Automating the Parking Process: A Study on Motion Planning Techniques for Autonomous Vehicles

In the rapidly evolving landscape of autonomous vehicle technologies and urban planning, the development of precise motion planning algorithms for autonomous parking has emerged as a critical research endeavor. This paper undertakes a comprehensive exploration of this vital area, with a specific focus on low-speed parking maneuvers. It meticulously analyzes and implements three prominent motion planning algorithms—Hybrid A-star, Reeds and Shepp, and Rapidly-exploring random tree star (RRT)—in known environments. Through a systematic evaluation conducted via simulations, this research assesses the distinct strengths and limitations of each algorithm across a spectrum of parking scenarios. Hybrid A-star's capacity to navigate intricate situations replete with obstacles, the proficiency of Reeds and Shepp in obstacle-free environments, and the efficient parking possibility exploration by RRT are intricately examined. These insights not only highlight the unique merits of each algorithm but also shed light on their potential applications in self-parking systems. The integration of these advanced algorithms into autonomous parking systems promises to significantly enhance parking efficiency and alleviate urban congestion, thereby making substantial contributions to the field of urban parking management. This study, thus, offers valuable academic insights into the practical implementation of motion planning algorithms for autonomous parking, addressing pertinent challenges and opportunities in this context.