Path Planning for Robots Combined with Zero-Shot and Hierarchical Reinforcement Learning in Novel Environments

Path planning for robots based on reinforcement learning encounters challenges in integrating semantic information about environments into the training process. In unseen or complex environmental information, agents often perform sub-optimally and require more training time. In response to these cha...

Full description

Saved in:
Bibliographic Details
Main Authors: Liwei Mei, Pengjie Xu
Format: Article
Language:English
Published: MDPI AG 2024-11-01
Series:Actuators
Subjects:
Online Access:https://www.mdpi.com/2076-0825/13/11/458
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846154822821085184
author Liwei Mei
Pengjie Xu
author_facet Liwei Mei
Pengjie Xu
author_sort Liwei Mei
collection DOAJ
description Path planning for robots based on reinforcement learning encounters challenges in integrating semantic information about environments into the training process. In unseen or complex environmental information, agents often perform sub-optimally and require more training time. In response to these challenges, this manuscript pioneers a framework integrating zero-shot learning combined with hierarchical reinforcement learning to enhance agent decision-making in complex environments. Zero-shot learning enables agents to infer correct actions for previously unseen objects or situations based on learned semantic associations. Subsequently, the path planning component utilizes hierarchical reinforcement learning with adaptive replay buffer, directed by the insights gained from zero-shot learning, to make decisions effectively. Two parts are trained separately, so zero-shot learning is available in different and unseen environments. Through simulation experiments, we compare the traditional hierarchical reinforcement learning method with the proposed method. The results prove that this structure can make full use of environmental information to generalize across unseen environments and plan collision-free paths.
format Article
id doaj-art-14821b1a5a724f839fc0515a3d001359
institution Kabale University
issn 2076-0825
language English
publishDate 2024-11-01
publisher MDPI AG
record_format Article
series Actuators
spelling doaj-art-14821b1a5a724f839fc0515a3d0013592024-11-26T17:42:31ZengMDPI AGActuators2076-08252024-11-01131145810.3390/act13110458Path Planning for Robots Combined with Zero-Shot and Hierarchical Reinforcement Learning in Novel EnvironmentsLiwei Mei0Pengjie Xu1School of Information Science and Technology, East China University of Science and Technology, Shanghai 200237, ChinaSchool of Mechanical Engineering, Shanghai Jiaotong University, Shanghai 200240, ChinaPath planning for robots based on reinforcement learning encounters challenges in integrating semantic information about environments into the training process. In unseen or complex environmental information, agents often perform sub-optimally and require more training time. In response to these challenges, this manuscript pioneers a framework integrating zero-shot learning combined with hierarchical reinforcement learning to enhance agent decision-making in complex environments. Zero-shot learning enables agents to infer correct actions for previously unseen objects or situations based on learned semantic associations. Subsequently, the path planning component utilizes hierarchical reinforcement learning with adaptive replay buffer, directed by the insights gained from zero-shot learning, to make decisions effectively. Two parts are trained separately, so zero-shot learning is available in different and unseen environments. Through simulation experiments, we compare the traditional hierarchical reinforcement learning method with the proposed method. The results prove that this structure can make full use of environmental information to generalize across unseen environments and plan collision-free paths.https://www.mdpi.com/2076-0825/13/11/458path planningzero-shot learninghierarchical reinforcement learningadaptive agents
spellingShingle Liwei Mei
Pengjie Xu
Path Planning for Robots Combined with Zero-Shot and Hierarchical Reinforcement Learning in Novel Environments
Actuators
path planning
zero-shot learning
hierarchical reinforcement learning
adaptive agents
title Path Planning for Robots Combined with Zero-Shot and Hierarchical Reinforcement Learning in Novel Environments
title_full Path Planning for Robots Combined with Zero-Shot and Hierarchical Reinforcement Learning in Novel Environments
title_fullStr Path Planning for Robots Combined with Zero-Shot and Hierarchical Reinforcement Learning in Novel Environments
title_full_unstemmed Path Planning for Robots Combined with Zero-Shot and Hierarchical Reinforcement Learning in Novel Environments
title_short Path Planning for Robots Combined with Zero-Shot and Hierarchical Reinforcement Learning in Novel Environments
title_sort path planning for robots combined with zero shot and hierarchical reinforcement learning in novel environments
topic path planning
zero-shot learning
hierarchical reinforcement learning
adaptive agents
url https://www.mdpi.com/2076-0825/13/11/458
work_keys_str_mv AT liweimei pathplanningforrobotscombinedwithzeroshotandhierarchicalreinforcementlearninginnovelenvironments
AT pengjiexu pathplanningforrobotscombinedwithzeroshotandhierarchicalreinforcementlearninginnovelenvironments