PhysiCycle: A Physically Consistent Multitask Learning Framework for Intention-Aware Cyclist Trajectory Prediction

doi:10.1109/TITS.2025.3632846

PhysiCycle: A Physically Consistent Multitask Learning Framework for Intention-Aware Cyclist Trajectory Prediction

2025-11-24

0

PRE

AI

DOI：10.1109/TITS.2025.3632846

Original

Original request for help

Save

Abstract

En 中文

Accurate prediction of cyclist trajectories is essential for safe and reliable autonomous driving and intelligent transportation systems (ITSs) in complex traffic scenarios. To address the challenges posed by cyclists’ diverse intentions and non-linear motion patterns, we propose PhysiCycle, a novel multi-task learning framework that jointly predicts future trajectories and turning intentions. This framework integrates interpretable physical modeling with deep learning to enhance both prediction accuracy and behavioral consistency. Our model integrates a dual-path encoder to extract temporal motion cues and behavioral features, an intention classifier module, and a physically consistent decoder with bicycle kinematics consistency constraints. Experimental results on a real-world cyclist action dataset demonstrate that our method significantly outperforms baseline models in both intention classification and trajectory accuracy, achieving strong physical plausibility and generalization performance.

Keywords:

Autonomous driving

physically consistent

multitask learning

intent classification

cyclist trajectory prediction

PhysiCycle: A Physically Consistent Multitask Learning Framework for Intention-Aware Cyclist Trajectory Prediction

Abstract

Journal

Organization