Multimodal Interaction-Aware Trajectory Prediction in Crowded Space


  • Xiaodan Shi The University of Tokyo
  • Xiaowei Shao The University of Tokyo
  • Zipei Fan The University of Tokyo
  • Renhe Jiang The University of Tokyo
  • Haoran Zhang The University of Tokyo
  • Zhiling Guo The University of Tokyo
  • Guangming Wu The University of Tokyo
  • Wei Yuan The University of Tokyo
  • Ryosuke Shibasaki The University of Tokyo



Accurate human path forecasting in complex and crowded scenarios is critical for collision avoidance of autonomous driving and social robots navigation. It still remains as a challenging problem because of dynamic human interaction and intrinsic multimodality of human motion. Given the observation, there is a rich set of plausible ways for an agent to walk through the circumstance. To address those issues, we propose a spatio-temporal model that can aggregate the information from socially interacting agents and capture the multimodality of the motion patterns. We use mixture density functions to describe the human path and predict the distribution of future paths with explicit density. To integrate more factors to model interacting people, we further introduce a coordinate transformation to represent the relative motion between people. Extensive experiments over several trajectory prediction benchmarks demonstrate that our method is able to forecast various plausible futures in complex scenarios and achieves state-of-the-art performance.




How to Cite

Shi, X., Shao, X., Fan, Z., Jiang, R., Zhang, H., Guo, Z., Wu, G., Yuan, W., & Shibasaki, R. (2020). Multimodal Interaction-Aware Trajectory Prediction in Crowded Space. Proceedings of the AAAI Conference on Artificial Intelligence, 34(07), 11982-11989.



AAAI Technical Track: Vision