Abstract
In complex and constrained environments, robot path planning faces the dual challenges of efficiency and solution quality. This letter presents a Light Reflection Heuristic RRT$^{*}$ algorithm (LRH-RRT$^{*}$), which generates the reference path by simulating light reflections along obstacle boundaries and adaptively adjusts the sampling distribution. A dynamic path pruning strategy is introduced to eliminate redundant nodes, and third-order Bézier curve interpolation is applied to smooth the path while satisfying the dynamic constraints of mobile robots. Experimental results demonstrate that LRH-RRT$^{*}$ improves planning efficiency and path quality in various narrow passage scenarios.