This work presents a wheeled humanoid robot for preliminary research into humanoid robots that play ping-pong. This humanoid robot comprises mainly a wheeled mobile base, a torso with a 3-DOF waist mounted on a mobile base, two 7-DOF robot arms, two 7-DOF robot hands and one 7-DOF robotic binocular head. An embedded DSP-based control system is also designed and constructed for real-time control. An intelligent hand-eye coordination control structure is then developed for this humanoid robot. The proposed design framework for robotic hand-eye coordination control that tracks the ball is based on the proposed control structure and involves application of self-organizing invertible map (SOIM), grey theory, and Kohonen neural network. The SOIM neural network acquires a calibration-free spatial representation of 3D targets. The Kohonen neural network is applied to learn the mapping from incremental changes in the spatial representation to incremental changes in the joint configurations of a robot arm.
|出版狀態||Published - 2008 十二月 1|
|事件||39th International Symposium on Robotics, ISR 2008 - Seoul, Korea, Republic of|
持續時間: 2008 十月 15 → 2008 十月 17
|Other||39th International Symposium on Robotics, ISR 2008|
|國家/地區||Korea, Republic of|
|期間||08-10-15 → 08-10-17|
All Science Journal Classification (ASJC) codes