Huang, Zhaoyan (Tongji University), Zhang, Chao (Tongji University), Zhang, Rui (SAIC Z-ONE Technology Co., Ltd.,), Ji, Yiding (Hong Kong University of Science and Technology (Guangzhou)), Hong, Jinlong (Tongji University), Gao, Bingzhao (Tongji University), Liu, Qingwei (SAIC Z-ONE Technology Co., Ltd.)

A Differentiable Constraint-Aware Motion Planning Module for Unsupervised Trajectory Optimization

Scheduled for presentation during the Regular Session "S26a-Motion Planning, Trajectory Optimization, and Control for Autonomous Vehicles" (TH-LM-T26), Thursday, November 20, 2025, 12:10−12:30, Broadbeach 1&2

2025 IEEE 28th International Conference on Intelligent Transportation Systems (ITSC), November 18-21, 2025, Gold Coast, Australia

This information is tentative and subject to change. Compiled on October 18, 2025

Abstract

Autonomous driving requires planning trajectories that are not only goal-oriented but also compliant with safety and feasibility constraints such as lane boundaries, inter-agent distances, and motion smoothness. However, in dynamic and uncertain environments, obtaining ground-truth trajectories for supervised learning can be costly or impractical. In this paper, we propose a constraint-aware, supervision-free trajectory planning framework that could learn safe and executable behaviors directly from violation-prone data. Our approach outputs control actions that are rolled out using a kinematic model to generate trajectories, which are then optimized via a differentiable loss incorporating learnable Lagrangian penalties. In particular, we develop a lane boundary constraint based on signed lateral deviations and enforce it through a smooth penalty formulation. Experiments on the nuScenes Open Motion Dataset demonstrate that our method ensures strict compliance with road boundaries while staying close to reference goals, and it can be seamlessly integrated as a plug-in module with End-to-End pipelines.