JACoP: Joint Alignment for Compliant Multi-Agent Prediction

2026-05-11

AI Summary

This work addresses the challenge in multi-agent trajectory prediction where individually optimized trajectories often lead to social collisions and environmental violations. To this end, the paper introduces JACoP, a novel framework that, for the first time, incorporates Markov Random Fields into multi-agent trajectory modeling. JACoP achieves scene-level compliant joint trajectory sampling through an anchor-driven agent-centric preliminary filtering stage followed by an energy-potential-based joint alignment mechanism. The proposed approach maintains high prediction accuracy while significantly reducing rates of social conflicts and environmental violations, thereby establishing a new standard for compliance in multi-agent trajectory prediction.

Abstract

Stochastic Human Trajectory Prediction (HTP) using generative modeling has emerged as a significant area of research. Although state-of-the-art models excel in optimizing the accuracy of individual agents, they often struggle to generate predictions that are collectively compliant, leading to output trajectories marred by social collisions and environmental violations, thus rendering them impractical for real-world applications. To bridge this gap, we present JACoP: Joint Alignment for Compliant Multi-Agent Prediction, an innovative multi-stage framework that ensures scene-level plausibility. JACoP incorporates an Anchor-Based Agent-Centric Profiler for effective initial compliance filtering and employs a Markov Random Field (MRF) based aligner to formalize the joint selection for scene predictions. By representing inter-agent spatial and social costs as MRF energy potentials, we successfully infer and sample from the joint trajectory distribution, achieving prediction with optimal scene compliance. Comprehensive experiments show that JACoP not only achieves competitive accuracy, but also sets a new standard in reducing both environmental violations and social collisions, thereby confirming its ability to produce collectively feasible and practically applicable trajectory predictions.

Problem

• Stochastic Human Trajectory Prediction
• Multi-Agent Prediction
• Social Collisions
• Environmental Violations
• Scene-level Plausibility

Innovation

• Joint Trajectory Prediction
• Markov Random Field
• Compliance Filtering
• Multi-Agent Systems
• Stochastic Human Trajectory Prediction