Magnet-Based Soft Robotic Skin Using a 3D-Printed Multi-Lattice Structure and CNN-Based Tactile Super-Resolution

Joowon Park; Kyungseo Park; Suan Sim; Sukho Park; Youngjun Ryu; Yunseong Bang

arxiv: 2605.28352 · v1 · pith:HCMER64Znew · submitted 2026-05-27 · 💻 cs.RO

Magnet-Based Soft Robotic Skin Using a 3D-Printed Multi-Lattice Structure and CNN-Based Tactile Super-Resolution

Yunseong Bang , Joowon Park , Suan Sim , Youngjun Ryu , Sukho Park , Kyungseo Park This is my paper

Pith reviewed 2026-06-29 11:26 UTC · model grok-4.3

classification 💻 cs.RO

keywords soft roboticstactile sensingmagnetic sensing3D printingconvolutional neural networkrobotic skinsuper-resolutionHall-effect sensors

0 comments

The pith

A 3D-printed multi-lattice structure spreads magnetic field changes from embedded magnets to Hall sensors, enabling a CNN to estimate contact location and normal force over large areas with overlapping receptive fields.

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

The paper establishes that external contact forces on a soft robotic skin are transduced into magnetic field changes by permanent magnets, which a tunable multi-lattice structure then distributes across an array of Hall-effect sensors to create large, overlapping receptive fields. This arrangement supports a large sensing area with few sensors and few blind spots while allowing the lattice parameters to adjust both mechanical compliance and sensing behavior. A convolutional neural network trained on measured data then maps the sensor signals to real-time estimates of contact position and normal force magnitude. The fabrication uses implicit modeling and selective laser sintering to produce complex conformal shapes quickly. If correct, the approach reduces the sensor density needed for whole-body robotic skins suitable for safe human-robot contact.

Core claim

External contact forces are converted to magnetic field changes by embedded permanent magnets, and the lattice spreads these changes across the sensing domain. This gives each sensor a large, overlapping receptive field and enables a large sensing area with minimal blind spots. Lattice parameters are tunable, enabling joint adjustment of mechanical compliance and transduction characteristics. An implicit modeling workflow and selective laser sintering (SLS) 3D printing support rapid fabrication of conformal, high-complexity structures. A convolutional neural network trained on experimental measurements estimates contact location and normal force in real time.

What carries the argument

The multi-lattice soft structure with embedded permanent magnets that distributes magnetic field perturbations to create overlapping receptive fields for each Hall-effect sensor.

If this is right

Large sensing areas become feasible with sparse sensor arrays because each sensor covers an extended receptive field.
Lattice parameters can be adjusted to match both the mechanical needs of the robot body and the signal characteristics required by the CNN.
Conformal skins for curved surfaces are manufacturable in one piece via SLS printing without dense wiring.
Real-time contact estimation supports closed-loop control for safe physical human-robot interaction.
The same hardware can scale to larger surfaces by extending the lattice and retraining the network on additional measurements.

Where Pith is reading between the lines

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

The design may allow detection of multiple simultaneous contacts if the CNN is trained on corresponding multi-point data sets.
Tuning the lattice could trade off between high compliance for safety and high sensitivity for precise force mapping.
Integration with existing robot skins would require only surface mounting of the printed lattice and sensor board rather than redesigning the entire structure.

Load-bearing premise

The multi-lattice structure spreads magnetic field changes to produce large overlapping receptive fields without introducing mechanical nonlinearity or crosstalk that the CNN cannot correct.

What would settle it

Apply repeated contacts at varying distances from magnets on a fabricated skin and check whether localization and force errors remain low or rise sharply once lattice deformation becomes nonlinear.

read the original abstract

This paper presents a magnet-based robotic skin that integrates a multilayer soft lattice with distributed Hall-effect sensor arrays and a tactile super-resolution model. External contact forces are converted to magnetic field changes by embedded permanent magnets, and the lattice spreads these changes across the sensing domain. This gives each sensor a large, overlapping receptive field and enables a large sensing area with minimal blind spots. Lattice parameters are tunable, enabling joint adjustment of mechanical compliance and transduction characteristics. An implicit modeling workflow and selective laser sintering (SLS) 3D printing support rapid fabrication of conformal, high-complexity structures. A convolutional neural network trained on experimental measurements estimates contact location and normal force in real time. Experiments validate localization accuracy and indicate scalability to larger surfaces, suggesting applicability to whole-body robotic skin and safe human-robot interaction.

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.

Desk Editor's Note private letter to a colleague

The paper integrates magnets in a tunable 3D-printed lattice with Hall sensors and a CNN to enlarge receptive fields for soft robotic skin, but the validation claims rest on unshown quantitative data.

read the letter

The main takeaway is a practical fabrication route for large-area conformable tactile skin. Magnets embedded in the lattice convert contact forces into distributed magnetic field changes that reach the sensors, and the CNN then estimates location and normal force from those signals. The lattice parameters can be adjusted to balance compliance and sensing range.

What stands out as new is the use of selective laser sintering with an implicit modeling workflow to print complex multi-lattice structures quickly. This lets them make high-detail conformal skins without traditional molding steps, and the tunability of the lattice for both mechanical and transduction properties is a useful engineering detail.

The experiments are described as validating localization accuracy and scalability to larger surfaces, yet the abstract supplies no error values, baselines, field maps, or linearity checks. That leaves the central assumption—that the lattice produces clean overlapping receptive fields without excessive nonlinearity or crosstalk—unexamined in the provided text. If the deformation-to-field mapping turns out strongly nonlinear, the CNN may not invert it reliably, which is exactly the stress-test concern.

This work is aimed at robotics groups building whole-body sensing for human-robot interaction. A reader focused on hardware prototypes or fabrication methods could extract the printing workflow and lattice design even if the sensing performance numbers need more scrutiny.

I would send it to peer review so the experimental data and any field measurements can be checked directly.

Referee Report

2 major / 2 minor

Summary. The paper introduces a magnet-based soft robotic skin that uses a 3D-printed multi-lattice structure with embedded permanent magnets and distributed Hall-effect sensors. The lattice spreads magnetic field changes from contact forces to create large, overlapping receptive fields for each sensor, minimizing blind spots. A CNN trained on experimental data performs tactile super-resolution to estimate contact location and normal force in real time. The design allows tunable compliance and is fabricated using SLS 3D printing with implicit modeling. Experiments are said to validate the localization accuracy and scalability to larger surfaces.

Significance. If the experimental results confirm the claims, this system could offer a practical approach to large-area tactile sensing for soft robots, with advantages in fabrication speed and conformability. The combination of mechanical design for field spreading and ML for inversion is a promising direction for scalable robotic skin.

major comments (2)

[Abstract] Abstract: The abstract asserts that 'experiments validate localization accuracy' and 'indicate scalability' but supplies no quantitative results, error bars, baselines, or details on data collection. This is load-bearing for the central claim that the lattice and CNN enable minimal blind spots and real-time estimation.
[Design/Transduction section] Design/Transduction (likely §3): The assumption that the multi-lattice structure reliably spreads magnetic field changes to create large overlapping receptive fields without introducing excessive mechanical nonlinearity or sensor crosstalk (that the CNN cannot compensate for) is central but lacks supporting analysis such as field distribution maps, linearity plots, or position-dependent error measurements.

minor comments (2)

[Fabrication] Provide the specific lattice parameters (e.g., cell size, wall thickness) used in the reported prototype and how they were selected.
[CNN Model] Include the CNN architecture details, training dataset size, and cross-validation procedure to support reproducibility of the super-resolution results.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the constructive feedback on our manuscript. We address each major comment below and outline revisions to improve clarity and support for our claims.

read point-by-point responses

Referee: [Abstract] Abstract: The abstract asserts that 'experiments validate localization accuracy' and 'indicate scalability' but supplies no quantitative results, error bars, baselines, or details on data collection. This is load-bearing for the central claim that the lattice and CNN enable minimal blind spots and real-time estimation.

Authors: We agree that the abstract would benefit from including key quantitative highlights to better substantiate the claims. In the revised manuscript, we will add concise statements on localization accuracy (e.g., mean error and standard deviation), force estimation performance, and a brief note on the experimental data collection protocol, while preserving the abstract's length constraints. revision: yes
Referee: [Design/Transduction section] Design/Transduction (likely §3): The assumption that the multi-lattice structure reliably spreads magnetic field changes to create large overlapping receptive fields without introducing excessive mechanical nonlinearity or sensor crosstalk (that the CNN cannot compensate for) is central but lacks supporting analysis such as field distribution maps, linearity plots, or position-dependent error measurements.

Authors: The experimental results in Section 4, including the CNN's super-resolution performance across the sensing area, provide indirect validation of the lattice's field-spreading effect. To directly address the concern, we will incorporate additional supporting analysis in the revised Design/Transduction section, such as simulated magnetic field distribution maps and position-dependent error plots from the collected data. revision: yes

Circularity Check

0 steps flagged

No significant circularity; system description with experimental validation

full rationale

The paper is a hardware and system description of a magnet-based soft robotic skin using 3D-printed lattice, embedded magnets, Hall sensors, and a CNN trained directly on experimental measurements. No derivation chain, first-principles equations, fitted parameters renamed as predictions, or self-citation load-bearing uniqueness theorems are present. Claims of receptive field spreading and super-resolution rest on physical fabrication and data-driven training rather than any self-referential reduction. This is the most common honest finding for experimental robotics papers without mathematical modeling sections.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

No mathematical model, free parameters, or invented physical entities are introduced in the abstract. The work relies on standard assumptions about magnetic field sensing and neural network generalization that are not audited here.

pith-pipeline@v0.9.1-grok · 5687 in / 1100 out tokens · 20357 ms · 2026-06-29T11:26:59.471458+00:00 · methodology

discussion (0)

Reference graph

Works this paper leans on

22 extracted references · 5 canonical work pages

[1]

Punyo-1: Soft tactile-sensing upper-body robot for large object manipulation and physical human interaction,

A. Goncalves, N. Kuppuswamy, A. Beaulieu, A. Uttamchandani, K. M. Tsui, and A. Alspach, “Punyo-1: Soft tactile-sensing upper-body robot for large object manipulation and physical human interaction, ” in 2022 IEEE 5th International Conference on Soft Robotics (RoboSoft), 2022, pp. 844–851

2022
[2]

Learning whole-body human-robot haptic interaction in social contexts,

J. Campbell and K. Y amane, “Learning whole-body human-robot haptic interaction in social contexts, ” in 2020 IEEE International Conference on Robotics and Automation (ICRA), 2020, pp. 10 177– 10 183

2020
[3]

Soft inﬂatable sensing modules for safe and interactive robots,

T. Kim, S. J. Y oon, and Y.-L. Park, “Soft inﬂatable sensing modules for safe and interactive robots,” IEEE Robotics and Automation Letters, vol. 3, no. 4, pp. 3216–3223, 2018

2018
[4]

A comprehensive realization of robot skin: Sensors, sensing, control, and applications,

G. Cheng, E. Dean-Leon, F. Bergner, J. Rogelio Guadarrama Olvera, Q. Leboutet, and P. Mittendorfer, “A comprehensive realization of robot skin: Sensors, sensing, control, and applications,” Proceedings of the IEEE , vol. 107, no. 10, pp. 2034–2051, Oct 2019

2034
[5]

From cyskin to proxyskin: Design, implementation and testing of a multi-modal robotic skin for human-robot interaction,

F. Giovinazzo, F. Grella, M. Sartore, M. Adami, R. Galletti, and G. Cannata, “From cyskin to proxyskin: Design, implementation and testing of a multi-modal robotic skin for human-robot interaction,” Sensors, vol. 24, no. 4, 2024. [Online]. Available: https://www.mdpi.com/1424-8220/24/4/1334

2024
[6]

Low-cost and easy-to-build soft robotic skin for safe and contact-rich human-robot collaboration,

K. Park, K. Shin, S. Y amsani, K. Gim, and J. Kim, “Low-cost and easy-to-build soft robotic skin for safe and contact-rich human-robot collaboration,” IEEE Transactions on Robotics, vol. 40, pp. 2327–2338, 2024

2024
[7]

Simulation, learning, and application of vision-based tactile sensing at large scale,

Q. K. Luu, N. H. Nguyen, and V. A. Ho, “Simulation, learning, and application of vision-based tactile sensing at large scale,” IEEE Transactions on Robotics, vol. 39, no. 3, pp. 2003–2019, June 2023

2003
[8]

Improving robotic tactile localization super-resolution via spatiotemporal continuity learning and overlapping air chambers,

X. Li, Y. Zhang, X. Xie, J. Li, and G. Shi, “Improving robotic tactile localization super-resolution via spatiotemporal continuity learning and overlapping air chambers,” Proceedings of the AAAI Conference on Artiﬁcial Intelligence , vol. 37, no. 5, pp. 6192–6199, Jun. 2023. [Online]. Available: https://ojs.aaai.org/index.php/AAAI/article/view/25763

2023
[9]

A biomimetic elastomeric robot skin using electrical impedance and acoustic tomography for tactile sensing,

K. Park, H. Yuk, M. Y ang, J. Cho, H. Lee, and J. Kim, “A biomimetic elastomeric robot skin using electrical impedance and acoustic tomography for tactile sensing, ” Science Robotics, vol. 7, no. 67, p. eabm7187, 2022. [Online]. Available: https://www.science.org/doi/abs/10.1126/scirobotics.abm7187

work page doi:10.1126/scirobotics.abm7187 2022
[10]

Soft magnetic skin for super-resolution tactile sensing with force self-decoupling,

Y. Y an, Z. Hu, Z. Y ang, W. Yuan, C. Song, J. Pan, and Y. Shen, “Soft magnetic skin for super-resolution tactile sensing with force self-decoupling, ” Science Robotics, vol. 6, no. 51, p. eabc8801, 2021. [Online]. Available: https://www.science.org/doi/abs/10.1126/scirobotics.abc8801

work page doi:10.1126/scirobotics.abc8801 2021
[11]

A soft skin with self-decoupled three-axis force-sensing taxels,

Y. Y an, A. Zermane, J. Pan, and A. Kheddar, “A soft skin with self-decoupled three-axis force-sensing taxels, ” Nature Machine Intelligence, vol. 6, no. 11, pp. 1284–1295, Nov. 2024. [Online]. Available: https://doi.org/10.1038/s42256-024-00904-9

work page doi:10.1038/s42256-024-00904-9 2024
[12]

Large-area magnetic skin for multi-point and multi-scale tactile sensing with super-resolution,

H. Hu, C. Zhang, X. Lai, H. Dai, C. Pan, H. Sun, D. Tang, Z. Hu, J. Fu, T. Li, and P. Zhao, “Large-area magnetic skin for multi-point and multi-scale tactile sensing with super-resolution, ” npj Flexible Electronics, vol. 8, no. 1, p. 42, Jul. 2024. [Online]. Available: https://doi.org/10.1038/s41528-024-00325-z

work page doi:10.1038/s41528-024-00325-z 2024
[13]

Magnetic tactile sensor with load tolerance and ﬂexibility using frame structures for estimating triaxial contact force distribution of humanoid,

T. Hiraoka, R. Kunita, K. Kojima, N. Hiraoka, M. Konishi, T. Makabe, A. Tang, K. Okada, and M. Inaba, “Magnetic tactile sensor with load tolerance and ﬂexibility using frame structures for estimating triaxial contact force distribution of humanoid, ” in 2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2024, pp. 11 294–11 301

2024
[14]

Design of ﬂexible tpu-based lattice structures for 3d printing: A comparative analysis of open-cell versus closed-cell topologies,

S. de la Rosa, P. F. Mayuet Ares, and L. Rodríguez-Parada, “Design of ﬂexible tpu-based lattice structures for 3d printing: A comparative analysis of open-cell versus closed-cell topologies, ” Polymers, vol. 17, no. 9, 2025. [Online]. Available: https://www.mdpi.com/2073- 4360/17/9/1133

2025
[15]

Stiﬀness and strength evaluation of lattice-based mechanical metamaterials by decoupled two-scale analysis,

N. Tsushima and R. Higuchi, “Stiﬀness and strength evaluation of lattice-based mechanical metamaterials by decoupled two-scale analysis,” Materials Today Communications, vol. 31, p. 103598, 2022. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S2352492822004640

2022
[16]

Mechanical metamaterials with star-shaped pores exhibiting negative and zero poisson ’s ratio,

L. Mizzi, E. Mahdi, K. Titov, R. Gatt, D. Attard, K. E. Evans, J. N. Grima, and J.-C. Tan, “Mechanical metamaterials with star-shaped pores exhibiting negative and zero poisson ’s ratio,” Materials Design , vol. 146, pp. 28–37, 2018. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S0264127518301424

2018
[17]

Experimental and analytical investigation of mechanical behavior of laser- sintered diamond-lattice structures,

C. Neﬀ, N. Hopkinson, and N. B. Crane, “Experimental and analytical investigation of mechanical behavior of laser- sintered diamond-lattice structures,” Additive Manufacturing , vol. 22, pp. 807–816, 2018. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S2214860418302136

2018
[18]

Energy absorption in lattice- structured materials under impact loading,

S. Bieler and K. Weinberg, “Energy absorption in lattice- structured materials under impact loading, ” European Journal of Mechanics - A/Solids , vol. 114, p. 105734, 2025. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S0997753825001688

2025
[19]

3d soft auxetic lattice structures fabricated by selective laser sintering: Tpu powder evaluation and process optimization,

S. Yuan, F. Shen, J. Bai, C. K. Chua, J. Wei, and K. Zhou, “3d soft auxetic lattice structures fabricated by selective laser sintering: Tpu powder evaluation and process optimization, ” Materials Design , vol. 120, pp. 317–327, 2017. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S0264127517301272

2017
[20]

Super-resolution tactile sensor arrays with sparse units enabled by deep learning,

D. Kong, Y. Lu, S. Zhou, M. Wang, G. Pang, B. Wang, L. Chen, X. Huang, H. Lyu, K. Xu, and G. Y ang, “Super-resolution tactile sensor arrays with sparse units enabled by deep learning,” Science Advances, vol. 11, no. 27, p. eadv2124, 2025. [Online]. Available: https://www.science.org/doi/abs/10.1126/sciadv.adv2124

work page doi:10.1126/sciadv.adv2124 2025
[21]

Gelsight: High- resolution robot tactile sensors for estimating geometry and force,

W. Yuan, S. Dong, and E. H. Adelson, “Gelsight: High- resolution robot tactile sensors for estimating geometry and force,” Sensors, vol. 17, no. 12, 2017. [Online]. Available: https://www.mdpi.com/1424-8220/17/12/2762

2017
[22]

Decoupled weight decay regularization,

I. Loshchilov and F. Hutter, “Decoupled weight decay regularization, ” in International Conference on Learning Representations, 2019. [Online]. Available: https://openreview.net/forum?id=Bkg6RiCqY7

2019

[1] [1]

Punyo-1: Soft tactile-sensing upper-body robot for large object manipulation and physical human interaction,

A. Goncalves, N. Kuppuswamy, A. Beaulieu, A. Uttamchandani, K. M. Tsui, and A. Alspach, “Punyo-1: Soft tactile-sensing upper-body robot for large object manipulation and physical human interaction, ” in 2022 IEEE 5th International Conference on Soft Robotics (RoboSoft), 2022, pp. 844–851

2022

[2] [2]

Learning whole-body human-robot haptic interaction in social contexts,

J. Campbell and K. Y amane, “Learning whole-body human-robot haptic interaction in social contexts, ” in 2020 IEEE International Conference on Robotics and Automation (ICRA), 2020, pp. 10 177– 10 183

2020

[3] [3]

Soft inﬂatable sensing modules for safe and interactive robots,

T. Kim, S. J. Y oon, and Y.-L. Park, “Soft inﬂatable sensing modules for safe and interactive robots,” IEEE Robotics and Automation Letters, vol. 3, no. 4, pp. 3216–3223, 2018

2018

[4] [4]

A comprehensive realization of robot skin: Sensors, sensing, control, and applications,

G. Cheng, E. Dean-Leon, F. Bergner, J. Rogelio Guadarrama Olvera, Q. Leboutet, and P. Mittendorfer, “A comprehensive realization of robot skin: Sensors, sensing, control, and applications,” Proceedings of the IEEE , vol. 107, no. 10, pp. 2034–2051, Oct 2019

2034

[5] [5]

From cyskin to proxyskin: Design, implementation and testing of a multi-modal robotic skin for human-robot interaction,

F. Giovinazzo, F. Grella, M. Sartore, M. Adami, R. Galletti, and G. Cannata, “From cyskin to proxyskin: Design, implementation and testing of a multi-modal robotic skin for human-robot interaction,” Sensors, vol. 24, no. 4, 2024. [Online]. Available: https://www.mdpi.com/1424-8220/24/4/1334

2024

[6] [6]

Low-cost and easy-to-build soft robotic skin for safe and contact-rich human-robot collaboration,

K. Park, K. Shin, S. Y amsani, K. Gim, and J. Kim, “Low-cost and easy-to-build soft robotic skin for safe and contact-rich human-robot collaboration,” IEEE Transactions on Robotics, vol. 40, pp. 2327–2338, 2024

2024

[7] [7]

Simulation, learning, and application of vision-based tactile sensing at large scale,

Q. K. Luu, N. H. Nguyen, and V. A. Ho, “Simulation, learning, and application of vision-based tactile sensing at large scale,” IEEE Transactions on Robotics, vol. 39, no. 3, pp. 2003–2019, June 2023

2003

[8] [8]

Improving robotic tactile localization super-resolution via spatiotemporal continuity learning and overlapping air chambers,

X. Li, Y. Zhang, X. Xie, J. Li, and G. Shi, “Improving robotic tactile localization super-resolution via spatiotemporal continuity learning and overlapping air chambers,” Proceedings of the AAAI Conference on Artiﬁcial Intelligence , vol. 37, no. 5, pp. 6192–6199, Jun. 2023. [Online]. Available: https://ojs.aaai.org/index.php/AAAI/article/view/25763

2023

[9] [9]

A biomimetic elastomeric robot skin using electrical impedance and acoustic tomography for tactile sensing,

K. Park, H. Yuk, M. Y ang, J. Cho, H. Lee, and J. Kim, “A biomimetic elastomeric robot skin using electrical impedance and acoustic tomography for tactile sensing, ” Science Robotics, vol. 7, no. 67, p. eabm7187, 2022. [Online]. Available: https://www.science.org/doi/abs/10.1126/scirobotics.abm7187

work page doi:10.1126/scirobotics.abm7187 2022

[10] [10]

Soft magnetic skin for super-resolution tactile sensing with force self-decoupling,

Y. Y an, Z. Hu, Z. Y ang, W. Yuan, C. Song, J. Pan, and Y. Shen, “Soft magnetic skin for super-resolution tactile sensing with force self-decoupling, ” Science Robotics, vol. 6, no. 51, p. eabc8801, 2021. [Online]. Available: https://www.science.org/doi/abs/10.1126/scirobotics.abc8801

work page doi:10.1126/scirobotics.abc8801 2021

[11] [11]

A soft skin with self-decoupled three-axis force-sensing taxels,

Y. Y an, A. Zermane, J. Pan, and A. Kheddar, “A soft skin with self-decoupled three-axis force-sensing taxels, ” Nature Machine Intelligence, vol. 6, no. 11, pp. 1284–1295, Nov. 2024. [Online]. Available: https://doi.org/10.1038/s42256-024-00904-9

work page doi:10.1038/s42256-024-00904-9 2024

[12] [12]

Large-area magnetic skin for multi-point and multi-scale tactile sensing with super-resolution,

H. Hu, C. Zhang, X. Lai, H. Dai, C. Pan, H. Sun, D. Tang, Z. Hu, J. Fu, T. Li, and P. Zhao, “Large-area magnetic skin for multi-point and multi-scale tactile sensing with super-resolution, ” npj Flexible Electronics, vol. 8, no. 1, p. 42, Jul. 2024. [Online]. Available: https://doi.org/10.1038/s41528-024-00325-z

work page doi:10.1038/s41528-024-00325-z 2024

[13] [13]

Magnetic tactile sensor with load tolerance and ﬂexibility using frame structures for estimating triaxial contact force distribution of humanoid,

T. Hiraoka, R. Kunita, K. Kojima, N. Hiraoka, M. Konishi, T. Makabe, A. Tang, K. Okada, and M. Inaba, “Magnetic tactile sensor with load tolerance and ﬂexibility using frame structures for estimating triaxial contact force distribution of humanoid, ” in 2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2024, pp. 11 294–11 301

2024

[14] [14]

Design of ﬂexible tpu-based lattice structures for 3d printing: A comparative analysis of open-cell versus closed-cell topologies,

S. de la Rosa, P. F. Mayuet Ares, and L. Rodríguez-Parada, “Design of ﬂexible tpu-based lattice structures for 3d printing: A comparative analysis of open-cell versus closed-cell topologies, ” Polymers, vol. 17, no. 9, 2025. [Online]. Available: https://www.mdpi.com/2073- 4360/17/9/1133

2025

[15] [15]

Stiﬀness and strength evaluation of lattice-based mechanical metamaterials by decoupled two-scale analysis,

N. Tsushima and R. Higuchi, “Stiﬀness and strength evaluation of lattice-based mechanical metamaterials by decoupled two-scale analysis,” Materials Today Communications, vol. 31, p. 103598, 2022. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S2352492822004640

2022

[16] [16]

Mechanical metamaterials with star-shaped pores exhibiting negative and zero poisson ’s ratio,

L. Mizzi, E. Mahdi, K. Titov, R. Gatt, D. Attard, K. E. Evans, J. N. Grima, and J.-C. Tan, “Mechanical metamaterials with star-shaped pores exhibiting negative and zero poisson ’s ratio,” Materials Design , vol. 146, pp. 28–37, 2018. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S0264127518301424

2018

[17] [17]

Experimental and analytical investigation of mechanical behavior of laser- sintered diamond-lattice structures,

C. Neﬀ, N. Hopkinson, and N. B. Crane, “Experimental and analytical investigation of mechanical behavior of laser- sintered diamond-lattice structures,” Additive Manufacturing , vol. 22, pp. 807–816, 2018. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S2214860418302136

2018

[18] [18]

Energy absorption in lattice- structured materials under impact loading,

S. Bieler and K. Weinberg, “Energy absorption in lattice- structured materials under impact loading, ” European Journal of Mechanics - A/Solids , vol. 114, p. 105734, 2025. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S0997753825001688

2025

[19] [19]

3d soft auxetic lattice structures fabricated by selective laser sintering: Tpu powder evaluation and process optimization,

S. Yuan, F. Shen, J. Bai, C. K. Chua, J. Wei, and K. Zhou, “3d soft auxetic lattice structures fabricated by selective laser sintering: Tpu powder evaluation and process optimization, ” Materials Design , vol. 120, pp. 317–327, 2017. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S0264127517301272

2017

[20] [20]

Super-resolution tactile sensor arrays with sparse units enabled by deep learning,

D. Kong, Y. Lu, S. Zhou, M. Wang, G. Pang, B. Wang, L. Chen, X. Huang, H. Lyu, K. Xu, and G. Y ang, “Super-resolution tactile sensor arrays with sparse units enabled by deep learning,” Science Advances, vol. 11, no. 27, p. eadv2124, 2025. [Online]. Available: https://www.science.org/doi/abs/10.1126/sciadv.adv2124

work page doi:10.1126/sciadv.adv2124 2025

[21] [21]

Gelsight: High- resolution robot tactile sensors for estimating geometry and force,

W. Yuan, S. Dong, and E. H. Adelson, “Gelsight: High- resolution robot tactile sensors for estimating geometry and force,” Sensors, vol. 17, no. 12, 2017. [Online]. Available: https://www.mdpi.com/1424-8220/17/12/2762

2017

[22] [22]

Decoupled weight decay regularization,

I. Loshchilov and F. Hutter, “Decoupled weight decay regularization, ” in International Conference on Learning Representations, 2019. [Online]. Available: https://openreview.net/forum?id=Bkg6RiCqY7

2019