Neural Interaction Energy for Multi-Agent Trajectory Prediction

TL;DR

This paper introduces MATE, a neural interaction energy framework that enhances multi-agent trajectory prediction by improving temporal stability and accuracy through novel interaction and motion constraints.

Contribution

The paper proposes a new neural interaction energy framework with stability constraints, advancing multi-agent trajectory prediction accuracy and robustness.

Findings

Outperforms previous methods on four datasets

Achieves higher prediction accuracy and stability

Demonstrates strong generalization capabilities

Abstract

Maintaining temporal stability is crucial in multi-agent trajectory prediction. Insufficient regularization to uphold this stability often results in fluctuations in kinematic states, leading to inconsistent predictions and the amplification of errors. In this study, we introduce a framework called Multi-Agent Trajectory prediction via neural interaction Energy (MATE). This framework assesses the interactive motion of agents by employing neural interaction energy, which captures the dynamics of interactions and illustrates their influence on the future trajectories of agents. To bolster temporal stability, we introduce two constraints: inter-agent interaction constraint and intra-agent motion constraint. These constraints work together to ensure temporal stability at both the system and agent levels, effectively mitigating prediction fluctuations inherent in multi-agent systems. Comparative evaluations against previous methods on four diverse datasets highlight the superior prediction accuracy and generalization capabilities of our model.