pith. sign in

arxiv: 2601.08056 · v2 · submitted 2026-01-12 · 🧬 q-bio.NC · cs.RO

The embodied brain: Bridging the brain, body, and behavior with neuromechanical digital twins

Sibo Wang-Chen , Pavan Ramdya This is my paper

Pith reviewed 2026-05-16 15:00 UTC · model grok-4.3

classification 🧬 q-bio.NC cs.RO
keywords neuromechanical digital twinsanimal behaviorneural controlbiomechanicscomputational modelingneuroscienceroboticsmachine learning
0
0 comments X

The pith

Neuromechanical digital twins let researchers infer hidden biophysical variables and generate testable hypotheses about animal behavior through simulation.

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

Animal behavior arises from interactions among the nervous system, body, and environment. Neuromechanical digital twins are computational models that embed artificial neural controllers inside realistic body models moving in simulated environments. These models enable calculation of biophysical details such as internal forces or neural signals that experiments struggle to access directly. Systematic changes to elements in the simulation produce predictions about behavior that can then be checked in living animals. The review also describes how the approach supports exchange among neuroscience, robotics, and machine learning while opening paths for healthcare uses.

Core claim

Neuromechanical digital twins are computational models that embed artificial neural controllers within realistic body models in simulated environments. They enable inference of biophysical variables that are difficult to measure experimentally. Through systematic perturbation, one can generate new experimentally testable hypotheses. The models facilitate exchange between neuroscience, robotics, and machine learning and have applications in healthcare. Coupling experimental studies with active probing of these twins is expected to accelerate progress in neuroscience.

What carries the argument

Neuromechanical digital twins: computational models that embed artificial neural controllers within realistic body models in simulated environments to infer hidden variables and test perturbations.

If this is right

  • Researchers gain access to internal variables such as muscle forces or neural activity patterns without needing invasive measurements.
  • Controlled perturbations in the model yield specific predictions about how real animals would adjust their behavior.
  • Knowledge and methods transfer more readily among studies of brains, robots, and learning algorithms.
  • Healthcare simulations become possible for modeling movement disorders or testing interventions.

Where Pith is reading between the lines

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

  • Comparing twins across species could reveal how body shape shapes the evolution of neural control strategies.
  • Real-time data streams from animals might be used to update the twins dynamically for more accurate ongoing predictions.
  • Robotics designs could draw tighter constraints from these models to produce locomotion that matches biological efficiency.

Load-bearing premise

The simulated bodies and neural controllers must accurately capture the real biophysical interactions between the nervous system, body, and environment.

What would settle it

A direct experimental test in a living animal where a behavioral or biophysical prediction derived from perturbing the digital twin does not match observed results.

Figures

Figures reproduced from arXiv: 2601.08056 by Pavan Ramdya, Sibo Wang-Chen.

Figure 1
Figure 1. Figure 1: Parallels between real animals and their neuromechanical digital twins. [PITH_FULL_IMAGE:figures/full_fig_p003_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Prior knowledge of biological systems helps infer structure, behavior, and function from limited [PITH_FULL_IMAGE:figures/full_fig_p004_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Two directions for creating a dialogue between animal experiments and neuromechanical simu [PITH_FULL_IMAGE:figures/full_fig_p005_3.png] view at source ↗
read the original abstract

Animal behavior reflects interactions between the nervous system, body, and environment. Therefore, biomechanics and environmental context must be considered to understand algorithms for behavioral control. Neuromechanical digital twins, namely computational models that embed artificial neural controllers within realistic body models in simulated environments, are a powerful tool for this purpose. Here, we review advances in neuromechanical digital twins while also highlighting emerging opportunities ahead. We first show how these models enable inference of biophysical variables that are difficult to measure experimentally. Through systematic perturbation, one can generate new experimentally testable hypotheses through these models. We then examine how neuromechanical twins facilitate the exchange between neuroscience, robotics, and machine learning, and showcase their applications in healthcare. We envision that coupling experimental studies with active probing of their neuromechanical twins will significantly accelerate progress in neuroscience.

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 / 2 minor

Summary. This review paper presents neuromechanical digital twins—computational models embedding artificial neural controllers within realistic body models in simulated environments—as tools for understanding animal behavior through the interactions of nervous system, body, and environment. It claims these models enable inference of hard-to-measure biophysical variables (e.g., internal forces, proprioceptive signals), generate new experimentally testable hypotheses via systematic perturbations, facilitate exchange between neuroscience, robotics, and machine learning, and support healthcare applications, with a vision for coupling them to experiments to accelerate neuroscience progress.

Significance. If the reviewed models demonstrate quantitative fidelity in capturing neuromechanical interactions, the work could meaningfully bridge disciplines by providing a framework for unmeasurable variable inference and hypothesis generation that transfers to living systems. This has potential implications for behavioral neuroscience, bio-inspired robotics, and clinical modeling, while highlighting opportunities for integrated experimental-computational workflows.

major comments (2)
  1. [Inference and hypothesis generation sections] The central claim that neuromechanical digital twins enable reliable inference of biophysical variables and generation of transferable hypotheses (abstract and main review sections) depends on quantitative validation of simulated outputs against experimental data. The review should explicitly summarize side-by-side comparisons from cited implementations, including metrics such as correlation coefficients or error rates for variables like muscle forces or sensory signals, to substantiate transferability rather than assuming it from model construction.
  2. [Hypothesis generation via perturbations] In the discussion of systematic perturbations for hypothesis generation, the manuscript needs to address cases where virtual ablations or perturbations have been directly compared to real animal experiments under matched conditions. Without this, the assertion that such perturbations produce predictions that hold in living animals remains a load-bearing assumption unsupported by the summarized literature.
minor comments (2)
  1. [Introduction] The introduction would benefit from an explicit early definition of 'neuromechanical digital twin' with a schematic or table contrasting it to related terms like embodied simulation or musculoskeletal models.
  2. [Healthcare applications] Ensure all cited studies in the healthcare applications section include at least one quantitative outcome (e.g., prediction accuracy or clinical correlation) to support the claimed utility.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for their constructive comments, which highlight important aspects of evidence presentation in this review. We address each major comment below and will revise the manuscript to strengthen the discussion of validation and transferability.

read point-by-point responses

  1. Referee: [Inference and hypothesis generation sections] The central claim that neuromechanical digital twins enable reliable inference of biophysical variables and generation of transferable hypotheses (abstract and main review sections) depends on quantitative validation of simulated outputs against experimental data. The review should explicitly summarize side-by-side comparisons from cited implementations, including metrics such as correlation coefficients or error rates for variables like muscle forces or sensory signals, to substantiate transferability rather than assuming it from model construction.

    Authors: We agree that the review would benefit from an explicit compilation of quantitative validations to support claims of inference and transferability. While the cited literature contains such comparisons, the manuscript does not currently summarize them in one place. In the revised version, we will add a dedicated subsection (likely in the inference section) that tabulates or summarizes key side-by-side results from representative implementations, including available metrics such as correlation coefficients, RMSE, or error rates for muscle forces, joint torques, and proprioceptive signals. revision: yes

  2. Referee: [Hypothesis generation via perturbations] In the discussion of systematic perturbations for hypothesis generation, the manuscript needs to address cases where virtual ablations or perturbations have been directly compared to real animal experiments under matched conditions. Without this, the assertion that such perturbations produce predictions that hold in living animals remains a load-bearing assumption unsupported by the summarized literature.

    Authors: We acknowledge the need to ground the hypothesis-generation claims in direct validation examples. The manuscript discusses perturbation approaches but does not systematically review matched virtual-versus-real comparisons. In revision, we will expand the perturbations subsection to explicitly cite and describe existing studies that perform such matched comparisons (e.g., in insect and rodent locomotion models), while noting the current scope and limitations of this evidence to avoid overstating transferability. revision: yes

Circularity Check

0 steps flagged

No circularity: review paper relies on external literature

full rationale

This manuscript is a review that summarizes advances in neuromechanical digital twins from the existing literature. It does not present original equations, fitted parameters, or new derivations whose outputs are then called predictions within the paper itself. All claims about inference of biophysical variables and hypothesis generation are attributed to cited prior implementations rather than being constructed from inputs internal to this text. No self-definitional, fitted-input, or self-citation-load-bearing steps appear in the derivation chain.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 0 invented entities

The review rests on the domain assumption that behavior emerges from brain-body-environment interactions; no new free parameters or invented entities are introduced in the abstract.

axioms (1)
  • domain assumption Animal behavior reflects interactions between the nervous system, body, and environment
    Opening sentence of the abstract; treated as foundational premise for the entire review.

pith-pipeline@v0.9.0 · 5438 in / 1178 out tokens · 39783 ms · 2026-05-16T15:00:23.535671+00:00 · methodology

discussion (0)

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

Lean theorems connected to this paper

Citations machine-checked in the Pith Canon. Every link opens the source theorem in the public Lean library.

What do these tags mean?
matches
The paper's claim is directly supported by a theorem in the formal canon.
supports
The theorem supports part of the paper's argument, but the paper may add assumptions or extra steps.
extends
The paper goes beyond the formal theorem; the theorem is a base layer rather than the whole result.
uses
The paper appears to rely on the theorem as machinery.
contradicts
The paper's claim conflicts with a theorem or certificate in the canon.
unclear
Pith found a possible connection, but the passage is too broad, indirect, or ambiguous to say the theorem truly supports the claim.

Reference graph

Works this paper leans on

56 extracted references · 56 canonical work pages

  1. [1]

    Myosuite–a contact-rich simulation suite for musculoskeletal motor control.arXiv preprint arXiv:2205.13600, 2022

    Vittorio, C., Huawei, W., Guillaume, D., Massimo, S. & Vikash, K. MyoSuite – a contact-rich simulation suite for musculoskeletal motor control.arXiv(2022). URLhttps://arxiv.org/ abs/2205.13600

    work page arXiv 2022

  2. [2]

    elegans brain, body and envi- ronment interactions.Nature Computational Science4, 978–990 (2024)

    Zhao, M.et al.An integrative data-driven model simulating C. elegans brain, body and envi- ronment interactions.Nature Computational Science4, 978–990 (2024). URLhttps://doi.org/ 10.1038/s43588-024-00738-w

    work page doi:10.1038/s43588-024-00738-w 2024

  3. [3]

    Nature632, 594–602 (2024)

    Aldarondo, D.et al.A virtual rodent predicts the structure of neural activity across behaviours. Nature632, 594–602 (2024). URLhttps://doi.org/10.1038/s41586-024-07633-4

    work page doi:10.1038/s41586-024-07633-4 2024

  4. [4]

    URLhttps://doi.org/10.1126/scirobotics.adv4408

    Liu, X.et al.Artificial embodied circuits uncover neural architectures of vertebrate visuomotor behaviors.Science Robotics10(2025). URLhttps://doi.org/10.1126/scirobotics.adv4408

    work page doi:10.1126/scirobotics.adv4408 2025

  5. [5]

    URLhttps://doi.org/10.1038/ s41592-022-01466-7

    Lobato-Rios, V .et al.NeuroMechFly, a neuromechanical model of adult Drosophila melanogaster.Nature Methods19, 620–627 (2022). URLhttps://doi.org/10.1038/ s41592-022-01466-7

    work page 2022

  6. [6]

    URLhttps://doi.org/10.1038/ s41592-024-02497-y

    Wang-Chen, S.et al.NeuroMechFly v2: simulating embodied sensorimotor control in adult Drosophila.Nature Methods21, 2353–2362 (2024). URLhttps://doi.org/10.1038/ s41592-024-02497-y

    work page 2024

  7. [7]

    URLhttps://doi.org/10.1038/s41586-025-09029-4

    Vaxenburg, R.et al.Whole-body physics simulation of fruit fly locomotion.Nature643, 1312–1320 (2025). URLhttps://doi.org/10.1038/s41586-025-09029-4

    work page doi:10.1038/s41586-025-09029-4 2025

  8. [8]

    W., Ghazanfar, A

    Krakauer, J. W., Ghazanfar, A. A., Gomez-Marin, A., MacIver, M. A. & Poeppel, D. Neu- roscience needs behavior: Correcting a reductionist bias.Neuron93, 480–490 (2017). URL https://doi.org/10.1016/j.neuron.2016.12.041

    work page doi:10.1016/j.neuron.2016.12.041 2017

  9. [9]

    URLhttps://doi

    Ayali, A.et al.The comparative investigation of the stick insect and cockroach models in the study of insect locomotion.Current Opinion in Insect Science12, 1–10 (2015). URLhttps://doi. org/10.1016/j.cois.2015.07.004

    work page doi:10.1016/j.cois.2015.07.004 2015

  10. [10]

    Mujoco: A physics en- gine for model-based control, in: 2012 IEEE/RSJ International Con- ference on Intelligent Robots and Systems, IEEE

    Todorov, E., Erez, T. & Tassa, Y. MuJoCo: A physics engine for model-based control. In2012 IEEE/RSJ International Conference on Intelligent Robots and Systems, 5026–5033 (2012). URLhttps: //doi.org/10.1109/IROS.2012.6386109

    work page doi:10.1109/iros.2012.6386109 2012

  11. [11]

    InThirty-fifth Conference on Neural Information Processing Systems(2021)

    Makoviychuk, V .et al.Isaac Gym: High performance GPU based physics simulation for robot learning. InThirty-fifth Conference on Neural Information Processing Systems(2021). URLhttps: //openreview.net/forum?id=fgFBtYgJQX_

    work page 2021

  12. [12]

    OpenSim: Open-source software to create and an- alyze dynamic simulations of movement,

    Delp, S. L.et al.OpenSim: Open-source software to create and analyze dynamic simulations of movement.IEEE Transactions on Biomedical Engineering54, 1940–1950 (2007). URLhttps: //doi.org/10.1109/TBME.2007.901024

    work page doi:10.1109/tbme.2007.901024 1940

  13. [13]

    & Ijspeert, A

    Arreguit, J., Tata Ramalingasetty, S. & Ijspeert, A. FARMS: Framework for animal and robot modeling and simulation.bioRxiv(2023). URLhttps://www.biorxiv.org/content/10.1101/ 2023.09.25.559130

    work page 2023

  14. [14]

    G.et al.Musculoskeletal simulation of limb movement biomechanics in Drosophila melanogaster.arXiv(2025)

    ¨Ozdil, P . G.et al.Musculoskeletal simulation of limb movement biomechanics in Drosophila melanogaster.arXiv(2025). URLhttps://arxiv.org/abs/2509.06426

    work page arXiv 2025

  15. [15]

    URLhttps://doi.org/10.7554/eLife.99005.2

    Karashchuk, L.et al.Sensorimotor delays constrain robust locomotion in a 3D kinematic model of fly walking.eLife(2025). URLhttps://doi.org/10.7554/eLife.99005.2. Reviewed preprint

    work page doi:10.7554/elife.99005.2 2025

  16. [16]

    G., Arreguit, J., Scherrer, C., Ijspeert, A

    ¨Ozdil, P . G., Arreguit, J., Scherrer, C., Ijspeert, A. & Ramdya, P . Centralized brain networks underlie body part coordination during grooming.bioRxiv(2024). URLhttps://www.biorxiv. org/content/10.1101/2024.12.17.628844. 14

    work page doi:10.1101/2024.12.17.628844 2024

  17. [17]

    A., Szczecinski, N

    Goldsmith, C. A., Szczecinski, N. S. & Quinn, R. D. Neurodynamic modeling of the fruit fly Drosophila melanogaster.Bioinspiration & Biomimetics15, 065003 (2020). URLhttp://doi. org/10.1088/1748-3190/ab9e52

    work page doi:10.1088/1748-3190/ab9e52 2020

  18. [18]

    & de Gardelle, V

    DeWolf, T.et al.Neuro-musculoskeletal modeling reveals muscle-level neural dynamics of adaptive learning in sensorimotor cortex (2024). URLhttps://doi.org/10.1101/2024.09. 11.612513

    work page doi:10.1101/2024.09 2024

  19. [19]

    T.et al.On all fours: A 3D framework to study closed-loop control of quadrupedal mouse locomotion

    Ramalingasetty, S. T.et al.On all fours: A 3D framework to study closed-loop control of quadrupedal mouse locomotion. InThe 2024 Conference on Artificial Life, ALIFE 2024 (2024). URLhttps://doi.org/10.1162/isal_a_00788

    work page doi:10.1162/isal_a_00788 2024

  20. [20]

    URLhttps://doi.org/10.1016/j.isci.2025.112056

    Ravel, G.et al.Modeling zebrafish escape swim reveals maximum neuromuscular power out- put and efficient body movement adaptation to increased water viscosity.iScience28, 112056 (2025). URLhttps://doi.org/10.1016/j.isci.2025.112056

    work page doi:10.1016/j.isci.2025.112056 2025

  21. [21]

    F., Kacer, E

    Roussel, Y., Gaudreau, S. F., Kacer, E. R., Sengupta, M. & Bui, T. V . Modeling spinal locomotor circuits for movements in developing zebrafish.eLife10(2021). URLhttps://doi.org/10. 7554/eLife.67453

    work page 2021

  22. [22]

    URLhttps://doi.org/10.1371/ journal.pcbi.1013171

    Zhao, P .et al.The roles of feedback loops in the Caenorhabditis elegans rhythmic forward locomotion.PLOS Computational Biology21, e1013171 (2025). URLhttps://doi.org/10.1371/ journal.pcbi.1013171

    work page 2025

  23. [23]

    Olivares, E., Izquierdo, E. J. & Beer, R. D. A neuromechanical model of multiple network rhyth- mic pattern generators for forward locomotion in C. elegans.Frontiers in Computational Neuro- science15(2021). URLhttps://doi.org/10.3389/fncom.2021.572339

    work page doi:10.3389/fncom.2021.572339 2021

  24. [24]

    Chari and L

    Pazzaglia, A.et al.Balancing central control and sensory feedback produces adaptable and robust locomotor patterns in a spiking, neuromechanical model of the salamander spinal cord. PLOS Computational Biology21, e1012101 (2025). URLhttps://doi.org/10.1371/journal. pcbi.1012101

    work page doi:10.1371/journal 2025

  25. [25]

    URLhttps://doi.org/10.1126/ scirobotics.abf6354

    Thandiackal, R.et al.Emergence of robust self-organized undulatory swimming based on lo- cal hydrodynamic force sensing.Science Robotics6(2021). URLhttps://doi.org/10.1126/ scirobotics.abf6354

    work page 2021

  26. [26]

    & Schreiber, S

    Pallasdies, F., Norton, P ., Schleimer, J.-H. & Schreiber, S. Neuronal synchronization and bidi- rectional activity spread explain efficient swimming in a whole-body model of hydrozoan jel- lyfish.The Journal of Neuroscience45, e1370242025 (2025). URLhttps://doi.org/10.1523/ JNEUROSCI.1370-24.2025

    work page 2025

  27. [27]

    P .et al.Neuromechanical wave resonance in jellyfish swimming.Proceedings of the National Academy of Sciences118(2021)

    Hoover, A. P .et al.Neuromechanical wave resonance in jellyfish swimming.Proceedings of the National Academy of Sciences118(2021). URLhttps://doi.org/10.1073/pnas.2020025118

    work page doi:10.1073/pnas.2020025118 2021

  28. [28]

    URLhttps://doi.org/10.1016/j.cell.2024.02.036

    Marin Vargas, A.et al.Task-driven neural network models predict neural dynamics of proprio- ception.Cell187, 1745–1761.e19 (2024). URLhttps://doi.org/10.1016/j.cell.2024.02.036

    work page doi:10.1016/j.cell.2024.02.036 2024

  29. [29]

    & Reimann, H

    Ramadan, R., Meischein, F. & Reimann, H. High-level motor planning allows flexible walking at different gait patterns in a neuromechanical model.Frontiers in Bioengineering and Biotechnol- ogy10(2022). URLhttps://doi.org/10.3389/fbioe.2022.959357

    work page doi:10.3389/fbioe.2022.959357 2022

  30. [30]

    & Ijspeert, A

    Di Russo, A., Stanev, D., Armand, S. & Ijspeert, A. Sensory modulation of gait characteristics in human locomotion: A neuromusculoskeletal modeling study.PLOS Computational Biology17, e1008594 (2021). URLhttps://doi.org/10.1371/journal.pcbi.1008594

    work page doi:10.1371/journal.pcbi.1008594 2021

  31. [31]

    Guillaume Bellegarda, Milad Shafiee, and Auke Ijspeert

    Bellegarda, G. & Ijspeert, A. CPG-RL: Learning central pattern generators for quadruped lo- comotion.IEEE Robotics and Automation Letters7, 12547–12554 (2022). URLhttps://doi.org/ 10.1109/LRA.2022.3218167. 15

    work page doi:10.1109/lra.2022.3218167 2022

  32. [32]

    InBiomimetic and Biohybrid Systems, 68–79 (2022)

    Stentiford, R.et al.Integrating spiking neural networks and deep learning algorithms on the Neurorobotics Platform. InBiomimetic and Biohybrid Systems, 68–79 (2022). URLhttps://doi. org/10.1007/978-3-031-20470-8_7

    work page doi:10.1007/978-3-031-20470-8_7 2022

  33. [33]

    URLhttps://doi.org/10.1038/s41598-021-90058-0

    Stark, H.et al.A three-dimensional musculoskeletal model of the dog.Scientific Reports11 (2021). URLhttps://doi.org/10.1038/s41598-021-90058-0

    work page doi:10.1038/s41598-021-90058-0 2021

  34. [34]

    URLhttps: //arxiv.org/abs/2402.18103

    Elisha, G.et al.Neurological disorders leading to mechanical dysfunction of the esophagus: an emergent behavior of a neuromechanical dynamical system.arXiv(2024). URLhttps: //arxiv.org/abs/2402.18103

    work page arXiv 2024

  35. [35]

    K., Sridharan, K

    Singh, A. K., Sridharan, K. S., Wu, S., Tirosh, O. & Raghavan, M. In-silico neuro-musculoskeletal model demonstrates spasticity progression with descending motor tracts loss in simulated clin- ical triage.Computers in Biology and Medicine192, 110270 (2025). URLhttps://doi.org/10. 1016/j.compbiomed.2025.110270

    work page arXiv 2025

  36. [36]

    URLhttps://doi.org/10.36227/ techrxiv.173397962.28177284/v1

    Sartori, M.et al.CEINMS-RT: an open-source framework for the continuous neuro-mechanical model-based control of wearable robots.TechRxiv(2024). URLhttps://doi.org/10.36227/ techrxiv.173397962.28177284/v1

    work page arXiv 2024

  37. [37]

    & Todoh, M

    Zhao, Y., Zhang, M., Wu, H., He, X. & Todoh, M. Neuromechanics-based neural feedback controller for planar arm reaching movements.Bioengineering10, 436 (2023). URLhttps: //doi.org/10.3390/bioengineering10040436

    work page doi:10.3390/bioengineering10040436 2023

  38. [38]

    URLhttps://doi.org/10.1113/JP282609

    Bruel, A.et al.Investigation of neural and biomechanical impairments leading to patholog- ical toe and heel gaits using neuromusculoskeletal modelling.The Journal of Physiology600, 2691–2712 (2022). URLhttps://doi.org/10.1113/JP282609

    work page doi:10.1113/jp282609 2022

  39. [39]

    URLhttps://doi.org/10.1109/TASE.2020.3033664

    Zhang, L.et al.Ankle joint torque estimation using an EMG-driven neuromusculoskeletal model and an artificial neural network model.IEEE Transactions on Automation Science and Engineering18, 564–573 (2021). URLhttps://doi.org/10.1109/TASE.2020.3033664

    work page doi:10.1109/tase.2020.3033664 2021

  40. [40]

    Cotton, R. J. KinTwin: Imitation learning with torque and muscle driven biomechanical models enables precise replication of able-bodied and impaired movement from markerless motion capture.arXiv(2025). URLhttps://arxiv.org/abs/2505.13436

    work page arXiv 2025

  41. [41]

    URLhttps://doi

    Feldotto, B.et al.Deploying and optimizing embodied simulations of large-scale spiking neural networks on HPC infrastructure.Frontiers in Neuroinformatics16(2022). URLhttps://doi. org/10.3389/fninf.2022.884180

    work page doi:10.3389/fninf.2022.884180 2022

  42. [42]

    URLhttps://arxiv.org/abs/2203.17138

    Bohez, S.et al.Imitate and Repurpose: Learning reusable robot movement skills from human and animal behaviors.arXiv(2022). URLhttps://arxiv.org/abs/2203.17138

    work page arXiv 2022

  43. [43]

    Robotics: Science and Systems (2020) https://doi.org/10.15607/RSS.2020.XVI.064

    Bin Peng, X.et al.Learning agile robotic locomotion skills by imitating animals. InRobotics: Science and Systems XVI, RSS2020 (2020). URLhttps://doi.org/10.15607/RSS.2020.XVI.064

    work page doi:10.15607/rss.2020.xvi.064 2020

  44. [44]

    URLhttps://doi.org/10

    Bonanno, M.et al.Neural control meets biomechanics in the motor assessment of neurological disorders: a narrative review.Frontiers in Neural Circuits19(2025). URLhttps://doi.org/10. 3389/fncir.2025.1608328

    work page arXiv 2025

  45. [45]

    Catalyzing next- generation artificial intelligence through NeuroAI.Nature Communications, 14:1597, 2023

    Zador, A.et al.Catalyzing next-generation artificial intelligence through NeuroAI.Nature Communications14(2023). URLhttps://doi.org/10.1038/s41467-023-37180-x

    work page doi:10.1038/s41467-023-37180-x 2023

  46. [46]

    & Ijspeert, A

    Ramdya, P . & Ijspeert, A. J. The neuromechanics of animal locomotion: From biology to robotics and back.Science Robotics8(2023). URLhttps://doi.org/10.1126/scirobotics.adg0279

    work page doi:10.1126/scirobotics.adg0279 2023

  47. [47]

    & Ivanenko, Y

    Taiar, R., Bernardo-Filho, M., Sa ˜nudo, B. & Ivanenko, Y. Editorial: The relationship between neural circuitry and biomechanical action.Frontiers in Human Neuroscience16(2022). URL https://doi.org/10.3389/fnhum.2022.838028. 16

    work page doi:10.3389/fnhum.2022.838028 2022

  48. [48]

    & Flores, P

    Rodrigues da Silva, M., Marques, F., Tavares da Silva, M. & Flores, P . A comprehensive review on biomechanical modeling applied to device-assisted locomotion.Archives of Com- putational Methods in Engineering30, 1897–1960 (2022). URLhttps://doi.org/10.1007/ s11831-022-09856-y

    work page 1960

  49. [49]

    & Falisse, A

    De Groote, F. & Falisse, A. Perspective on musculoskeletal modelling and predictive simula- tions of human movement to assess the neuromechanics of gait.Proceedings of the Royal Society B: Biological Sciences288, 20202432 (2021). URLhttps://doi.org/10.1098/rspb.2020.2432

    work page doi:10.1098/rspb.2020.2432 2021

  50. [50]

    H., Coppack, R

    Smith, S. H., Coppack, R. J., van den Bogert, A. J., Bennett, A. N. & Bull, A. M. Review of musculoskeletal modelling in a clinical setting: Current use in rehabilitation design, surgical decision making and healthcare interventions.Clinical Biomechanics83, 105292 (2021). URL https://doi.org/10.1016/j.clinbiomech.2021.105292

    work page doi:10.1016/j.clinbiomech.2021.105292 2021

  51. [51]

    D., Lautzenheiser, S

    Sylvester, A. D., Lautzenheiser, S. G. & Kramer, P . A. A review of musculoskeletal modelling of human locomotion.Interface Focus11, 20200060 (2021). URLhttps://doi.org/10.1098/rsfs. 2020.0060

    work page doi:10.1098/rsfs 2021

  52. [52]

    URLhttps://doi.org/10.3389/fnbot.2020.570308

    Chen, K.et al.Neurorobots as a means toward neuroethology and explainable AI.Frontiers in Neurorobotics14(2020). URLhttps://doi.org/10.3389/fnbot.2020.570308

    work page doi:10.3389/fnbot.2020.570308 2020

  53. [53]

    & Wayne, G

    Merel, J., Botvinick, M. & Wayne, G. Hierarchical motor control in mammals and machines. Nature Communications10(2019). URLhttps://doi.org/10.1038/s41467-019-13239-6

    work page doi:10.1038/s41467-019-13239-6 2019

  54. [54]

    K.et al.A Drosophila computational brain model reveals sensorimotor processing

    Shiu, P . K.et al.A Drosophila computational brain model reveals sensorimotor processing. Nature634, 210–219 (2024). URLhttps://doi.org/10.1038/s41586-024-07763-9

    work page doi:10.1038/s41586-024-07763-9 2024

  55. [55]

    K.et al.Connectome-constrained networks predict neural activity across the fly visual system.Nature634, 1132–1140 (2024)

    Lappalainen, J. K.et al.Connectome-constrained networks predict neural activity across the fly visual system.Nature634, 1132–1140 (2024). URLhttps://doi.org/10.1038/ s41586-024-07939-3

    work page 2024

  56. [56]

    If deep learning is the answer, what is the question?

    Saxe, A., Nelli, S. & Summerfield, C. If deep learning is the answer, what is the question?Nature Reviews Neuroscience22, 55–67 (2020). URLhttp://doi.org/10.1038/s41583-020-00395-8. 17

    work page doi:10.1038/s41583-020-00395-8 2020