MoCap systems and hand movement reconstruction using cubic spline

摘要

The reproduction of hand movements by a robot remains difficult and conventional learning methods do not allow us to faithfully recreate these movements because it is very difficult (if not impossible) when the number of crossing points is very large. MoCap (Motion capture) systems and by using different technologies of movement tracking allows us to have a good tracking in terms of accuracy and number of captured frames in time(depending on the used techniques). The motion capture data have to be interpolated to guarantee a good trajectory reconstruction; we have used two types of interpolation: the cubic spline interpolation and the constrained cubic spline. The obtained results shows that the constrained cubic spline interpolation gives good reconstruction of the movement. The reconstructed movement have been simulated on a puma 560 robot using the robotics toolbox.