Safe and secure practical autonomy

Safe practical autonomy is ensured by encapsulating an unreliable or untrusted machine learning algorithm within a control-based algorithm. A safety envelope is utilized to ensure that the machine learning algorithm does not output control signals that are beyond safe thresholds or limits. Secure pr...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Wolford, Brian R, McLean, Angus L, Roup, Alexander V, Bertram, Joshua R
Format:	Patent
Sprache:	eng
Schlagworte:	AEROPLANES AIRCRAFT ANALOGUE COMPUTERS AVIATION CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING CONTROLLING COSMONAUTICS COUNTING ELECTRIC DIGITAL DATA PROCESSING GYROSCOPIC INSTRUMENTS HELICOPTERS MEASURING MEASURING DISTANCES, LEVELS OR BEARINGS NAVIGATION PERFORMING OPERATIONS PHOTOGRAMMETRY OR VIDEOGRAMMETRY PHYSICS REGULATING SIGNALLING SURVEYING SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES TESTING TRAFFIC CONTROL SYSTEMS TRANSPORTING
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Beschreibung
Zusammenfassung:	Safe practical autonomy is ensured by encapsulating an unreliable or untrusted machine learning algorithm within a control-based algorithm. A safety envelope is utilized to ensure that the machine learning algorithm does not output control signals that are beyond safe thresholds or limits. Secure practical autonomy is ensured by verification using digital certificates or cryptographic signatures. The verification may be for individual partitions of an autonomous system or apparatus. The partitions include trusted and untrusted partitions. Trusted partitions are verified for security, while untrusted partitions are verified for safety and security.