Learning-based Approach for Estimation of Axis of Rotation for Markerless Visual Servoing to Tumbling Object

The increased satellite launches have made the capture of debris and On-Orbit servicing of the orbiting satellites essential. In space, objects exhibit a tumbling motion around their major inertial axis. In this paper, we propose a featureless approach for a robotic system to visual servo control in case of an uncooperative tumbling object. In contrast to the previously studied approaches that require a 3D CAD model of the object or its reconstruction, we propose a novel solution that also forgoes the need for special markers. For this purpose, we leverage a deep convolutional neural network technique to automatically estimate the axis of rotation vector of a tumbling object from its video and motion characteristics. Position-Based Visual Servoing algorithm can then use the extracted data for control. The effectiveness of the proposed framework is exhibited by implementing simulation in V-Rep on the Reachy Robotic arm.