Experiments on whole-body manipulation and locomotion with footstep real-time optimization

This paper focuses on the experiments on the HRP-2 humanoid robot using a framework of manipulation and locomotion with real-time footstep adaptation. Two classes of experiments are presented. On the one hand, a grasping task at various height level illustrates a whole-body task in combination with locomotion. On the other, stepping over obstacle experiments illustrate the particularity of humanoid robots. In all presented examples, footsteps are considered as a part of the robot's kinematic chain and are resolved as an optimization problem along with other degrees of freedom of the robot. The environment is perceived by the stereo vision system mounted on the robot which closes the loop with the control through an online footstep adaptation scheme.