A Review of Parking Trajectory Planning and Modeling Techniques for Autonomous Vehicles

Xianjian Jin^1,2,*, Yinchen Tao¹, Yuhuai Zhang¹, Haoze Wu¹, Jianning Lu¹, Nonsly Valerienne Opinat Ikiela¹
1 School of Mechatronic Engineering and Automation, Shanghai University, Shanghai, China
2 Shanghai Key Laboratory of Intelligent Manufacturing and Robotics, Shanghai University, Shanghai, China
* Corresponding Author: Xianjian Jin. Email: email

Computer Modeling in Engineering & Sciences https://doi.org/10.32604/cmes.2026.082644

Received 19 March 2026; Accepted 26 August 2026; Published online 14 September 2026

Download PDF

Abstract

Autonomous parking is a key bottleneck to achieving fully autonomous driving, especially in the final parking problem of automated valet parking (AVP). Unlike traditional structured highway driving, parking scenarios impose stringent requirements on trajectory feasibility, and it requires the simultaneous resolution of nonholonomic motion constraints, narrow passage navigation, and collision avoidance in unstructured environments. This paper provides a comprehensive overview of parking trajectory planning and modeling techniques. Different aspects of parking trajectory planning strategies and modeling methodologies in recent literature are categorized into six major classes: graph-search-based methods, sampling-based methods, artificial potential field (APF)-based methods, numerical optimization-based methods, and geometry-based methods, artificial intelligence (deep learning and reinforcement learning)-based methods. The pros and cons of these methodologies are discussed. Finally, future research directions in this field are also provided.