How can we enable safe aviation autonomy with machine-learning (ML) in the loop?
How can we enable safe aviation autonomy with machine-learning (ML) in the loop?
Future aviation systems, in the form of unmanned aircraft systems (UAS) and urban air mobility (UAM) services, will operate at increased levels of autonomy by extensively leveraging machine-learning-enabled components (LECs), in tasks as diverse as visual perception, intent prediction, and decision-making. Despite the promise of LECs to outperform their traditional, non-learning based counterparts, today’s LECs can be notoriously poor at generalizing beyond their training data, and largely lack appropriate methods for verification and validation. To enable wider and trusted adoption of LECs, this project identifies three technical challenges that must be overcome to achieve the vision of autonomous aviation systems with LECs in the loop.
Future aviation systems, in the form of unmanned aircraft systems (UAS) and urban air mobility (UAM) services, will operate at increased levels of autonomy by extensively leveraging machine-learning-enabled components (LECs), in tasks as diverse as visual perception, intent prediction, and decision-making. Despite the promise of LECs to outperform their traditional, non-learning based counterparts, today’s LECs can be notoriously poor at generalizing beyond their training data, and largely lack appropriate methods for verification and validation. To enable wider and trusted adoption of LECs, this project identifies three technical challenges that must be overcome to achieve the vision of autonomous aviation systems with LECs in the loop.
Technical Challenges
Technical Challenges
Assurances for Autonomous Systems with LECs: Can we develop deep neural networks that are robust, generalize to unseen scenarios, and verifiable?
Assurances for Autonomous Systems with LECs: Can we develop deep neural networks that are robust, generalize to unseen scenarios, and verifiable?
Run-Time Fault Detection, Isolation, and Recovery for LECs: Can we detect faulty operation of LEC-based autonomous aviation systems, isolate errors, and safely transfer authority to traditional software modules?
Run-Time Fault Detection, Isolation, and Recovery for LECs: Can we detect faulty operation of LEC-based autonomous aviation systems, isolate errors, and safely transfer authority to traditional software modules?
Airspace Management with LEC-based Autonomous Systems: What will it take to scale our assurances and fault recovery mechanisms to fleets of vehicles in crowded airspace?
Airspace Management with LEC-based Autonomous Systems: What will it take to scale our assurances and fault recovery mechanisms to fleets of vehicles in crowded airspace?