A conflict-free routing method for automated guided vehicles using reinforcement learning

Taichi Chujo, Kosei Nishida, Tatsushi Nishi

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In a modern large-scale fabrication, hundreds of vehicles are used for transportation. Since traffic conditions are changing rapidly, the routing of automated guided vehicles (AGV) needs to be changed according to the change in traffic conditions. We propose a conflict-free routing method for AGVs using reinforcement learning in dynamic transportation. An advantage of the proposed method is that a change in the state can be obtained as an evaluation function. Therefore, the action can be selected according to the states. A deadlock avoidance method in bidirectional transport systems is developed using reinforcement learning. The effectiveness of the proposed method is demonstrated by comparing the performance with the conventional Q learning algorithm from computational results.

Original languageEnglish
Title of host publication2020 International Symposium on Flexible Automation, ISFA 2020
PublisherAmerican Society of Mechanical Engineers (ASME)
ISBN (Electronic)9780791883617
DOIs
Publication statusPublished - 2020
Event2020 International Symposium on Flexible Automation, ISFA 2020 - Virtual, Online
Duration: Jul 8 2020Jul 9 2020

Publication series

Name2020 International Symposium on Flexible Automation, ISFA 2020

Conference

Conference2020 International Symposium on Flexible Automation, ISFA 2020
CityVirtual, Online
Period7/8/207/9/20

ASJC Scopus subject areas

  • Artificial Intelligence
  • Control and Systems Engineering

Fingerprint Dive into the research topics of 'A conflict-free routing method for automated guided vehicles using reinforcement learning'. Together they form a unique fingerprint.

Cite this