Learning walk and trot from the same objective using different types of exploration
This work addresses gait learning for quadruped robots, but it is incremental as it builds on existing policy search methods with a novel initialization approach.
The authors tackled the problem of learning quadruped gaits like walk and trot by encoding symmetry properties into the initial covariance of a Gaussian search distribution to enable strategic exploration, resulting in significantly enhanced performance compared to random gaits.
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.