Using a $7.5 million, five-year grant from the U.S. Department of Defense, a multi-university team that includes Johns Hopkins engineers is tackling one of today’s most complex and important technological challenges: how to ensure the safety of autonomous systems, from self-driving cars and aerial delivery drones to robotic surgical assistants.
“The potential practical ramifications of this project are broad and boil down to making sure that artificial intelligence-based systems are safe,” says René Vidal, the Herschel L. Seder Professor of Biomedical Engineering and the inaugural director of the Mathematical Institute for Data Science. He is working with Noah Cowan, professor of mechanical engineering and director of the Locomotion in Mechanical and Biological Systems laboratory, and collaborators at Northeastern University, the University of Michigan, and the University of California, Berkeley on the Multidisciplinary University Research Initiative, or MURI project, called Control and Learning Enabled Verifiable Robust AI, or CLEVR-AI.
“Using this grant,” says Vidal, “we are developing theoretical and algorithmic foundations to support a new class of verifiable, safe, AI-enabled dynamical systems that, like living systems, will adapt to novel scenarios, where data are generated — and decisions are made — in real time.”
Despite recent advances in artificial intelligence and machine learning, the goal of designing control systems capable of fully using AI/machine learning methods to learn from and interact with the environment the way humans and animals do remains elusive, the researchers say.
“Animals, including humans, move with such grace and agility, and are able to adjust and change their movements and behavior according to what is happening around them,” says Cowan. “As engineers, we seek to learn from them while creating robust control systems that are safe and reliable. Our goal here is to bridge the gap between biological sensing and control systems, and safe and reliable autonomous systems.”
The field of artificial intelligence has tried to address this gap by building computational systems that attempt to mimic or approximate aspects of the brain. Unfortunately, that approach and the resulting designs do not reliably create safe systems. The team’s project seeks to overcome this by combining machine learning, dynamical systems theory, and formal verification methods, leveraging each team member’s strengths. For instance, Vidal is an expert in machine learning, computer vision, and biomedical data science, and Cowan’s expertise is in understanding sensing, computation, and control in animals. Both are leading authorities in the field of robotics and control theory.
“Our approach,” says Cowan, “will integrate traditional mathematical control theory with new and emerging AI to make systems verifiable, robust, safe, and correct.”