pith. sign in

arxiv: 2606.00397 · v1 · pith:T4M44PGOnew · submitted 2026-05-29 · 💻 cs.RO · cs.SY· eess.SY

SoFiE: Soft Finger Exoskeleton for Intelligent Grasping

Magnus Malthe Sigsgaard Nielsen , Nicklas Nikolaj Gr{\o}nvall , Xiaofeng Xiong , Saravana Prashanth Murali Babu This is my paper

Pith reviewed 2026-06-28 21:43 UTC · model grok-4.3

classification 💻 cs.RO cs.SYeess.SY
keywords soft exoskeletongrasping assistancetactile sensingproprioceptive sensingwearable roboticstendon-driven actuation3D-printed materials
0
0 comments X

The pith

A 3D-printed soft finger exoskeleton assists index flexion while sensing pose, contact force, and object stiffness through integrated StretchSense and MagSense elements.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper presents SoFiE as a modular, untethered exoskeleton for assisting index-finger flexion in grasping. It fabricates the device from flexible 3D-printed materials, drives flexion via tendon and compact DC motor, and uses a conductive spring called StretchSense for passive extension that also measures deformation through resistance change. A magnet and magnetometer pair embedded in the fingertip, called MagSense, estimates contact force and material compliance. Motor encoder data further supports state estimation. Experiments confirm reliable pose tracking, stiffness differentiation, and task-specific sensor patterns, establishing a proof of concept for lightweight wearable assistance without external tethers.

Core claim

SoFiE shows that a fully untethered soft exoskeleton can combine tendon-driven actuation, proprioceptive sensing via the StretchSense conductive spring, and tactile sensing via the MagSense magnet-magnetometer pair to deliver reliable finger-pose estimation from motor feedback, distinguish object stiffness, and produce distinct sensor signatures across grasping tasks, all controlled by an embedded microcontroller.

What carries the argument

StretchSense conductive spring for combined extension and proprioception plus MagSense magnet-magnetometer pair for contact force and compliance estimation, supported by motor encoder feedback.

If this is right

  • Actuator-level sensing supplies the data needed for safe and adaptive closed-loop control.
  • The system can differentiate materials by stiffness during contact.
  • Distinct sensor signatures appear for different grasping tasks.
  • The modular construction supports scaling to multi-finger or full-hand assistive devices.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • Embedding both actuation and sensing in the same soft structure could reduce the size and weight of future wearable robots.
  • Untethered operation opens the possibility of daily-use devices for home rehabilitation without external hardware.
  • The proof-of-concept design may be adapted to other joints where similar soft sensing is needed.

Load-bearing premise

The compact motor, microcontroller, and custom sensors maintain reliable operation in a fully untethered setup without external power, computation, or frequent recalibration.

What would settle it

A trial in which MagSense or StretchSense readings cease to correlate reliably with measured finger pose or object stiffness after several hours of continuous untethered use.

Figures

Figures reproduced from arXiv: 2606.00397 by Magnus Malthe Sigsgaard Nielsen, Nicklas Nikolaj Gr{\o}nvall, Saravana Prashanth Murali Babu, Xiaofeng Xiong.

Figure 1
Figure 1. Figure 1: a) SoFiE worn by a user, with key components highlighted, [PITH_FULL_IMAGE:figures/full_fig_p001_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Disassembled view of the index finger module of SoFiE, highlighting [PITH_FULL_IMAGE:figures/full_fig_p002_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: a) left: Stretch strain plot for the 1 mm StretchSense showing the physical behavior of the spring. Right: Force and resistive change shown against the stroke distance, showing how the resistance and the force of the spring behave inversely of each other. b) right, As the actuator tightens the tendons and flexes the index finger, the spring is stretched, lowering its resistance. When the tendons are relaxe… view at source ↗
Figure 4
Figure 4. Figure 4: a) Five different everyday objects, measuring the maximum magnetic flux, relative resistance, and position of the motor during grasping for each [PITH_FULL_IMAGE:figures/full_fig_p005_4.png] view at source ↗
read the original abstract

Soft wearable robotic systems have emerged as a promising solution for assisting individuals with reduced hand function. This paper presents SoFiE, a modular soft finger exoskeleton designed to assist index-finger flexion during grasping tasks. The proposed system is primarily fabricated using 3D-printed flexible materials, enabling a lightweight, low-profile, and modular design. Actuation is achieved through a tendon-driven mechanism powered by a compact DC motor, while passive extension is provided by a compliant conductive spring. This element, termed StretchSense, also functions as a proprioceptive sensor by exhibiting resistance changes under deformation. Furthermore, a novel tactile sensing approach, MagSense, is introduced, using a magnet and magnetometer pair embedded in a soft fingertip structure to estimate contact force and object compliance. The system is fully untethered and controlled by an embedded microcontroller. In addition, actuator-level sensing through motor encoder feedback enables estimation of the system state, providing a foundation for safe and adaptive control strategies. Experimental validation demonstrates the capability of the system to provide reliable pose estimation, distinguish between materials with different stiffness, and generate distinct sensor signatures across different grasping tasks. This paper details the design, fabrication, and sensing concepts of the proposed exoskeleton as a proof of concept toward modular, soft, and assistive wearable robotics.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

2 major / 1 minor

Summary. The manuscript presents SoFiE, a modular soft finger exoskeleton for index-finger flexion assistance during grasping. Fabricated primarily via 3D-printed flexible materials, the system uses tendon-driven actuation powered by a compact DC motor with passive extension from a compliant conductive spring (StretchSense) that also serves as a proprioceptive sensor via resistance changes. A novel MagSense tactile sensor (magnet-magnetometer pair in a soft fingertip) estimates contact force and object compliance. The device is fully untethered with embedded microcontroller control and motor-encoder feedback for state estimation. The central claim is that basic experimental validation demonstrates reliable pose estimation, distinction between materials of differing stiffness, and distinct sensor signatures across grasping tasks, offered as a proof-of-concept for soft assistive wearable robotics.

Significance. If the demonstrations are placed on a quantitative footing, the work would advance soft wearable robotics by showing successful integration of multi-modal sensing (proprioceptive resistance, magnetometer-based contact, and encoder) with tendon actuation in a lightweight, modular, fully untethered package. The dual-use StretchSense element and the MagSense approach constitute concrete technical contributions that could support adaptive control strategies. Credit is given for the untethered implementation and the modular 3D-printed fabrication route.

major comments (2)
  1. [Abstract] Abstract: the central claim that 'experimental validation demonstrates the capability of the system to provide reliable pose estimation, distinguish between materials with different stiffness, and generate distinct sensor signatures' is unsupported by any reported quantitative metrics (RMSE, classification accuracy, statistical tests, or calibration procedures), rendering the strength of the experimental contribution impossible to assess.
  2. [Abstract] Abstract, final paragraph: the assertion of reliable untethered operation of the compact DC motor, embedded microcontroller, and custom sensors without external power or frequent recalibration is presented without supporting data on power consumption, battery endurance, thermal behavior, or drift, which is load-bearing for the claimed practicality of the system.
minor comments (1)
  1. The manuscript would benefit from explicit diagrams or equations defining the resistance-to-angle mapping for StretchSense and the magnetometer-to-force mapping for MagSense to improve reproducibility.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the detailed review and constructive suggestions regarding the abstract. We address each major comment below and will revise the manuscript accordingly.

read point-by-point responses

  1. Referee: [Abstract] Abstract: the central claim that 'experimental validation demonstrates the capability of the system to provide reliable pose estimation, distinguish between materials with different stiffness, and generate distinct sensor signatures' is unsupported by any reported quantitative metrics (RMSE, classification accuracy, statistical tests, or calibration procedures), rendering the strength of the experimental contribution impossible to assess.

    Authors: We agree that the abstract would benefit from explicit quantitative metrics to support the stated claims. The body of the manuscript reports experimental results on resistance-based pose estimation via StretchSense, material stiffness distinction via MagSense, and distinct sensor patterns across tasks, but these are presented without aggregated statistics such as RMSE or accuracy values in the abstract itself. We will revise the abstract to incorporate specific quantitative results (e.g., RMSE for pose estimation and classification performance for stiffness distinction) drawn from the experimental sections. revision: yes

  2. Referee: [Abstract] Abstract, final paragraph: the assertion of reliable untethered operation of the compact DC motor, embedded microcontroller, and custom sensors without external power or frequent recalibration is presented without supporting data on power consumption, battery endurance, thermal behavior, or drift, which is load-bearing for the claimed practicality of the system.

    Authors: We acknowledge that the abstract asserts reliable untethered operation without accompanying quantitative data on power consumption, battery endurance, thermal behavior, or sensor drift. The manuscript describes the fully untethered hardware implementation but does not include these specific measurements. As this is presented as a proof-of-concept, we will add a dedicated subsection or table reporting power consumption, estimated battery life under typical grasping loads, and any observed drift in the revised manuscript to substantiate the practicality claims. revision: yes

Circularity Check

0 steps flagged

No significant circularity

full rationale

The paper is a hardware design and fabrication report describing a modular soft finger exoskeleton, its tendon-driven actuation, StretchSense and MagSense sensing elements, and basic experimental demonstrations of pose estimation and material distinction. No equations, derivations, fitted parameters, or predictive models are present in the abstract or described content; all claims reduce to physical construction and direct observation rather than any self-referential chain.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 2 invented entities

Only the abstract is available; no equations, fitted constants, or background axioms are extractable. The two named sensing concepts are presented as novel but without independent evidence or derivation details.

invented entities (2)
  • StretchSense no independent evidence
    purpose: compliant conductive spring providing both passive extension and resistance-based proprioception
    Introduced in the abstract as a new dual-function element; no external validation supplied.
  • MagSense no independent evidence
    purpose: magnet-magnetometer pair embedded in soft fingertip to estimate contact force and object compliance
    Presented as a novel tactile approach; performance claims rest solely on abstract description.

pith-pipeline@v0.9.1-grok · 5784 in / 1278 out tokens · 22615 ms · 2026-06-28T21:43:18.611710+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. SoftPINCH: EMG-Driven Soft Exoskeleton Assistance for Finger Flexion and Grasping

    cs.RO 2026-06 unverdicted novelty 4.0

    SoftPINCH is an EMG-driven soft exoskeleton using CNN+LSTM decoding and magnetic fingertip sensing that achieves 99.4% cross-subject accuracy and reduces muscular effort during pinch grasping.

Reference graph

Works this paper leans on

19 extracted references · 13 canonical work pages · cited by 1 Pith paper

  1. [1]

    The relationship between hand grip and pinch strengths and disease activity, articular damage, pain, and disability in patients with rheumatoid arthritis,

    M. Dedeoglu, Ü. Gafuroglu, Ö. Yilmaz, and H. Bodur, “The relationship between hand grip and pinch strengths and disease activity, articular damage, pain, and disability in patients with rheumatoid arthritis,”Archives of Rheumatology, vol. 28, pp. 69–77, 2013

    2013

  2. [2]

    Rheumatoid arthritis: Hand function, activities of daily living, grip strength and essential assistive de- vices,

    I. Sipham and S. J. Pitout, “Rheumatoid arthritis: Hand function, activities of daily living, grip strength and essential assistive de- vices,”Curationis, vol. 26, pp. 98–106, 2003.DOI: 10 . 4102 / curationis.v26i3.857

    2003

  3. [3]

    Relation between handgrip strength and quality of life in patients with arthritis in korea: The korea national health and nutrition examination survey, 2015-2018,

    S.-Y . Chang, B.-D. Han, K.-D. Han, H.-J. Park, and S. Kang, “Relation between handgrip strength and quality of life in patients with arthritis in korea: The korea national health and nutrition examination survey, 2015-2018,”Medicina (Kaunas), vol. 58:172, 2022.DOI: 10.3390/ medicina58020172

    2015

  4. [4]

    Assessing health-related quality of life in hand osteoarthritis: A literature review,

    M. Michon, E. Maheu, and F. Berenbaum, “Assessing health-related quality of life in hand osteoarthritis: A literature review,”Annals of the rheumatic diseases, vol. 70, pp. 921–928, 2011.DOI: 10.1136/ ard.2010.131151

    arXiv 2011

  5. [5]

    Grip strength impairment and neuropathic-like pain as determinants of function and quality of life in hand osteoarthritis,

    S. Mathieu, F. Fayet, M. -H. Salembien, M. Rodere, M. Soubrier, and A. Tournadre, “Grip strength impairment and neuropathic-like pain as determinants of function and quality of life in hand osteoarthritis,” Open acces rheumatoogy: research and reviews, vol. 17, pp. 47–56, 2025.DOI:10.2147/OARRR.S512888

    work page doi:10.2147/oarrr.s512888 2025

  6. [6]

    2018 update of the eular recommendations for the management of hand osteoarthritis,

    M. Kloppenburg et al., “2018 update of the eular recommendations for the management of hand osteoarthritis,”Annals of the rheumatic diseases, vol. 78, pp. 16–24, 2019.DOI: 10.1136/annrheumdis- 2018-213826

    work page doi:10.1136/annrheumdis- 2018

  7. [7]

    A survey on robotic devices for upper limb rehabilitation,

    P. aciejasz, J. Eschweiler, K. Gerlach-Hahn, A. Jansen-Troy, and S. Leonhardt, “A survey on robotic devices for upper limb rehabilitation,” Journal of neuroengineering and rehabilitation, vol. 11, 2014.DOI: 10.1186/1743-0003-11-3

    work page doi:10.1186/1743-0003-11-3 2014

  8. [9]

    Moving toward soft robotics: A decade review of the design of hand exoskeletons,

    T. Shahid, D. Gouwanda, S. G. Nurzaman, and A. A. Gopalai, “Moving toward soft robotics: A decade review of the design of hand exoskeletons,”Biomimetics, vol. 3, 2018.DOI: 10 . 3390 / biomimetics3030017

    2018

  9. [10]

    Soft wearable robots: Development status and technical challenges,

    Y . Shi, W. Dong, W. Lin, and Y . Gao, “Soft wearable robots: Development status and technical challenges,”Sensors, vol. 22, 2022. DOI:10.3390/s22197584

    work page doi:10.3390/s22197584 2022

  10. [11]

    Soft robotic glove for combined assistance and at-home rehabilitation,

    P. Polygerinos, Z. Wang, K. C. Galloway, R. J. Wood, and C. J. Walsh, “Soft robotic glove for combined assistance and at-home rehabilitation,” Robotics and Autonomous Systems, vol. 73, pp. 135–143, 2015.DOI: 10.1016/j.robot.2014.08.014

    work page doi:10.1016/j.robot.2014.08.014 2015

  11. [12]

    A fully fabric-based bidirectional soft robotic glove for assistance and rehabilitation of hand impaired patients,

    H. K. Yap et al., “A fully fabric-based bidirectional soft robotic glove for assistance and rehabilitation of hand impaired patients,”IEEE Robotics and Automation Letters, vol. 2, no. 3, pp. 1383–1390, 2017. DOI:10.1109/LRA.2017.2669366

    work page doi:10.1109/lra.2017.2669366 2017

  12. [13]

    Assisting hand function after spinal cord injury with a fabric-based soft robotic glove,

    L. Cappello et al., “Assisting hand function after spinal cord injury with a fabric-based soft robotic glove,”Journal of neuroengineering and rehabilitation, vol. 15, 2018.DOI: 10.1186/s12984-018- 0391-x

    work page doi:10.1186/s12984-018- 2018

  13. [14]

    Exo-glove: A wearable robot for the hand with a soft tendon routing system,

    H. In, B. B. Kang, M. Sin, and K. -J. Cho, “Exo-glove: A wearable robot for the hand with a soft tendon routing system,”IEEE Robotics and Automation Magazine, vol. 22, no. 1, pp. 97–105, 2015.DOI: 10.1109/MRA.2014.2362863

    work page doi:10.1109/mra.2014.2362863 2015

  14. [15]

    Exo-glove poly ii: A polymer-based soft wearable robot for the hand with a tendon-driven actuation system,

    B. B. Kang, H. Choi, H. Lee, and K. J. Cho, “Exo-glove poly ii: A polymer-based soft wearable robot for the hand with a tendon-driven actuation system,”Soft robotics, vol. 6, pp. 214–227, 2019.DOI: 10.1089/soro.2018.0006

    work page doi:10.1089/soro.2018.0006 2019

  15. [16]

    A soft tactile sensor based on magnetics and hybrid flexible- rigid electronics,

    M. Neto, P. Ribeiro, R. Nunes, L. Jamone, A. Bernardino, and S. Cardoso, “A soft tactile sensor based on magnetics and hybrid flexible- rigid electronics,”Sensors, vol. 21, no. 15, 2021,ISSN: 1424-8220. DOI: 10.3390/s21155098 [Online]. Available: https://www. mdpi.com/1424-8220/21/15/5098

    work page doi:10.3390/s21155098 2021

  16. [17]

    Soft robotic glove with integrated sensing for intuitive grasping assistance post spinal cord injury,

    Y . M. Zhou, D. Wagner, K. Nuckols, R. Heimgartner, C. Correia, and M. Clarke, “Soft robotic glove with integrated sensing for intuitive grasping assistance post spinal cord injury,”2019 International Conference on Robotics and Automation (ICRA), 2019.DOI: 10 . 1109/ICRA.2019.8794367

    arXiv 2019

  17. [18]

    A review of soft wearable robots that provide active assistance: Trends, common actuation methods, fabrication, and applications,

    C. Thalman and P. Artemiadis, “A review of soft wearable robots that provide active assistance: Trends, common actuation methods, fabrication, and applications,”Wearable Technologies, vol. 1, 2020. DOI:10.1017/wtc.2020.4

    work page doi:10.1017/wtc.2020.4 2020

  18. [19]

    Flexo- glove: A 3d printed soft exoskeleton robotic glove for impaired hand rehabilitation and assistance,

    A. Mohammadi, J. Lavranos, P. Choong, and D. Oetomo, “Flexo- glove: A 3d printed soft exoskeleton robotic glove for impaired hand rehabilitation and assistance,”Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference, pp. 2120–2123, 2018.DOI:...

    work page doi:10.1109/embc.2018.8512617 2018

  19. [20]

    Development of 3d-printed myoelectric hand orthosis for patients with spinal cord injury,

    H. J. Yoo, S. Lee, J. Kim, C. Park, and B. Lee, “Development of 3d-printed myoelectric hand orthosis for patients with spinal cord injury,”Journal of neuroengineering and rehabilitation, vol. 16, 2019. DOI:10.1186/s12984-019-0633-6

    work page doi:10.1186/s12984-019-0633-6 2019