Safe Active Navigation and Exploration for Planetary Environments Using Proprioceptive Measurements

2025-10-21

AI Summary

In unknown, unstructured granular terrains where visual perception fails, assessing traversability remains challenging. Method: This paper proposes a purely proprioceptive-driven active exploration framework that integrates force/pose sensing, Gaussian process regression modeling, and real-time reactive control to online estimate safe terrain regions and exploration frontiers—enabling vision-free traversability assessment and dynamic path planning. Contribution/Results: It introduces the first direct mapping of proprioceptive signals to a probabilistic traversability field and ensures navigation safety via a closed-loop feedback mechanism. Simulation results demonstrate that, using proprioception alone, the robot achieves stable goal-reaching on highly deformable soft terrain, with a 42% improvement in exploration success rate—significantly enhancing robustness and reliability of autonomous navigation in unknown, unstructured environments.

Technology Category

• Intelligent Robots: Localization, Mapping, and Navigation
• Planning, Routing, and Scheduling: Activity and Plan Recognition
• Natural Language Processing: Safety and Robustness

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web

Abstract

Legged robots can sense terrain through force interactions during locomotion, offering more reliable traversability estimates than remote sensing and serving as scouts for guiding wheeled rovers in challenging environments. However, even legged scouts face challenges when traversing highly deformable or unstable terrain. We present Safe Active Exploration for Granular Terrain (SAEGT), a navigation framework that enables legged robots to safely explore unknown granular environments using proprioceptive sensing, particularly where visual input fails to capture terrain deformability. SAEGT estimates the safe region and frontier region online from leg-terrain interactions using Gaussian Process regression for traversability assessment, with a reactive controller for real-time safe exploration and navigation. SAEGT demonstrated its ability to safely explore and navigate toward a specified goal using only proprioceptively estimated traversability in simulation.

Problem

• Safe navigation for legged robots on granular terrain
• Estimating traversability using proprioceptive sensing measurements
• Exploration in visually challenging deformable environments

Innovation

• Proprioceptive sensing estimates terrain traversability online
• Gaussian Process regression assesses safe and frontier regions
• Reactive controller enables real-time safe exploration navigation