Dynamics Model Abstraction Scheme Using Radial Basis Functions
Figure 4
Plots (a) and (c) show the motor commands (in joint coordinates) and plots (b), (d), and (e) show the sensor responses during the movement. We compare the dense position-driven versus the sparse velocity-driven strategies for the case related to object 0 (see the experimental results). In (b) (Sensor 1), it can be clearly seen how the sensor responses are directly related with the motor command changes in plot (a). The sensor responses, obtained using the sparse velocity-driven strategy, are more stable. Motor commands increasing the derivative of joint coordinates cause increments in sensor 1 response during a certain period, while motor commands decreasing the derivative of joint coordinates cause decrements in sensor 1 response, plot (b). The piece of trajectory monitored by these plots is mainly related to sensor 1. It can be seen in the right plots (d) and (e) that the other sensors are not so sensitive to the motions in this example. Nevertheless, sparse velocity-driven control still leads to much more stable sensor responses. Dense position-driven control causes large vibrations that highly affect the capability of the neural network to approach the sensor response function.
