Texas A&M’s ARM-MIP will build a metals lab run by robots and AI

A $24.9 million grant from the U.S. National Science Foundation will fund a new national facility at Texas A&M University where robots and artificial intelligence will automate the process of alloy discovery. The Autonomous Robotic Metallurgist Materials Innovation Platform, or ARM-MIP, is designed to reach more than 200 users a year and 50 alloys per month in its first year, scaling to more than 200 alloys per month by year six.

“Through ARM-MIP, we seek to democratize access to research facilities,” said Dr. Raymundo Arróyave, Chevron Professor II in the Department of Materials Science and Engineering and director of ARM-MIP. The platform will be located at the RELLIS Campus alongside the U.S. Army Transformation and Training Command’s central testing hub.

$24.9M NSF Grant Establishes Autonomous Robotic Metallurgist Materials Innovation Platform

A $24.9 million investment from the National Science Foundation will establish a facility capable of producing over 200 metal alloys each month by year six, demonstrating a substantial commitment to automated materials discovery. The facility’s co-location with the Army Transformation and Training Command’s testing hub suggests potential applications of the developed alloys in defense technologies, as well as broader industrial and scientific uses. This accelerated pace will be enabled by robotic systems that handle alloy melting, shaping, heat treatment, and testing around the clock, a process previously reliant on extensive manual labor.

According to Dr. Access to ARM-MIP will be free for academic users, while commercial entities can utilize the platform under negotiated terms, with intellectual property agreements established prior to project commencement. The team anticipates that by year six, half of the facility’s equipment time will be dedicated to external researchers, fostering collaboration and knowledge sharing. Multiscale Technologies will provide its MIND 3.0 platform as the knowledge-sharing backbone, ensuring data, workflows, and models are accessible to the wider materials science community.

ARM-MIP differs from other materials discovery efforts by controlling not only alloy composition but also the manufacturing process itself. The platform will meticulously manage parameters like heating and cooling rates, recognizing that a metal’s internal structure, and therefore its properties, is heavily influenced by its creation history.

“Experiments that once required years of labor will now be completed in weeks,” explained Dr. “This will allow students and researchers to focus less on making samples and more on making discoveries.” Graduate student Mrinalini Mulukutla highlighted the potential for freeing researchers from repetitive tasks, stating, “By automating routine work that machines can do, it will free students like me to spend more time imagining and designing newer materials that will enable future technologies, rather than managing the logistics of getting there.”

ARM-MIP’s Robotic Systems Accelerate Alloy Creation & Testing Cycles

The facility’s design centers on a closed-loop system where robots handle the physical processes of alloy creation, melting, shaping, heat treatment, and testing, while AI algorithms analyze results and guide subsequent experiments. Simulations will precede physical experimentation, ensuring robotic resources are focused on promising alloy compositions. This level of control is crucial, as two alloys with identical chemical formulas can exhibit drastically different behaviors depending on how they were processed, mirroring the impact of a blacksmith’s quenching technique on a blade.

Graduate student Mrinalini Mulukutla, who contributed to the program’s earlier BIRDSHOT initiative, highlighted the potential for automation to alleviate bottlenecks. “We’ve built some really exciting AI-driven frameworks, but behind the scenes there’s still a lot of manual coordination, sample tracking, repetitive lab work, and data management,” she said.

“What excites me about ARM-MIP is that it has the potential to change that.” The platform’s ambition extends beyond simply accelerating research; it aims to democratize access to advanced materials science capabilities. Dr. Angela Wilson, Texas A&M vice president for research, added, “It will be a national asset that will drive scientific advancement, strengthen U.S. competitiveness and create new opportunities for researchers and students alike.”

BIRDSHOT Program Validates AI-Guided Discovery & Facility Design

Ibrahim Karaman, the co-director of ARM-MIP and head of the Department of Materials Science and Engineering, said “We are building a time machine for metallurgy,” a claim substantiated by preliminary results from the program’s earlier BIRDSHOT initiative. That initial program demonstrated a 100-fold acceleration of alloy discovery, synthesizing and characterizing over 1,150 alloys in just four years, a feat previously requiring significantly more time and manual effort from graduate students and postdoctoral researchers.

ARM-MIP intends to expand upon this success by integrating fully automated robotic systems to eliminate the manual bottlenecks that still constrained the BIRDSHOT program, allowing for continuous, around-the-clock experimentation. Mulukutla explained, “I have had the chance to help brainstorm ideas from set-up to building and deploying these frameworks for accelerated alloy development.

We have demonstrated the strengths of AI-guided materials design but have also come across many bottlenecks in the overall process.” She anticipates ARM-MIP will alleviate these burdens, freeing researchers to concentrate on the creative aspects of materials design and enabling the development of technologies for the future.