Multiple Subgoals-guided Hierarchical Learning in Robot Navigation

OnderzoeksoutputAcademicpeer review

43 Downloads (Pure)

Samenvatting

Solving obstacle-clustered robotic navigation tasks via model-free reinforcement learning (RL) is challenging due to the extended decision horizon and sparse rewards. Previous work has demonstrated efficient learning with single subgoal-conditioned hierarchical approaches. The subgoal is the action from the high-level policy and it operates on the low-level module, which could invoke sub-optimal policy when the selected subgoal is suboptimal. This work introduces multiple subgoals-guided navigation (MSGN) which consists of a high-level multiple subgoals Planner and a low-level goal-conditioned RL Controller. By passing multiple subgoals to the low-level agent, MSGN could alleviate the suboptimal subgoal problem by transferring the subgoal selection process to the RL agent. At the same time, multiple subgoals could help the goal-conditioned RL agent better explore and understand the environment and task. We tested our method on the Safety Gym suite. The results verified that MSGN could achieve a higher success rate and lower collision cost compared to baselines.

Originele taal-2English
Titel2022 IEEE International Conference on Robotics and Biomimetics, ROBIO 2022
UitgeverijInstitute of Electrical and Electronics Engineers Inc.
Pagina's9-14
Aantal pagina's6
ISBN van elektronische versie9781665481090
DOI's
StatusPublished - 18-jan.-2023
Evenement2022 IEEE International Conference on Robotics and Biomimetics, ROBIO 2022 - Jinghong, China
Duur: 5-dec.-20229-dec.-2022

Publicatie series

Naam2022 IEEE International Conference on Robotics and Biomimetics, ROBIO 2022

Conference

Conference2022 IEEE International Conference on Robotics and Biomimetics, ROBIO 2022
Land/RegioChina
StadJinghong
Periode05/12/202209/12/2022

Citeer dit