Vision-based Autonomous Detecting and Grasping Framework for the Fully-actuated Aerial Manipulator

The Aerial Manipulator (AM) combines the flexibility of aerial platforms with the manipulative capability of manipulators. Autonomous grasping of the AM poses challenges due to its complex kinematics/dynamics and target object pose acquisition. This paper introduces a fully-actuated AM which consists of a fully-actuated hexarotor and a 3-DoF manipulator. The fully-actuated aerial platform provides a more stable view for the camera during the AM motion. The feedback linearization controller is used in the aerial platform to ensure the stability of the AM during the motion of the manipulator. The YOLO v5 object detector combines the Oriented Bounding Box (OBB) to form a rotating object detector which can identify the target object and obtain its tilt angle. Combined with the depth camera, the position of the target object in three-dimensional (3D) space can be obtained. Within the working space, the manipulator performs autonomous planning and grasping according to the position and tilt angle of the target. Experimental demonstrates the performance of the proposed AM system.