Learning a Contact-Adaptive Controller for Robust, Efficient Legged Locomotion
This addresses the challenge of adaptive and efficient movement for quadruped robots in dynamic environments, representing a strong specific gain rather than a broad paradigm shift.
The paper tackled the problem of robust and efficient legged locomotion by developing a hierarchical framework combining model-based control and reinforcement learning, resulting in a controller that is up to 85% more energy efficient and more robust than baselines.
We present a hierarchical framework that combines model-based control and reinforcement learning (RL) to synthesize robust controllers for a quadruped (the Unitree Laikago). The system consists of a high-level controller that learns to choose from a set of primitives in response to changes in the environment and a low-level controller that utilizes an established control method to robustly execute the primitives. Our framework learns a controller that can adapt to challenging environmental changes on the fly, including novel scenarios not seen during training. The learned controller is up to 85~percent more energy efficient and is more robust compared to baseline methods. We also deploy the controller on a physical robot without any randomization or adaptation scheme.