Connecting Autonomous Laboratories to Speed Scientific Advancement

Researchers at Carnegie Mellon University will develop AI-based tools that will enable autonomous laboratories to work together as one connected research ecosystem. The project has been selected to receive funding by the U.S. Department of Energy (DOE) as part of the Genesis Mission. 

The CMU research team, led by Herman Herman(opens in new window), director of CMU’s National Robotics Engineering Center(opens in new window) (NREC), will partner with Argonne National Laboratory (ANL) and Lawrence Livermore National Laboratory (LLNL) to design and deploy a new generation of AI agents – intelligent software assistants that can make decisions and carry out tasks with minimal human guidance – to accelerate scientific breakthroughs by enabling robotic laboratories with different scientific equipment to work on complex experiments at the same time with minimal human involvement. 

Rather than requiring engineers to manually program each robot and scientific instrument, the AI agents will automatically generate the software instructions needed to perform complex tasks in each laboratory's unique environment. Using digital twins — virtual copies of each laboratory — the agents will practice, test, refine and optimize robotic workflows before deploying them to physical laboratory systems.  

"This project represents an important step toward intelligent laboratories that can learn, adapt, and collaborate," said Herman. "By combining AI agents, digital twins, and advanced robotics, we aim to create a scalable foundation for autonomous scientific discovery across Carnegie Mellon’s AI Science Foundry and the national laboratory ecosystem." 

During the initial phase of the program, the team will demonstrate autonomous generation of robotic software instructions for increasingly complex laboratory tasks at CMU’s AI Science Foundry(opens in new window) and testing at ANL and LLNL. 

The Genesis Mission is a historic national initiative led by the U.S. Department of Energy, which is building the world’s most powerful integrated science discovery platform. By uniting government, industry, academia and philanthropy, it is accelerating breakthroughs in energy, scientific discovery and national security through a new platform that combines AI, supercomputing, quantum systems and advanced scientific instruments. 

The goal of the Phase I RFA awards is to identify promising pathways toward transformative scientific capabilities and establish a foundation for future investment and scale. Project teams will design and demonstrate research workflows that integrate AI with scientific investigation, while rigorously evaluating whether those approaches can accelerate discovery, improve predictive capabilities, enhance experimentation, or generate new scientific insights. 

Carnegie Mellon will lead the development of the AI-generated robotic autonomy stack and systems integration, while researchers at ANL, led by Arvind Ramanathan, a computational biologist in ANL’s Data Science and Learning Division, will contribute expertise in data science and AI for biological research. Researchers at LLNL, led by Aldair Gongora, staff engineer in the Analytics for Advanced Manufacturing Group, and Yongqin Jiao, director of LLNL’s Center for Bioengineering and Biomanufacturing, will advance autonomous experimentation platforms and synthetic biology capabilities that support distributed AI-driven scientific workflows.  

The project will use intelligent AI agents that can reason about laboratory capabilities, generate reusable robotic skills, adapt to differences in instruments and layouts, and continuously improve performance through simulation-based learning. By enabling laboratories to share robotic capabilities and AI-generated software modules, the platform is expected to dramatically reduce the time required to deploy new autonomous experiments across multiple sites.