Abstract: A humanoid robot leg that may include a shank, an ankle that includes an ankle joint that is configured to perform yaw and pitch rotations, a knee joint, multiple ankle related (AR) rotational motors that are in mechanical communication, via multiple AR transmission mechanisms, with the ankle joint, and a knee related (KR) rotational motor that is in mechanical communication, via a KR transmission mechanism, with the knee joint. The multiple AR rotational motors and the KR rotational motor are positioned above the knee joint.
Abstract: There is provided a method for learning a bipedal robot control policy, the method includes (i) learning, by a processing circuit, an action-related corrective policy that once applied reduces a gap associated with an initial simulation state transition function and with a real world state transition function; and (ii) determining a control policy of the bipedal robot in a simulator, using the action-related corrective policy.