The multi-dimensional actions control approach for obstacle avoidance based on reinforcement learning

Loading...
Thumbnail Image

Access rights

openAccess
publishedVersion

URL

Journal Title

Journal ISSN

Volume Title

A1 Alkuperäisartikkeli tieteellisessä aikakauslehdessä

Major/Subject

Mcode

Degree programme

Language

en

Pages

20

Series

SYMMETRY, Volume 13, issue 8

Abstract

In robotics, obstacle avoidance is an essential ability for distance sensor-based robots. This type of robot has axisymmetrically distributed distance sensors to acquire obstacle distance, so the state is symmetrical. Training the control policy with a reinforcement learning method is a trend. Considering the complexity of environments, such as narrow paths and right-angle turns, robots will have a better ability if the control policy can control the steering direction and speed simultaneously. This paper proposes the multi-dimensional action control (MDAC) approach based on a reinforcement learning technique, which can be used in multiple continuous action space tasks. It adopts a hierarchical structure, which has high and low-level modules. Low-level policies output concrete actions and the high-level policy determines when to invoke low-level modules according to the environment’s features. We design robot navigation experiments with continuous action spaces to test the method’s performance. It is an end-to-end approach and can solve complex obstacle avoidance tasks in navigation.

Description

Publisher Copyright: © 2021 by the authors. Licensee MDPI, Basel, Switzerland.

Other note

Citation

Wu, M, Gao, Y, Wang, P, Zhang, F & Liu, Z 2021, 'The multi-dimensional actions control approach for obstacle avoidance based on reinforcement learning', SYMMETRY, vol. 13, no. 8, 1335. https://doi.org/10.3390/sym13081335