Social-DPF: Socially Acceptable Distribution Prediction of Futures

Authors

  • Xiaodan Shi Center for Spatial Information Science, the University of Tokyo
  • Xiaowei Shao Center for Spatial Information Science, the University of Tokyo Earth Observation Data Integration and Fusion Research Initiative, the University of Tokyo
  • Guangming Wu Center for Spatial Information Science, the University of Tokyo
  • Haoran Zhang Center for Spatial Information Science, the University of Tokyo
  • Zhiling Guo Center for Spatial Information Science, the University of Tokyo
  • Renhe Jiang Information Technology Center, the University of Tokyo
  • Ryosuke Shibasaki Center for Spatial Information Science, the University of Tokyo

Keywords:

Motion & Tracking, Vision for Robotics & Autonomous Driving, Applications, Multi-modal Vision

Abstract

We consider long-term path forecasting problems in crowds, where future sequence trajectories are generated given a short observation. Recent methods for this problem have focused on modeling social interactions and predicting multi-modal futures. However, it is not easy for machines to successfully consider social interactions, such as avoiding collisions while considering the uncertainty of futures under a highly interactive and dynamic scenario. In this paper, we propose a model that incorporates multiple interacting motion sequences jointly and predicts multi-modal socially acceptable distributions of futures. Specifically, we introduce a new aggregation mechanism for social interactions, which selectively models long-term inter-related dynamics between movements in a shared environment through a message passing mechanism. Moreover, we propose a loss function that not only accesses how accurate the estimated distributions of the futures are but also considers collision avoidance. We further utilize mixture density functions to describe the trajectories and learn the multi-modality of future paths. Extensive experiments over several trajectory prediction benchmarks demonstrate that our method is able to forecast socially acceptable distributions in complex scenarios.

Downloads

Published

2021-05-18

How to Cite

Shi, X., Shao, X., Wu, G., Zhang, H., Guo, Z., Jiang, R., & Shibasaki, R. (2021). Social-DPF: Socially Acceptable Distribution Prediction of Futures. Proceedings of the AAAI Conference on Artificial Intelligence, 35(3), 2550-2557. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/16357

Issue

Section

AAAI Technical Track on Computer Vision II