US 12,073,729 B2
Machine-learned operating system and processor
John W. Borghese, Cedar Rapids, IA (US); Ryan M. Murphy, Marion, IA (US); and Ella M. Atkins, Ann Arbor, MI (US)
Assigned to Rockwell Collins, Inc., Cedar Rapids, IA (US)
Filed by Rockwell Collins, Inc., Cedar Rapids, IA (US)
Filed on Apr. 27, 2021, as Appl. No. 17/241,436.
Prior Publication US 2022/0343770 A1, Oct. 27, 2022
Int. Cl. G08G 5/00 (2006.01); B64C 39/02 (2023.01); G06N 20/00 (2019.01)
CPC G08G 5/0039 (2013.01) [B64C 39/024 (2013.01); G06N 20/00 (2019.01); B64U 2201/10 (2023.01)] 11 Claims
OG exemplary drawing
 
1. A computing device, comprising:
a user interface;
one or more operational processors, wherein the one or more operational processors are configured to execute a set of program instructions, wherein the set of program instructions is configured to cause the one or more operational processors to:
receive one or more input signals indicative of one or more input conditions, wherein the one or more input conditions comprise an altitude, an air speed, and a heading;
determine the one or more input conditions based on the one or more input signals;
determine one or more output signals based on the one or more determined input conditions, wherein the one or more output signals comprise an alert; and
provide the one or more output signals to the user interface; and
one or more machine-learning processors, wherein the one or more machine-learning processors are configured to develop one or more machine-learning analyzers, wherein the one or more machine-learning analyzers are configured to:
determine one or more predicted output signals based on the one or more input conditions;
identify one or more operational parameters of the one or more operational processors, wherein the one or more operational parameters comprise an accuracy of the one or more predicted output signals relative to the one or more output signals;
determine one or more modifications to the set of program instructions, wherein the one or more modifications satisfy a selected quality metric; and
provide the one or more modifications to the one or more operational processors such that the one or more operational processors execute the set of program instructions with the one or more modifications, wherein the one or more modifications increase the accuracy.