Make your plans to attend
Vaccination required
>
Conference 11993 > Paper 11993-36
Paper 11993-36

Automatic aircraft avoidance for laser uplink safety

Abstract

We develop classifiers based on machine learning and neural networks to perform automatic aircraft detection on camera data to assist with uplink laser safety for deep space optical communications. Our classifiers can achieve a low false positive rate (FPR) for a true positive rate (TPR) of 100% and do so with a short response time. The FPR will be kept sufficiently low to avoid unnecessary shuttering events and interruptions of the communications link. Our approach can be used to complement transponder-based aircraft detection systems to ensure the safety of unpowered aircrafts and aircrafts at low altitudes.

Presenter

Jet Propulsion Lab. (United States)
Presenter/Author
Jet Propulsion Lab. (United States)
Author
Jet Propulsion Lab. (United States)
Author
Seán Meenehan
Jet Propulsion Lab. (United States)