Chatting about Conditional Trajectory Prediction

2026-04-20

AI Summary

This work addresses the limitations of existing trajectory prediction methods, which often neglect the ego-vehicle’s motion state and struggle to effectively model dynamic social interactions, thereby hindering safe path planning. To overcome these challenges, we propose CiT (Cross-temporal Intention-aware Trajectory prediction), a novel conditional trajectory prediction framework that introduces, for the first time, a cross-temporal intention refinement mechanism. CiT jointly models the behavioral intentions of both the ego-vehicle and surrounding agents across different temporal horizons, enabling dynamic fusion of social interaction cues with the ego-vehicle’s potential actions. Tightly integrated into robotic motion planning modules, CiT generates multi-agent trajectory predictions conditioned on the ego-vehicle’s candidate maneuvers. Extensive experiments demonstrate that CiT significantly outperforms current state-of-the-art methods across multiple benchmarks, achieving leading performance in trajectory prediction.

Technology Category

• Humans and AI: Human-Aware Planning and Behavior Prediction
• Planning, Routing, and Scheduling: Temporal Planning
• Intelligent Robots: Motion and Path Planning

Application Category

• Social Networks and Social Media: Influence propagation, information diffusion, and the prediction on networks
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Human behavior has the nature of mutual dependencies, which requires human-robot interactive systems to predict surrounding agents trajectories by modeling complex social interactions, avoiding collisions and executing safe path planning. While there exist many trajectory prediction methods, most of them do not incorporate the own motion of the ego agent and only model interactions based on static information. We are inspired by the humans theory of mind during trajectory selection and propose a Cross time domain intention-interactive method for conditional Trajectory prediction(CiT). Our proposed CiT conducts joint analysis of behavior intentions over time, and achieves information complementarity and integration across different time domains. The intention in its own time domain can be corrected by the social interaction information from the other time domain to obtain a more precise intention representation. In addition, CiT is designed to closely integrate with robotic motion planning and control modules, capable of generating a set of optional trajectory prediction results for all surrounding agents based on potential motions of the ego agent. Extensive experiments demonstrate that the proposed CiT significantly outperforms the existing methods, achieving state-of-the-art performance in the benchmarks.

Problem

• trajectory prediction
• social interaction
• conditional prediction
• human-robot interaction
• motion planning

Innovation

• conditional trajectory prediction
• cross-time-domain interaction
• theory of mind
• social interaction modeling
• robot motion planning integration