Abstract— In this paper, we explore the capabilities of actuated models of the compass gait walker on rough terrain. We solve for the optimal high-level feedback policy to negoti...
— This paper presents an algorithm for adapting periodic behavior to gradual shifts in task parameters. Since learning optimal control in high dimensional domains is subject to t...
— Although there has been an increasing interest in dynamic bipedal locomotion for significant improvement of energy efficiency and dexterity of mobile robots in the real world...
Abstract. In this paper we study distributed online learning of locomotion gaits for modular robots. The learning is based on a stochastic approximation method, SPSA, which optimiz...