Dynamic Weight A* Based Path Planning Optimization Algorithm for Indoor Service Robots

The increasing use of indoor service robots in fields such as engineering, healthcare, and home services has highlighted the need for efficient path planning algorithms to enhance navigation performance. Traditional path planning methods often struggle in complex dynamic environments, facing challenges from frequent changes and real-time requirements. This study introduces an improved path planning algorithm based on Dynamic Weighted A* (DWA*). By integrating Simultaneous Localization and Mapping (SLAM) technology and utilizing dynamic heuristic weight adjustments, incremental path replanning strategies, and a multi-sensor temporal synchronization framework, this algorithm significantly improves navigation efficiency in dynamic settings. Experimental results show that, in simulated office environments, the DWA* algorithm reduces path planning latency by 37% compared to the traditional A* method, increases the dynamic obstacle avoidance success rate to 95.3%, and keeps CPU peak usage below 20%. This research offers a novel solution for the efficient navigation of indoor service robots in complex dynamic scenarios. The algorithm exhibits strong robustness and real-time performance in practical applications, effectively addressing the challenges of rapidly changing environments and providing reliable technical support for real-world deploymen.