The role of data-driven priors in multi-agent crowd trajectory estimation

Gang Qiao, Sejong Yoon, Mubbasir Kapadia, Vladimir Pavlovic

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

1 Citation (Scopus)

Abstract

Trajectory interpolation, the process of filling-in the gaps and removing noise from observed agent trajectories, is an essential task for the motion inference in a multi-agent setting. A desired trajectory interpolation method should be robust to noise, changes in environments or agent densities, while also being able to yield realistic group movement behaviors. Such realistic behaviors are, however, challenging to model as they require avoidance of agent-agent or agent-environment collisions and, at the same time, demand computational efficiency. In this paper, we propose a novel framework composed of data-driven priors (local, global or combined) and an efficient optimization strategy for multi-agent trajectory interpolation. The data-driven priors implicitly encode the dependencies of movements of multiple agents and the collision-avoiding desiderata, enabling elimination of costly pairwise collision constraints, resulting in reduced computational complexity and often improved estimation. Various combinations of priors and optimization algorithms are evaluated in comprehensive simulated experiments. Our experimental results reveal important insights, including the significance of the global flow prior and the lesser-than-expected influence of data-driven collision priors.

Original languageEnglish (US)
Title of host publication32nd AAAI Conference on Artificial Intelligence, AAAI 2018
PublisherAAAI press
Pages4710-4717
Number of pages8
ISBN (Electronic)9781577358008
StatePublished - Jan 1 2018
Event32nd AAAI Conference on Artificial Intelligence, AAAI 2018 - New Orleans, United States
Duration: Feb 2 2018Feb 7 2018

Publication series

Name32nd AAAI Conference on Artificial Intelligence, AAAI 2018

Other

Other32nd AAAI Conference on Artificial Intelligence, AAAI 2018
CountryUnited States
CityNew Orleans
Period2/2/182/7/18

Fingerprint

Trajectories
Interpolation
Computational efficiency
Computational complexity
Experiments

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence

Cite this

Qiao, G., Yoon, S., Kapadia, M., & Pavlovic, V. (2018). The role of data-driven priors in multi-agent crowd trajectory estimation. In 32nd AAAI Conference on Artificial Intelligence, AAAI 2018 (pp. 4710-4717). (32nd AAAI Conference on Artificial Intelligence, AAAI 2018). AAAI press.
Qiao, Gang ; Yoon, Sejong ; Kapadia, Mubbasir ; Pavlovic, Vladimir. / The role of data-driven priors in multi-agent crowd trajectory estimation. 32nd AAAI Conference on Artificial Intelligence, AAAI 2018. AAAI press, 2018. pp. 4710-4717 (32nd AAAI Conference on Artificial Intelligence, AAAI 2018).
@inproceedings{a7eeafca4a3a4c30957b1a391805bce2,
title = "The role of data-driven priors in multi-agent crowd trajectory estimation",
abstract = "Trajectory interpolation, the process of filling-in the gaps and removing noise from observed agent trajectories, is an essential task for the motion inference in a multi-agent setting. A desired trajectory interpolation method should be robust to noise, changes in environments or agent densities, while also being able to yield realistic group movement behaviors. Such realistic behaviors are, however, challenging to model as they require avoidance of agent-agent or agent-environment collisions and, at the same time, demand computational efficiency. In this paper, we propose a novel framework composed of data-driven priors (local, global or combined) and an efficient optimization strategy for multi-agent trajectory interpolation. The data-driven priors implicitly encode the dependencies of movements of multiple agents and the collision-avoiding desiderata, enabling elimination of costly pairwise collision constraints, resulting in reduced computational complexity and often improved estimation. Various combinations of priors and optimization algorithms are evaluated in comprehensive simulated experiments. Our experimental results reveal important insights, including the significance of the global flow prior and the lesser-than-expected influence of data-driven collision priors.",
author = "Gang Qiao and Sejong Yoon and Mubbasir Kapadia and Vladimir Pavlovic",
year = "2018",
month = "1",
day = "1",
language = "English (US)",
series = "32nd AAAI Conference on Artificial Intelligence, AAAI 2018",
publisher = "AAAI press",
pages = "4710--4717",
booktitle = "32nd AAAI Conference on Artificial Intelligence, AAAI 2018",

}

Qiao, G, Yoon, S, Kapadia, M & Pavlovic, V 2018, The role of data-driven priors in multi-agent crowd trajectory estimation. in 32nd AAAI Conference on Artificial Intelligence, AAAI 2018. 32nd AAAI Conference on Artificial Intelligence, AAAI 2018, AAAI press, pp. 4710-4717, 32nd AAAI Conference on Artificial Intelligence, AAAI 2018, New Orleans, United States, 2/2/18.

The role of data-driven priors in multi-agent crowd trajectory estimation. / Qiao, Gang; Yoon, Sejong; Kapadia, Mubbasir; Pavlovic, Vladimir.

32nd AAAI Conference on Artificial Intelligence, AAAI 2018. AAAI press, 2018. p. 4710-4717 (32nd AAAI Conference on Artificial Intelligence, AAAI 2018).

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

TY - GEN

T1 - The role of data-driven priors in multi-agent crowd trajectory estimation

AU - Qiao, Gang

AU - Yoon, Sejong

AU - Kapadia, Mubbasir

AU - Pavlovic, Vladimir

PY - 2018/1/1

Y1 - 2018/1/1

N2 - Trajectory interpolation, the process of filling-in the gaps and removing noise from observed agent trajectories, is an essential task for the motion inference in a multi-agent setting. A desired trajectory interpolation method should be robust to noise, changes in environments or agent densities, while also being able to yield realistic group movement behaviors. Such realistic behaviors are, however, challenging to model as they require avoidance of agent-agent or agent-environment collisions and, at the same time, demand computational efficiency. In this paper, we propose a novel framework composed of data-driven priors (local, global or combined) and an efficient optimization strategy for multi-agent trajectory interpolation. The data-driven priors implicitly encode the dependencies of movements of multiple agents and the collision-avoiding desiderata, enabling elimination of costly pairwise collision constraints, resulting in reduced computational complexity and often improved estimation. Various combinations of priors and optimization algorithms are evaluated in comprehensive simulated experiments. Our experimental results reveal important insights, including the significance of the global flow prior and the lesser-than-expected influence of data-driven collision priors.

AB - Trajectory interpolation, the process of filling-in the gaps and removing noise from observed agent trajectories, is an essential task for the motion inference in a multi-agent setting. A desired trajectory interpolation method should be robust to noise, changes in environments or agent densities, while also being able to yield realistic group movement behaviors. Such realistic behaviors are, however, challenging to model as they require avoidance of agent-agent or agent-environment collisions and, at the same time, demand computational efficiency. In this paper, we propose a novel framework composed of data-driven priors (local, global or combined) and an efficient optimization strategy for multi-agent trajectory interpolation. The data-driven priors implicitly encode the dependencies of movements of multiple agents and the collision-avoiding desiderata, enabling elimination of costly pairwise collision constraints, resulting in reduced computational complexity and often improved estimation. Various combinations of priors and optimization algorithms are evaluated in comprehensive simulated experiments. Our experimental results reveal important insights, including the significance of the global flow prior and the lesser-than-expected influence of data-driven collision priors.

UR - http://www.scopus.com/inward/record.url?scp=85060456436&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85060456436&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:85060456436

T3 - 32nd AAAI Conference on Artificial Intelligence, AAAI 2018

SP - 4710

EP - 4717

BT - 32nd AAAI Conference on Artificial Intelligence, AAAI 2018

PB - AAAI press

ER -

Qiao G, Yoon S, Kapadia M, Pavlovic V. The role of data-driven priors in multi-agent crowd trajectory estimation. In 32nd AAAI Conference on Artificial Intelligence, AAAI 2018. AAAI press. 2018. p. 4710-4717. (32nd AAAI Conference on Artificial Intelligence, AAAI 2018).