Data-driven sequential goal selection model for multi-agent simulation

Wenxi Liu; Zhe Huang; Rynson W. H. Lau; Dinesh Manocha

doi:10.1145/2671015.2671024

Data-driven sequential goal selection model for multi-agent simulation

Wenxi Liu
, Zhe Huang
, Rynson W. H. Lau
, Dinesh Manocha

Department of Computer Science

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

1 Citation (Scopus)

Abstract

With recent advances in distributed virtual worlds, online users have access to larger and more immersive virtual environments. Sometimes the number of users in virtual worlds is not large enough to make the virtual world realistic. In our paper, we present a crowd simulation algorithm that allows a large number of virtual agents to navigate around the virtual world autonomously by sequentially selecting the goals. Our approach is based on our sequential goal selection model (SGS) which can learn goal-selection patterns from synthetic sequences. We demonstrate our algorithm's simulation results in complex scenarios containing more than 20 goals.

Original language	English
Title of host publication	Proceedings of the ACM Symposium on Virtual Reality Software and Technology, VRST
Publisher	Association for Computing Machinery
Pages	107-116
ISBN (Print)	9781450332538
DOIs	https://doi.org/10.1145/2671015.2671024
Publication status	Published - 11 Nov 2014
Event	20th ACM Symposium on Virtual Reality Software and Technology, VRST 2014 - Edinburgh, United Kingdom Duration: 11 Nov 2014 → 13 Nov 2014

Conference

Conference	20th ACM Symposium on Virtual Reality Software and Technology, VRST 2014
Place	United Kingdom
City	Edinburgh
Period	11/11/14 → 13/11/14

Research Keywords

Crowd simulation
Data-driven animation
Goal selection

Access Output

10.1145/2671015.2671024

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@inproceedings{e798f48a864943b1aaa5312c6df88066,

title = "Data-driven sequential goal selection model for multi-agent simulation",

abstract = "With recent advances in distributed virtual worlds, online users have access to larger and more immersive virtual environments. Sometimes the number of users in virtual worlds is not large enough to make the virtual world realistic. In our paper, we present a crowd simulation algorithm that allows a large number of virtual agents to navigate around the virtual world autonomously by sequentially selecting the goals. Our approach is based on our sequential goal selection model (SGS) which can learn goal-selection patterns from synthetic sequences. We demonstrate our algorithm's simulation results in complex scenarios containing more than 20 goals.",

keywords = "Crowd simulation, Data-driven animation, Goal selection",

author = "Wenxi Liu and Zhe Huang and Lau, \{Rynson W. H.\} and Dinesh Manocha",

year = "2014",

month = nov,

day = "11",

doi = "10.1145/2671015.2671024",

language = "English",

isbn = "9781450332538",

pages = "107--116",

booktitle = "Proceedings of the ACM Symposium on Virtual Reality Software and Technology, VRST",

publisher = "Association for Computing Machinery",

address = "United States",

note = "20th ACM Symposium on Virtual Reality Software and Technology, VRST 2014 ; Conference date: 11-11-2014 Through 13-11-2014",

}

Liu, W, Huang, Z, Lau, RWH & Manocha, D 2014, Data-driven sequential goal selection model for multi-agent simulation. in Proceedings of the ACM Symposium on Virtual Reality Software and Technology, VRST. Association for Computing Machinery, pp. 107-116, 20th ACM Symposium on Virtual Reality Software and Technology, VRST 2014, Edinburgh, United Kingdom, 11/11/14. https://doi.org/10.1145/2671015.2671024

Data-driven sequential goal selection model for multi-agent simulation. / Liu, Wenxi; Huang, Zhe; Lau, Rynson W. H. et al.
Proceedings of the ACM Symposium on Virtual Reality Software and Technology, VRST. Association for Computing Machinery, 2014. p. 107-116.

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

TY - GEN

T1 - Data-driven sequential goal selection model for multi-agent simulation

AU - Liu, Wenxi

AU - Huang, Zhe

AU - Lau, Rynson W. H.

AU - Manocha, Dinesh

PY - 2014/11/11

Y1 - 2014/11/11

N2 - With recent advances in distributed virtual worlds, online users have access to larger and more immersive virtual environments. Sometimes the number of users in virtual worlds is not large enough to make the virtual world realistic. In our paper, we present a crowd simulation algorithm that allows a large number of virtual agents to navigate around the virtual world autonomously by sequentially selecting the goals. Our approach is based on our sequential goal selection model (SGS) which can learn goal-selection patterns from synthetic sequences. We demonstrate our algorithm's simulation results in complex scenarios containing more than 20 goals.

AB - With recent advances in distributed virtual worlds, online users have access to larger and more immersive virtual environments. Sometimes the number of users in virtual worlds is not large enough to make the virtual world realistic. In our paper, we present a crowd simulation algorithm that allows a large number of virtual agents to navigate around the virtual world autonomously by sequentially selecting the goals. Our approach is based on our sequential goal selection model (SGS) which can learn goal-selection patterns from synthetic sequences. We demonstrate our algorithm's simulation results in complex scenarios containing more than 20 goals.

KW - Crowd simulation

KW - Data-driven animation

KW - Goal selection

UR - https://www.scopus.com/pages/publications/84911168835

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-84911168835&origin=recordpage

U2 - 10.1145/2671015.2671024

DO - 10.1145/2671015.2671024

M3 - RGC 32 - Refereed conference paper (with host publication)

SN - 9781450332538

SP - 107

EP - 116

BT - Proceedings of the ACM Symposium on Virtual Reality Software and Technology, VRST

PB - Association for Computing Machinery

T2 - 20th ACM Symposium on Virtual Reality Software and Technology, VRST 2014

Y2 - 11 November 2014 through 13 November 2014

ER -

Data-driven sequential goal selection model for multi-agent simulation

Abstract

Conference

Research Keywords

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this