Dynamics Model Abstraction Scheme Using Radial Basis Functions

Figure 2

Diagram of the whole system architecture. The robot's picture in the left is showing the different joints of the 3 DOF Robonova arm involved in the movement. The PC applied appropriate motor commands to each joint of the arm at all times during the movement to follow the desired trajectory. To relieve the computer from interface computation and allow real-time communication with the robot, an FPGA board containing position acquisition modules and motor-driver controller circuits with PWM (pulse with modulation) was connected to the robot. The communication task between devices and the operations described above was synchronised by the computer speeding up the process. Finally, the batch learning with RBF of sensorimotor data collected during the movements was performed in the PC. The dataset was split up into training data (75%) and test data (25%).