Automated Deep Reinforcement Learning Environment for Hardware of a Modular Legged Robot

Sehoon Ha, Joohyung Kim, Katsu Yamane

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In this paper, we present an automated learning environment for developing control policies directly on the hardware of a modular legged robot. This environment facilitates the reinforcement learning process by computing the rewards using a vision-based tracking system and relocating the robot to the initial position using a resetting mechanism. We employ two state-of-the-art deep reinforcement learning (DRL) algorithms, Trust Region Policy Optimization (TRPO) and Deep Deterministic Policy Gradient (DDPG), to train neural network policies for simple rowing and crawling motions. Using the developed environment, we demonstrate both learning algorithms can effectively learn policies for simple locomotion skills on highly stochastic hardware and environments. We further expedite learning by transferring policies learned on a single legged configuration to multi-legged ones.

Original languageEnglish (US)
Title of host publication2018 15th International Conference on Ubiquitous Robots, UR 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages348-354
Number of pages7
ISBN (Print)9781538663349
DOIs
StatePublished - Aug 20 2018
Externally publishedYes
Event15th International Conference on Ubiquitous Robots, UR 2018 - Honolulu, United States
Duration: Jun 27 2018Jun 30 2018

Publication series

Name2018 15th International Conference on Ubiquitous Robots, UR 2018

Conference

Conference15th International Conference on Ubiquitous Robots, UR 2018
CountryUnited States
CityHonolulu
Period6/27/186/30/18

ASJC Scopus subject areas

  • Artificial Intelligence
  • Control and Optimization
  • Mechanical Engineering

Fingerprint Dive into the research topics of 'Automated Deep Reinforcement Learning Environment for Hardware of a Modular Legged Robot'. Together they form a unique fingerprint.

  • Cite this

    Ha, S., Kim, J., & Yamane, K. (2018). Automated Deep Reinforcement Learning Environment for Hardware of a Modular Legged Robot. In 2018 15th International Conference on Ubiquitous Robots, UR 2018 (pp. 348-354). [8442201] (2018 15th International Conference on Ubiquitous Robots, UR 2018). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/URAI.2018.8442201