Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Pedestrian simulation as multi-objective reinforcement learning
KTH, School of Electrical Engineering and Computer Science (EECS), Centres, Centre for High Performance Computing, PDC. (Computational Brain Science Lab)
KTH, School of Electrical Engineering and Computer Science (EECS), Computational Science and Technology (CST).
KTH, School of Electrical Engineering and Computer Science (EECS), Computational Science and Technology (CST).ORCID iD: 0000-0002-7257-0761
KTH, School of Electrical Engineering and Computer Science (EECS), Computational Science and Technology (CST).ORCID iD: 0000-0002-2358-7815
Show others and affiliations
2018 (English)In: Proceedings of the 18th International Conference on Intelligent Virtual Agents, IVA 2018, 2018, p. 307-312Conference paper, Published paper (Refereed)
Abstract [en]

Modelling and simulation of pedestrian crowds require agents to reach pre-determined goals and avoid collisions with static obstacles and dynamic pedestrians, while maintaining natural gait behaviour. We model pedestrians as autonomous, learning, and reactive agents employing Reinforcement Learning (RL). Typical RL-based agent simulations suffer poor generalization due to handcrafted reward function to ensure realistic behaviour. In this work, we model pedestrians in a modular framework integrating navigation and collision-avoidance tasks as separate modules. Each such module consists of independent state-spaces and rewards, but with shared action-spaces. Empirical results suggest that such modular framework learning models can show satisfactory performance without tuning parameters, and we compare it with the state-of-art crowd simulation methods.

Place, publisher, year, edition, pages
2018. p. 307-312
Keywords [en]
Agent-based simulation, Multi-objective learning, Parallel learning, Reinforcement learning
National Category
Other Engineering and Technologies
Identifiers
URN: urn:nbn:se:kth:diva-241487DOI: 10.1145/3267851.3267914Scopus ID: 2-s2.0-85058477147ISBN: 9781450360135 (print)OAI: oai:DiVA.org:kth-241487DiVA, id: diva2:1281770
Conference
18th ACM International Conference on Intelligent Virtual Agents, IVA 2018; Western Sydney University's new Parramatta City Campus, Sydney; Australia; 5 November 2018 through 8 November 2018
Note

QC 20190123

Available from: 2019-01-23 Created: 2019-01-23 Last updated: 2019-06-03Bibliographically approved

Open Access in DiVA

fulltext(1792 kB)19 downloads
File information
File name FULLTEXT01.pdfFile size 1792 kBChecksum SHA-512
770a5947cd443e309d62595e35391ca72f6ae38bdd760fb952602535b1788801bc1238c9bde12e6fe1acad5ebef0c5ed76c729d7f33517890873fab915bc91b2
Type fulltextMimetype application/pdf

Other links

Publisher's full textScopus

Authority records BETA

Yang, FangkaiPeters, ChristopherLansner, AndersHerman, Pawel

Search in DiVA

By author/editor
Ravichandran, Naresh BalajiYang, FangkaiPeters, ChristopherLansner, AndersHerman, Pawel
By organisation
Centre for High Performance Computing, PDCComputational Science and Technology (CST)
Other Engineering and Technologies

Search outside of DiVA

GoogleGoogle Scholar
Total: 19 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

doi
isbn
urn-nbn

Altmetric score

doi
isbn
urn-nbn
Total: 131 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf