Document Type : Research Article
Abstract
An autonomous or robotic car is commonly known as a self-driving car. This vehicle can sense its surroundings, navigate, and meet human transportation needs without any human intervention, which is a significant step forward in the advancement of future technologies. Self-driving cars use GPS, cameras, lidar, radar, and navigational paths to perceive their environment. The benefits of autonomous cars, such as increased reliability, fewer traffic collisions, increased roadway capacity, reduced traffic police, reduced traffic congestion, and care insurance, are compelling for the development of autonomous vehicles. However, issues such as software reliability, cybersecurity, liability for damage, and loss of driver-related jobs must be overcome. This study aimed to investigate local and global path planning for self-driving cars using two algorithms, namely A* and the potential field algorithm. The objective was to determine the effectiveness of each algorithm and explore how they could be combined to achieve optimal results. This article proposes a path-planning approach for a self-driving car in an environment with obstacles. The path planner is based on the strategy of using both global and local planners. The global planner is designed using the A* algorithm, which is used to generate an initial global path that provides an efficient way to guarantee the shortest path to the goal in an environment. The local planner is implemented using the potential field algorithm, which is used to adjust the path in real-time based on local obstacles and other dynamic factors. The intention of using a potential function is based on its safety, simplicity, and low computational cost. The proposed approach is evaluated in a simulated environment and shows promising results in providing an efficient way to guarantee the shortest path to the goal in an environment with obstacles. The combination of global and local planning techniques is expected to enhance the robustness and safety of autonomous vehicles in real-world scenarios.