Jean-Guillaume Durand
Head of Perception, Xwing

AI in Transportation/Aerospace

June 6, 2:00pm
Location: Magnolia

Certifying Machine Learning for Autonomous Flight

Over the past decade, machine learning (ML) has demonstrated impressive results, often surpassing human capabilities in sensing and perception tasks relevant to autonomous flight. Xwing is an autonomous aircraft company that leverages these research breakthroughs to improve the performance and safety of SuperPilot, its autonomy stack. In this talk, we will first present where Xwing uses ML to leverage a safety advantage. We will then break down why these ML models do not fit into the traditional aerospace certification paradigm. To overcome this limitation, we will introduce Xwing’s methodology to certification: a framework centered around a statistical verifier for black-box subsystems. The framework is model-agnostic and tool-independent, making it adaptable to many use cases in the industry. We will demonstrate results on vision-based landing, a widespread application in autonomous flight.

Jean-Guillaume Durand is the Head of Perception at Xwing, a company developing autonomous flight for regional air cargo. Using onboard aircraft sensors, the Xwing Perception team develops certifiable robotics solutions to enable safe autonomous flight (runway and taxiway detection, ground obstacle detection, vision-based navigation, etc.). Prior to joining Xwing, Jean-Guillaume worked on full-stack autonomy and perception for large commercial aircraft at Airbus Wayfinder, and for delivery drones at Amazon Prime Air. He received his Ph.D. from the Georgia Institute of Technology.