Research Analyzer
← Back ICRA 2026

SureGrip: Perceptual Grasping of Natural Handholds for Free-Climbing Robots

Peter Panorel, Khoon Chuan Goh, Kenji Nagaoka

PDF

AI summary

Key figure (auto-extracted from paper)
SureGrip enables free-climbing robots to reliably detect and mechanically validate natural handholds from depth data, proving that spine finger count and placement dictate grasp stability.
Free-climbing robots Perceptual grasping Handhold detection Spine gripper Surface feasibility Depth-based perception

Problem

Free-climbing robots struggle to identify and securely attach to natural handholds on irregular, unstructured terrains because existing grasp detection methods are designed for discrete objects rather than continuous surface contact feasibility.

Approach

SureGrip processes depth images to extract surface contours and evaluates candidate handholds using gripper-specific geometric and mechanical metrics, such as local slope thresholds and finger engagement ratios, to predict stable attachment.

Key results

  • Depth-based contour segmentation pipeline for detecting handholds on unstructured terrain
  • Gripper-aware feasibility metrics mapping surface geometry to load-bearing contact conditions
  • Experimental validation confirming reliable handhold detection and secure grasp classification across artificial and natural surfaces
  • Demonstration that both spine finger count and spatial distribution critically govern pulling force and stability

Why it matters

Provides a principled perception-to-contact framework that enhances climbing safety and efficiency for planetary and terrestrial exploration robots.

Abstract

Exploration of steep and irregular terrains, such as lunar caves and vertical rock faces, requires free-climbing robots capable of identifying and securely grasping natural handholds. This study introduced SureGrip, a novel framework for detecting handholds and evaluating grasp quality in free- climbing robots. By integrating depth-based contour extraction with gripper-specific contact analysis, SureGrip accurately iden- tifies candidate handholds and quantifies their suitability using the proposed grasp metrics. Experimental results confirm that the framework can reliably detect handhold locations, estimate surface slopes, and distinguish between secure and unsuitable grasps across a range of artificial and natural surfaces. The findings emphasize the importance of both the number and placement of spine fingers for stable attachment. SureGrip thus enables informed handhold selection, improving climbing safety and efficiency.

Index terms

Perception for Grasping and Manipulation Grasping Field Robots

Related papers