Development and simulation of an autonomous parking system using a low-cost lidar sensor and ultrasonic sensors

Abstract

The automotive industry is constantly transforming, driven by the increasing demand for modern cars with exclusive features. A major challenge for drivers is the difficulty of parking, and the industry seeks solutions through parking assistance. In this context, this work proposes the development of an autonomous parking system, using a lowcost one-dimensional LiDAR sensor for the detection, measurement and classification of the parking space. For this purpose, a detailed bibliographic research was carried out, analyzing the possible paths and possibilities for the implementation of the system, with special focus on the detection of the parking space. After analysis, the RRT* motion planning algorithm was selected for performing simulations in MATLAB software, due to the ease of implementation and the fast-processing speed of the algorithm. In addition, a small-scale prototype of the autonomous parking system was developed and tested. Achieving good results in identifying, measuring and classifying parallel and perpendicular parking spaces. In future work, the aim is to implement the motion planning algorithm in the small-scale prototype, as well as to implement the complete system in a real-scale test vehicle to evaluate the performance and effectiveness of the system under real conditions.