Trajectory Path Optimization and Cost Minimization in Motion Planning for Autonomous Mobility

Abstract: Due to the impact of a dynamic environment, the need for safety, smoothness, and real-time requirements, as well as the nonholonomic restrictions of vehicles, the study of path planning methods has always been a fundamental and challenging subject, especially in complex contexts. Nevertheless, due to the enhancements they represent for people's ways of life, safer and faster transit, better accessibility, comfort, convenience, efficiency, and environmental friendliness, autonomous vehicles are still popular and appealing. Motion planning needs to be carried out utilizing a variety of techniques to solve the issue of moving through complicated settings that contain numerous barriers. In our project, the ego vehicle must navigate a traffic light-controlled intersection safely, which is a difficult challenge. Using a 3D simulation environment we can successfully and safely provide a solution for the issue of using perception to identify traffic signal placements and statuses despite lighting conditions and occlusions. We simulate various traffic scenarios with various lighting conditions using simulation systems like CARLA and Automated Driving ToolboxTM.

Keywords: CARLA, Motion Planning, A*, Dijkstra's, Radar, Lidar.