{"slug": "national-lab-in-livermore-using-autonomous-ai-to-quicken-broaden-experimentation", "title": "National lab in Livermore using autonomous AI to quicken, broaden experimentation", "summary": "Lawrence Livermore National Laboratory is using autonomous AI to accelerate experimentation and broaden scientific discovery across metal alloys, chemical compounds, and cancer treatments, with staff scientist Aldair Gongora leading the implementation. The lab's Project ARMOR (Advanced Robotics for Materials Manufacturing Optimization and Research) enables scientists to run hundreds or thousands of experiments remotely, a shift from the traditional one-variable-at-a-time approach. Christopher Spadaccini, Materials Engineering Division leader, said the technology is 'at the tip of the iceberg' and 'set to explode.'", "body_md": "**Getting your**\n\n[Trinity Audio](//trinityaudio.ai)player ready...As artificial intelligence becomes increasingly ubiquitous, Lawrence Livermore National Laboratory is turning it into the ultimate lab assistant, with scientists utilizing the evolving technology to [accelerate experimentation and speed the discovery](https://www.llnl.gov/article/54711/llnl-selected-lead-10-projects-under-does-genesis-mission) of metal alloys, chemical compounds and cancer treatments.\n\nThe adoption of AI at the lab has made autonomous experimentation commonplace, allowing scientists to run experiments while they’re away and greatly expand the scope of scientific inquiry.\n\n“We’re entering this exciting era, and we’re forging that era here at the (Advanced Manufacturing Laboratory) for the next generation of experimenters,” said Aldair Gongora, a Lawrence Livermore National Laboratory staff scientist who is leading the implementation of AI. “Whether it’s in batteries, whether it’s in biology, whether it’s in alloys, (scientists) now have at their fingertips the ability to run dozens or hundreds, maybe thousands and – in my dream – millions of experiments.”\n\nIn the past, the field of experimental science was a slow endeavor as scientists were limited to changing one variable at a time before recording an experiment’s results. As modern labs evolved, onerous tasks like manual pipetting were automated to allow scientists to focus on the brain work of science: forming hypotheses and data analysis.\n\nBetween 2008 and 2014, advances in an early branch of artificial intelligence known as [machine learning](https://computing.llnl.gov/casc/ml), which allows computers to learn and adapt, sped up the experimental process at Lawrence Livermore National Laboratory. Yet those developments pale in comparison to the recent growth of artificial intelligence, said Christopher Spadaccini, Materials Engineering Division leader at Lawrence Livermore National Laboratory.\n\n“We’re at the tip of the iceberg right now. We’re just learning what this can do,” Spadaccini said. “That interface with hardware and the physical world is really exciting, and I think it’s set to explode.”\n\nInside the [Advanced Manufacturing Lab](https://engineering.llnl.gov/collaboration/aml), Gongora talked over the hum of whirring automated instruments, including one humorously labeled “Peter Pipetter.” As the principal investigator of [Project ARMOR](https://www.llnl.gov/article/54736/how-llnl-using-ai-robotics-automation-accelerate-advanced-manufacturing) – Advanced Robotics for Materials Manufacturing Optimization and Research – Gongora oversees AI automation of the experimental process across materials science, chemistry and biology.\n\nMany material properties can only reliably be determined by experiment, so that process remains the “gold standard” of science, he said.\n\nTake [Livermorium](https://www.livermoreca.gov/our-community/livermorium), for example. Element 116 on the periodic table had been purely theoretical until December 2000, when scientists at Lawrence Livermore National Laboratory synthesized it for the first time.\n\nThough the radioactive atom lasted less than 80 milliseconds before decaying to flerovium, it was long enough to prove the material existed.\n\n“When you look at PhD dissertations that were written 10 or 20 years ago, especially experimental ones, the amount of experimental data is often very limited,” Gongora said. “But now with these types of platforms and testbeds, I think even the way that scientists address these problems and the data output can fundamentally change as well.”\n\nAs artificial intelligence ingrains itself within Lawrence Livermore National Laboratory, staff scientists like Rodrigo Telles are building that “connective tissue” between algorithms and the robots tasked with multi-phase experiments.\n\nThat’s because scientists’ knowledge is required to “orchestrate” sequential actions for an experiment. Otherwise, the autonomous equipment is like a band without a conductor.\n\n“You can’t load something in the centrifuge and then think that the robot’s going to go grab it, right?” Telles said. “You need to have steps that make sure that the centrifuge is done, your microwell plate is back where you think it’s supposed to be, your robotic arm can go and grab it and retrieve it. The AI doesn’t really know about that.”\n\nOnce the arrangement has been set, scientists are freed of many laborious burdens of experimentation. Gongora recalled a chemist working in the materials science lab, Sarah Finnegan, who used to spend four to six hours pipetting samples into a tube rotator. The process limited how many hypotheses she could test.\n\nSince her embrace of AI, she now orders a series of experiments to run Friday afternoon and comes back to full results on Monday, Gongora said. That additional time has allowed her to expand the scope of research.\n\nWhile the integration of AI is still in its infancy, scientists believe they’re still at the beginning of comprehending its benefits for scientific discovery. Gongora said AI may be as revolutionary to experimental science as the supercomputer was to mathematics.\n\nSpadaccini said the scientific field is at the beginning of a new age.\n\n“I’m not sure we fully understand how AI is going to change how we do science and engineering,” Spadaccini said. “It’s a hard question to answer because I think it’s so big, and it could impact every step in the process. Right now, we’re just learning what steps to start with.”", "url": "https://wpnews.pro/news/national-lab-in-livermore-using-autonomous-ai-to-quicken-broaden-experimentation", "canonical_source": "https://www.mercurynews.com/2026/08/14/national-lab-in-livermore-using-autonomous-ai-to-quicken-broaden-experimentation/", "published_at": "2026-08-14 23:05:33+00:00", "updated_at": "2026-08-14 23:13:00.086710+00:00", "lang": "en", "topics": ["artificial-intelligence", "machine-learning", "robotics", "ai-research"], "entities": ["Lawrence Livermore National Laboratory", "Aldair Gongora", "Christopher Spadaccini", "Project ARMOR", "Advanced Manufacturing Laboratory", "Rodrigo Telles"], "alternates": {"html": "https://wpnews.pro/news/national-lab-in-livermore-using-autonomous-ai-to-quicken-broaden-experimentation", "markdown": "https://wpnews.pro/news/national-lab-in-livermore-using-autonomous-ai-to-quicken-broaden-experimentation.md", "text": "https://wpnews.pro/news/national-lab-in-livermore-using-autonomous-ai-to-quicken-broaden-experimentation.txt", "jsonld": "https://wpnews.pro/news/national-lab-in-livermore-using-autonomous-ai-to-quicken-broaden-experimentation.jsonld"}}