It Is Not the Journey but the Destination: Endpoint Conditioned Trajectory Prediction
It addresses trajectory forecasting for self-driving cars and social robots, representing a strong specific gain in a domain-specific area.
The paper tackles human trajectory prediction for autonomous navigation by introducing PECNet, which infers distant endpoints to improve long-range multi-modal forecasting, achieving state-of-the-art performance with ~20.9% improvement on the Stanford Drone benchmark and ~40.8% on the ETH/UCY benchmark.
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/