Towards Real-Time Credible and Scalable Agent-Based Simulations of Autonomous Pedestrians Navigation
International audience In this paper, we focus on real-time simulation of autonomous pedestrians navigation. We introduce a Macroscopic-Influenced Microscopic (MIM) approach which aims at reducing the gap between microscopic and macroscopic approaches by providing credible walking paths for a potent...
Published in: | Proceedings of the 20th ACM Symposium on Virtual Reality Software and Technology - VRST '14 |
---|---|
Main Authors: | , |
Other Authors: | , , |
Format: | Conference Object |
Language: | English |
Published: |
HAL CCSD
2014
|
Subjects: | |
Online Access: | https://hal.science/hal-01217231 https://doi.org/10.1145/2671015.2671030 |
id |
ftccsdartic:oai:HAL:hal-01217231v1 |
---|---|
record_format |
openpolar |
spelling |
ftccsdartic:oai:HAL:hal-01217231v1 2023-06-06T11:58:20+02:00 Towards Real-Time Credible and Scalable Agent-Based Simulations of Autonomous Pedestrians Navigation Simo Kanmeugne, Patrick Beynier, Aurélie Systèmes Multi-Agents (SMA) Laboratoire d'Informatique de Paris 6 (LIP6) Université Pierre et Marie Curie - Paris 6 (UPMC)-Centre National de la Recherche Scientifique (CNRS)-Université Pierre et Marie Curie - Paris 6 (UPMC)-Centre National de la Recherche Scientifique (CNRS) Edinburgh, United Kingdom 2014-11 https://hal.science/hal-01217231 https://doi.org/10.1145/2671015.2671030 en eng HAL CCSD ACM info:eu-repo/semantics/altIdentifier/doi/10.1145/2671015.2671030 hal-01217231 https://hal.science/hal-01217231 doi:10.1145/2671015.2671030 Proceedings of the 20th ACM Symposium on Virtual Reality Software and Technology, VRST '14 The 20th ACM Symposium on Virtual Reality Software and Technology, VRST '14 https://hal.science/hal-01217231 The 20th ACM Symposium on Virtual Reality Software and Technology, VRST '14, Nov 2014, Edinburgh, United Kingdom. pp.127-136, ⟨10.1145/2671015.2671030⟩ [INFO]Computer Science [cs] info:eu-repo/semantics/conferenceObject Conference papers 2014 ftccsdartic https://doi.org/10.1145/2671015.2671030 2023-04-16T06:14:41Z International audience In this paper, we focus on real-time simulation of autonomous pedestrians navigation. We introduce a Macroscopic-Influenced Microscopic (MIM) approach which aims at reducing the gap between microscopic and macroscopic approaches by providing credible walking paths for a potentially highly congested crowd of autonomous pedestrians. Our approach originates from a least-effort formulation of the navigation task, which allows us to consistently account for congestion at every level of decision. We use the multi-agent paradigm and describe pedestrians as autonomous and situated agents who plan dynamically for energy efficient paths and interact with each other through the environment. The navigable space is considered as a set of contiguous resources that agents use to build their paths. We emulate the dynamic path computation for each agent with an evolutionary search algorithm, especially designed to be executed in real-time, individually and autonomously. We have compared an implementation of our approach with the ORCA model, on low density and high density scenarios, and obtained promising results in terms of credibility and scalability. We believe that ORCA model and other microscopic models could be easily extended to embrace our approach, thus providing richer simulations of potentially highly congested crowd of autonomous pedestrians. Conference Object Orca Archive ouverte HAL (Hyper Article en Ligne, CCSD - Centre pour la Communication Scientifique Directe) Proceedings of the 20th ACM Symposium on Virtual Reality Software and Technology - VRST '14 127 136 |
institution |
Open Polar |
collection |
Archive ouverte HAL (Hyper Article en Ligne, CCSD - Centre pour la Communication Scientifique Directe) |
op_collection_id |
ftccsdartic |
language |
English |
topic |
[INFO]Computer Science [cs] |
spellingShingle |
[INFO]Computer Science [cs] Simo Kanmeugne, Patrick Beynier, Aurélie Towards Real-Time Credible and Scalable Agent-Based Simulations of Autonomous Pedestrians Navigation |
topic_facet |
[INFO]Computer Science [cs] |
description |
International audience In this paper, we focus on real-time simulation of autonomous pedestrians navigation. We introduce a Macroscopic-Influenced Microscopic (MIM) approach which aims at reducing the gap between microscopic and macroscopic approaches by providing credible walking paths for a potentially highly congested crowd of autonomous pedestrians. Our approach originates from a least-effort formulation of the navigation task, which allows us to consistently account for congestion at every level of decision. We use the multi-agent paradigm and describe pedestrians as autonomous and situated agents who plan dynamically for energy efficient paths and interact with each other through the environment. The navigable space is considered as a set of contiguous resources that agents use to build their paths. We emulate the dynamic path computation for each agent with an evolutionary search algorithm, especially designed to be executed in real-time, individually and autonomously. We have compared an implementation of our approach with the ORCA model, on low density and high density scenarios, and obtained promising results in terms of credibility and scalability. We believe that ORCA model and other microscopic models could be easily extended to embrace our approach, thus providing richer simulations of potentially highly congested crowd of autonomous pedestrians. |
author2 |
Systèmes Multi-Agents (SMA) Laboratoire d'Informatique de Paris 6 (LIP6) Université Pierre et Marie Curie - Paris 6 (UPMC)-Centre National de la Recherche Scientifique (CNRS)-Université Pierre et Marie Curie - Paris 6 (UPMC)-Centre National de la Recherche Scientifique (CNRS) |
format |
Conference Object |
author |
Simo Kanmeugne, Patrick Beynier, Aurélie |
author_facet |
Simo Kanmeugne, Patrick Beynier, Aurélie |
author_sort |
Simo Kanmeugne, Patrick |
title |
Towards Real-Time Credible and Scalable Agent-Based Simulations of Autonomous Pedestrians Navigation |
title_short |
Towards Real-Time Credible and Scalable Agent-Based Simulations of Autonomous Pedestrians Navigation |
title_full |
Towards Real-Time Credible and Scalable Agent-Based Simulations of Autonomous Pedestrians Navigation |
title_fullStr |
Towards Real-Time Credible and Scalable Agent-Based Simulations of Autonomous Pedestrians Navigation |
title_full_unstemmed |
Towards Real-Time Credible and Scalable Agent-Based Simulations of Autonomous Pedestrians Navigation |
title_sort |
towards real-time credible and scalable agent-based simulations of autonomous pedestrians navigation |
publisher |
HAL CCSD |
publishDate |
2014 |
url |
https://hal.science/hal-01217231 https://doi.org/10.1145/2671015.2671030 |
op_coverage |
Edinburgh, United Kingdom |
genre |
Orca |
genre_facet |
Orca |
op_source |
Proceedings of the 20th ACM Symposium on Virtual Reality Software and Technology, VRST '14 The 20th ACM Symposium on Virtual Reality Software and Technology, VRST '14 https://hal.science/hal-01217231 The 20th ACM Symposium on Virtual Reality Software and Technology, VRST '14, Nov 2014, Edinburgh, United Kingdom. pp.127-136, ⟨10.1145/2671015.2671030⟩ |
op_relation |
info:eu-repo/semantics/altIdentifier/doi/10.1145/2671015.2671030 hal-01217231 https://hal.science/hal-01217231 doi:10.1145/2671015.2671030 |
op_doi |
https://doi.org/10.1145/2671015.2671030 |
container_title |
Proceedings of the 20th ACM Symposium on Virtual Reality Software and Technology - VRST '14 |
container_start_page |
127 |
op_container_end_page |
136 |
_version_ |
1767966924567740416 |