A Pedestrian Path-planning Model in Accordance with Obstacle's Danger with Reinforcement Learning

Thanh Trung Trinh, Dinh Minh Vu, Masaomi Kimura

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

1 Citation (Scopus)

Abstract

Most microscopic pedestrian navigation models use the concept of "forces"applied to the pedestrian agents to replicate the navigation environment. While the approach could provide believable results in regular situations, it does not always resemble natural pedestrian navigation behaviour in many typical settings. In our research, we proposed a novel approach using reinforcement learning for simulation of pedestrian agent path planning and collision avoidance problem. The primary focus of this approach is using human perception of the environment and danger awareness of interferences. The implementation of our model has shown that the path planned by the agent shares many similarities with a human pedestrian in several aspects such as following common walking conventions and human behaviours.

Original languageEnglish
Title of host publicationProceedings of the 2020 3rd International Conference on Information Science and System, ICISS 2020
PublisherAssociation for Computing Machinery
Pages115-120
Number of pages6
ISBN (Electronic)9781450377256
DOIs
Publication statusPublished - 2020 Mar 19
Event3rd International Conference on Information Science and System, ICISS 2020 - Virtual, Online, United Kingdom
Duration: 2020 Mar 192020 Mar 22

Publication series

NameACM International Conference Proceeding Series

Conference

Conference3rd International Conference on Information Science and System, ICISS 2020
CountryUnited Kingdom
CityVirtual, Online
Period20/3/1920/3/22

Keywords

  • navigation
  • path planning
  • Pedestrian
  • PPO
  • reinforcement learning

ASJC Scopus subject areas

  • Human-Computer Interaction
  • Computer Networks and Communications
  • Computer Vision and Pattern Recognition
  • Software

Fingerprint Dive into the research topics of 'A Pedestrian Path-planning Model in Accordance with Obstacle's Danger with Reinforcement Learning'. Together they form a unique fingerprint.

Cite this