As these autonomous systems grow in complexity and ubiquity, so too could the ways in which they fail. Now, MIT engineers have developed an approach that can be paired with any autonomous system, to quickly identify a range of potential failures in that system before they are deployed in the real world. Designers often test the safety of autonomous systems by identifying their most likely, most severe failures. “Our method can discover hidden correlations in the system,” Dawson says. In principle, the team’s approach could find and fix failures in any autonomous system as long as it comes with an accurate simulation of its behavior.