Magnetic Tactile-Driven Soft Actuator for Intelligent Grasping and Firmness Evaluation

2025-11-30

AI Summary

Soft robotic systems face dual challenges in dexterous manipulation: the absence of integrated tactile sensing and signal distortion induced by actuator deformation. To address these, this work introduces SoftMag—a novel soft actuator that unifies magnetic actuation and magnetic tactile sensing within a single structural design for the first time. Leveraging multiphysics modeling and a neural-network-based decoupling algorithm, SoftMag effectively suppresses mechanical parasitic effects, enabling high-fidelity tactile signal recovery. Furthermore, we develop a triaxial contact force prediction model and an exploratory hardness estimation algorithm to support real-time, multi-task inference. Experimental results demonstrate robust performance across diverse operational conditions. The hardness estimates achieve a Pearson correlation coefficient of 0.82 against gold-standard measurements, validating SoftMag’s capability for non-destructive material quality assessment.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Multiagent Systems: Teamwork
• Planning, Routing, and Scheduling: Activity and Plan Recognition

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Soft robots are powerful tools for manipulating delicate objects, yet their adoption is hindered by two gaps: the lack of integrated tactile sensing and sensor signal distortion caused by actuator deformations. This paper addresses these challenges by introducing the SoftMag actuator: a magnetic tactile-sensorized soft actuator. Unlike systems relying on attached sensors or treating sensing and actuation separately, SoftMag unifies them through a shared architecture while confronting the mechanical parasitic effect, where deformations corrupt tactile signals. A multiphysics simulation framework models this coupling, and a neural-network-based decoupling strategy removes the parasitic component, restoring sensing fidelity. Experiments including indentation, quasi-static and step actuation, and fatigue tests validate the actuator's performance and decoupling effectiveness. Building upon this foundation, the system is extended into a two-finger SoftMag gripper, where a multi-task neural network enables real-time prediction of tri-axial contact forces and position. Furthermore, a probing-based strategy estimates object firmness during grasping. Validation on apricots shows a strong correlation (Pearson r over 0.8) between gripper-estimated firmness and reference measurements, confirming the system's capability for non-destructive quality assessment. Results demonstrate that combining integrated magnetic sensing, learning-based correction, and real-time inference enables a soft robotic platform that adapts its grasp and quantifies material properties. The framework offers an approach for advancing sensorized soft actuators toward intelligent, material-aware robotics.

Problem

• Develops a soft actuator with integrated magnetic tactile sensing to overcome signal distortion from deformations
• Introduces a neural network decoupling strategy to restore sensing fidelity by removing parasitic mechanical effects
• Enables real-time contact force prediction and object firmness estimation for intelligent grasping and quality assessment

Innovation

• Integrated magnetic tactile sensing in soft actuator
• Neural network decoupling to remove deformation interference
• Real-time force and firmness estimation for adaptive grasping