Figure 5.

Dynamic biped walker model. (A) For the walker model, only the hip angles q₁, q₂ and the knee angles q₃, q₄ are actuated. The reference angle to the flat ground is denoted by q₅. In this multi-task learning experiment we want to learn walking patterns for different step heights. Examples for step heights of 0.15, 0.25, and 0.3 m for a single step are shown in (B–D). These patterns were learned using the proposed movement primitives with shared synergies (M = 2 and N = 3). The green bars in (B–D) denote the true (maximum) step heights, which are 0.19, 0.24, and 0.31 m.