Get 20M+ Full-Text Papers For Less Than $1.50/day. Subscribe now for You or Your Team.

Learn More →

A Q-learning approach based on human reasoning for navigation in a dynamic environment

A Q-learning approach based on human reasoning for navigation in a dynamic environment SUMMARYA Q-learning approach is often used for navigation in static environments where state space is easy to define. In this paper, a new Q-learning approach is proposed for navigation in dynamic environments by imitating human reasoning. As a model-free method, a Q-learning method does not require the environmental model in advance. The state space and the reward function in the proposed approach are defined according to human perception and evaluation, respectively. Specifically, approximate regions instead of accurate measurements are used to define states. Moreover, due to the limitation of robot dynamics, actions for each state are calculated by introducing a dynamic window that takes robot dynamics into account. The conducted tests show that the obstacle avoidance rate of the proposed approach can reach 90.5% after training, and the robot can always operate below the dynamics limitation. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Robotica Cambridge University Press

A Q-learning approach based on human reasoning for navigation in a dynamic environment

Robotica , Volume 37 (3): 24 – Oct 30, 2018

Loading next page...
 
/lp/cambridge-university-press/a-q-learning-approach-based-on-human-reasoning-for-navigation-in-a-iWzuioiegM

References (29)

Publisher
Cambridge University Press
Copyright
Copyright © Cambridge University Press 2018 
ISSN
1469-8668
eISSN
0263-5747
DOI
10.1017/S026357471800111X
Publisher site
See Article on Publisher Site

Abstract

SUMMARYA Q-learning approach is often used for navigation in static environments where state space is easy to define. In this paper, a new Q-learning approach is proposed for navigation in dynamic environments by imitating human reasoning. As a model-free method, a Q-learning method does not require the environmental model in advance. The state space and the reward function in the proposed approach are defined according to human perception and evaluation, respectively. Specifically, approximate regions instead of accurate measurements are used to define states. Moreover, due to the limitation of robot dynamics, actions for each state are calculated by introducing a dynamic window that takes robot dynamics into account. The conducted tests show that the obstacle avoidance rate of the proposed approach can reach 90.5% after training, and the robot can always operate below the dynamics limitation.

Journal

RoboticaCambridge University Press

Published: Oct 30, 2018

Keywords: Autonomous navigation; Mobile robot; Dynamic environment; Q-learning

There are no references for this article.