Path planning for a statically stable biped robot using PRM and reinforcement learning

Prasad Kulkarni, Dip Goswami, Prithwijit Guha, Ashish Dutta

Research output: Contribution to journalArticleAcademicpeer-review

8 Citations (Scopus)

Abstract

In this paper path planning and obstacle avoidance for a statically stable biped robot using PRM and reinforcement learning is discussed. The main objective of the paper is to compare these two methods of path planning for applications involving a biped robot. The statically stable biped robot under consideration is a 4-degree of freedom walking robot that can follow any given trajectory on flat ground and has a fixed step length of 200 mm. It is proved that the path generated by the first method produces the shortest smooth path but it also increases the computational burden on the controller, as the robot has to turn at almost all steps. However the second method produces paths that are composed of straight-line segments and hence requires less computation for trajectory following. Experiments were also conducted to prove the effectiveness of the reinforcement learning based path planning method.

Original languageEnglish
Pages (from-to)197-214
Number of pages18
JournalJournal of Intelligent and Robotic Systems
Volume47
Issue number3
DOIs
Publication statusPublished - 1 Nov 2006
Externally publishedYes

Keywords

  • Potential function
  • PRM
  • Reinforcement learning
  • Statically stable biped robot

Fingerprint Dive into the research topics of 'Path planning for a statically stable biped robot using PRM and reinforcement learning'. Together they form a unique fingerprint.

  • Cite this