Modeling Conditional Dependencies in Multiagent Trajectories

Publikation: Beiträge in ZeitschriftenKonferenzaufsätze in FachzeitschriftenForschungbegutachtet

Authors

We study modeling joint densities over sets of random variables (next-step movements of multiple agents) which are conditioned on aligned observations (past trajectories). For this setting, we propose an autoregressive approach to model intra-timestep dependencies, where distributions over joint movements are represented by autoregressive factorizations. In our approach, factors are randomly ordered and estimated with a graph neural network to account for permutation equivariance, while a recurrent neural network encodes past trajectories. We further propose a conditional two-stream attention mechanism, to allow for efficient training of random factorizations. We experiment on trajectory data from professional soccer matches and find that we model low frequency trajectories better than variational approaches.
OriginalspracheEnglisch
ZeitschriftProceedings of Machine Learning Research
Jahrgang151
Seiten (von - bis)10518-10533
Anzahl der Seiten16
ISSN2640-3498
PublikationsstatusErschienen - 2022
VeranstaltungThe 25th International Conference on Artificial Intelligence and Statistics - AISTATS 2022 - Virtual Conference, Online
Dauer: 28.03.202230.03.2022
Konferenznummer: 25
http://aistats.org/aistats2022/

Bibliographische Notiz

Publisher Copyright:
Copyright © 2022 by the author(s)

Zugehörige Aktivitäten