Clustered Lidar-Based Potential Field Path Planning

Mobile service robots operating in complex indoor environments require collision-free path planning to reach their goals. The artificial potential field (APF) path planning method is a commonly used technique that considers the robot as a point in the potential field and is easy to implement using lidar sensor data. Since the APF method has a significant disadvantage of local minima, many APF studies have focused on solving it. In this paper, however, we take a different approach to improve the performance of the APF. We propose a Clustered LiDAR-based Potential Field path planning method that introduces 2D lidar clustering to distinguish obstacles in partially observable environments. The proposed method is implemented in ROS and demonstrated using a simulated mobile manipulator in Gazebo.