Trend analysis parameter’s impact for M1.
<div><p>Reinforcement learning is a remarkable aspect of the artificial intelligence field with many applications. Reinforcement learning facilitates learning new tasks based on action and reward principles. Motion planning addresses the navigation problem for robots. Current motion plan...
Saved in:
| Main Author: | |
|---|---|
| Other Authors: | , , , , |
| Published: |
2025
|
| Subjects: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1852023531877957632 |
|---|---|
| author | Raed Alharthi (18340157) |
| author2 | Iram Noreen (12334120) Amna Khan (735548) Turki Aljrees (16715369) Zoraiz Riaz (20571028) Nisreen Innab (20389920) |
| author2_role | author author author author author |
| author_facet | Raed Alharthi (18340157) Iram Noreen (12334120) Amna Khan (735548) Turki Aljrees (16715369) Zoraiz Riaz (20571028) Nisreen Innab (20389920) |
| author_role | author |
| dc.creator.none.fl_str_mv | Raed Alharthi (18340157) Iram Noreen (12334120) Amna Khan (735548) Turki Aljrees (16715369) Zoraiz Riaz (20571028) Nisreen Innab (20389920) |
| dc.date.none.fl_str_mv | 2025-01-16T18:45:31Z |
| dc.identifier.none.fl_str_mv | 10.1371/journal.pone.0312559.t003 |
| dc.relation.none.fl_str_mv | https://figshare.com/articles/dataset/Trend_analysis_parameter_s_impact_for_M1_/28223251 |
| dc.rights.none.fl_str_mv | CC BY 4.0 info:eu-repo/semantics/openAccess |
| dc.subject.none.fl_str_mv | Sociology Science Policy Mental Health Space Science Biological Sciences not elsewhere classified Information Systems not elsewhere classified robotic systems due could help deal artificial intelligence field art comparison shows motion planning addresses based motion planning problem becomes worse based reinforcement algorithm reward system ’ task learning due deep learning integration th </ sup proposed approach ’ div >< p cluttered passage environment causes late convergence complex environment cluttered narrow passage environment proposed approach cluttered environment complex environment reinforcement learning navigation problem reward principles reward policies path planning timely responses research presents remarkable aspect processing requirements novel q many applications less responsive less efficient issues using existing algorithms computationally expensive collision avoidance agent converged |
| dc.title.none.fl_str_mv | Trend analysis parameter’s impact for M1. |
| dc.type.none.fl_str_mv | Dataset info:eu-repo/semantics/publishedVersion dataset |
| description | <div><p>Reinforcement learning is a remarkable aspect of the artificial intelligence field with many applications. Reinforcement learning facilitates learning new tasks based on action and reward principles. Motion planning addresses the navigation problem for robots. Current motion planning approaches lack support for automated, timely responses to the environment. The problem becomes worse in a complex environment cluttered with obstacles. Reinforcement learning can increase the capacity of robotic systems due to the reward system’s capability and feedback to the environment. This could help deal with a complex environment. Existing algorithms for path planning are slow, computationally expensive, and less responsive to the environment, which causes late convergence to a solution. Furthermore, they are less efficient for task learning due to post-processing requirements. Reinforcement learning can address these issues using its action feedback and reward policies. This research presents a novel Q-learning-based reinforcement algorithm with deep learning integration. The proposed approach is evaluated in a narrow and cluttered passage environment. Further, improvements in the convergence of reinforcement learning-based motion planning and collision avoidance are addressed. The proposed approach’s agent converged in 210<sup>th</sup> episodes in a cluttered environment and 400<sup>th</sup> episodes in a narrow passage environment. A state-of-the-art comparison shows that the proposed approach outperformed existing approaches based on the number of turns and convergence of the path by the planner.</p></div> |
| eu_rights_str_mv | openAccess |
| id | Manara_e6897fdea87f4266324d49b1e7e2ea63 |
| identifier_str_mv | 10.1371/journal.pone.0312559.t003 |
| network_acronym_str | Manara |
| network_name_str | ManaraRepo |
| oai_identifier_str | oai:figshare.com:article/28223251 |
| publishDate | 2025 |
| repository.mail.fl_str_mv | |
| repository.name.fl_str_mv | |
| repository_id_str | |
| rights_invalid_str_mv | CC BY 4.0 |
| spelling | Trend analysis parameter’s impact for M1.Raed Alharthi (18340157)Iram Noreen (12334120)Amna Khan (735548)Turki Aljrees (16715369)Zoraiz Riaz (20571028)Nisreen Innab (20389920)SociologyScience PolicyMental HealthSpace ScienceBiological Sciences not elsewhere classifiedInformation Systems not elsewhere classifiedrobotic systems duecould help dealartificial intelligence fieldart comparison showsmotion planning addressesbased motion planningproblem becomes worsebased reinforcement algorithmreward system ’task learning duedeep learning integrationth </ supproposed approach ’div >< pcluttered passage environmentcauses late convergencecomplex environment clutterednarrow passage environmentproposed approachcluttered environmentcomplex environmentreinforcement learningnavigation problemreward principlesreward policiespath planningtimely responsesresearch presentsremarkable aspectprocessing requirementsnovel qmany applicationsless responsiveless efficientissues usingexisting algorithmscomputationally expensivecollision avoidanceagent converged<div><p>Reinforcement learning is a remarkable aspect of the artificial intelligence field with many applications. Reinforcement learning facilitates learning new tasks based on action and reward principles. Motion planning addresses the navigation problem for robots. Current motion planning approaches lack support for automated, timely responses to the environment. The problem becomes worse in a complex environment cluttered with obstacles. Reinforcement learning can increase the capacity of robotic systems due to the reward system’s capability and feedback to the environment. This could help deal with a complex environment. Existing algorithms for path planning are slow, computationally expensive, and less responsive to the environment, which causes late convergence to a solution. Furthermore, they are less efficient for task learning due to post-processing requirements. Reinforcement learning can address these issues using its action feedback and reward policies. This research presents a novel Q-learning-based reinforcement algorithm with deep learning integration. The proposed approach is evaluated in a narrow and cluttered passage environment. Further, improvements in the convergence of reinforcement learning-based motion planning and collision avoidance are addressed. The proposed approach’s agent converged in 210<sup>th</sup> episodes in a cluttered environment and 400<sup>th</sup> episodes in a narrow passage environment. A state-of-the-art comparison shows that the proposed approach outperformed existing approaches based on the number of turns and convergence of the path by the planner.</p></div>2025-01-16T18:45:31ZDatasetinfo:eu-repo/semantics/publishedVersiondataset10.1371/journal.pone.0312559.t003https://figshare.com/articles/dataset/Trend_analysis_parameter_s_impact_for_M1_/28223251CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/282232512025-01-16T18:45:31Z |
| spellingShingle | Trend analysis parameter’s impact for M1. Raed Alharthi (18340157) Sociology Science Policy Mental Health Space Science Biological Sciences not elsewhere classified Information Systems not elsewhere classified robotic systems due could help deal artificial intelligence field art comparison shows motion planning addresses based motion planning problem becomes worse based reinforcement algorithm reward system ’ task learning due deep learning integration th </ sup proposed approach ’ div >< p cluttered passage environment causes late convergence complex environment cluttered narrow passage environment proposed approach cluttered environment complex environment reinforcement learning navigation problem reward principles reward policies path planning timely responses research presents remarkable aspect processing requirements novel q many applications less responsive less efficient issues using existing algorithms computationally expensive collision avoidance agent converged |
| status_str | publishedVersion |
| title | Trend analysis parameter’s impact for M1. |
| title_full | Trend analysis parameter’s impact for M1. |
| title_fullStr | Trend analysis parameter’s impact for M1. |
| title_full_unstemmed | Trend analysis parameter’s impact for M1. |
| title_short | Trend analysis parameter’s impact for M1. |
| title_sort | Trend analysis parameter’s impact for M1. |
| topic | Sociology Science Policy Mental Health Space Science Biological Sciences not elsewhere classified Information Systems not elsewhere classified robotic systems due could help deal artificial intelligence field art comparison shows motion planning addresses based motion planning problem becomes worse based reinforcement algorithm reward system ’ task learning due deep learning integration th </ sup proposed approach ’ div >< p cluttered passage environment causes late convergence complex environment cluttered narrow passage environment proposed approach cluttered environment complex environment reinforcement learning navigation problem reward principles reward policies path planning timely responses research presents remarkable aspect processing requirements novel q many applications less responsive less efficient issues using existing algorithms computationally expensive collision avoidance agent converged |