SCAN: A Spatial Context Attentive Network for Joint Multi-Agent Intent Prediction
Date
2021-01-29
Authors
Sekhon, Jasmine
Major Professor
Advisor
Committee Member
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
Safe navigation of autonomous agents in human centric environments requires the ability to understand and predict motion of neighboring pedestrians. However, predicting pedestrian intent is a complex problem. Pedestrian motion is governed by complex social navigation norms, is dependent on neighbors' trajectories, and is multimodal in nature. In this work, we propose SCAN, a Spatial Context Attentive Network that can jointly predict socially-acceptable multiple future trajectories for all pedestrians in a scene. SCAN encodes the influence of spatially close neighbors using a novel spatial attention mechanism in a manner that relies on fewer assumptions, is parameter efficient, and is more interpretable compared to state-of-the-art spatial attention approaches. Through experiments on several datasets we demonstrate that our approach can also quantitatively outperform state of the art trajectory prediction methods in terms of accuracy of predicted intent.
Series Number
Journal Issue
Is Version Of
Versions
Series
Academic or Administrative Unit
Type
Preprint
Comments
This preprint is available as Sekhon, Jasmine, and Cody Fleming. "SCAN: A Spatial Context Attentive Network for Joint Multi-Agent Intent Prediction." arXiv preprint arXiv:2102.00109 (2021). doi: https://doi.org/10.48550/arXiv.2102.00109.
Published as Sekhon, J. ., & Fleming, C. (2021). SCAN: A Spatial Context Attentive Network for Joint Multi-Agent Intent Prediction. Proceedings of the AAAI Conference on Artificial Intelligence, 35(7), 6119-6127. https://doi.org/10.1609/aaai.v35i7.16762.