SILM: A Subjective Intent Based Low-Latency Framework for Multiple Traffic Participants Joint Trajectory Prediction

2025-04-23

AI Summary

Existing trajectory prediction methods neglect the subjective intentions of traffic participants, resulting in high uncertainty, poor generalization across heterogeneous scenarios, and insufficient real-time performance. To address these limitations, we propose a map-free, low-latency joint trajectory prediction framework that explicitly models subjective intention for the first time. Our approach introduces a keypoint-based intention representation mechanism, a lightweight spatiotemporal encoder, and an intention-driven graph neural network, enabling end-to-end joint optimization. We further design a map-free joint prediction architecture and release the first intent-aware trajectory prediction benchmark dataset. Experiments demonstrate that our method reduces inference latency by 38% on average compared to state-of-the-art approaches, while maintaining high accuracy and strong generalization across diverse heterogeneous traffic scenarios. The framework is computationally efficient and deployment-friendly.

Technology Category

• Humans and AI: Human-Aware Planning and Behavior Prediction
• Planning, Routing, and Scheduling: Model-Based Reasoning
• Computer Vision: Motion & Tracking

Application Category

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

Abstract

Trajectory prediction is a fundamental technology for advanced autonomous driving systems and represents one of the most challenging problems in the field of cognitive intelligence. Accurately predicting the future trajectories of each traffic participant is a prerequisite for building high safety and high reliability decision-making, planning, and control capabilities in autonomous driving. However, existing methods often focus solely on the motion of other traffic participants without considering the underlying intent behind that motion, which increases the uncertainty in trajectory prediction. Autonomous vehicles operate in real-time environments, meaning that trajectory prediction algorithms must be able to process data and generate predictions in real-time. While many existing methods achieve high accuracy, they often struggle to effectively handle heterogeneous traffic scenarios. In this paper, we propose a Subjective Intent-based Low-latency framework for Multiple traffic participants joint trajectory prediction. Our method explicitly incorporates the subjective intent of traffic participants based on their key points, and predicts the future trajectories jointly without map, which ensures promising performance while significantly reducing the prediction latency. Additionally, we introduce a novel dataset designed specifically for trajectory prediction. Related code and dataset will be available soon.

Problem

• Predicting trajectories without considering intent increases uncertainty
• Existing methods struggle with real-time heterogeneous traffic scenarios
• Low-latency joint prediction without map while ensuring accuracy

Innovation

• Subjective intent-based trajectory prediction framework
• Low-latency joint prediction without map dependency
• Novel dataset for heterogeneous traffic scenarios