Conventional obstacle avoidance path planning based on Q-learning often results in the agent falling into the local optimal point (LOP). Although such conventional path planning methods have been used in a variety of maps, complications that prevent successful navigation around obstacles occur. Thus, to improve the success rate of obstacle avoidance path planning, this paper introduces the detection of the LOP in the navigation process. Two auxiliary methods based on changing the temporary goal of the agent are proposed for escaping the LOPs. Using the proposed methods, an improved obstacle avoidance path planning algorithm is simulated, resulting in a better outcome.
Q-Learning-Based Obstacle Avoidance Path Planning with Local Optimal Points
Lect. Notes Electrical Eng.
30.10.2021
14 pages
Aufsatz/Kapitel (Buch)
Elektronische Ressource
Englisch
Obstacle Avoidance Path Planning of Rotor UAV
British Library Conference Proceedings | 2017
|A PATH PLANNING STRATEGY FOR OBSTACLE AVOIDANCE
British Library Conference Proceedings | 2006
|An Optimal Obstacle Avoidance Path Planning Algorithm for the Excalibur Robot
British Library Conference Proceedings | 1991
|