Dynamics Model Abstraction Scheme Using Radial Basis Functions
Figure 1
(a) Computing scheme. An FPGA processing platform embeds all the real-time control interfaces. The robot is connected to the FPGA which receives commands from the host PC. The robot is equipped with three accelerometers in its arm. The computer captures the sensor data. A RBF is used for learning the objects models from sensorimotor complexes. (b) Dense position-driven scheme. A motor moves from an initial position to a final position temporally targeting each intermediate point along this trajectory. (c) Sparse velocity-driven scheme. For each position indicated above, a target velocity is calculated for a motor with a time step of 0.015 s. Using a fixed sampling frequency for obtaining feedback position, we calculate the distance from this current position to a position corresponding to a change of direction. (d(A)) Dense position-driven trajectory. The trajectory is defined in terms of regularly sampled intermediate points (dashed line). (d(B)) The thinner continuous line represents the real curve executed by the robot's arm in the space under the sparse velocity-driven control. The black arrows indicate points in which changes of direction take place. The thicker continuous line corresponds to the smooth velocity-driven trajectory executed anticipating the points in which changes of direction are applied before the arm reaches them.
