Learning Perceptual Locomotion on Uneven Terrains using Sparse Visual Observations

TL;DR

This paper demonstrates that a robot can effectively navigate uneven terrains using only sparse visual data from sensors like Lidar or RGB-D, achieving robust locomotion over stairs and obstacles.

Contribution

It introduces a learning framework that integrates sparse visual observations with proprioception for effective perceptual locomotion across diverse terrains.

Findings

High success rate in traversing obstacles and stairs

Robust performance against noise and unseen terrains

Effective use of sparse visual data from common sensors

Abstract

To proactively navigate and traverse various terrains, active use of visual perception becomes indispensable. We aim to investigate the feasibility and performance of using sparse visual observations to achieve perceptual locomotion over a range of common terrains (steps, ramps, gaps, and stairs) in human-centered environments. We formulate a selection of sparse visual inputs suitable for locomotion over the terrains of interest, and propose a learning framework to integrate exteroceptive and proprioceptive states. We specifically design the state observations and a training curriculum to learn feedback control policies effectively over a range of different terrains. We extensively validate and benchmark the learned policy in various tasks: omnidirectional walking on flat ground, and forward locomotion over various obstacles, showing high success rate of traversability. Furthermore, we study exteroceptive ablations and evaluate policy generalization by adding various levels of noise and testing on new unseen terrains. We demonstrate the capabilities of autonomous perceptual locomotion that can be achieved by only using sparse visual observations from direct depth measurements, which are easily available from a Lidar or RGB-D sensor, showing robust ascent and descent over high stairs of 20 cm height, i.e., 50% leg length, and robustness against noise and unseen terrains.