Terrain Classification for the Spot Quadrupedal Mobile Robot Using Only Proprioceptive Sensing

2025-08-22

AI Summary

Quadruped robots frequently experience sinking and slipping on complex terrains, necessitating terrain classification driven solely by proprioceptive signals—without reliance on external perception—to enable traversability modeling and safe navigation. This paper proposes the first high-accuracy terrain classification method leveraging only proprioceptive inputs—including foot-ground contact forces, joint angles, foot sinkage, and over 100 additional dimensions. By applying dimensionality reduction to extract discriminative features and integrating machine learning, the method achieves 97% classification accuracy across three representative terrain types. Subsequently, a traversability map is constructed to inform path planning. Crucially, the approach operates without vision or LiDAR sensors, relying exclusively on onboard sensing. Its robustness and practicality are validated on the Boston Dynamics Spot platform. The method significantly enhances quadruped robots’ autonomous adaptation and decision-making capabilities in unknown, unstructured environments.

Technology Category

• Intelligent Robots: Localization, Mapping, and Navigation
• Natural Language Processing: Safety and Robustness
• Computer Vision: Low Level & Physics-based Vision

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods

Abstract

Quadrupedal mobile robots can traverse a wider range of terrain types than their wheeled counterparts but do not perform the same on all terrain types. These robots are prone to undesirable behaviours like sinking and slipping on challenging terrains. To combat this issue, we propose a terrain classifier that provides information on terrain type that can be used in robotic systems to create a traversability map to plan safer paths for the robot to navigate. The work presented here is a terrain classifier developed for a Boston Dynamics Spot robot. Spot provides over 100 measured proprioceptive signals describing the motions of the robot and its four legs (e.g., foot penetration, forces, joint angles, etc.). The developed terrain classifier combines dimensionality reduction techniques to extract relevant information from the signals and then applies a classification technique to differentiate terrain based on traversability. In representative field testing, the resulting terrain classifier was able to identify three different terrain types with an accuracy of approximately 97%

Problem

• Classifying terrain types for quadruped robots using proprioceptive sensing
• Preventing undesirable behaviors like sinking and slipping on challenging terrains
• Creating traversability maps for safer robot navigation path planning

Innovation

• Proprioceptive sensing for terrain classification
• Dimensionality reduction of robot motion signals
• Classification based on traversability differentiation