Multimodal Sensing for Robot-Assisted Sub-Tissue Feature Detection in Physiotherapy Palpation

2025-12-24

AI Summary

Reliable identification of subsurface anatomical features—such as tendon location, diameter, depth, and multiplicity—remains challenging in soft-tissue palpation when relying solely on force sensing. Method: This study introduces a compact, multimodal tactile sensor that uniquely integrates high-resolution vision-based tactile imaging with six-axis force/torque sensing. By synchronously acquiring high-fidelity tactile images and force-controlled feedback, it enables non-invasive, robust subsurface structural identification, overcoming the ambiguity inherent in force-only perception. Experiments on silicone tissue phantoms demonstrate significantly improved detection accuracy across diverse tendon geometries—including crossed, multiple, superficial, and deep configurations—while force signals ensure safe contact and tactile imagery precisely resolves presence, morphology, and spatial relationships. Contribution: The work pioneers the synergistic fusion of vision-based tactile imaging with closed-loop force control, establishing an interpretable, high-precision paradigm for subsurface perception in physical therapy robotics.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Computer Vision: Low Level & Physics-based Vision
• Humans and AI: Brain-Sensing and Analysis

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Location- and context-aware Web and WoT applications and services
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Security and Privacy: Large-scale security measurements

Abstract

Robotic palpation relies on force sensing, but force signals in soft-tissue environments are variable and cannot reliably reveal subtle subsurface features. We present a compact multimodal sensor that integrates high-resolution vision-based tactile imaging with a 6-axis force-torque sensor. In experiments on silicone phantoms with diverse subsurface tendon geometries, force signals alone frequently produce ambiguous responses, while tactile images reveal clear structural differences in presence, diameter, depth, crossings, and multiplicity. Yet accurate force tracking remains essential for maintaining safe, consistent contact during physiotherapeutic interaction. Preliminary results show that combining tactile and force modalities enables robust subsurface feature detection and controlled robotic palpation.

Problem

• Detects subtle subsurface features in soft tissues
• Combines tactile imaging with force-torque sensing
• Enables safe robotic palpation for physiotherapy applications

Innovation

• Integrates vision-based tactile imaging with force-torque sensing
• Uses tactile images to reveal subsurface structural differences
• Combines tactile and force modalities for robust feature detection