Engineer receives $4.5 million to develop AI-powered hypersonic guidance and navigation systems

By Emily Dieckman, College of Engineering

Today

Roberto Furfaro, professor of systems and industrial engineering at the University of Arizona, has been awarded $4.5 million to lead the development of improved guidance, navigation and control systems for autonomous vehicles operating at hypersonic speeds . The proposed three-year research is sponsored by the Joint Hypersonic Transition Office through the University Consortium for Applied Hypersonics (UCAH).

Hypersonic speed – of Mach 5 or more – is a speed that exceeds five times the speed of sound. As the United States strives to develop hypersonic technologies, research in the field has never been greater.

“Many conventional systems are designed using linear theory and are not designed to fly or intercept at this speed,” Furfaro said. “There are a lot of things going on in hypersonic flow that are so nonlinear that they’re not fully understood, and that we need to characterize if we’re going to design systems that work under those conditions.”

Consider how, when a car is traveling at 80 mph, a one-second delay in driver decision-making can have catastrophic results. Hypersonic vehicles, which travel thousands of miles per hour and face additional factors such as shock waves and extreme heat, have even less room for error.

Arizona is home to the Arizona Research Center for Hypersonics, where researchers perform simulations and wind tunnel testing to learn more about vehicle behavior in extreme environments. The AI-powered guidance, control and navigation methods developed by Furfaro and his team will act as the “brains” of hypersonic vehicles – including interceptors, which are high-speed, maneuverable vehicles designed for defense against enemy aircraft.

“This investment is a major win for our burgeoning hypersonic research program,” said David W. Hahn, Dean Craig M. Berge of the College of Engineering. “Roberto has a wide range of expertise in areas such as spaceflight mechanics and machine learning, which makes him and his team exceptionally well qualified to lead this effort.”

To train the hypersonic systems to navigate and respond to extremely complex, high-speed situations on their own, the team uses a type of machine learning called meta-reinforcement learning.

“With meta-learning, we can train it not just on one scenario, but on many scenarios,” Furfaro said. “The system is able to learn about one delivery environment, and each time it converges faster to the next one. By enabling this continuous learning, we are fundamentally able to have a system that is always adapting. “

A strong team builds a test environment

UArizona alumnus Brian Gaudet, a research engineer at the university’s Space Systems Engineering Laboratory, plays a critical role in the development and implementation of the AI ​​system. Other collaborators and co-investigators include a professor of aerospace and mechanical engineering Samy Missoum, which is working on Department of Defense funded work to characterize hypersonic environments; and Professor of Materials Science and Engineering Erica Corralwho serves as Co-Director of Industrial and National Lab Engagement and Workforce Development for the UCAH Consortium Engagement Council.

Furfaro will also work with aerospace and mechanical engineering professors Alex Craig and Jesse Smallwho work in experimental aerodynamics, and Kyle Hanquist, assistant professor in the same department specializing in computational fluid dynamics. Other collaborators are at the University of Texas at Austin and Raytheon Missiles and Defense.

“The University of Arizona has a nationally leading hypersonic research program, which received $10 million in federal and state support in 2021 to improve our research facilities,” said the president of the University of Arizona. Robert C. Robbins. “Many of the top experts in the field agree that artificial intelligence will play an increasingly important role in advancing the field, and Professor Furfaro’s receipt of this highly competitive grant will bring together many areas of expertise to advance this critical area.”

Researchers will use this data – gathered from simulations and wind tunnel tests of vehicle behavior in hypersonic flow – to characterize and create a simulated environment to train the system’s adaptive brain.

“We are incredibly supportive of the University of Arizona’s work in developing hypersonic technology and talent,” said Wes Kremer, president of Raytheon Missiles & Defense. “The advances Professor Furfaro and his team will bring to guidance, navigation and control systems will have a direct impact on our nation’s ability to develop advanced hypersonic capabilities.”