Quantitative Comparison of Path Planning Algorithms in Simulated Environment

摘要

Path planning algorithms play a pivotal role in autonomous navigation systems across various domains, from robotics to self-driving vehicles. This research undertakes an extensive quantitative analysis, comparing various notable path planning algorithms in a simulated setting. The evaluated algorithms includes D*, A*, Dijkstra, and Rapidly Exploring Random Tree (RRT). We assess and contrast these algorithms using various metrics related to accuracy. The simulation environment in Matlab is designed to mimic real-world scenarios, incorporates obstacles. Performance metrics such as path length, travel time, and battery consumption in finding optimal paths are systematically measured and analyzed for each algorithm under identical condition. Through rigorous experimentation and statistical analysis, this research identifies the strengths and weaknesses of each algorithm in handling different environmental complexities. Results demonstrates that A* path planning method performs better than the other methods.