Artificial Intelligence for Safety Critical Applications in Aerospace

Starting in the 1970s, decades of effort went into building human-designed rules for providing automatic maneuver guidance to pilots to avoid mid-air collisions. The resulting system was later mandated worldwide on all large aircraft and significantly improved the safety of the airspace. Recent work has investigated the feasibility of using computational techniques to help derive optimized decision logic that better handles various sources of uncertainty and balances competing system objectives. This approach has resulted in a system called Airborne Collision Avoidance System (ACAS) X that significantly reduces the risk of mid-air collision while also reducing the alert rate, and it was recently accepted as an international standard. Using ACAS X as a case study, this talk will discuss lessons learned about building trust in advanced decision-making systems in aerospace. This talk will also outline research challenges in facilitating greater levels of automation into safety critical systems and the ongoing work at the Stanford for AI Safety.

Speaker: mykel Kochenderfer, Stanford