Abstract
A learning feedforward controller (LFFC) using a dilated B-splines network (BSN) is proposed in this paper. The LFFC acts as an add-on element to the existing feedback controller (FBC) for control performance enhancement. The LFFC signal is updated iteratively based on the FBC signal of previous iteration as the task repeats. In the LFFC approach, there are two parameters to tune: the B-spline support width and the learning gain. A frequency domain design approach is presented with detailed design formulae for dilation 2. Simulation results are presented for the path following control of the USU ODIS robot (omnidirectional inspection systems), a new family member of the Utah State University (USU) ODVs (Omni Directional Vehicles).
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call