Modeling Conditional Dependencies in Multiagent Trajectories

Research output: Journal contributionsConference article in journalResearchpeer-review

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.
Original languageEnglish
JournalProceedings of Machine Learning Research
Volume151
Pages (from-to)10518-10533
Number of pages16
ISSN2640-3498
Publication statusPublished - 2022
EventThe 25th International Conference on Artificial Intelligence and Statistics - AISTATS 2022 - Virtual Conference, Online
Duration: 28.03.202230.03.2022
Conference number: 25
http://aistats.org/aistats2022/

Bibliographical note

Funding Information:
We would like to thank Marius Lehne at SAP SE for his essential support and help while writing this paper as well as all reviewers for their valuable feedback.

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

Recently viewed

Publications

  1. Partitioned beta diversity patterns of plants across sharp and distinct boundaries of quartz habitat islands
  2. From entity to process
  3. Control versus Complexity
  4. Challenges and boundaries in implementing social return on investment
  5. Machine Learning and Knowledge Discovery in Databases
  6. Should learners use their hands for learning? Results from an eye-tracking study
  7. Is sensitivity for the complexity of mathematics teaching measurable?
  8. Introduction Mobile Digital Practices. Situating People, Things, and Data
  9. Visualization of the Plasma Frequency by means of a Particle Simulation using a Normalized Periodic Model
  10. Computational modeling of amorphous polymers
  11. Early Detection of Faillure in Conveyor Chain Systems by Wireless Sensor Node
  12. Formative Perspectives on the Relation Between CSR Communication and CSR Practices
  13. TARGET SETTING FOR OPERATIONAL PERFORMANCE IMPROVEMENTS - STUDY CASE -
  14. From Knowledge to Application
  15. Neural correlates of the enactment effect in the brain
  16. Machine Learning and Knowledge Discovery in Databases
  17. Competing Vegetation Structure Indices for Estimating Spatial Constrains in Carabid Abundance Patterns in Chinese Grasslands Reveal Complex Scale and Habitat Patterns
  18. Spaces for challenging experiences, indeterminacy, and experimentation
  19. Mapping Khulan habitats - a GIS based approach.
  20. Commitment to grand challenges in fluid forms of organizing
  21. Soft Optimal Computing Methods to Identify Surface Roughness in Manufacturing Using a Monotonic Regressor
  22. A Review of the Application of Machine Learning and Data Mining Approaches in Continuum Materials Mechanics
  23. Determination of 10 particle-associated multiclass polar and semi-polar pesticides from small streams using accelerated solvent extraction
  24. Training effects of two different unstable shoe constructions on postural control in static and dynamic testing situations
  25. Intraspecific trait variation patterns along a precipitation gradient in Mongolian rangelands
  26. Artificial Intelligence in Foreign Language Learning and Teaching
  27. Unraveling Privacy Concerns in Complex Data Ecosystems with Architectural Thinking
  28. A survey of empirical studies using transaction level data on exports and imports