Versatile Locomotion Skills for Hexapod Robots

TL;DR

This paper presents a versatile hexapod robot capable of performing stairs climbing, obstacle avoidance, and squeezing under objects, trained entirely in simulation and successfully transferred to real-world tasks using a two-phase learning approach.

Contribution

The authors introduce a novel training method combining reinforcement and supervised learning to develop robust locomotion skills for hexapod robots using only onboard observations.

Findings

High success rates in real-world tasks

Effective sim-to-real transfer achieved

Robust performance in cluttered environments

Abstract

Hexapod robots are potentially suitable for carrying out tasks in cluttered environments since they are stable, compact, and light weight. They also have multi-joint legs and variable height bodies that make them good candidates for tasks such as stairs climbing and squeezing under objects in a typical home environment or an attic. Expanding on our previous work on joist climbing in attics, we train a legged hexapod equipped with a depth camera and visual inertial odometry (VIO) to perform three tasks: climbing stairs, avoiding obstacles, and squeezing under obstacles such as a table. Our policies are trained with simulation data only and can be deployed on lowcost hardware not requiring real-time joint state feedback. We train our model in a teacher-student model with 2 phases: In phase 1, we use reinforcement learning with access to privileged information such as height maps and joint feedback. In phase 2, we use supervised learning to distill the model into one with access to only onboard observations, consisting of egocentric depth images and robot pose captured by a tracking VIO camera. By manipulating available privileged information, constructing simulation terrains, and refining reward functions during phase 1 training, we are able to train the robots with skills that are robust in non-ideal physical environments. We demonstrate successful sim-to-real transfer and achieve high success rates across all three tasks in physical experiments.