Robust Quadrupedal Locomotion on Sloped Terrains: A Linear Policy Approach

TL;DR

This paper presents a lightweight, linear policy-based approach for quadrupedal robot locomotion on sloped terrains, achieving robustness with minimal sensing and actuation, suitable for low-cost hardware deployment.

Contribution

The paper introduces a linear feedback policy for end-foot trajectory control in quadrupeds, trained with a model-free algorithm, enabling robust walking on slopes with minimal sensing.

Findings

Robust walking on sloped terrains demonstrated in simulation.

Method is computationally lightweight and suitable for low-cost hardware.

Minimal sensing and actuation are sufficient for effective locomotion.

Abstract

In this paper, with a view toward fast deployment of locomotion gaits in low-cost hardware, we use a linear policy for realizing end-foot trajectories in the quadruped robot, Stoch $2$. In particular, the parameters of the end-foot trajectories are shaped via a linear feedback policy that takes the torso orientation and the terrain slope as inputs. The corresponding desired joint angles are obtained via an inverse kinematics solver and tracked via a PID control law. Augmented Random Search, a model-free and a gradient-free learning algorithm is used to train this linear policy. Simulation results show that the resulting walking is robust to terrain slope variations and external pushes. This methodology is not only computationally light-weight but also uses minimal sensing and actuation capabilities in the robot, thereby justifying the approach.