Recognition and Grasping of Objects by Active Vision using Indoor Autonomous Mobile Robot
Seiji Aoyagi, Shota Ushiro, Masahito Fukuda, Tomokazu Takahashi, Masato Suzuki
Object recognition in actual indoor environment is difficult at present even if using Deep Learning method, in which illumination condition greatly changes, and many objects are randomly put; even they may be physically overlapped. In this research, an object recognition method for robot to grasp objects is proposed, which makes the best use of robot capability of actively moving. The method is concretely as follows: small light and web-camera are set on the tip of robot arm. The robot actively illuminates the object (Active Lighting), actively changes the viewpoint of web-camera (Active Vision), and pushes and/or slides the overlapped objects to separate them (Graspless Manipulation). The effectiveness of proposed method was experimentally verified in case of 50 complicated scenes using a home robot equipped with dual arms and vision sensors.