Active Cross-Modal Visuo-Tactile Perception of Deformable Linear Objects

TL;DR

This paper introduces a cross-modal visuo-tactile perception framework that combines visual foundation models and tactile exploration to accurately reconstruct 3D shapes of deformable linear objects, especially under severe occlusions.

Contribution

It integrates foundation-model-based visual perception with tactile sensing for robust 3D shape reconstruction of deformable objects, addressing occlusion challenges in robotic manipulation.

Findings

Accurately reconstructs complex cable shapes with occlusions

Combines visual and tactile data for improved shape estimation

Demonstrates effectiveness on robotic platform with real experiments

Abstract

This paper presents a novel cross-modal visuo-tactile perception framework for the 3D shape reconstruction of deformable linear objects (DLOs), with a specific focus on cables subject to severe visual occlusions. Unlike existing methods relying predominantly on vision, whose performance degrades under varying illumination, background clutter, or partial visibility, the proposed approach integrates foundation-model-based visual perception with adaptive tactile exploration. The visual pipeline exploits SAM for instance segmentation and Florence for semantic refinement, followed by skeletonization, endpoint detection, and point-cloud extraction. Occluded cable segments are autonomously identified and explored with a tactile sensor, which provides local point clouds that are merged with the visual data through Euclidean clustering and topology-preserving fusion. A B-spline interpolation driven by endpoint-guided point sorting yields a smooth and complete reconstruction of the cable shape. Experimental validation using a robotic manipulator equipped with an RGB-D camera and a tactile pad demonstrates that the proposed framework accurately reconstructs both simple and highly curved single or multiple cable configurations, even when large portions are occluded. These results highlight the potential of foundation-model-enhanced cross-modal perception for advancing robotic manipulation of deformable objects.