Communications Chemistry · 2026
as a taxonomy for robot manipulation in chemistry
Kefeng Huang, Alice E. Martin, Jonathon Pipe, Tianyuan Wang, Barnabas A. Franklin,
Christopher S. Horbaczewskyj, Andy M. Tyrrell, Ian J. S. Fairlamb, Jihong Zhu
doi.org/10.1038/s42004-026-02249-3

Background
University of Liverpool · Burger et al., Nature 2020
Robot arm on wheels: carries samples between stations, operates instruments
688 experiments in 8 days, a ten-variable search for photocatalysts that produce hydrogen from water
One demonstrated photocatalysis workflow; touch calibration at each station

Burger et al., Nature 583, 237–241 (2020), doi:10.1038/s41586-020-2442-2 · Abstract; Methods (mobile robot, touch-feedback calibration)
Background
Darvish et al., Matter 2025 (arXiv 2024)
Takes instructions in ordinary language, plans laboratory work, monitors experiments by camera
A 19-step electrochemistry plan, tasks run in parallel (quinone derivatives for flow batteries)
No automatic experimental setup yet, such as fetching clean vessels or inserting tubes and probes

Darvish et al., Matter 8, 101897 (2025), doi:10.1016/j.matt.2024.10.015 · arXiv:2401.06949v2, Abstract; Discussion: Limitations
Background
Steiner et al., Science 2019 · Mehr et al., Science 2020
χDL writes a synthesis as process steps (add, filter, evaporate); a compiler targets compatible hardware such as the Chemputer
12 literature compounds synthesised automatically (2020); three pharmaceuticals without human intervention (2019)
Processes in abstract vessels; the physical handling can differ between apparatus

Mehr et al., Science 370, 101–108 (2020), doi:10.1126/science.abc2986 · Steiner et al., Science 363, eaav2211 (2019), doi:10.1126/science.aav2211
Background
Burger et al. (2020) · Darvish et al. (2025) · Mehr et al. (2020) · Huang et al., Commun. Chem. 2026, Introduction
TARMAC · Taxonomy
Laboratory instructions hide physical handling.
A taxonomy groups actions by what they physically require.
A primitive is one named action, such as Pouring or Scooping.
Each robot still needs its own controller.

Huang et al., Commun. Chem. 2026, Fig. 1; Introduction; Methods (Instantiating TARMAC)
TARMAC · Taxonomy
Huang et al., Commun. Chem. 2026, Methods (Derivation of manipulation primitives); Author contributions
TARMAC · Taxonomy
One action = the smallest meaningful observable manipulation
Example: “set up the apparatus” → position a vessel, insert a component, couple two parts.

Huang et al., Commun. Chem. 2026, Fig. 2; Methods (Derivation of manipulation primitives)
TARMAC · Taxonomy




Pouring · Tooling
Directing gravity-driven liquid flow by tilting or reorienting a container.
Frames: teaching-corpus examples, tarmac-paper.github.io (Dataset examples) · Definition: Huang et al., Commun. Chem. 2026, Supplementary Table 1
TARMAC · Taxonomy
Huang et al., Commun. Chem. 2026, Results (The TARMAC taxonomy); Methods (Derivation of manipulation primitives and core features)
TARMAC · Taxonomy
562 annotated actions → 4 categories → 18 primitives
direct, finite, geometric endpoint
direct, finite, force or torque endpoint
through a tool, container or implement
sustained or repeated motion
Counts are action instances in the corpus, not time spent.
Huang et al., Commun. Chem. 2026, Table 1; Fig. 3; Discussion
TARMAC · Taxonomy
Huang et al., Commun. Chem. 2026, Supplementary Table 1 (primitives, definitions and examples from the annotated data)
TARMAC · Evaluation
| Evaluation | Question | Result |
|---|---|---|
| Specification adequacy | Do the written rules reproduce our labels? | 82.9–86.7% agreement on the same 562 actions |
| Expressive coverage | Do published procedures fit the vocabulary? | 904 of 917 steps in 23 procedures |
| Robotic executability | Can robots run and compose the primitives? | 8 primitives, 5 tasks, 4 configurations |
Agreement, coverage and proof of concept are different measures; none is a robot success rate
Huang et al., Commun. Chem. 2026, Table 3; Introduction
TARMAC · Evaluation 1
Macro-F1 0.74 → 0.84. A definition check on the derivation corpus, not human inter-rater agreement
Redrawn from Huang et al., Commun. Chem. 2026, Fig. 4a; Results; Methods (Specification-adequacy probe via rule-following classification)
TARMAC · Evaluation 2
904 of 917 manipulative steps mapped to a primitive (98.6%)
13 unmapped: cutting or sectioning 6 · ultrasonication 3 · machine-driven tensile stretching 4
Redrawn from Huang et al., Commun. Chem. 2026, Fig. 5 (cell shading on a log scale; · marks zero); Results (Expressive coverage across published procedures); Methods (Cross-corpus protocol decomposition)
TARMAC · Evaluation 3




8 of 18 primitives · 5 tasks · 4 configurations · 4 of 4 categories
Proof of concept, not a success-rate benchmark
Huang et al., Commun. Chem. 2026, Table 2; Fig. 6; Supplementary Videos 1–5 · clips: tarmac-paper.github.io (B and C at 4× source speed)
TARMAC · Discussion
χDL, Chemputation: which matter and energy changes are needed
↓ realised as
apparatus-dependent manipulations, named as primitives
↓ executed by
trajectories, forces, contact strategies
Interpretation from the Discussion, not a further experiment
Huang et al., Commun. Chem. 2026, Introduction; Discussion · χDL: Mehr et al. (2020) · Chemputation: Cronin et al., PNAS (2026)
TARMAC · Discussion
Huang et al., Commun. Chem. 2026, Discussion; Results; Methods
Summary
Huang et al., Commun. Chem. 2026, doi:10.1038/s42004-026-02249-3
Resources
doi.org/10.1038/s42004-026-02249-3Communications Chemistry (2026), open access, CC BY 4.0
tarmac-paper.github.ioVideos, dataset examples, overview
github.com/kefhuang/tarmac-paperArchived on Zenodo: doi:10.5281/zenodo.22071890
Supplementary Data 1–3 with the articleAnnotations · classification results · procedure decompositions


Huang et al., Commun. Chem. 2026, Data availability; Code availability
Acknowledgements
Questions
Huang et al., Commun. Chem. 2026, Acknowledgements; Funding
Claims and evidence · feature combinations · bimanual recovery · per-primitive counts
Backup
| Evaluation exercise | Specific claim supported |
|---|---|
| Rule-following classification | Concordance of 82.9–86.7% and macro-F1 of 0.74–0.84 across 562 actions show that the written specification recovers intended assignments within the derivation corpus and that workflow context contributes to primitive identification. |
| Cross-corpus protocol decomposition | Mapping 904 of 917 manipulative steps across 23 procedures, while retaining 13 unmapped steps as boundary cases, supports high expressive coverage within the examined external procedures while exposing operation classes outside the present scope. |
| Robotic instantiation | Five tasks across four configurations, covering 8 of 18 primitives and all four high-level categories, provide proof-of-concept evidence that representative primitives can be instantiated, composed, transferred across embodiments, and applied across the experimental lifecycle. |
Redrawn from Huang et al., Commun. Chem. 2026, Table 3
Backup
| Wrench Dependent | Indirect Control | Cyclic Motion | Count ↓ | Taxonomic Category |
|---|---|---|---|---|
| ✓ | ✗ | ✗ | 198 | Coupling |
| ✗ | ✗ | ✗ | 169 | Positioning |
| ✗ | ✓ | ✗ | 73 | Tooling |
| ✓ | ✓ | ✗ | 64 | |
| ✗ | ✗ | ✓ | 44 | Agitating |
| ✗ | ✓ | ✓ | 13 | |
| ✓ | ✗ | ✓ | 0 | |
| ✓ | ✓ | ✓ | 1 |
Highlighted cells mark the dominant feature of each category. Counts are annotated actions (total 562).
Redrawn from Huang et al., Commun. Chem. 2026, Table 1
Backup

Misaligned iron ring: Rotational-C (loosen) → Rotational-P (re-orient) → Rotational-C (re-secure), then assembly continues.
Huang et al., Commun. Chem. 2026, Fig. 6 (row C); Results (Robotic instantiation); Supplementary Video 4
Backup
Redrawn from Huang et al., Commun. Chem. 2026, Fig. 3 (562 annotated actions in the teaching-video corpus)