The spring loaded inverted pendulum (SLIP) model has been extensively shown to be fundamental for legged locomotion. However, the way this low-order template model dynamics is anchored in high-dimensional articulated multibody systems describing compliantly actuated robots (and animals) is not obvious and has not been shown so far. In this paper, an articulated leg mechanism and a corresponding quadrupedal robot design are introduced, for which the natural oscillation dynamics is structurally equivalent to the SLIP. On the basis of this property, computationally simple and robust control methods are proposed, which implement the gaits of pronking, trotting, and dynamic walking in the real robotic system. Experiments with a compliantly actuated quadruped featuring only low performance electrical drives validate the effectiveness of the proposed approach.

Integrating robots in complex everyday environments requires a multitude of problems to be solved. One crucial feature among those is to equip robots with a mechanism for teaching them a new task in an easy and natural way. When teaching tasks that involve sequences of different skills, with varying order and number of these skills, it is desirable to only demonstrate full task executions instead of all individual skills. For this purpose, we propose a novel approach that simultaneously learns to segment trajectories into reoccurring patterns and the skills to reconstruct these patterns from unlabelled demonstrations without further supervision. Moreover, the approach learns a skill conditioning that can be used to understand possible sequences of skills, a practical mechanism to be used in, for example, human-robot-interactions for a more intelligent and adaptive robot behaviour. The Bayesian and variational inference based approach is evaluated on synthetic and real human demonstrations with varying complexities and dimensionality, showing the successful learning of segmentations and skill libraries from unlabelled data.

No abstract

In quadruped gait learning, policy search methods that scale high dimensional continuous action spaces are commonly used. In most approaches, it is necessary to introduce prior knowledge on the gaits to limit the highly non-convex search space of the policies. In this work, we propose a new approach to encode the symmetry properties of the desired gaits, on the initial covariance of the Gaussian search distribution, allowing for strategic exploration. Using episode-based likelihood ratio policy gradient and relative entropy policy search, we learned the gaits walk and trot on a simulated quadruped. Comparing these gaits to random gaits learned by initialized diagonal covariance matrix, we show that the performance can be significantly enhanced.

No abstract