Diverse Yet Consistent: Context-Guided Diffusion with Energy-Based Joint Refinement for Multi-Agent Motion Prediction

2026-05-21

AI Summary

This work addresses the challenge in multi-agent trajectory prediction of simultaneously capturing diverse individual motion patterns and consistent group interactions, a balance that existing approaches often fail to achieve due to the lack of effective evaluation of joint dynamics. The authors propose a novel diffusion-based framework that first leverages historical trajectory context to guide the generation of diverse individual motions and then refines the joint trajectory distribution through an energy-based optimization. This strategy enhances interaction consistency among agents while preserving the plausibility of individual trajectories. By integrating context-guided diffusion with energy-based joint refinement—a combination not previously explored—the method achieves state-of-the-art performance across four standard benchmarks, including ETH and UCY, significantly improving both marginal (ADE/FDE) and joint (JADE/JFDE) prediction metrics.

Abstract

Deepgenerative models havebecomeapromisingapproach for human motion prediction due to their ability to capture multimodal distributions and represent diverse human be haviors. However, generating predictions that are both di verse and jointly consistent among interacting agents re mains challenging. In addition, most existing approaches are primarily evaluated using single-agent (marginal) met rics, which fail to fully reflect the joint dynamics of multi agent interactions. We propose a diffusion-based frame work that improves multi-agent motion prediction by lever aging rich contextual information from historical trajecto ries. This information is incorporated through a guidance mechanism to enhance the diversity and expressiveness of predicted motions. To further enforce interaction consis tency, we introduce an energy-based formulation that re fines the joint trajectory distribution while preserving the plausibility of individual trajectories. Extensive experi ments on four benchmark datasets demonstrate that our approach consistently outperforms existing methods. No tably, our approach substantially improves both marginal (ADE/FDE) and joint (JADE/JFDE) metrics on ETH/UCY over strong marginal baselines. Compared with prior joint prediction methods, it delivers significant gains in marginal metrics while maintaining competitive joint performance.

Problem

• multi-agent motion prediction
• diversity
• joint consistency
• interaction dynamics
• trajectory prediction

Innovation

• diffusion model
• energy-based refinement
• multi-agent motion prediction
• context-guided generation
• joint trajectory consistency