Knowledge-Informed Multi-Agent Trajectory Prediction at Signalized Intersections for Infrastructure-to-Everything

2025-01-23

AI Summary

Accurately predicting multi-vehicle trajectories at signalized intersections remains challenging due to complex vehicle–infrastructure interactions and dynamic traffic signal dependencies. Method: This paper proposes an infrastructure-deployable multi-agent joint prediction framework. It introduces, for the first time, continuous signal-aware and driving-policy-aware mechanisms to explicitly model the joint intent–action distribution. The framework integrates a dynamic graph attention network, real-time adaptive traffic signal encoding, and intersection topology-guided joint modeling, and is supported by an I2X service architecture enabling low-latency, subscription-based trajectory prediction. Contribution/Results: Evaluated on V2X-Seq and SinD benchmarks, the method achieves over 30% improvement in average displacement error (ADE) and final displacement error (FDE) over state-of-the-art methods. It significantly enhances both single- and multi-agent prediction accuracy and—uniquely—enables scalable, subscription-driven, real-time trajectory prediction for all vehicles across entire intersections.

Technology Category

• Planning, Routing, and Scheduling: Model-Based Reasoning
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Multiagent Systems: Adversarial Agents

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Multi-agent trajectory prediction at signalized intersections is crucial for developing efficient intelligent transportation systems and safe autonomous driving systems. Due to the complexity of intersection scenarios and the limitations of single-vehicle perception, the performance of vehicle-centric prediction methods has reached a plateau. Furthermore, most works underutilize critical intersection information, including traffic signals, and behavior patterns induced by road structures. Therefore, we propose a multi-agent trajectory prediction framework at signalized intersections dedicated to Infrastructure-to-Everything (I2XTraj). Our framework leverages dynamic graph attention to integrate knowledge from traffic signals and driving behaviors. A continuous signal-informed mechanism is proposed to adaptively process real-time traffic signals from infrastructure devices. Additionally, leveraging the prior knowledge of the intersection topology, we propose a driving strategy awareness mechanism to model the joint distribution of goal intentions and maneuvers. To the best of our knowledge, I2XTraj represents the first multi-agent trajectory prediction framework explicitly designed for infrastructure deployment, supplying subscribable prediction services to all vehicles at intersections. I2XTraj demonstrates state-of-the-art performance on both the Vehicle-to-Infrastructure dataset V2X-Seq and the aerial-view dataset SinD for signalized intersections. Quantitative evaluations show that our approach outperforms existing methods by more than 30% in both multi-agent and single-agent scenarios.

Problem

• Traffic Prediction
• Smart Transportation
• Autonomous Driving

Innovation

• I2XTraj
• Intersection Signal Interaction
• Multi-Vehicle Path Prediction