A Reinforcement Learning-Based Double Layer Controller for Mobile Robot in Human-Shared Environments

Various approaches have been explored to address the path planning problem for mobile robots. However, it remains a significant challenge, particularly in environments where a multi-tasking mobile robot operates alongside stochastically moving humans. This paper focuses on path planning for a mobile...

Full description

Saved in:
Bibliographic Details
Main Authors: Jian Mi, Jianwen Liu, Yue Xu, Zhongjie Long, Jun Wang, Wei Xu, Tao Ji
Format: Article
Language:English
Published: MDPI AG 2025-07-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/15/14/7812
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849409119066259456
author Jian Mi
Jianwen Liu
Yue Xu
Zhongjie Long
Jun Wang
Wei Xu
Tao Ji
author_facet Jian Mi
Jianwen Liu
Yue Xu
Zhongjie Long
Jun Wang
Wei Xu
Tao Ji
author_sort Jian Mi
collection DOAJ
description Various approaches have been explored to address the path planning problem for mobile robots. However, it remains a significant challenge, particularly in environments where a multi-tasking mobile robot operates alongside stochastically moving humans. This paper focuses on path planning for a mobile robot executing multiple pickup and delivery tasks in an environment shared with humans. To plan a safe path and achieve high task success rate, a Reinforcement Learning (RL)-based double layer controller is proposed in which a double-layer learning algorithm is developed. The high-level layer integrates a Finite-State Automaton (FSA) with RL to perform global strategy learning and task-level decision-making. The low-level layer handles local path planning by incorporating a Markov Decision Process (MDP) that accounts for environmental uncertainties. We verify the proposed double layer algorithm under different configurations and evaluate its performance based on several metrics, including task success rate, reward, etc. The proposed method outperforms conventional RL in terms of reward (+63.1%) and task success rate (+113.0%). The simulation results demonstrate the effectiveness of the proposed algorithm in solving path planning problem with stochastic human uncertainties.
format Article
id doaj-art-ae128b82bfaf4aea8e716555819e4e1b
institution Kabale University
issn 2076-3417
language English
publishDate 2025-07-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-ae128b82bfaf4aea8e716555819e4e1b2025-08-20T03:35:36ZengMDPI AGApplied Sciences2076-34172025-07-011514781210.3390/app15147812A Reinforcement Learning-Based Double Layer Controller for Mobile Robot in Human-Shared EnvironmentsJian Mi0Jianwen Liu1Yue Xu2Zhongjie Long3Jun Wang4Wei Xu5Tao Ji6Department of Transport Engineering, College of Architecture Science and Engineering, Yangzhou University, Yangzhou 225127, ChinaDepartment of Transport Engineering, College of Architecture Science and Engineering, Yangzhou University, Yangzhou 225127, ChinaDepartment of Transport Engineering, College of Architecture Science and Engineering, Yangzhou University, Yangzhou 225127, ChinaKey Laboratory of the Ministry of Education for Modern Measurement & Control Technology, School of Electromechanical Engineering, Beijing Information Science & Technology University, Beijing 102206, ChinaCollege of Information Science & Technology, Beijing University of Chemical Technology, Beijing 100029, ChinaSmart Lab of Innovation, Sinotrans Innovation & Technology Co., Ltd., Beijing 100029, ChinaDepartment of Transport Engineering, College of Architecture Science and Engineering, Yangzhou University, Yangzhou 225127, ChinaVarious approaches have been explored to address the path planning problem for mobile robots. However, it remains a significant challenge, particularly in environments where a multi-tasking mobile robot operates alongside stochastically moving humans. This paper focuses on path planning for a mobile robot executing multiple pickup and delivery tasks in an environment shared with humans. To plan a safe path and achieve high task success rate, a Reinforcement Learning (RL)-based double layer controller is proposed in which a double-layer learning algorithm is developed. The high-level layer integrates a Finite-State Automaton (FSA) with RL to perform global strategy learning and task-level decision-making. The low-level layer handles local path planning by incorporating a Markov Decision Process (MDP) that accounts for environmental uncertainties. We verify the proposed double layer algorithm under different configurations and evaluate its performance based on several metrics, including task success rate, reward, etc. The proposed method outperforms conventional RL in terms of reward (+63.1%) and task success rate (+113.0%). The simulation results demonstrate the effectiveness of the proposed algorithm in solving path planning problem with stochastic human uncertainties.https://www.mdpi.com/2076-3417/15/14/7812reinforcement learningdouble-layer controlpath planningmobile robotshuman-shared environmentsMDP
spellingShingle Jian Mi
Jianwen Liu
Yue Xu
Zhongjie Long
Jun Wang
Wei Xu
Tao Ji
A Reinforcement Learning-Based Double Layer Controller for Mobile Robot in Human-Shared Environments
Applied Sciences
reinforcement learning
double-layer control
path planning
mobile robots
human-shared environments
MDP
title A Reinforcement Learning-Based Double Layer Controller for Mobile Robot in Human-Shared Environments
title_full A Reinforcement Learning-Based Double Layer Controller for Mobile Robot in Human-Shared Environments
title_fullStr A Reinforcement Learning-Based Double Layer Controller for Mobile Robot in Human-Shared Environments
title_full_unstemmed A Reinforcement Learning-Based Double Layer Controller for Mobile Robot in Human-Shared Environments
title_short A Reinforcement Learning-Based Double Layer Controller for Mobile Robot in Human-Shared Environments
title_sort reinforcement learning based double layer controller for mobile robot in human shared environments
topic reinforcement learning
double-layer control
path planning
mobile robots
human-shared environments
MDP
url https://www.mdpi.com/2076-3417/15/14/7812
work_keys_str_mv AT jianmi areinforcementlearningbaseddoublelayercontrollerformobilerobotinhumansharedenvironments
AT jianwenliu areinforcementlearningbaseddoublelayercontrollerformobilerobotinhumansharedenvironments
AT yuexu areinforcementlearningbaseddoublelayercontrollerformobilerobotinhumansharedenvironments
AT zhongjielong areinforcementlearningbaseddoublelayercontrollerformobilerobotinhumansharedenvironments
AT junwang areinforcementlearningbaseddoublelayercontrollerformobilerobotinhumansharedenvironments
AT weixu areinforcementlearningbaseddoublelayercontrollerformobilerobotinhumansharedenvironments
AT taoji areinforcementlearningbaseddoublelayercontrollerformobilerobotinhumansharedenvironments
AT jianmi reinforcementlearningbaseddoublelayercontrollerformobilerobotinhumansharedenvironments
AT jianwenliu reinforcementlearningbaseddoublelayercontrollerformobilerobotinhumansharedenvironments
AT yuexu reinforcementlearningbaseddoublelayercontrollerformobilerobotinhumansharedenvironments
AT zhongjielong reinforcementlearningbaseddoublelayercontrollerformobilerobotinhumansharedenvironments
AT junwang reinforcementlearningbaseddoublelayercontrollerformobilerobotinhumansharedenvironments
AT weixu reinforcementlearningbaseddoublelayercontrollerformobilerobotinhumansharedenvironments
AT taoji reinforcementlearningbaseddoublelayercontrollerformobilerobotinhumansharedenvironments