A Study on Mobile Robot Path Planning in Constrained Environments Using an Enhanced RRT Algorithm

This research aims to solve the path planning problem for mobile robots in narrow environment roads by means of an improved Rapid Exploration Random Tree (RRT) algorithm. Narrow environment roads usually have restricted space, making traditional path planning methods challenging. This study combines the advantages of the RRT algorithm and introduces some improvements to accommodate this complex situation. First, we modify the extension strategy of RRT and introduce an intelligent local path search method to better explore feasible paths in narrow environments. This localized path search strategy helps the robot to overcome obstacles in narrow regions while maintaining path validity. Second, we employ a dynamic sampling strategy to increase the search efficiency of RRT. As the robot approaches the target region, the sampling density increases to converge to the optimal path faster. Finally, we verify the performance of the proposed algorithm through simulation and real robot experiments. The experimental results show that the improved RRT algorithm is able to plan paths more efficiently in narrow environment roads, enabling the mobile robot to successfully traverse complex passages and crowded spaces. This study provides an effective solution for mobile robot path planning in narrow environments, which can help robots better cope with challenges such as indoor navigation and rescue missions in practical applications.