Reinforcement Learning-Based Intelligent Path Planning for Optimal Navigation in Dynamic Environments

Yadav, Anil Kumar; Sharma, Purushottam; Cheng, Cheng; Prasad, Shiv Shankar

doi:10.1007/s11063-025-11821-2

Journal article 45 views 3 downloads

Reinforcement Learning-Based Intelligent Path Planning for Optimal Navigation in Dynamic Environments

Anil Kumar Yadav, Purushottam Sharma, Cheng Cheng

, Shiv Shankar Prasad Shukla

Neural Processing Letters, Volume: 58, Issue: 1, Start page: 10

Swansea University Author: Cheng Cheng

PDF | Version of Record

© The Author(s) 2026. This article is licensed under a Creative Commons Attribution 4.0 International License.
Download (2.59MB)

Check full text

DOI (Published version): 10.1007/s11063-025-11821-2

Abstract

Path selection and planning are crucial for autonomous mobile robots (AMRs) to navigate efficiently and avoid obstacles. Traditional methods rely on analytical search to identify the shortest distance. However, Reinforcement learning enhances performance by optimizing a sequence of actions efficient...

Full description

Published in:	Neural Processing Letters
ISSN:	1370-4621 1573-773X
Published:	Springer Nature 2026
Online Access:	Check full text
URI:	https://cronfa.swan.ac.uk/Record/cronfa71192

first_indexed	2026-01-05T12:34:44Z
last_indexed	2026-01-31T05:34:32Z
id	cronfa71192
recordtype	SURis
fullrecord	<?xml version="1.0"?><rfc1807><datestamp>2026-01-30T13:14:04.6857950</datestamp><bib-version>v2</bib-version><id>71192</id><entry>2026-01-05</entry><title>Reinforcement Learning-Based Intelligent Path Planning for Optimal Navigation in Dynamic Environments</title><swanseaauthors><author><sid>11ddf61c123b99e59b00fa1479367582</sid><ORCID>0000-0003-0371-9646</ORCID><firstname>Cheng</firstname><surname>Cheng</surname><name>Cheng Cheng</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2026-01-05</date><deptcode>MACS</deptcode><abstract>Path selection and planning are crucial for autonomous mobile robots (AMRs) to navigate efficiently and avoid obstacles. Traditional methods rely on analytical search to identify the shortest distance. However, Reinforcement learning enhances performance by optimizing a sequence of actions efficiently. It is an iterative approach used for computational sequence modeling and dynamic programming. RL received sensory input from the environment in the form of observation or state. The agent interpreted every reward or penalty through trial-and-error interaction. Policy maximizes the rewards and selects the optimal action among all possible actions. A challenging problem in traditional reinforcement learning is environment generalization for dynamic systems. Q-learning faces challenges in dynamic environments because it relies on rewards or penalties based on the entire sequence of actions from the start to the end state. This approach often fails to produce optimal results when the environment changes unexpectedly due to state transitions, iterations, or blocked routes. Such limitations make Q-learning less effective for dynamic path planning. To overcome these challenges, this study focuses on optimizing reward functions for efficient navigation in RL-based path planning, aiming to enhance navigation efficiency and obstacle avoidance. The proposed method evaluates the shortest decision path by considering total steps, counted steps, and discount rates in dynamic environments. By implementing this RL with an optimized reward mechanism, the study analyzes state reward values across different environments, and it evaluates the effect on state-action pair-based Q-Learning and neural networks using Deep Q-Learning algorithms. Here, results demonstrate that the optimized reward function effectively decreases the number of iterations and episodes while achieving a 30% to 70% reduction in overall trajectory distance. These results highlight the effectiveness of reward-based reinforcement learning, demonstrating its potential to improve path optimization, learning rate, episode completion, and decision accuracy in intelligent navigation systems. Q-learning-based reinforcement learning becomes more effective by combining multiple agents and utilizing decision-making techniques such as federated and transfer learning on larger maps to ensure convergence.</abstract><type>Journal Article</type><journal>Neural Processing Letters</journal><volume>58</volume><journalNumber>1</journalNumber><paginationStart>10</paginationStart><paginationEnd/><publisher>Springer Nature</publisher><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint>1370-4621</issnPrint><issnElectronic>1573-773X</issnElectronic><keywords>Q-learning (QL); Reinforcement learning (RL); Reward function; Policy iteration; Path optimization; Trajectory planning; Navigation</keywords><publishedDay>1</publishedDay><publishedMonth>2</publishedMonth><publishedYear>2026</publishedYear><publishedDate>2026-02-01</publishedDate><doi>10.1007/s11063-025-11821-2</doi><url/><notes/><college>COLLEGE NANME</college><department>Mathematics and Computer Science School</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>MACS</DepartmentCode><institution>Swansea University</institution><apcterm>SU Library paid the OA fee (TA Institutional Deal)</apcterm><funders>Authors have been supported by UKRI EPSRC Grant funded Doctoral Training Centre at Swansea University, through project RS718. Authors also have been supported by UKRI EPSRC Grant EP/W020408/1.</funders><projectreference/><lastEdited>2026-01-30T13:14:04.6857950</lastEdited><Created>2026-01-05T12:32:40.9799197</Created><path><level id="1">Faculty of Science and Engineering</level><level id="2">School of Mathematics and Computer Science - Computer Science</level></path><authors><author><firstname>Anil Kumar</firstname><surname>Yadav</surname><order>1</order></author><author><firstname>Purushottam</firstname><surname>Sharma</surname><order>2</order></author><author><firstname>Cheng</firstname><surname>Cheng</surname><orcid>0000-0003-0371-9646</orcid><order>3</order></author><author><firstname>Shiv Shankar Prasad</firstname><surname>Shukla</surname><order>4</order></author></authors><documents><document><filename>71192__36147__ffbf7a0abbaf4339ba74d181e09ffa8b.pdf</filename><originalFilename>71192.VOR.pdf</originalFilename><uploaded>2026-01-30T13:11:59.8060812</uploaded><type>Output</type><contentLength>2715332</contentLength><contentType>application/pdf</contentType><version>Version of Record</version><cronfaStatus>true</cronfaStatus><documentNotes>© The Author(s) 2026. This article is licensed under a Creative Commons Attribution 4.0 International License.</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language><licence>http://creativecommons.org/licenses/by/4.0/</licence></document></documents><OutputDurs/></rfc1807>
spelling	2026-01-30T13:14:04.6857950 v2 71192 2026-01-05 Reinforcement Learning-Based Intelligent Path Planning for Optimal Navigation in Dynamic Environments 11ddf61c123b99e59b00fa1479367582 0000-0003-0371-9646 Cheng Cheng Cheng Cheng true false 2026-01-05 MACS Path selection and planning are crucial for autonomous mobile robots (AMRs) to navigate efficiently and avoid obstacles. Traditional methods rely on analytical search to identify the shortest distance. However, Reinforcement learning enhances performance by optimizing a sequence of actions efficiently. It is an iterative approach used for computational sequence modeling and dynamic programming. RL received sensory input from the environment in the form of observation or state. The agent interpreted every reward or penalty through trial-and-error interaction. Policy maximizes the rewards and selects the optimal action among all possible actions. A challenging problem in traditional reinforcement learning is environment generalization for dynamic systems. Q-learning faces challenges in dynamic environments because it relies on rewards or penalties based on the entire sequence of actions from the start to the end state. This approach often fails to produce optimal results when the environment changes unexpectedly due to state transitions, iterations, or blocked routes. Such limitations make Q-learning less effective for dynamic path planning. To overcome these challenges, this study focuses on optimizing reward functions for efficient navigation in RL-based path planning, aiming to enhance navigation efficiency and obstacle avoidance. The proposed method evaluates the shortest decision path by considering total steps, counted steps, and discount rates in dynamic environments. By implementing this RL with an optimized reward mechanism, the study analyzes state reward values across different environments, and it evaluates the effect on state-action pair-based Q-Learning and neural networks using Deep Q-Learning algorithms. Here, results demonstrate that the optimized reward function effectively decreases the number of iterations and episodes while achieving a 30% to 70% reduction in overall trajectory distance. These results highlight the effectiveness of reward-based reinforcement learning, demonstrating its potential to improve path optimization, learning rate, episode completion, and decision accuracy in intelligent navigation systems. Q-learning-based reinforcement learning becomes more effective by combining multiple agents and utilizing decision-making techniques such as federated and transfer learning on larger maps to ensure convergence. Journal Article Neural Processing Letters 58 1 10 Springer Nature 1370-4621 1573-773X Q-learning (QL); Reinforcement learning (RL); Reward function; Policy iteration; Path optimization; Trajectory planning; Navigation 1 2 2026 2026-02-01 10.1007/s11063-025-11821-2 COLLEGE NANME Mathematics and Computer Science School COLLEGE CODE MACS Swansea University SU Library paid the OA fee (TA Institutional Deal) Authors have been supported by UKRI EPSRC Grant funded Doctoral Training Centre at Swansea University, through project RS718. Authors also have been supported by UKRI EPSRC Grant EP/W020408/1. 2026-01-30T13:14:04.6857950 2026-01-05T12:32:40.9799197 Faculty of Science and Engineering School of Mathematics and Computer Science - Computer Science Anil Kumar Yadav 1 Purushottam Sharma 2 Cheng Cheng 0000-0003-0371-9646 3 Shiv Shankar Prasad Shukla 4 71192__36147__ffbf7a0abbaf4339ba74d181e09ffa8b.pdf 71192.VOR.pdf 2026-01-30T13:11:59.8060812 Output 2715332 application/pdf Version of Record true © The Author(s) 2026. This article is licensed under a Creative Commons Attribution 4.0 International License. true eng http://creativecommons.org/licenses/by/4.0/
title	Reinforcement Learning-Based Intelligent Path Planning for Optimal Navigation in Dynamic Environments
spellingShingle	Reinforcement Learning-Based Intelligent Path Planning for Optimal Navigation in Dynamic Environments Cheng Cheng
title_short	Reinforcement Learning-Based Intelligent Path Planning for Optimal Navigation in Dynamic Environments
title_full	Reinforcement Learning-Based Intelligent Path Planning for Optimal Navigation in Dynamic Environments
title_fullStr	Reinforcement Learning-Based Intelligent Path Planning for Optimal Navigation in Dynamic Environments
title_full_unstemmed	Reinforcement Learning-Based Intelligent Path Planning for Optimal Navigation in Dynamic Environments
title_sort	Reinforcement Learning-Based Intelligent Path Planning for Optimal Navigation in Dynamic Environments
author_id_str_mv	11ddf61c123b99e59b00fa1479367582
author_id_fullname_str_mv	11ddf61c123b99e59b00fa1479367582_***_Cheng Cheng
author	Cheng Cheng
author2	Anil Kumar Yadav Purushottam Sharma Cheng Cheng Shiv Shankar Prasad Shukla
format	Journal article
container_title	Neural Processing Letters
container_volume	58
container_issue	1
container_start_page	10
publishDate	2026
institution	Swansea University
issn	1370-4621 1573-773X
doi_str_mv	10.1007/s11063-025-11821-2
publisher	Springer Nature
college_str	Faculty of Science and Engineering
hierarchytype
hierarchy_top_id	facultyofscienceandengineering
hierarchy_top_title	Faculty of Science and Engineering
hierarchy_parent_id	facultyofscienceandengineering
hierarchy_parent_title	Faculty of Science and Engineering
department_str	School of Mathematics and Computer Science - Computer Science{{{_:::_}}}Faculty of Science and Engineering{{{_:::_}}}School of Mathematics and Computer Science - Computer Science
document_store_str	1
active_str	0
description	Path selection and planning are crucial for autonomous mobile robots (AMRs) to navigate efficiently and avoid obstacles. Traditional methods rely on analytical search to identify the shortest distance. However, Reinforcement learning enhances performance by optimizing a sequence of actions efficiently. It is an iterative approach used for computational sequence modeling and dynamic programming. RL received sensory input from the environment in the form of observation or state. The agent interpreted every reward or penalty through trial-and-error interaction. Policy maximizes the rewards and selects the optimal action among all possible actions. A challenging problem in traditional reinforcement learning is environment generalization for dynamic systems. Q-learning faces challenges in dynamic environments because it relies on rewards or penalties based on the entire sequence of actions from the start to the end state. This approach often fails to produce optimal results when the environment changes unexpectedly due to state transitions, iterations, or blocked routes. Such limitations make Q-learning less effective for dynamic path planning. To overcome these challenges, this study focuses on optimizing reward functions for efficient navigation in RL-based path planning, aiming to enhance navigation efficiency and obstacle avoidance. The proposed method evaluates the shortest decision path by considering total steps, counted steps, and discount rates in dynamic environments. By implementing this RL with an optimized reward mechanism, the study analyzes state reward values across different environments, and it evaluates the effect on state-action pair-based Q-Learning and neural networks using Deep Q-Learning algorithms. Here, results demonstrate that the optimized reward function effectively decreases the number of iterations and episodes while achieving a 30% to 70% reduction in overall trajectory distance. These results highlight the effectiveness of reward-based reinforcement learning, demonstrating its potential to improve path optimization, learning rate, episode completion, and decision accuracy in intelligent navigation systems. Q-learning-based reinforcement learning becomes more effective by combining multiple agents and utilizing decision-making techniques such as federated and transfer learning on larger maps to ensure convergence.
published_date	2026-02-01T05:33:28Z
_version_	1856805806744272896
score	11.09611

Reinforcement Learning-Based Intelligent Path Planning for Optimal Navigation in Dynamic Environments

Similar Items