A Unified Framework for Trajectory Prediction with Explicit Planning and Reaction Decomposition

2026-08-06

AI Summary

This work addresses the limitation of existing trajectory prediction methods that overlook the phased role of social interaction in motion planning, leading to insufficient long-term consistency and stability. The authors propose INTraJ, a unified framework that explicitly models social interaction through a two-stage mechanism: first generating a global reference trajectory based on future social context (planning stage), followed by context-aware residual learning for local refinement (reactive stage). This approach reformulates trajectory prediction as a planning-driven, structured process and supports both single- and multi-agent forecasting. Evaluated on four benchmarks—including Argoverse 2 and ETH/UCY—the method achieves state-of-the-art performance, demonstrating significant improvements over existing approaches, particularly in final displacement error (FDE) and long-horizon consistency metrics.

Abstract

Trajectory prediction has shifted toward structured formulations with explicit social modeling. However, existing methods inadequately distinguish the functional roles of social influence in trajectory planning. Observing that agents typically form motion plans by anticipating others' future behaviors before making local reactive adjustments, we identify social interactions as playing staged roles, namely planning precedes reaction. We propose INTraJ, a unified framework that decomposes social influence into two stages: a planning stage constructs reference trajectories using future social information, and a reaction stage recovers local adjustments from the residual between full-context prediction and the reference. INTraJ supports both multi-target and single-target paradigms. Extensive experiments on four standard benchmarks, including Argoverse 2, Argoverse 2-ped, ETH/UCY, and SDD, demonstrate consistent improvements, particularly in FDE and long-horizon consistency, with state-of-the-art performance achieved in several settings. INTraJ reframes trajectory prediction as a planning-driven two-stage process, validating that staged social modeling is critical for stable predictions. The code is publicly available at https://github.com/11isnotavailable/INTraJ.

Problem

• trajectory prediction
• social interaction
• planning
• reaction
• structured modeling

Innovation

• trajectory prediction
• social interaction modeling
• planning-reaction decomposition
• two-stage framework
• reference trajectory