Path Planning Method Considering Blind Spots Based on ROS Navigation Stack and Dynamic Window Approach for Wheeled Mobile Robot

Abstract

This paper proposes a path planning method considering blind spots based on ros navigation stack and dynamic window approach (DWA) for a wheeled mobile robot. The proposed method uses a laser range finder (LRF) and RGB-D cameras to recognize environmental information in real-time. Blind spots occur when there are corners or obstacles in environments. If a human or object moves towards a robot from blind spots, a collision may occur. In order to avoid this collision, this paper describes a local path planning method considering blind spots. Blind spots are estimated from environmental information measured by RGB-D cameras. In the proposed method, the path planning method considering blind spots is achieved by the cost map “Blind Spots Layer (BSL)” and DWA which is local path planning with improved the cost function. The effectiveness of the proposed method is further demonstrated through simulations.