Human-inspired robot control - Examples in robotic batting

A human-inspired control system approach to acquiring the skills in dynamic manipulation of objects using robotic manipulators is established, where the desired space trajectories for the manipulators are not specified explicitly. A robotic batting is taken as a task example. The problem is solved and results in an iterative learning of the joint driving torque patterns of manipulator that are considered as the task skills. A multi-layered artificial neural network is used to learn and generalize the joint driving torque against various desired ball velocities, and an iterative optimal control algorithm is adopted to generate the supervisory joint driving torque signals for the neural network. An on-line identification mechanism of manipulator physical parameters is newly introduced to cope with the unknown physical parameter problem of manipulator. Computer simulation examples on a three-degree-of-freedom manipulator are outlined, and the results are depicted to explain the idea and verify the proposed approach.