Agent-Centric Social Trajectory Prediction: A Free Energy Principle Perspective

ArXi:2605.25748v1 Announce Type: new Trajectory prediction methods have nstrated remarkable capabilities in capturing complex motion patterns. However, existing methods rely on global state assumptions, suffer from insufficient belief inference under partial observability, and lack cognitive behavioral constraints in prediction. These limitations severely compromise both deployment feasibility and physical plausibility in real-world settings.