The DOI matches its Crossref record; 158 of the 159 references it cites were found in a registry or an index, and 1 are not checked yet; 36 of the 82 sources its claims cite were checked for support.
NeuroMechFly v2: simulating embodied sensorimotor control in adult Drosophila
Open accessPublished version of a preprint
Abstract
We present NeuroMechFly v2, a framework that expands Drosophila neuromechanical modeling by enabling visual and olfactory sensing, ascending motor feedback, and complex terrains that can be navigated using leg adhesion. We illustrate its capabilities by first constructing biologically inspired locomotor controllers that use ascending motor feedback to perform path integration and head stabilization. Then, we add visual and olfactory sensing to this controller and train it using reinforcement learning to perform a multimodal navigation task in closed loop. Finally, we illustrate more biorealistic modeling in two ways: our model navigates a complex odor plume using a Drosophila odor taxis strategy, and it uses a connectome-constrained visual system network to follow another simulated fly. With this framework, NeuroMechFly can be used to accelerate the discovery of explanatory models of the nervous system and to develop machine learning-based controllers for autonomous artificial agents and robots.
Verified 2026-10-12 · 1 reference not checked yet
Overview
CoChat Summary
TL;DR
NeuroMechFly 2.0 (FlyGym) expands the Drosophila neuromechanical model with MuJoCo physics, leg adhesion, visual/olfactory sensing, rugged terrain, and a Gymnasium-compatible interface for hierarchical sensorimotor control. It demonstrates terrain-dependent locomotor controller trade-offs and closed-loop multimodal navigation using a reinforcement-learning-trained controller.
Key findings
- Leg adhesion (20–40 mN) enabled 3D locomotion: without adhesion the fly failed to sustain forward locomotion at slopes as small as 5°, while with adhesion it could locomote on inclines up to 120° and occasionally beyond 90°.
- Benchmarking three controllers over flat, gapped, blocks, and mixed terrain (N = 20 trials each) showed the CPG controller was fast, the rule-based controller was more robust on rugged terrain, and the hybrid controller had higher baseline speed than the rule-based controller and covered greater distances on rugged terrain.
- Vision and olfaction were implemented with 721 ommatidia per eye, a ~270° combined azimuth, ~17° binocular overlap, and a 7:3 yellow:pale ommatidia ratio; virtual odor sensors on antennae and maxillary palps supported visual object chasing and olfactory chemotaxis.
- A hierarchical RL controller solved a multimodal task—avoiding a visual obstacle while approaching an attractive odor source over rugged terrain—using a vision model trained on 10,000 samples for 150 epochs and an RL decision module trained for 266,000 decision steps (~3.7 simulated hours).
Methods
- FlyGym is a Python package built on MuJoCo and dm_control, complying with the Gymnasium MDP interface; actions include joint actuation signals and leg adhesion on/off, while observations include joint states, fly state, ground reaction forces, and optional visual/olfactory inputs.
- The biomechanical model was updated with antennal segmentation, neck/head/leg adjustments, and leg adhesion via MuJoCo actuators; stepping kinematics were derived from recordings of tethered flies, and terrains included flat, gapped, blocks, and mixed surfaces.
- Controllers included CPG-based, rule-based (Walknet-inspired), and hybrid CPG-plus-sensory-feedback strategies; turning was controlled by a two-dimensional descending signal, and the multimodal RL model used a graph-convolution vision module plus an SAC-trained MLP decision module.
Limitations
- Stated: the model cannot fully represent real biological adhesion; lift-off mechanisms for Drosophila are unknown, so adhesion was abstracted as on during stance and off during swing; dorsal rim area ommatidia were not implemented; odor chemotaxis was simplified by the absence of complex plumes; and behaviors involving wings/halteres (flight), abdomen (egg-laying), and proboscis (feeding) were not yet demonstrated.
- Stated future improvements: GPU-accelerated/differentiable simulation, connectome-constrained neural circuits, and musculoskeletal/tendon-muscle models.
- Evident: visual color uses green and blue channels as proxies for yellow- and pale-type ommatidia rather than full spectral reflectance, and the RL navigation task used a simplified mixed terrain with reduced gap widths (0.2 mm) and block heights (0.3 mm); all reported results are simulation-only, with no real-fly validation of the full hierarchical controller presented.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
8 Valid · 20 Not valid · 21 Not checked · 79 Own results and interpretations
The cited sources that could be checked couldn’t confirm or dispute this claim.
In the paper
“We opted for a relatively high adhesion force (20-40 mN) to be consistent with the high, but somewhat variable, forces reported across insect species 52,51 .”
What the sources say
- Could not verifycites [52] Cowley, B. R. et al. Mapping model units to visual neurons reveals population code for social behaviour. Nature 629, 1100–1108 (2024). sourceExperimental — accuracy not yet measured
The Methods sections on courtship experiments and flies (page unavailable) describe behavioural recordings and fly handling, not adhesion measurements. Searches for “adhesion force,” “20–40 mN,” and insect attachment forces found no passage supporting the stated force or its variation across species. (LLM, conf=0.77)
- Could not verifycites [51] Demir, M., Kadakia, N., Anderson, H. D., Clark, D. A. & Emonet, T. Walking Drosophila navigate complex plumes using stochastic decisions biased by the timing of odor encounters. Elife 9, e57524 (2020). sourceExperimental — accuracy not yet measured
The citing authors describe their own choice of adhesion force; the citation is offered for reported forces across insect species. The source’s Materials and methods describes walking-fly odor experiments, and searches for “adhesion force,” “20-40 mN,” and insect adhesion forces found no passage addressing those measurements. (LLM, conf=0.75)
plainstates an association- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Could not verify
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“The adult fruit fly, Drosophila melanogaster , is an ideal organism for modeling biological hierarchical controller in its entirety.”
What the sources say
- Partly supportedcites [24] Dorkenwald, S. et al. Neuronal wiring diagram of an adult brain. Nature 634, 124–138 (2024). sourceExperimental — accuracy not yet measured
The Discussion (Connectome analysis; page not supplied) says the whole-brain wiring diagram enables brain simulations, supporting the idea that adult Drosophila is useful for modeling neural function. It does not describe a biological hierarchical controller modeled in its entirety; it notes that the diagram excludes the ventral nerve cord, which could be required for an entire nervous-system connectome. (LLM, conf=0.86)
- Not checked — no full text of the sourcecites [27] Jenett, A. et al. A GAL4-driver line resource for Drosophila neurobiology. Cell Rep. 2, 991–1001 (2012). source
- Not checked — no full text of the sourcecites [35] Drechsler, P. & Federle, W. Biomechanics of smooth adhesive pads in insects: Influence of tarsal secretion on attachment performance. J. Comp. Physiol. A Neuroethol. Sens. Neural Behav. Physiol. 192, 1213–1222 (2006). source
plain- Asserted: passes — The authors put it forward as true.
- Checkable: unclear — It is unclear whether it could be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
The cited sources that could be checked couldn’t confirm or dispute this claim.
In the paper
“Second, we moved the simulation framework from PyBullet to MuJoCo 45 , a more widely used physics simulator.”
What the sources say
- Could not verifycites [45] Cognigni, P., Felsenberg, J. & Waddell, S. Do the right thing: neural network mechanisms of memory formation, expression and update in Drosophila. Curr. Opinion Neurobiol. 49, 51–58 (2018). sourceExperimental — accuracy not yet measured
The Introduction and Conclusions discuss neural mechanisms of memory in Drosophila, not physics simulation. Searches for PyBullet, MuJoCo, and a change of simulation framework found no relevant passage in our copy. The source therefore does not verify the cited statement. (LLM, conf=0.78)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Could not verify
The cited sources that could be checked couldn’t confirm or dispute this claim.
In the paper
“The modularity of our framework makes it possible for users to implement additional signal processing by downstream olfactory centers (e.g., lateral horn or mushroom body 71,72 ).”
What the sources say
- Could not verifycites [71] Haarnoja, T., Zhou, A., Abbeel, P. & Levine, S. Soft Actor-Critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor. In Proceedings of the 35th International Conference on Machine Learning (PMLR, 2018). sourceExperimental — accuracy not yet measured
The Asynchronous Learning System section (pp. 2–3) describes separate subsystems for robotic reinforcement learning, not a framework for modeling olfactory centers. Searches for lateral horn, mushroom body, and downstream olfactory signal processing found no passage in our copy addressing the attributed claim. (LLM, conf=0.78)
- Not matchedcites [72] Holl, P., Thuerey, N. & Koltun, V. Learning to control PDEs with differentiable physics. In International Conference on Learning Representations (2020); https://openreview.net/forum?id=HyeSin4FPB
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Could not verify
The cited sources that could be checked couldn’t confirm or dispute this claim.
In the paper
“Additionally, signals like ascending motor-related feedback 79 and those encoding internal states 33 or learning-based 72 changes in sensory valence can be easily incorporated into user-defined controllers.”
What the sources say
- Could not verifycites [79] Wang-Chen, S. et al. Code accompanying ‘NeuroMechFly v2, simulating embodied sensorimotor control in adult Drosophila’. Zenodo https://doi.org/10.5281/zenodo.12973000 (2024). sourceExperimental — accuracy not yet measured
The Zenodo Description identifies this as a snapshot of FlyGym code, and the file listing names controller examples. Neither passage addresses whether ascending motor-related feedback, internal-state signals, or learned changes in sensory valence can be easily incorporated into user-defined controllers. Searches for those signals and sensory valence found no supporting passage in our copy. (LLM, conf=0.74)
- Not checked — no full text of the sourcecites [33] Todorov, E., Erez, T. & Tassa, Y. MuJoCo: a physics engine for model-based control. In 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems. https://doi.org/10.1109/IROS.2012.6386109 (IEEE, 2012). source
- Not matchedcites [72] Holl, P., Thuerey, N. & Koltun, V. Learning to control PDEs with differentiable physics. In International Conference on Learning Representations (2020); https://openreview.net/forum?id=HyeSin4FPB
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Could not verify
50 more claims
Create a free account to see all 128 claims and every source verdict.
- It may state two separate claims as one. 34
- Probably not a substantial claim. 50
- The quote only partly states this claim. 2
Citations
Cites
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
PyTorch: An Imperative Style, High-Performance Deep Learning Library
Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., Antiga, L., et al. (2019) · arXiv · doi:10.48550/arxiv.1912.01703 · Cited by 31,473
Semi-supervised classification with graph convolutional networks
Kipf, T. N., & Welling, M. (2016) · arXiv · doi:10.48550/arxiv.1609.02907 · Cited by 24,853
A robust layered control system for a mobile robot
Brooks, R. (1986) · IEEE Journal on Robotics and Automation · doi:10.1109/jra.1986.1087032 · Cited by 7,799
Ultrasensitive fluorescent proteins for imaging neuronal activity
Chen, T.-W., Wardill, T. J., Sun, Y., Pulver, S. R., Renninger, S. L., Baohan, A., Schreiter, E. R., Kerr, R. A., Orger, M. B., Jayaraman, V., et al. (2013) · Nature · doi:10.1038/nature12354 · Cited by 6,474 · cited 1×
“Additionally, thousands of transgenic fly lines enable the repeated targeting of sparse sets of neurons 27 for optical activation 28 , silencing 29 and recordings 30 .”
Soft actor-critic Off-policy maximum entropy deep reinforcement learning with a stochastic actor
Haarnoja, T., Zhou, A., Abbeel, P., & Levine, S. (2018) · arXiv · doi:10.48550/arxiv.1801.01290 · Cited by 5,594
MuJoCo: A physics engine for model-based control
Todorov, E., Erez, T., & Tassa, Y. (2012) · 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems · doi:10.1109/iros.2012.6386109 · Cited by 4,767 · cited 7×
“MuJoCo is known for better stability and performance 34 and supports a wider range of actuators including those for leg adhesion.”
InfluentialIndependent optical excitation of distinct neural populations
Klapoetke, N. C., Murata, Y., Kim, S. S., Pulver, S. R., Birdsey-Benson, A., Cho, Y. K., Morimoto, T. K., Chuong, A. S., Carpenter, E. J., Tian, Z., et al. (2014) · Nature Methods · doi:10.1038/nmeth.2836 · Cited by 2,344 · cited 1×
“Additionally, thousands of transgenic fly lines enable the repeated targeting of sparse sets of neurons 27 for optical activation 28 , silencing 29 and recordings 30 .”
Azevedo, F. A. C., Carvalho, L. R. B., Grinberg, L. T., Farfel, J. M., Ferretti, R. E. L., Leite, R. E. P., Filho, W. J., Lent, R., & Herculano‐Houzel, S. (2009) · Journal of Comparative Neurology · doi:10.1002/cne.21974 · Cited by 2,337
Central pattern generators for locomotion control in animals and robots: A review
Ijspeert, A. J. (2008) · Neural Networks · doi:10.1016/j.neunet.2008.03.014 · Cited by 1,853
Research works printed but not linked: 3
- Ho, J. & Ermon, S. Generative adversarial imitation learning. In Proc. 30th International Conference on Neural Information Processing Systems. 4572–4580 (Curran Associates, 2016).
- Caggiano, V., Wang, H., Durandau, G., Sartori, M. & Kumar, V. MyoSuite: a contact-rich simulation suite for musculoskeletal motor control. Proc. Mach. Learn. Res. 168, 492–507 (2022).
- Holl, P., Thuerey, N. & Koltun, V. Learning to control PDEs with differentiable physics. In International Conference on Learning Representations (2020); https://openreview.net/forum?id=HyeSin4FPB
Cited by
Connectomic reconstruction of a female Drosophila ventral nerve cord
Azevedo, A., Lesser, E., Phelps, J. S., Mark, B., Elabbady, L., Kuroda, S., Sustar, A., Moussa, A., Khandelwal, A., Dallmann, C. J., et al. (2024) · Nature · doi:10.1038/s41586-024-07389-x · Cited by 120
Whole-body physics simulation of fruit fly locomotion
Vaxenburg, R., Siwanowicz, I., Merel, J., Robie, A. A., Morrow, C. M., Novati, G., Stefanidi, Z., Both, G., Card, G. M., Reiser, M. B., et al. (2025) · Nature · doi:10.1038/s41586-025-09029-4 · Cited by 109
Whole-body simulation of realistic fruit fly locomotion with deep reinforcement learningPreprint
Vaxenburg, R., Siwanowicz, I., Merel, J., Robie, A. A., Morrow, C. M., Novati, G., Stefanidi, Z., Both, G., Card, G. M., Reiser, M. B., et al. (2024) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2024.03.11.584515 · Cited by 23
Synaptic-resolution connectomics: towards large brains and connectomic screening
Helmstaedter, M. N. (2025) · Nature reviews. Neuroscience · doi:10.1038/s41583-025-00998-z · Cited by 30
“How many synapses, and which, need to be changed or created or removed to imprint a particular experience?”
Artificial embodied circuits uncover neural architectures of vertebrate visuomotor behaviors
Liu, X., Loring, M. D., Zunino, L., Fouke, K. E., Longchamp, F. A., Bernardino, A., Ijspeert, A. J., & Naumann, E. A. (2025) · Science Robotics · doi:10.1126/scirobotics.adv4408 · Cited by 8
Metadata
- Authors
- Wang-Chen, S., Stimpfling, V. A., Lam, T. K. C., Özdil, P. G., Genoud, L., Hurtak, F., & Ramdya, P.
- Affiliations
- École Polytechnique Fédérale de Lausanne (CH)
- Corresponding author
- Ramdya, Pavan
- ORCID
- Venue
- Nature Methods
- Published
- 2024-11-12
- Volume
- 21
- Issue
- 12
- Pages
- 2353-2362
- ISSN
- 1548-7091 (ISSN-L)
- 1548-7105
- OpenAlex
- W4404252550
- Cited by
- 43
- References
- 79
- Citations by year
- 2026: 22 · 2025: 11 · 2024: 9
- FWCI
- 7.32
- Type
- journal article
- Language
- en
- Open access
- green
- doi.org
- Licence
- cc-by-nc-nd
- www.springernature.com/gp/researchers/text-and-data-mining (tdm)
- www.springernature.com/gp/researchers/text-and-data-mining (vor)
- Locations
- Nature Methods (publishedVersion)
- bioRxiv (Cold Spring Harbor Laboratory) (acceptedVersion, cc-by-nc-nd)
- PubMed (publishedVersion)
- Infoscience (Ecole Polytechnique Fédérale de Lausanne) (submittedVersion, cc-by-nc-nd)
- Funders
- Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung (175667, 181239)
- Boehringer Ingelheim Fonds
- Topics
- Life Sciences › Neuroscience › Cellular and Molecular Neuroscience › Neurobiology and Insect Physiology Research
- Physical Sciences › Engineering › Control and Systems Engineering › Robotic Locomotion and Control
- Physical Sciences › Engineering › Aerospace Engineering › Biomimetic flight and propulsion mechanisms
- Keywords
- Drosophila, sensorimotor control, path integration, head stabilization, multimodal navigation, reinforcement learning, robot locomotion
- MeSH terms
- Machine Learning, Animals, Behavior, Animal, Brain, Computer Simulation, Drosophila, Drosophila melanogaster, Models, Neurological, Smell, Connectome
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-10-12, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-12 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: NeuroMechFly v2: simulating embodied sensorimotor control in adult Drosophila. https://app.cochat.ai/papers/10.1038/s41592-024-02497-y
- The paper
- Wang-Chen, S., Stimpfling, V. A., Lam, T. K. C., Özdil, P. G., Genoud, L., Hurtak, F., & Ramdya, P. (2024). NeuroMechFly v2: simulating embodied sensorimotor control in adult Drosophila. Nature Methods. https://doi.org/10.1038/s41592-024-02497-y
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.