Navigating Obstacles with Monocular Image Inputs: A Comparative Analysis of Path Planning Algorithms

Effective path planning in obstacle-filled environments is essential for the deployment of autonomous mobile robots. This paper provides an extensive comparative analysis of different path planning algorithms that utilize monocular image inputs for navigating obstacles. We evaluate the performance of popular graph based algorithms such as BFS, DFS, Dijkstra, A*. examining their efficiency and effectiveness in complex and dynamic settings. Using a standardized dataset, we rigorously test each algorithm’s ability to interpret monocular image data, determine viable paths, and avoid obstacles. Key metrics such as computational efficiency, accuracy of obstacle avoidance, and resilience to environmental variations are analyzed to identify the strengths and limitations of each method. Our findings underscore the trade-offs between traditional algorithms and deep learning approaches, providing valuable insights for selecting the most suitable path planning techniques for applications in robotics and autonomous vehicles. This study aims to bridge the gap between theoretical research and practical application, enhancing the development of more adaptive and dependable autonomous navigation systems. 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.