Navigating by Touch: Haptic Monte Carlo Localization via Geometric Sensing and Terrain Classification

TL;DR

This paper introduces a proprioceptive localization method for legged robots that fuses terrain classification and geometric data using Monte Carlo estimation, enabling accurate navigation in extreme environments without relying on external sensors.

Contribution

The paper presents a novel proprioceptive localization algorithm combining terrain classification and geometric sensing via Monte Carlo methods for legged robots.

Findings

Localization error kept below 20cm over 1.2km traversal

Operates online and onboard a quadruped robot in diverse terrains

Uses only foot sensors, IMU, and joints for localization

Abstract

Legged robot navigation in extreme environments can hinder the use of cameras and laser scanners due to darkness, air obfuscation or sensor damage. In these conditions, proprioceptive sensing will continue to work reliably. In this paper, we propose a purely proprioceptive localization algorithm which fuses information from both geometry and terrain class, to localize a legged robot within a prior map. First, a terrain classifier computes the probability that a foot has stepped on a particular terrain class from sensed foot forces. Then, a Monte Carlo-based estimator fuses this terrain class probability with the geometric information of the foot contact points. Results are demonstrated showing this approach operating online and onboard a ANYmal B300 quadruped robot traversing a series of terrain courses with different geometries and terrain types over more than 1.2km. The method keeps the localization error below 20cm using only the information coming from the feet, IMU, and joints of the quadruped.