The NSF Autonomous Robotic Metallurgist Materials Innovation Platform (ARM-MIP, DMR-2534344) at Texas A&M University is an open-access national user facility that designs, makes, tests, and learns from new alloys, closing the discovery loop by integrating robotics, artificial intelligence, physics-based simulation, and automated experimentation into a single autonomous laboratory. Advanced alloys underpin many nationally critical technologies, from transportation and energy systems to medical devices, yet bringing a new alloy from concept to deployment can take more than a decade. Scientists and engineers from universities, national laboratories, and industry come to ARM-MIP as hands-on users, running their own discovery campaigns and carrying autonomous-laboratory techniques back to their home institutions. Remote access modes, including artificial-intelligence-guided campaign design and digital-twin-supported experiment planning, extend these capabilities to additional researchers, including those at non-R1 and EPSCoR institutions. Training is delivered through on-site user instruction, the Computational Materials Science Summer School (CMS3), and dedicated modules in artificial-intelligence-enabled discovery workflows.
ARM-MIP integrates high-throughput synthesis and processing, automated multimodal characterization, physics-informed simulation, and Bayesian decision-making within a single closed-loop, artificial-intelligence-orchestrated facility. Capabilities include automated vacuum arc melting and directed-energy deposition, high-throughput thermo-mechanical processing, automated electron microscopy with diffraction-based phase analysis, focused-ion-beam tomography, and high-throughput mechanical, thermal, and magnetic property measurement. In-house research pursues two coordinated thrusts: a materials-science thrust on metastable, chemically and microstructurally complex alloys, and a methodological thrust that develops the autonomous-laboratory capabilities themselves, from physics-informed Bayesian decision-making and agentic artificial intelligence to digital-twin orchestration and human-robot collaboration.
