Experimental Study on Path Planning Algorithms for Warehouse Mobile Robot Based on Reinforcement Learning

Planning in mobile robots is an essential task because it helps to achieve efficient movement in terms of time, computational resources, and safety. Warehouse robots, for example, are equipped with sensors and cameras to avoid obstacles and to move products around the warehouse pick and pack orders....

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE NW Russia Young Researchers in Electrical and Electronic Engineering Conference S. 170 - 175
Hauptverfasser: Hammoud, Moahmmed, Haydar, Ola, Lupin, Sergey
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 29.01.2024
Schlagworte:
ISSN:2376-6565
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract Planning in mobile robots is an essential task because it helps to achieve efficient movement in terms of time, computational resources, and safety. Warehouse robots, for example, are equipped with sensors and cameras to avoid obstacles and to move products around the warehouse pick and pack orders. In this project, we have used path-planning algorithms based on Reinforcement Learning (RL), which include Q-learning (QL), State-Action-Reward-State-Action (SARSA), and Expected SARSA (ESARSA). We evaluated these algorithms on a benchmark dataset with different sizes and obstacle densities. Our findings show that QL produces a more optimal path, but the path is risky since it is close to obstacles. On the other hand, SARSA produces a safer path. However, in terms of convergence speed, SARSA is slow, while ESARSA is faster and more stable but with extra computations.
AbstractList Planning in mobile robots is an essential task because it helps to achieve efficient movement in terms of time, computational resources, and safety. Warehouse robots, for example, are equipped with sensors and cameras to avoid obstacles and to move products around the warehouse pick and pack orders. In this project, we have used path-planning algorithms based on Reinforcement Learning (RL), which include Q-learning (QL), State-Action-Reward-State-Action (SARSA), and Expected SARSA (ESARSA). We evaluated these algorithms on a benchmark dataset with different sizes and obstacle densities. Our findings show that QL produces a more optimal path, but the path is risky since it is close to obstacles. On the other hand, SARSA produces a safer path. However, in terms of convergence speed, SARSA is slow, while ESARSA is faster and more stable but with extra computations.
Author Lupin, Sergey
Hammoud, Moahmmed
Haydar, Ola
Author_xml – sequence: 1
  givenname: Moahmmed
  surname: Hammoud
  fullname: Hammoud, Moahmmed
  email: hammoudmsh93@gmail.com
  organization: Institute of Microdevices and Control Systems National Research University of Electronic Technology,Moscow,Russia
– sequence: 2
  givenname: Ola
  surname: Haydar
  fullname: Haydar, Ola
  email: oulahaider@gmail.com
  organization: Institute of Microdevices and Control Systems National Research University of Electronic Technology,Moscow,Russia
– sequence: 3
  givenname: Sergey
  surname: Lupin
  fullname: Lupin, Sergey
  email: lupin@miee.ru
  organization: Institute of Microdevices and Control Systems National Research University of Electronic Technology,Moscow,Russia
BookMark eNo1kN1OwkAUhFejiYi8gRf7AsVzdrt_l0gQTTAS1HhJtvYU1pRd0pZE3l4a9WouZuZLZq7ZRUyRGOMIY0Rwd7N6mqJGI2EsQORjhFxbocwZGznjrFQgNWjpztlASKMzrbS6YqO2_QIAIdAZYQcszL731IQdxc7X_LU7lEeeIl_6bsuXtY8xxA2f1JvUhG67a3mVGv7hG9qmQ0v8ORWhJr5KRer4vW-p7MsrCvGU-6Seyhfkm55ywy4rX7c0-tMhe3-YvU0fs8XL_Gk6WWQB0XUZKfRKu0L73BSFBlF5ZZRHLwy63rOGHBiq8oKEtaVBILAaUQkoSxJyyG5_uYGI1vvTNt8c1__vyB9-YFx3
ContentType Conference Proceeding
DBID 6IE
6IL
CBEJK
RIE
RIL
DOI 10.1109/ElCon61730.2024.10468257
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP All) 1998-Present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISBN 9798350360639
9798350360646
EISSN 2376-6565
EndPage 175
ExternalDocumentID 10468257
Genre orig-research
GroupedDBID 6IE
6IF
6IK
6IL
6IN
AAJGR
AAWTH
ABLEC
ADZIZ
ALMA_UNASSIGNED_HOLDINGS
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CBEJK
CHZPO
IEGSK
IPLJI
OCL
RIE
RIL
ID FETCH-LOGICAL-i119t-e51a569b6a47bb602fa575a1a271951a587e907ef4be288d710e08611520dde23
IEDL.DBID RIE
IngestDate Wed Aug 27 02:17:05 EDT 2025
IsPeerReviewed false
IsScholarly false
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i119t-e51a569b6a47bb602fa575a1a271951a587e907ef4be288d710e08611520dde23
PageCount 6
ParticipantIDs ieee_primary_10468257
PublicationCentury 2000
PublicationDate 2024-Jan.-29
PublicationDateYYYYMMDD 2024-01-29
PublicationDate_xml – month: 01
  year: 2024
  text: 2024-Jan.-29
  day: 29
PublicationDecade 2020
PublicationTitle IEEE NW Russia Young Researchers in Electrical and Electronic Engineering Conference
PublicationTitleAbbrev ElCon
PublicationYear 2024
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0002219728
Score 1.8588138
Snippet Planning in mobile robots is an essential task because it helps to achieve efficient movement in terms of time, computational resources, and safety. Warehouse...
SourceID ieee
SourceType Publisher
StartPage 170
SubjectTerms machine learning
Mobile robot
Multi-category classification
SCITOS G5
wall-following robot
Title Experimental Study on Path Planning Algorithms for Warehouse Mobile Robot Based on Reinforcement Learning
URI https://ieeexplore.ieee.org/document/10468257
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV09T8MwELWgYoCFryK-5YE1beI4cTJC1YoBqqoC0a2y42sbqcQoTZH495zdppSBgc2yZcnySb73znfvCLlTiY5CKUMvUyL1EP9zD3kWkhWuhVQAfCKdpZ9Ev5-MRulgXazuamEAwCWfQcsO3V--NtnShsra9j8SGY3YJbtCiFWx1iagwpjtoJXU2Tp-2u7OO6ZADx36yAMZb9XbfzVScX6kd_jPExyR5k9FHh1sfM0x2YHihBxsiQmekry7JdZPbX7gFzUFHSDEo3VrIno_n5oyr2bvC4polb7JEmbI_YE-G4XvAx0aZSr6gK5N281DcMKqmYsh0rUW67RJXnvdl86jt26k4OVBkFYeRIGM4lTFkgulYp9NJKI0GUgmgtSuJQKQJMOEK2BJohF1AFIdBIvMx-ePhWekUZgCzgmNgljFiUaQCYpnYSYDrnwVaok4K9ZcXZCmvbXxx0orY1xf2OUf81dk39rGBjVYek0aVbmEG7KXfVb5orx1Fv4GQf-oCA
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LTwIxEG4UTdSLL4xve_C6sNvtvo5KIBqBEIKRG2m3A2yCu2ZZTPz3TguLePDgrWmzm6aTdL5vOvMNIfcyVJ4rhGvFMogsxP_cQp6FZIWrQEgAPhbG0u2g2w2Hw6i3KlY3tTAAYJLPoKaH5i1fZfFCh8rq-j0SGU2wTXY8zpmzLNdah1QY0z20wjJfx47qzVkjS9FHuzYyQcZr5Q9-tVIxnqR1-M89HJHqT00e7a29zTHZgvSEHGzICZ6SpLkh1091huAXzVLaQ5BHy-ZE9GE2yfKkmL7PKeJV-iZymCL7B9rJJN4QtJ_JrKCP6NyU_rgPRlo1NlFEulJjnVTJa6s5aDxZq1YKVuI4UWGB5wjPj6QveCClb7OxQJwmHMECJ9JrYQBIk2HMJbAwVIg7AMkOwkVm4wXI3DNSSbMUzgn1HF_6oUKYCZLHbiwcLm3pKoFIy1dcXpCqPrXRx1ItY1Qe2OUf83dk72nQaY_az92XK7Kv7aRDHCy6JpUiX8AN2Y0_i2Se3xprfwMs0qtP
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=proceeding&rft.title=IEEE+NW+Russia+Young+Researchers+in+Electrical+and+Electronic+Engineering+Conference&rft.atitle=Experimental+Study+on+Path+Planning+Algorithms+for+Warehouse+Mobile+Robot+Based+on+Reinforcement+Learning&rft.au=Hammoud%2C+Moahmmed&rft.au=Haydar%2C+Ola&rft.au=Lupin%2C+Sergey&rft.date=2024-01-29&rft.pub=IEEE&rft.eissn=2376-6565&rft.spage=170&rft.epage=175&rft_id=info:doi/10.1109%2FElCon61730.2024.10468257&rft.externalDocID=10468257