English

It Is Not the Journey but the Destination: Endpoint Conditioned Trajectory Prediction

Computer Vision and Pattern Recognition 2020-07-21 v3 Machine Learning

Abstract

Human trajectory forecasting with multiple socially interacting agents is of critical importance for autonomous navigation in human environments, e.g., for self-driving cars and social robots. In this work, we present Predicted Endpoint Conditioned Network (PECNet) for flexible human trajectory prediction. PECNet infers distant trajectory endpoints to assist in long-range multi-modal trajectory prediction. A novel non-local social pooling layer enables PECNet to infer diverse yet socially compliant trajectories. Additionally, we present a simple "truncation-trick" for improving few-shot multi-modal trajectory prediction performance. We show that PECNet improves state-of-the-art performance on the Stanford Drone trajectory prediction benchmark by ~20.9% and on the ETH/UCY benchmark by ~40.8%. Project homepage: https://karttikeya.github.io/publication/htf/

Keywords

Cite

@article{arxiv.2004.02025,
  title  = {It Is Not the Journey but the Destination: Endpoint Conditioned Trajectory Prediction},
  author = {Karttikeya Mangalam and Harshayu Girase and Shreyas Agarwal and Kuan-Hui Lee and Ehsan Adeli and Jitendra Malik and Adrien Gaidon},
  journal= {arXiv preprint arXiv:2004.02025},
  year   = {2020}
}

Comments

Accepted at ECCV 2020 (Oral)