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

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/ read more

PDF Abstract ECCV 2020 PDF ECCV 2020 Abstract

Datasets


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Trajectory Prediction ETH/UCY PECNet ADE-8/12 0.29 # 5
FDE-8/12 0.48 # 5
Multi Future Trajectory Prediction ETH/UCY PECNet FDE-8/12 0.48 # 1
Multi-future Trajectory Prediction ETH/UCY PECNet ADE-8/12 0.29 # 1
Trajectory Prediction Stanford Drone PECNet ADE-8/12 @K = 20 9.96 # 3
FDE-8/12 @K= 20 15.88 # 2
Multi-future Trajectory Prediction Stanford Drone PECNet ADE-8/12 16.16 # 1

Methods


No methods listed for this paper. Add relevant methods here