Robust Quadrupedal Locomotion on Sloped Terrains: A Linear Policy Approach

2020/10/30 by Kartik Paigwar, Lokesh Krishna, Paigwar, Kartik +17
Computer Science · Engineering · #Prosthetics and Rehabilitation Robotics #Robotic Locomotion and Control #Robotic Mechanisms and Dynamics #cs.AI #cs.LG #cs.RO #cs.SY #eess.SY

paper · pdf · doi:10.48550/arxiv.2010.16342

Accepted in 4th Conference on Robot Learning 2020, MIT, USA

arxiv created 2020/11/10 · arxiv updated 2020/11/11

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.

Related

• Learning Linear Policies for Robust Bipedal Locomotion on Terrains with Varying Slopes
• Gait Library Synthesis for Quadruped Robots via Augmented Random Search
• Vision-aided Dynamic Quadrupedal Locomotion on Discrete Terrain using Motion Libraries
• Quadruped Locomotion on Non-Rigid Terrain using Reinforcement Learning
• Terrain-Aware Quadrupedal Locomotion via Reinforcement Learning