Neural Interaction Energy for Multi-Agent Trajectory Prediction
This work addresses prediction consistency for multi-agent systems, offering incremental improvements in stability and accuracy.
The paper tackled the problem of temporal instability in multi-agent trajectory prediction by introducing the MATE framework, which uses neural interaction energy and constraints to reduce fluctuations, resulting in superior prediction accuracy and generalization on four datasets.
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.