Learning Linear Policies for Robust Bipedal Locomotion on Terrains with Varying Slopes

Abstract-- In this paper, with a view toward deployment of light-weight control frameworks for bipedal walking robots, we realize end-foot trajectories that are shaped by a single linear feedback policy. We learn this policy via a model-free and a gradient free learning algorithm, Augmented Random Search (ARS), in the two robot platforms Rabbit and Digit. Towards the end, we also provide preliminary results of hardware transfer to Digit. Locomotion for legged robots has been an active field of research for the past decade owing to the rapid progress in actuator and sensing modules. Actuators like the BLDC Figure 1: Figure showing Rabbit (Top) and Digit (Bottom) in motors have become efficient and powerful, and sensors Simulation: Traversing incline and decline with robustness like the IMUs have become more accurate and affordable.