pith. machine review for the scientific record. sign in

arxiv: 2605.13925 · v1 · submitted 2026-05-13 · 💻 cs.RO

Recognition: no theorem link

Towards Robotic Dexterous Hand Intelligence: A Survey

Weiguang Zhao , Xihao Guo , Tian Liang , Rui Zhang , Irwin King , Kaizhu Huang
Authors on Pith no claims yet

Pith reviewed 2026-05-15 05:41 UTC · model grok-4.3

classification 💻 cs.RO
keywords dexterous manipulationrobotic handshardware designcontrol and learningdatasetsevaluation protocolssurvey
0
0 comments X

The pith

A survey reviews hardware, methods, data, and evaluation to map the trajectory and open challenges in robotic dexterous hand research.

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

The paper examines robotic dexterous hands by breaking down their physical designs, including actuators, transmissions, sensors, and the trade-offs in force, flexibility, speed, and complexity. It then groups control and learning techniques by their main approaches and shows how they have changed over time. Datasets, sensory inputs, and testing methods are collected to show how progress is measured and trained. Linking these four areas produces a clearer view of what limits current systems and which problems need priority attention next.

Core claim

Existing dexterous hand studies differ widely in hand shape, sensors, tasks, training data, and testing rules, which prevents direct comparison and hides the field's overall direction; a unified review across hardware analysis, control and learning paradigms, data resources, and evaluation practices supplies the missing structure and names the chief remaining obstacles.

What carries the argument

The four-aspect review structure that connects hardware trade-offs, chronological method evolution, consolidated datasets and benchmarks, and explicit limitation discussion.

If this is right

  • Direct comparisons between hand designs and algorithms become feasible once evaluation practices are aligned.
  • Researchers can target the listed limitations rather than repeating isolated advances.
  • New work can combine hardware improvements with learning methods more deliberately.
  • Datasets and benchmarks gain clearer value when interpreted alongside the hardware and method choices that produced them.

Where Pith is reading between the lines

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

  • Standardized multi-hand benchmarks could accelerate the field in the same way shared datasets did for vision tasks.
  • Greater use of simulation for data generation might reduce reliance on scarce real-world recordings.
  • The identified integration challenges point toward hybrid systems that combine multiple sensing modes with adaptive control.

Load-bearing premise

The papers selected for review are representative enough of all hand types, tasks, and testing methods to show the real overall direction without major gaps from author choices.

What would settle it

A new review that selects a comparable set of papers yet identifies a substantially different set of main barriers or a different ordering of progress would contradict the claimed trajectory.

Figures

Figures reproduced from arXiv: 2605.13925 by Irwin King, Kaizhu Huang, Rui Zhang, Tian Liang, Weiguang Zhao, Xihao Guo.

Figure 1
Figure 1. Figure 1: System-Level Architecture of Dexterous Hands: Actuation, Transmission, and Multimodal Perception [PITH_FULL_IMAGE:figures/full_fig_p003_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Research Workflow on Dexterous Hand manipulation across varying task regimes. In this section, we first summarize a general open-ended workflow shared by dexterous-hand tasks in Section III-A, and then examine the current progress of dexterous-hand research from the perspec￾tive of specific task categories, as shown in [PITH_FULL_IMAGE:figures/full_fig_p006_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Research on Dexterous Hand system level, high-level task planning is decoupled from low-level execution, so task generalization can be separated from policy realization [78]. In learning-augmented systems, high-level planners may further leverage large language mod￾els to decompose complex manipulation goals into ordered sub-goals, while low-level controllers map these sub-goals into executable motor comma… view at source ↗
Figure 2
Figure 2. Figure 2: In the first stage (task planning), problem discovery [PITH_FULL_IMAGE:figures/full_fig_p007_2.png] view at source ↗
Figure 4
Figure 4. Figure 4: In-Hand Manipulation Timeline fusion generates actions directly in the 6D force–torque space, enabling precise tactile manipulation under geometric and fric￾tional uncertainty [93]. DexHandDiff introduces interaction￾aware diffusion planning to mitigate ghost states and improve adaptability under changing targets [94]. ManiDext condi￾tions diffusion policies on object 3D motion trajectories to synthesize h… view at source ↗
Figure 5
Figure 5. Figure 5: Grasp & Pick-and-Place Timeline controllers. OpenVLA [109] establishes the open-source VLA paradigm by fine-tuning vision–language–action models for robotic manipulation, enabling dexterous hands to execute language-conditioned tasks. Octo [110] scales this paradigm to large trajectory datasets and demonstrates cross-embodiment generalization, while subsequent work further expands training data sources by … view at source ↗
Figure 6
Figure 6. Figure 6: Overview of diffusion policies connecting multimodal perception to [PITH_FULL_IMAGE:figures/full_fig_p010_6.png] view at source ↗
Figure 7
Figure 7. Figure 7: General architecture of a Vision-Language-Action (VLA) foundation [PITH_FULL_IMAGE:figures/full_fig_p010_7.png] view at source ↗
Figure 8
Figure 8. Figure 8: Tool Use & Device Operation Timeline manipulation in the real world with minimal data. Xu et al. [160] use hierarchical RL to decouple tool-deformation control from task-level planning, enabling a multifingered hand to learn complex three-way dynamics and non-intuitive tool-use strategies, ultimately achieving robust indirect grasp￾ing with articulated tools. Atar et al. [161] employ sim-to￾real reinforcem… view at source ↗
Figure 9
Figure 9. Figure 9: Bimanual Manipulation Timeline Reinforcement Learning. Reinforcement learning plays a crucial role in bimanual manipulation, enabling coordi￾nated control in high-dimensional coupled systems, adapting to complex contact-rich dynamics, providing flexible online adjustment, and leveraging demonstrations to achieve strong generalization, thereby enhancing the robustness and intelli￾gence of bimanual manipulat… view at source ↗
read the original abstract

Robotic dexterous hands are central to contact-rich manipulation, with rapid progress driven by advances in hardware, sensing, control, simulation, and data generation. However, existing studies are often developed under different assumptions regarding hand embodiments, sensory configurations, task settings, training data, and evaluation protocols, making systematic comparison difficult and obscuring the developmental trajectory of the field. This survey provides a holistic review of dexterous hand research from four complementary aspects. First, we present a hardware-level analysis covering actuation, transmission, perception, and representative hand designs, highlighting the key trade-offs in force capability, compliance, bandwidth, integration, and system complexity. Furthermore, we review control and learning methods for dexterous manipulation from a methodological perspective, grouping representative works by major paradigms and tracing their evolution in chronological order. In addition, we consolidate datasets, modality design, and evaluation practices, which enables methodological progress to be interpreted together with the ways in which it is trained, benchmarked, and assessed. Finally, we discuss the major limitations of current dexterous hand research and summarize the corresponding future directions. By connecting hardware analysis, methodological development, data resources, and evaluation, this survey aims to provide a structured understanding of dexterous hand research and to clarify the most important open challenges for future study.

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

0 major / 3 minor

Summary. The paper is a survey on robotic dexterous hands that reviews the field from four complementary aspects: hardware-level analysis of actuation, transmission, perception, and representative designs with associated trade-offs; methodological review of control and learning methods grouped by major paradigms and traced chronologically; consolidation of datasets, modality design, and evaluation practices; and discussion of current limitations with corresponding future directions. The central aim is to synthesize these elements into a structured understanding of dexterous hand research and to clarify the most important open challenges.

Significance. If the literature coverage is balanced, the survey would be significant for the robotics community by addressing the challenge of systematic comparison across studies that use differing assumptions on embodiments, sensing, tasks, data, and protocols. The four-part structure that explicitly connects hardware analysis, methodological evolution, data resources, and evaluation practices is a strength, as is the chronological tracing of methods, which can help reveal developmental trajectories in a rapidly advancing area.

minor comments (3)
  1. [Hardware-level analysis] § Hardware-level analysis: the discussion of trade-offs in force capability, compliance, bandwidth, integration, and system complexity would benefit from an explicit comparative table of representative hand designs to facilitate cross-referencing with the methods and evaluation sections.
  2. [Control and learning methods] § Control and learning methods: while the grouping by paradigms and chronological tracing is effective, the selection criteria for representative works should be stated more explicitly to allow readers to assess coverage across embodiments and task settings.
  3. [Datasets, modality design, and evaluation] § Datasets and evaluation: the consolidation of evaluation practices is useful, but the survey should include a summary of how many works use each benchmark or protocol to better support claims about the difficulty of systematic comparison.

Simulated Author's Rebuttal

0 responses · 0 unresolved

We thank the referee for the positive and constructive review, which accurately summarizes the scope and structure of our survey. We appreciate the recognition of the four-part organization, the chronological tracing of methods, and the potential value to the robotics community in facilitating systematic comparisons. The recommendation for minor revision is noted, and we address the report below.

Circularity Check

0 steps flagged

No significant circularity

full rationale

This paper is a literature survey synthesizing hardware, methods, datasets, and challenges in dexterous hand research. It contains no derivations, equations, fitted parameters, or quantitative predictions. The central claim is an aim to provide a structured overview, which is self-contained as a review and does not reduce to any self-definition, self-citation chain, or renamed input. No load-bearing steps exist that could exhibit circularity.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

This is a literature survey with no new mathematical derivations, fitted parameters, or postulated entities; all content rests on cited prior work.

pith-pipeline@v0.9.0 · 5539 in / 1019 out tokens · 40200 ms · 2026-05-15T05:41:46.618649+00:00 · methodology

discussion (0)

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

Reference graph

Works this paper leans on

218 extracted references · 218 canonical work pages · 10 internal anchors

  1. [1]

    Hands for dexterous manipulation and robust grasping: a difficult road toward simplicity,

    A. Bicchi, “Hands for dexterous manipulation and robust grasping: a difficult road toward simplicity,”IEEE Transactions on Robotics and Automation, vol. 16, no. 6, pp. 652–662, 2000

    work page 2000

  2. [2]

    Mechanical aspects of robot hands, active hand orthoses, and prostheses: A compar- ative review,

    J. Vertongen, D. G. Kamper, G. Smit, and H. Vallery, “Mechanical aspects of robot hands, active hand orthoses, and prostheses: A compar- ative review,”IEEE/ASME Transactions on Mechatronics (T-MECH), vol. 26, no. 2, pp. 955–965, 2020

    work page 2020

  3. [3]

    Actuated palms for soft robotic hands: review and perspectives,

    M. Pozzi, M. Malvezzi, D. Prattichizzo, and G. Salvietti, “Actuated palms for soft robotic hands: review and perspectives,”IEEE/ASME Transactions on Mechatronics (T-MECH), vol. 29, no. 2, pp. 902–912, 2023

    work page 2023

  4. [4]

    Soft robotics enables neuroprosthetic hand design,

    G. Gu, N. Zhang, C. Chen, H. Xu, and X. Zhu, “Soft robotics enables neuroprosthetic hand design,”ACS Nano, vol. 17, no. 11, pp. 9661– 9672, 2023

    work page 2023

  5. [5]

    Tactile sensing for dexterous in-hand manipulation in robotics—a review,

    H. Yousef, M. Boukallel, and K. Althoefer, “Tactile sensing for dexterous in-hand manipulation in robotics—a review,”Sensors and Actuators A: Physical, vol. 167, no. 2, pp. 171–187, 2011

    work page 2011

  6. [6]

    A review of tactile information: Perception and action through touch,

    Q. Li, O. Kroemer, Z. Su, F. F. Veiga, M. Kaboli, and H. J. Ritter, “A review of tactile information: Perception and action through touch,” IEEE Transactions on Robotics (T-RO), vol. 36, no. 6, pp. 1619–1634, 2020. JOURNAL OF LATEX CLASS FILES, VOL. 18, NO. 9, SEPTEMBER 2020 17

    work page 2020

  7. [7]

    The structure, material and performance of multi-functional tactile sensor and its application in robot field: A review,

    T. Liang, Z. Liu, H. Zhang, X. Zhou, and Y . Liang, “The structure, material and performance of multi-functional tactile sensor and its application in robot field: A review,”Materials Today, 2025

    work page 2025

  8. [8]

    Non-invasive human-machine interface (hmi) systems with hybrid on-body sensors for controlling upper-limb pros- thesis: A review,

    H. Zhou and G. Alici, “Non-invasive human-machine interface (hmi) systems with hybrid on-body sensors for controlling upper-limb pros- thesis: A review,”IEEE Sensors Journal, vol. 22, no. 11, pp. 10292– 10307, 2022

    work page 2022

  9. [9]

    An overview of learning-based dexterous grasping: Recent advances and future directions,

    X. Song, Y . Li, Y . Zhang,et al., “An overview of learning-based dexterous grasping: Recent advances and future directions,”Artificial Intelligence Review, vol. 58, p. 300, 2025

    work page 2025

  10. [10]

    Dexterous manipulation through imitation learning: A survey,

    S. An, Z. Meng, C. Tang, Y . Zhou, T. Liu, F. Ding, S. Zhang, Y . Mu, R. Song, W. Zhang,et al., “Dexterous manipulation through imitation learning: A survey,”arXiv preprint arXiv:2504.03515, 2025

    work page arXiv 2025

  11. [11]

    Human-like dexterous manipulation for anthropomorphic five-fingered hands: A review,

    Y . Huang, D. Fan, H. Duan, D. Yan, W. Qi, J. Sun, Q. Liu, and P. Wang, “Human-like dexterous manipulation for anthropomorphic five-fingered hands: A review,”Biomimetic Intelligence and Robotics, p. 100212, 2025

    work page 2025

  12. [12]

    Interactive imitation learning for dexterous robotic manipulation: Challenges and perspectives – a survey,

    E. Welte and R. Rayyes, “Interactive imitation learning for dexterous robotic manipulation: Challenges and perspectives – a survey,” 2025

    work page 2025

  13. [13]

    Anthropomorphic soft robotic end-effector for use with collaborative robots in the construction industry,

    C. Firth, K. Dunn, M. H. Haeusler, and Y . Sun, “Anthropomorphic soft robotic end-effector for use with collaborative robots in the construction industry,”Automation in Construction, vol. 138, p. 104218, 2022

    work page 2022

  14. [14]

    Towards damage-less robotic fragile fruit grasping: A systematic review on system design, end effector, and visual and tactile feedback,

    Q. Wang, Y . Tu, W. Xu, J. Zhang, A. Knoll, M. Zhou, and Y . Ying, “Towards damage-less robotic fragile fruit grasping: A systematic review on system design, end effector, and visual and tactile feedback,” Journal of Field Robotics, 2025

    work page 2025

  15. [15]

    Empower dexterous robotic hand for human-centric smart manufacturing: A perception and skill learn- ing perspective,

    B. Gao, J. Fan, and P. Zheng, “Empower dexterous robotic hand for human-centric smart manufacturing: A perception and skill learn- ing perspective,”Robotics and Computer-Integrated Manufacturing (RCIM), vol. 93, p. 102909, 2025

    work page 2025

  16. [16]

    Dexterous hand towards intelligent manufac- turing: A review of technologies, trends, and potential applications,

    J. Zhang, H. Zhao, K. Chen, G. Fei, X. Li, Y . Wang, Z. Yang, S. Zheng, S. Liu, and H. Ding, “Dexterous hand towards intelligent manufac- turing: A review of technologies, trends, and potential applications,” Robotics and Computer-Integrated Manufacturing (RCIM), vol. 95, p. 103021, 2025

    work page 2025

  17. [17]

    Robot modeling and control-[book review; m. spong, s. hutchinson, and m. vidyasagar],

    S. B. Skaar, “Robot modeling and control-[book review; m. spong, s. hutchinson, and m. vidyasagar],”IEEE Transactions on Automatic Control (T-ACON), vol. 52, no. 2, pp. 378–379, 2007

    work page 2007

  18. [18]

    The magneto-thermal analysis of a high torque density joint motor for humanoid robots,

    W. Zhang, Z. Yu, X. Chen, and Q. Huang, “The magneto-thermal analysis of a high torque density joint motor for humanoid robots,” inIEEE/RAS International Conference on Humanoid Robots (Hu- manoids), pp. 112–117, 2018

    work page 2018

  19. [19]

    Design and analysis of a permanent magnet frameless motor,

    K. Guo, Y . Guo, S. Fang, C. Li, and W. Xue, “Design and analysis of a permanent magnet frameless motor,”IEEE Journal of Emerging and Selected Topics in Power Electronics, vol. 12, no. 3, pp. 3124–3134, 2024

    work page 2024

  20. [20]

    Simulation analysis of a sandwich cantilever ultrasonic motor for a dexterous prosthetic hand,

    K. Guo, J. Lu, and H. Yang, “Simulation analysis of a sandwich cantilever ultrasonic motor for a dexterous prosthetic hand,”Micro- machines, vol. 14, no. 12, p. 2150, 2023

    work page 2023

  21. [21]

    Miniature robot finger using a micro linear ultrasonic motor and a closed-loop linkage,

    S. Izuhara and T. Mashimo, “Miniature robot finger using a micro linear ultrasonic motor and a closed-loop linkage,” inIEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 1–9, 2018

    work page 2018

  22. [22]

    Development of a miniaturised hydraulic actuation system for artificial hands,

    A. Kargov, T. Werner, C. Pylatiuk, and S. Schulz, “Development of a miniaturised hydraulic actuation system for artificial hands,”Sensors and Actuators A: Physical, vol. 141, no. 2, pp. 548–557, 2008

    work page 2008

  23. [23]

    A dexterous and compliant hand based on soft hydraulic actuation for human inspired fine in-hand manipulation,

    J. Zhou, J. Huang, Q. Dou, P. Abeel, and Y . Liu, “A dexterous and compliant hand based on soft hydraulic actuation for human inspired fine in-hand manipulation,”IEEE Transactions on Robotics (T-RO), 2024

    work page 2024

  24. [24]

    Measurement and modeling of mck- ibben pneumatic artificial muscles,

    C.-P. Chou and B. Hannaford, “Measurement and modeling of mck- ibben pneumatic artificial muscles,”IEEE Transactions on Robotics and Automation, vol. 12, no. 1, pp. 90–102, 1996

    work page 1996

  25. [25]

    Force and moment generation of fiber-reinforced pneumatic soft actuators,

    J. Bishop-Moser, G. Krishnan, and S. Kota, “Force and moment generation of fiber-reinforced pneumatic soft actuators,” inIEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 4460–4465, 2013

    work page 2013

  26. [26]

    Programmable soft robotics actuator with pneumatic networks (pneunets),

    Y . W. Hadi, B. A. Y . Sunarya, A. F. Alifdhyatra, E. Hidayat, J. Salomo, A. Purwidyantri, B. A. Prabowo, and I. Anshori, “Programmable soft robotics actuator with pneumatic networks (pneunets),”IEEE Sensors Journal, vol. 23, no. 17, pp. 19382–19389, 2023

    work page 2023

  27. [27]

    New soft robots really suck: Vacuum- powered systems empower diverse capabilities,

    M. A. Robertson and J. Paik, “New soft robots really suck: Vacuum- powered systems empower diverse capabilities,”Science Robotics, vol. 2, no. 9, p. eaan6357, 2017

    work page 2017

  28. [28]

    Design and analysis of reconfigurable origami-based vacuum pneumatic artificial muscles for versatile robotic system,

    J.-G. Lee and H. Rodrigue, “Design and analysis of reconfigurable origami-based vacuum pneumatic artificial muscles for versatile robotic system,”Soft Robotics, vol. 11, no. 6, pp. 984–993, 2024

    work page 2024

  29. [29]

    3d printable linear soft vacuum actuators: their modeling, performance quantification and application in soft robotic systems,

    C. Tawk, G. M. Spinks, M. in het Panhuis, and G. Alici, “3d printable linear soft vacuum actuators: their modeling, performance quantification and application in soft robotic systems,”IEEE/ASME Transactions on Mechatronics (T-MECH), vol. 24, no. 5, pp. 2118– 2129, 2019

    work page 2019

  30. [30]

    Dexterous robotic hand based on rotational shape memory alloy actuator-joints,

    H. Baek, A. M. Khan, V . Bijalwan, S. Jeon, and Y . Kim, “Dexterous robotic hand based on rotational shape memory alloy actuator-joints,” IEEE Transactions on Medical Robotics and Bionics (T-MRB), vol. 5, no. 4, pp. 1082–1092, 2023

    work page 2023

  31. [31]

    Advances in dielectric elastomers for actua- tors and artificial muscles,

    P. Brochu and Q. Pei, “Advances in dielectric elastomers for actua- tors and artificial muscles,”Macromolecular Rapid Communications, vol. 31, no. 1, pp. 10–36, 2010

    work page 2010

  32. [32]

    A review of the applications and challenges of dielectric elastomer actuators in soft robotics,

    Q. Zhang, W. Yu, J. Zhao, C. Meng, and S. Guo, “A review of the applications and challenges of dielectric elastomer actuators in soft robotics,”Machines, vol. 13, no. 2, p. 101, 2025

    work page 2025

  33. [33]

    Multifunctional magnetic muscles for soft robotics,

    M. Seong, K. Sun, S. Kim, H. Kwon, S.-W. Lee, S. C. Veerla, D. K. Kang, J. Kim, S. Kondaveeti, S. M. Tawfik,et al., “Multifunctional magnetic muscles for soft robotics,”Nature Communications (NC), vol. 15, no. 1, p. 7929, 2024

    work page 2024

  34. [34]

    Piezo robotic hand for motion manipulation from micro to macro,

    S. Zhang, Y . Liu, J. Deng, X. Gao, J. Li, W. Wang, M. Xun, X. Ma, Q. Chang, J. Liu,et al., “Piezo robotic hand for motion manipulation from micro to macro,”Nature Communications (NC), vol. 14, no. 1, p. 500, 2023

    work page 2023

  35. [35]

    Biomimetic rigid-soft finger design for highly dexterous and adaptive robotic hands,

    N. Zhang, P. Zhou, X. Yang, F. Shen, J. Ren, T. Hou, L. Dong, R. Bian, D. Wang, G. Gu,et al., “Biomimetic rigid-soft finger design for highly dexterous and adaptive robotic hands,”Science Advances, vol. 11, no. 17, 2025

    work page 2025

  36. [36]

    A lightweight prosthetic hand with 19-dof dexterity and human-level functions,

    H. Yang, Z. Tao, J. Yang, W. Ma, H. Zhang, M. Xu, M. Wu, S. Sun, H. Jin, W. Li,et al., “A lightweight prosthetic hand with 19-dof dexterity and human-level functions,”Nature Communications (NC), vol. 16, no. 1, p. 955, 2025

    work page 2025

  37. [37]

    Discrete pneumatic-tendon-coupled actuators with inter- connected air circuit for untethered soft robots,

    J. Xia, J. Huang, S. Fu, J. Qu, L. Mo, Y . Li, T. Ren, Y . Yang, Y . Li, and H. Liu, “Discrete pneumatic-tendon-coupled actuators with inter- connected air circuit for untethered soft robots,”Advanced Intelligent Systems, vol. 7, no. 4, 2025

    work page 2025

  38. [38]

    Birglen, T

    L. Birglen, T. Lalibert ´e, and C. Gosselin,Underactuated Robotic Hands, vol. 40 ofSpringer Tracts in Advanced Robotics. Berlin, Heidelberg: Springer, 2008

    work page 2008

  39. [39]

    The dexmart hand: Mechatronic design and experimental evaluation of synergy- based control for human-like grasping,

    G. Palli, C. Melchiorri, G. Vassura, U. Scarcia, L. Moriello, G. Berselli, A. Cavallo, G. De Maria, C. Natale, S. Pirozzi,et al., “The dexmart hand: Mechatronic design and experimental evaluation of synergy- based control for human-like grasping,”The International Journal of Robotics Research, vol. 33, no. 5, pp. 799–824, 2014

    work page 2014

  40. [40]

    Disturbance compensation control for humanoid robot hand driven by tendon-sheath based on disturbance observer,

    M. Yin, H. Wang, D. Shang, M. Li, T. Xu, and X. Wu, “Disturbance compensation control for humanoid robot hand driven by tendon-sheath based on disturbance observer,”IEEE Transactions on Automation Science and Engineering (T-ASE), 2025

    work page 2025

  41. [41]

    Shadowrobot dexterous hand

    S. R. Company, “Shadowrobot dexterous hand.” https://www. shadowrobot.com/dexterous-hand-series/, 2005

    work page 2005

  42. [42]

    The robonaut 2 hand-designed to do work with tools,

    L. B. Bridgwater, C. Ihrke, M. A. Diftler, M. E. Abdallah, N. A. Radford, J. Rogers, S. Yayathi, R. S. Askew, and D. M. Linn, “The robonaut 2 hand-designed to do work with tools,” inIEEE International Conference on Robotics and Automation (ICRA), pp. 3425–3430, 2012

    work page 2012

  43. [43]

    The hand of the dlr hand arm sys- tem: Designed for interaction,

    M. Grebenstein, M. Chalon, W. Friedl, S. Haddadin, T. Wimb ¨ock, G. Hirzinger, and R. Siegwart, “The hand of the dlr hand arm sys- tem: Designed for interaction,”The International Journal of Robotics Research, vol. 31, no. 13, pp. 1531–1555, 2012

    work page 2012

  44. [44]

    Posefusion: Robust object-in-hand pose estimation with selectlstm,

    Y . Tu, J. Jiang, S. Li, N. Hendrich, M. Li, and J. Zhang, “Posefusion: Robust object-in-hand pose estimation with selectlstm,” inIEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 6839–6846, 2023

    work page 2023

  45. [45]

    Svh 5-finger gripping hand

    S. G. . C. KG, “Svh 5-finger gripping hand.” https://schunk.com/de en/gripping-systems/highlights/svh/, 2025

    work page 2025

  46. [46]

    Modeling and realistic simulation of a dexterous robotic hand: Svh hand use-case,

    F. M. Ribeiro, T. Correia, J. Lima, G. Gonc ¸alves, and V . H. Pinto, “Modeling and realistic simulation of a dexterous robotic hand: Svh hand use-case,” inIEEE International Conference on Autonomous Robot Systems and Competitions (ICARSC), pp. 132–138, 2023

    work page 2023

  47. [47]

    Integrated linkage-driven dexterous an- thropomorphic robotic hand,

    U. Kim, D. Jung, H. Jeong, J. Park, H.-M. Jung, J. Cheong, H. R. Choi, H. Do, and C. Park, “Integrated linkage-driven dexterous an- thropomorphic robotic hand,”Nature Communications (NC), vol. 12, no. 1, p. 7177, 2021

    work page 2021

  48. [48]

    Kinetostatic analysis of underactuated fingers,

    L. Birglen and C. M. Gosselin, “Kinetostatic analysis of underactuated fingers,”IEEE Transactions on Robotics and Automation, vol. 20, no. 2, pp. 211–221, 2004

    work page 2004

  49. [49]

    Grasp-state plane analysis of two- phalanx underactuated fingers,

    L. Birglen and C. M. Gosselin, “Grasp-state plane analysis of two- phalanx underactuated fingers,”Mechanism and Machine Theory, vol. 41, no. 7, pp. 807–822, 2006. JOURNAL OF LATEX CLASS FILES, VOL. 18, NO. 9, SEPTEMBER 2020 18

    work page 2006

  50. [50]

    Underactuated finger mechanism using con- tractible slider-cranks and stackable four-bar linkages,

    D. Yoon and Y . Choi, “Underactuated finger mechanism using con- tractible slider-cranks and stackable four-bar linkages,”IEEE/ASME Transactions on Mechatronics (T-MECH), vol. 22, no. 5, pp. 2046– 2057, 2017

    work page 2046

  51. [51]

    Rapid hand: A robust, affordable, perception- integrated, dexterous manipulation platform for generalist robot auton- omy,

    Z. Wan, Z. Bi, Z. Zhou, H. Ren, Y . Zeng, Y . Li, L. Qi, X. Yang, M.-H. Yang, and H. Cheng, “Rapid hand: A robust, affordable, perception- integrated, dexterous manipulation platform for generalist robot auton- omy,”arXiv preprint arXiv:2506.07490, 2025

    work page arXiv 2025

  52. [52]

    A new four-fingered robot hand with dual turning mech- anism,

    M. Higashimori, H. Jeong, I. Ishii, M. Kaneko, A. Namiki, and M. Ishikawa, “A new four-fingered robot hand with dual turning mech- anism,” inIEEE International Conference on Robotics and Automation (ICRA), pp. 2679–2684, 2005

    work page 2005

  53. [53]

    A planetary gear based underactuated self-adaptive robotic finger,

    Q. Quan, Q. Wang, Z. Deng, S. Jiang, X. Hou, and D. Tang, “A planetary gear based underactuated self-adaptive robotic finger,” in IEEE International Conference on Robotics and Biomimetics (ROBIO), pp. 1586–1591, 2013

    work page 2013

  54. [54]

    Externally sensorless dynamic regrasping and manipulation by a triple-fingered robotic hand with torsional fingertip joints,

    K. Tahara, K. Maruta, A. Kawamura, and M. Yamamoto, “Externally sensorless dynamic regrasping and manipulation by a triple-fingered robotic hand with torsional fingertip joints,” inIEEE International Conference on Robotics and Automation (ICRA), pp. 3252–3257, 2012

    work page 2012

  55. [55]

    Design of a roller-based dexterous hand for object grasping and within-hand manipulation,

    S. Yuan, A. D. Epps, J. B. Nowak, and J. K. Salisbury, “Design of a roller-based dexterous hand for object grasping and within-hand manipulation,” inIEEE International Conference on Robotics and Automation (ICRA), pp. 8870–8876, 2020

    work page 2020

  56. [56]

    Proprioception,

    J. C. Tuthill and E. Azim, “Proprioception,”Current Biology, vol. 28, no. 5, pp. R194–R203, 2018

    work page 2018

  57. [57]

    Towards generalized manipulation learning through grasp mechanics-based features and self- supervision,

    A. S. Morgan, W. G. Bircher, and A. M. Dollar, “Towards generalized manipulation learning through grasp mechanics-based features and self- supervision,”IEEE Transactions on Robotics (T-RO), vol. 37, no. 5, pp. 1553–1569, 2021

    work page 2021

  58. [58]

    Dynamic in-hand sliding manipulation,

    J. Shi, J. Z. Woodruff, P. B. Umbanhowar, and K. M. Lynch, “Dynamic in-hand sliding manipulation,”IEEE Transactions on Robotics (T-RO), vol. 33, no. 4, pp. 778–795, 2017

    work page 2017

  59. [59]

    Divide and conquer: 3d point cloud instance segmentation with point-wise binarization,

    W. Zhao, Y . Yan, C. Yang, J. Ye, X. Yang, and K. Huang, “Divide and conquer: 3d point cloud instance segmentation with point-wise binarization,” inIEEE/CVF International Conference on Computer Vision (ICCV), pp. 562–571, 2023

    work page 2023

  60. [60]

    Bfanet: Revisiting 3d semantic segmentation with boundary feature analysis,

    W. Zhao, R. Zhang, Q. Wang, G. Cheng, and K. Huang, “Bfanet: Revisiting 3d semantic segmentation with boundary feature analysis,” inIEEE/CVF conference on Computer Vision and Pattern Recognition (CVPR), pp. 29395–29405, 2025

    work page 2025

  61. [61]

    Development of a neural network- based control system for the dlr-hit ii robot hand using leap motion,

    C. Li, A. Fahmy, and J. Sienz, “Development of a neural network- based control system for the dlr-hit ii robot hand using leap motion,” IEEE Access, vol. 7, pp. 136914–136923, 2019

    work page 2019

  62. [62]

    Self-body discovery based on visuomotor coherence,

    R. Saegusa, G. Metta, and G. Sandini, “Self-body discovery based on visuomotor coherence,” inInternational Conference on Human System Interaction, pp. 356–362, 2010

    work page 2010

  63. [63]

    Multisensory five-finger dexterous hand: The dlr/hit hand ii,

    H. Liu, K. Wu, P. Meusel, N. Seitz, G. Hirzinger, M. Jin, Y . Liu, S. Fan, T. Lan, and Z. Chen, “Multisensory five-finger dexterous hand: The dlr/hit hand ii,” inIEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 3692–3697, 2008

    work page 2008

  64. [64]

    Fas a flexible antagonistic spring element for a high performance over,

    W. Friedl, M. Chalon, J. Reinecke, M. Grebenstein,et al., “Fas a flexible antagonistic spring element for a high performance over,” in IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 1366–1372, 2011

    work page 2011

  65. [65]

    Tactonet: Tactile ordinal network based on unimodal probability for object hardness classification,

    S. Fang, Z. Yi, T. Mi, Z. Zhou, C. Ye, W. Shang, T. Xu, and X. Wu, “Tactonet: Tactile ordinal network based on unimodal probability for object hardness classification,”IEEE Transactions on Automation Science and Engineering (T-ASE), vol. 20, no. 4, pp. 2784–2794, 2022

    work page 2022

  66. [66]

    Tactclnet: Tactile continual learning network based on generative replay for object hardness recognition,

    Y . Liu, Z. Yi, S. Fang, Y . Zhang, F. Wan, Z.-X. Yang, X. Lu, and X. Wu, “Tactclnet: Tactile continual learning network based on generative replay for object hardness recognition,”IEEE Transactions on Automation Science and Engineering (T-ASE), 2024

    work page 2024

  67. [67]

    Recent progresses on flexible tactile sensors,

    Y . Wan, Y . Wang, and C. F. Guo, “Recent progresses on flexible tactile sensors,”Materials Today Physics, vol. 1, pp. 61–73, 2017

    work page 2017

  68. [68]

    Optoelectronically innervated soft prosthetic hand via stretchable optical waveguides,

    H. Zhao, K. O’brien, S. Li, and R. F. Shepherd, “Optoelectronically innervated soft prosthetic hand via stretchable optical waveguides,” Science Robotics, vol. 1, no. 1, 2016

    work page 2016

  69. [69]

    Multimodal tactile sensing fused with vision for dexterous robotic housekeeping,

    Q. Mao, Z. Liao, J. Yuan, and R. Zhu, “Multimodal tactile sensing fused with vision for dexterous robotic housekeeping,”Nature Com- munications (NC), vol. 15, no. 1, p. 6871, 2024

    work page 2024

  70. [70]

    Soft sensors via conductive textile stitching: Enabling strain, tactile, and volumetric sensing,

    J. Seong, J.-H. Lee, and M.-W. Han, “Soft sensors via conductive textile stitching: Enabling strain, tactile, and volumetric sensing,”Advanced Materials Technologies, vol. 10, no. 6, p. 2401306, 2025

    work page 2025

  71. [71]

    A fabric-based multimodal flexible tactile sensor with precise sensing and discrimination capabilities for pressure- proximity-magnetic field signals,

    M. Song, Q. Liu, X. Xu, B. Wang, Y . Lu, L. Yang, X. Liu, Y . Wang, M. Li, and D. Wang, “A fabric-based multimodal flexible tactile sensor with precise sensing and discrimination capabilities for pressure- proximity-magnetic field signals,”Advanced Functional Materials, vol. 35, no. 19, p. 2420445, 2025

    work page 2025

  72. [72]

    Texture recognition based on multi- sensory integration of proprioceptive and tactile signals,

    B. Rostamian, M. Koolani, P. Abdollahzade, M. Lankarany, E. Falotico, M. Amiri, and N. V . Thakor, “Texture recognition based on multi- sensory integration of proprioceptive and tactile signals,”Scientific Reports, vol. 12, no. 1, p. 21690, 2022

    work page 2022

  73. [73]

    A wire-driven miniature five fingered robot hand using elastic elements as joints,

    Y . Ogahara, Y . Kawato, K. Takemura, and T. Maeno, “A wire-driven miniature five fingered robot hand using elastic elements as joints,” in IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), vol. 3, pp. 2672–2677, 2003

    work page 2003

  74. [74]

    A vision-based collocated actuation-sensing scheme for a compliant tendon-driven robotic hand.,

    K. Gilday, T. G. Thuruthel, and F. Iida, “A vision-based collocated actuation-sensing scheme for a compliant tendon-driven robotic hand.,” inRoboSoft, pp. 760–765, 2020

    work page 2020

  75. [75]

    An 18-dof hand integrating force–position multimodal perception using a monocular camera,

    S. Chen, J. Li, Z. Deng, P. Wang, C. Wei, and X. Cao, “An 18-dof hand integrating force–position multimodal perception using a monocular camera,”Nature Communications (NC), vol. 16, no. 1, p. 6801, 2025

    work page 2025

  76. [76]

    Neuromorphic sensorimotor loop embodied by monolithically integrated, low-voltage, soft e-skin,

    W. Wang, Y . Jiang, D. Zhong, Z. Zhang, S. Choudhury, J.-C. Lai, H. Gong, S. Niu, X. Yan, Y . Zheng,et al., “Neuromorphic sensorimotor loop embodied by monolithically integrated, low-voltage, soft e-skin,” Science, vol. 380, no. 6646, pp. 735–742, 2023

    work page 2023

  77. [77]

    Continuous relaxation of symbolic planner for one- shot imitation learning,

    D.-A. Huang, D. Xu, Y . Zhu, A. Garg, S. Savarese, L. Fei-Fei, and J. C. Niebles, “Continuous relaxation of symbolic planner for one- shot imitation learning,” inIEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 2635–2642, 2019

    work page 2019

  78. [78]

    Towards a unified understanding of robot ma- nipulation: A comprehensive survey,

    S. Bai, W. Song, J. Chen, Y . Ji, Z. Zhong, J. Yang, H. Zhao, W. Zhou, W. Zhao, Z. Li,et al., “Towards a unified understanding of robot ma- nipulation: A comprehensive survey,”arXiv preprint arXiv:2510.10903, 2025

    work page arXiv 2025

  79. [79]

    Llm-planner: Few-shot grounded planning for embodied agents with large language models,

    C. H. Song, J. Wu, C. Washington, B. M. Sadler, W.-L. Chao, and Y . Su, “Llm-planner: Few-shot grounded planning for embodied agents with large language models,” inIEEE/CVF International Conference on Computer Vision (ICCV), pp. 2998–3009, 2023

    work page 2023

  80. [80]

    The mod- ular multisensory dlr-hit-hand: hardware and software architecture,

    H. Liu, P. Meusel, G. Hirzinger, M. Jin, Y . Liu, and Z. Xie, “The mod- ular multisensory dlr-hit-hand: hardware and software architecture,” IEEE/ASME Transactions on Mechatronics (T-MECH), vol. 13, no. 4, pp. 461–469, 2009

    work page 2009

Showing first 80 references.