A Robotic Charging Scheme for Electric Vehicles Based on Monocular Vision and Force Perception

Abstract

Electric Vehicles are rapidly gaining popularity worldwide. The main two problems limiting their use are the short driving distance and inconvenient charging process. In this paper, we propose a technical scheme for opening the cover and inserting the plug into the charging port autonomously based on monocular vision guidance technology and force sensing technology. The whole system consists of a monocular camera, an UR5 robot with the plug mounted at the end and a charging port. The process firstly obtains the pixel coordinates of the target, and then calculates the spatial position of the target, thereby guiding the robot arm to complete the operation of opening the cover. Then the SVM algorithm is applied to analyze the force/torque data during the plug-in-hole process. The plug is inserted into the hole according to the data analysis result. Finally, the feasibility of the proposed scheme is demonstrated in a series of successful experiments.