Dynamic Weighted A* Path Planning for Autonomous Vehicles in Evolving Environments

Abstract

This research addresses the critical challenge of path planning for autonomous vehicles in dynamic environments, where obstacles may unpredictably change positions or emerge. The purpose of this study is to introduce and evaluate the effectiveness of the dynamic weighted A* algorithm, a novel approach that integrates dynamic obstacle awareness, steering dynamics and trajectory optimization for adaptive and real-time path planning. The algorithm's performance is rigorously assessed through comprehensive simulations, encompassing various grid resolutions and obstacle configurations. Results demonstrate the algorithm's capability to dynamically adapt to changing scenarios, providing a promising solution for autonomous vehicles navigating unpredictable environments. The study contributes valuable insights into the field of autonomous vehicle path planning, offering an algorithmic approach that balances efficiency, adaptability and real-time responsiveness. The outcomes of this research not only highlight the practicality and efficacy of the dynamic weighted A* algorithm but also contribute to advancing the discourse on path planning algorithms for autonomous vehicles in dynamic settings. These findings have implications for the development and implementation of robust navigation systems, ensuring the safe and efficient operation of autonomous vehicles in real-world scenarios.