An Improved Bi-Directional RRT* Based Path Planning Algorithm for Mine UAV Inspection

Unmanned Aerial Vehicle (UAV) inspection plays a crucial role in ensuring the safety and efficiency of coal mine operations. However, the unstructured nature of coal mine tunnels and the limitations of traditional path planning algorithms have hindered UAV inspection effectiveness. In this paper, we propose a path planning algorithm based on an improved bi-directional RRT ^* approach to address these challenges. Our algorithm focuses on optimizing path generation efficiency and obstacle avoidance. By enhancing the sample point generation strategy and incorporating an extended step function, the algorithm significantly reduces the number of generated sample points, leading to faster path planning. To ensure the UAV's safety during movement, we introduce corner constraints and an obstacle avoidance strategy, which minimize the steering angle and maintain a safe distance from obstacles. Moreover, the generated paths are further improved using B-spline curves to comply with UAV dynamics constraints, resulting in smoother planned trajectories. Through extensive simulations, we demonstrate that our improved bi-directional RRT ^* algorithm effectively avoids obstacles while achieving substantial gains in path generation efficiency.