Figure 5.

Optimization results in the frontal targets (new targets). (a) Error map in ${\mathit{q}}_{\mathrm{target}}$ (cm). (b) Frontal targets. (c) Trajectories when L_h = 5 and L_s = 4. (d) Learning progress. Trajectories at the 0, 10, 20, 30, 40, 50, 100, 150, 200, 300, 400 and 500th generations are shown. (e) Trajectories when L_h = 5 and L_s = 0. (f) Trajectories when L_h = 0 and L_s = 8. (g) Trajectories by the horizontal policy. (h) Trajectories by the sagittal policy.