Deep Learning on 3D Object Detection for Automatic Plug-in Charging Using a Mobile Manipulator

Increasing research attention has been attracted to automatic plug-in changing in an unmanned and dangerous environment. In this work, we develop an object detection solution based on deep learning on 3D point clouds using a mobile robot manipulator to provide mobility and manipulation. In this solution, the 3D point cloud technology is adopted to measure the shapes and depth information for plug-in charging. Then the deep learning is employed to deal with the uncertainty in 3D detection, such as inconsistent light conditions, irregular distribution, and structural ambiguity of point clouds. We utilize a mobile robot manipulator carrying a 3D camera and a gripper to detect the targeted objects and automate plug-in charging operations. The proposed 3D object detection principle and procedure for the automatic plug-in charging are presented in detail. The automatic plug-in charging testing is conducted to validate the developed 3D object detection algorithm using a mobile robot manipulator.

Automated summary

Research focus has shifted towards automatic plug-in changing in unmanned and dangerous environments, utilizing deep learning on 3D point clouds for object detection. A mobile robot manipulator is used to provide mobility and manipulation for automated plug-in charging operations. Conducted testing validates the 3D object detection algorithm developed for automatic plug-in charging.