Sensorimotor Coordination in a Humanoid Robot: Building Intelligence on the iCub - Bioinspired Approaches for Human-Centric Technologies - page 166

Fig. 6.7 Prediction error per degree of freedom for the (a) simulated Sarcos, (b) Sarcos, and (c)
Barrett datasets. The results for LWPR, GPR, and LGP are taken from Nguyen-Tuong
et al. ( 2008 ). The mean error over 25 runs is reported for RFRR with D ∈ 500, 1,000, 2,000,
whereas error bars mark a distance of one standard deviation. Note that in some cases the
prediction errors for KRR are very close to zero and therefore barely noticeable