AC-VRNN: Attentive Conditional-VRNN for Multi-Future Trajectory Prediction

TL;DR

This paper introduces AC-VRNN, a novel generative model for multi-future human trajectory prediction that incorporates attention mechanisms and prior belief maps, outperforming existing methods in crowded scenarios.

Contribution

The paper presents a new Conditional Variational Recurrent Neural Network architecture with attention and belief map conditioning for improved multi-future trajectory prediction.

Findings

Outperforms state-of-the-art methods on multiple datasets

Effectively models multi-modal human trajectories in crowded scenes

Utilizes attention mechanisms for online hidden state refinement

Abstract

Anticipating human motion in crowded scenarios is essential for developing intelligent transportation systems, social-aware robots and advanced video surveillance applications. A key component of this task is represented by the inherently multi-modal nature of human paths which makes socially acceptable multiple futures when human interactions are involved. To this end, we propose a generative architecture for multi-future trajectory predictions based on Conditional Variational Recurrent Neural Networks (C-VRNNs). Conditioning mainly relies on prior belief maps, representing most likely moving directions and forcing the model to consider past observed dynamics in generating future positions. Human interactions are modeled with a graph-based attention mechanism enabling an online attentive hidden state refinement of the recurrent estimation. To corroborate our model, we perform extensive experiments on publicly-available datasets (e.g., ETH/UCY, Stanford Drone Dataset, STATS SportVU NBA, Intersection Drone Dataset and TrajNet++) and demonstrate its effectiveness in crowded scenes compared to several state-of-the-art methods.