> ## Content Index
> Fetch the complete content index at: https://acentricresearch.com/llms.txt
> Use this file to discover other available public pages before exploring further.

# Self-driving (autonomous) laboratories: Junction Brief – November 2026
- URL: https://acentricresearch.com/research/self-driving-laboratories-brief-2026-11/
- Published: 2026-11-21T01:01:23.000Z
- Updated: 2026-11-21T09:41:29.000Z
- Author: Kevin Meyer
- Tags: ai-materials, junction-brief

> Acentric Research is produced with AI tools under human review. The authors are not financial professionals, and nothing here is investment advice or a recommendation to buy or sell any security. AI analysis can be wrong; check every claim against its cited source.

This Brief is an initial scan, not a full investigation. The method and scores behind it are in [AI × Materials in the Landscape Report](https://acentricresearch.com/research/landscape-2026-11/#ai-materials).

### Overview

In a self-driving laboratory, as the Berkeley Lab feature story describes its A-Lab, software chooses the next experiment, robots mix and heat the samples, instruments measure the result, and the software uses it to plan the next round, with little human involvement. DOE states that the pace of scientific discovery is constrained by the traditional, human-driven experimental process. \[1\]\[2\] This Brief covers artificial intelligence (AI) used this way for materials.

What stands out is that there is a peer-reviewed demonstration and new commercial interest, but little public evidence yet that these laboratories produce useful materials. Several of the main claims come from the companies themselves, and a published critique argues that the A-Lab paper’s analysis did not support its claim of new materials. \[3\]\[4\]\[5\]\[6\] The sources opened date from 2023 to 2026; the main laboratory paper is from November 2023 and the two funding reports from 2025\. Later developments were not searched.

### Current state

**A research demonstration.** Lawrence Berkeley National Laboratory’s A-Lab is described in the laboratory’s own feature story as designed as a closed loop, in which decision making is handled without human interference, and as able to process 50 to 100 times as many samples as a human every day. \[2\] In a 2023 paper in the journal Nature, the A-Lab team reported that over 17 days of continuous operation it made 41 of 58 target compounds, a 71 percent success rate, using computed stability data from the Materials Project and Google DeepMind, recipes proposed by language models trained on the literature, and active learning. 

Seventeen targets were not obtained; the authors identify slow reaction kinetics, precursor volatility, amorphization and computational inaccuracy as the reasons. \[3\] A 2024 critique in PRX Energy argues that the A-Lab paper’s analysis had four common shortfalls and concludes that no new materials were discovered in that work, estimating that about two thirds of the claimed successes are likely known compounds in a disordered form. \[4\] The A-Lab authors later published a correction (Nature, 2026-01-19) stating that concerns had been raised about identifying the structures from diffraction data and that their claims of novelty meant new to the prediction platform, not necessarily new to science. \[7\] 

The correction adds that the authors re-analyzed the diffraction patterns, that this re-analysis was peer reviewed after publication, that they confirmed the platform’s conclusion in 36 of its 40 reported successes with 4 inconclusive, and that the total of compounds made was updated to exclude four targets whose presence is inconclusive from diffraction alone. It also removed one compound from the discussion that had been mistakenly included in the training data. The counts in this Brief (41 of 58, 17 not obtained) are those of the 2023 paper, and the correction’s base of 40 reported successes differs from the paper’s 41\. \[7\]

**How the A-Lab works.** According to the feature story, a robot weighs and mixes powder precursors, chosen from nearly 200, a second arm loads them into furnaces that can reach 2200 degrees Fahrenheit, and a third moves the samples to an X-ray diffractometer and an electron microscope. The results go back to the AI system, which sets the next recipe. Researchers watch through video feeds and alerts. \[2\]

**Companies.** Periodic Labs came out of stealth in September 2025 with a claimed $300 million seed round, to build “AI scientists” and automated laboratories, with a first focus on superconductors and semiconductor heat problems. A news report adds that critics say real-world usefulness beyond stability predictions is still limited. \[5\] Lila Sciences told Reuters in October 2025 that it had raised a $115 million extension, and described “AI Science Factories”, facilities equipped with robotic instruments controlled by AI. It said it had signed a 235,500-square-foot lease in Cambridge, Massachusetts and plans to offer its platform to commercial customers. The company claims its platform has already made thousands of discoveries across life sciences, chemistry and materials; the report presents this as the company’s claim. \[6\] Dunia, another company building an autonomous laboratory for materials, describes itself as “accelerating the discovery of materials - starting with energy” and says its autonomous lab accelerates the typical research timeline up to tenfold; both are company statements. \[8\]

**Public programs.** DOE’s Genesis Mission opportunity includes a challenge titled “Achieving AI-Driven Autonomous Laboratories”, covering robotics, edge AI, real-time analysis and feedback, and hypothesis generation, with DOE user facilities and national laboratories as the base. Its stated focus areas for fiscal 2026 include robotics that can safely interact with scientific instruments and manage experimental workflows. \[1\] NSF’s materials research centers solicitation of 2026 says proposals that incorporate autonomous experimentation, where robotics and AI accelerate closed-loop discovery, are strongly encouraged, and that centers may align with the Materials Genome Initiative. \[9\] DOE says its user facilities and national laboratories have the infrastructure and expertise to serve as the nucleus for this kind of high-throughput discovery. \[1\]

**How far it has come.** A laboratory demonstration at one national laboratory, and companies building their own laboratories. The sources opened do not show a commercial laboratory delivering a product.

### Opportunities

Robots can run around the clock, and the loop produces data for AI models, including failed attempts, which Periodic Labs says is the point of its approach. \[5\]\[2\] DOE states that automating parts of the experimental process will increase the volume of data produced and improve repeatability. \[1\] Lila says its platform has drawn interest from firms in energy, semiconductors and drug development, without naming them. \[6\]

### Challenges

- **Engineering.** Solid-state synthesis can fail for reasons a computer does not predict; the A-Lab did not obtain 17 of its 58 targets. \[3\]
- **Evidence.** Most evidence is one laboratory’s paper and company statements. A news report says critics call real-world usefulness limited. \[5\]
- **Capital and scale-up.** Lila’s chief executive said the company will not itself scale up new energy breakthroughs; partners will do that. The Periodic Labs report names the risk as whether the leap from demonstration to durable deployment proves achievable. \[6\]\[5\]

### Data sources

- **DOE and NSF funding opportunities** for programs. \[1\]\[9\]
- **Scientific papers**, such as the Nature paper, for experimental results. \[3\]
- **Company releases and press**, as company claims. \[5\]\[6\]
- **Company websites** for descriptions in the companies’ own words. \[8\]
- **USAspending.gov** for federal awards. \[10\]

### Changelog

- 2026-11-18: First published.

### Sources

1. US Department of Energy, “The Genesis Mission: Transforming Science and Energy with AI”, Notice of Request for Application DE-FOA-0003612, issued 2026-03-17, Amendment 000003 of 2026-04-20; challenge 11\. [science.osti.gov](https://science.osti.gov/-/media/grants/pdf/foas/2026/DE-FOA-0003612-000003.pdf?ref=acentricresearch.com) (accessed 2026-11-18)
2. “Meet the autonomous lab of the future”, Lawrence Berkeley National Laboratory feature story, EurekAlert!, 2023-04-17\. [eurekalert.org](https://www.eurekalert.org/news-releases/985585?ref=acentricresearch.com) (accessed 2026-11-18)
3. N. J. Szymanski and others, “An autonomous laboratory for the accelerated synthesis of novel materials”, Nature, published 2023-11-29 (the journal now lists the title with “inorganic” in place of “novel”, after a 2026 author correction). [doi.org](https://doi.org/10.1038/s41586-023-06734-w?ref=acentricresearch.com) (full text read from the open-access copy at [osti.gov](https://www.osti.gov/pages/servlets/purl/2281696?ref=acentricresearch.com), accessed 2026-11-18)
4. J. Leeman and others, “Challenges in High-Throughput Inorganic Materials Prediction and Autonomous Synthesis”, PRX Energy 3, 011002, published 2024-03-07\. [doi.org](https://doi.org/10.1103/PRXEnergy.3.011002?ref=acentricresearch.com) (abstract only, as deposited with Crossref, [api.crossref.org](https://api.crossref.org/works/10.1103/prxenergy.3.011002?ref=acentricresearch.com), accessed 2026-11-18; the publisher page refused a scripted request, so the full text was not opened)
5. Chris McKay, “Periodic Labs launches with $300M to build an ‘AI scientist’”, Maginative, 2025-09-30 (reports company claims). [maginative.com](https://www.maginative.com/article/periodic-labs-launches-with-300m-to-build-an-ai-scientist/?ref=acentricresearch.com) (accessed 2026-11-18)
6. Krystal Hu, “Exclusive-AI lab Lila Sciences tops $1.3 billion valuation with new Nvidia backing”, Reuters, 2025-10-14, as carried by The Star (reports statements the company made to Reuters). [thestar.com.my](https://www.thestar.com.my/tech/tech-news/2025/10/14/exclusive-ai-lab-lila-sciences-tops-13-billion-valuation-with-new-nvidia-backing?ref=acentricresearch.com) (accessed 2026-11-18)
7. N. J. Szymanski and others, “Author Correction: An autonomous laboratory for the accelerated synthesis of inorganic materials”, Nature 650, E1, published 2026-01-19 (open access; authors’ statement). [doi.org](https://doi.org/10.1038/s41586-025-09992-y?ref=acentricresearch.com) (page read at [nature.com](https://www.nature.com/articles/s41586-025-09992-y?ref=acentricresearch.com), accessed 2026-11-18)
8. Dunia, company home page (company statements). [dunia.ai](https://www.dunia.ai/?ref=acentricresearch.com) (accessed 2026-11-18)
9. National Science Foundation, “Materials Research Science and Engineering Centers (MRSEC)”, solicitation NSF 26-500\. [nsf.gov](https://www.nsf.gov/funding/opportunities/mrsec-materials-research-science-engineering-centers/nsf26-500/solicitation?ref=acentricresearch.com) (accessed 2026-11-18)
10. USAspending.gov, home page. [usaspending.gov](https://www.usaspending.gov/?ref=acentricresearch.com) (accessed 2026-11-18)