paper presents an implementation of the policy gradient machine learning algorithm that searches for a parameterized walk while optimizing for both speed and stability. To the best of our knowledge, previous learned walks have all focused exclusively on speed. Our method is fully implemented and tested on the Sony Aibo ERS-7 robot platform. The resulting gait is reasonably fast and considerably more stable compared to our previous fast gaits. We demonstrate that this stability can significantly improve the robot's visual object recognition.