Toward Obstacle Avoidance for Mobile Robots Using Deep Reinforcement Learning Algorithm

Xiaoshan Gao, Liang Yan, Gang Wang, Tiantian Wang, Nannan Du, Chris Gerada

Research output: Chapter in Book/Conference proceedingConference contributionpeer-review

Abstract

The state-of-the-art deep reinforcement learning algorithm, i.e., the deep deterministic policy gradient (DDPG), has achieved good performance in continuous control problems for the robotics. However, the conventional experience replay mechanism of the DDPG algorithm stores the experience explored by the mobile robot in the bufer pool, and trains the neural network through random sampling, without considering whether the transition is valuable, which can probably influence the network performance. To overcome the limitation, the DDPG framework with separating experience is developed for mobile robot collision-free navigation in this study, to replay the transitions of valuable and the failed experience discretely. Additionally, environment state vector is designed including mobile robot and obstacles, the reward function and action space are also designed. The simulation results show that the proposed model can possess the collision-free navigation capacity to deal with multiple obstacles.

Original languageEnglish
Title of host publicationProceedings of the 16th IEEE Conference on Industrial Electronics and Applications, ICIEA 2021
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages2136-2139
Number of pages4
ISBN (Electronic)9781665422482
DOIs
Publication statusPublished - 1 Aug 2021
Externally publishedYes
Event16th IEEE Conference on Industrial Electronics and Applications, ICIEA 2021 - Chengdu, China
Duration: 1 Aug 20214 Aug 2021

Publication series

NameProceedings of the 16th IEEE Conference on Industrial Electronics and Applications, ICIEA 2021

Conference

Conference16th IEEE Conference on Industrial Electronics and Applications, ICIEA 2021
Country/TerritoryChina
CityChengdu
Period1/08/214/08/21

Keywords

  • deep deterministic policy gradient
  • mobile robot
  • obstacle avoidance

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Industrial and Manufacturing Engineering
  • Instrumentation
  • Computer Vision and Pattern Recognition
  • Energy Engineering and Power Technology

Fingerprint

Dive into the research topics of 'Toward Obstacle Avoidance for Mobile Robots Using Deep Reinforcement Learning Algorithm'. Together they form a unique fingerprint.

Cite this