Research on Path Planning Algorithm for Mobile Robots in Complex Scenarios

This study focuses on the key technological breakthroughs of autonomous navigation for mobile robots in complex scenarios. Aiming at the shortcomings of traditional path planning methods in dynamic environments, such as low computational efficiency, high path redundancy and insufficient obstacle avoidance response, A collaborative optimization framework integrating the improved A* algorithm and the enhanced Dynamic Window Method (DWA) is proposed. The core innovations include: 1) Constructing A* dynamic heuristic correction and bidirectional optimization mechanism in Algorithm A, through nonlinear weight compensation functions and path continuity constraints, combined with bidirectional search and neighborhood directional expansion strategies, significantly reducing path turning points (42% lower than traditional methods); 2) Improve the DWA evaluation function, establish a nonlinear coupling model of the obstacle potential field gradient and kinematic constraints, and achieve adaptive optimization of the multi-objective cost function; 3) By deeply integrating global path and local obstacle avoidance through dynamic waypoint guidance and trajectory smoothing processing, the collaborative optimization problem of low efficiency in global search and local optimal traps is broken through. Experiments show that this framework achieves a 35% reduction in planning time, a 29% optimization of path curvature, and a 22.4% increase in the success rate of dynamic obstacle negotiation in complex scenarios. It effectively synchronously optimizes computational efficiency, path continuity, and operational safety, providing a new paradigm for robust navigation of service robots in dynamic obstacle environments.