SRefiner: Soft-Braid Attention for Multi-Agent Trajectory Refinement

2025-07-06

AI Summary

To address the limited prediction accuracy in multi-agent trajectory forecasting caused by neglecting topological relationships among trajectories, this paper proposes an iterative optimization framework based on a soft-braided topology. The core innovation lies in the first application of braid theory to trajectory modeling, introducing Soft-Braid Attention—a novel mechanism that explicitly captures spatiotemporal topological interactions at soft crossing points. This mechanism is further extended to jointly model lane–trajectory relationships. By integrating spatial proximity and motion states, it enables multi-round, multi-agent collaborative refinement. Evaluated on two benchmark datasets—Argoverse 2 and nuScenes—the method significantly outperforms four state-of-the-art baselines in trajectory refinement, achieving new state-of-the-art performance.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Multiagent Systems: Modeling other Agents
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Accurate prediction of multi-agent future trajectories is crucial for autonomous driving systems to make safe and efficient decisions. Trajectory refinement has emerged as a key strategy to enhance prediction accuracy. However, existing refinement methods often overlook the topological relationships between trajectories, which are vital for improving prediction precision. Inspired by braid theory, we propose a novel trajectory refinement approach, Soft-Braid Refiner (SRefiner), guided by the soft-braid topological structure of trajectories using Soft-Braid Attention. Soft-Braid Attention captures spatio-temporal topological relationships between trajectories by considering both spatial proximity and vehicle motion states at ``soft intersection points". Additionally, we extend this approach to model interactions between trajectories and lanes, further improving the prediction accuracy. SRefiner is a multi-iteration, multi-agent framework that iteratively refines trajectories, incorporating topological information to enhance interactions within traffic scenarios. SRefiner achieves significant performance improvements over four baseline methods across two datasets, establishing a new state-of-the-art in trajectory refinement. Code is here https://github.com/Liwen-Xiao/SRefiner.

Problem

• Enhances multi-agent trajectory prediction accuracy using topological relationships
• Models interactions between trajectories and lanes for better predictions
• Improves traffic scenario interactions via iterative refinement with topological information

Innovation

• Soft-Braid Attention captures spatio-temporal topological relationships
• Models interactions between trajectories and lanes
• Multi-iteration framework refines trajectories iteratively