US 12,223,847 B2
Spatio-temporal track density shaping
Thomas Frewen, West Hartford, CT (US); Hala Mostafa, Marlborough, CT (US); Michael D. Dubois, Franklin, MA (US); and Stephen K. Freitag, Marlborough, MA (US)
Assigned to Raytheon Company, Arlington, VA (US)
Filed by Raytheon Company, Arlington, VA (US)
Filed on Feb. 22, 2022, as Appl. No. 17/677,663.
Prior Publication US 2023/0267844 A1, Aug. 24, 2023
Int. Cl. G08G 5/00 (2006.01); G06F 18/214 (2023.01); G06N 20/00 (2019.01)
CPC G08G 5/0043 (2013.01) [G06F 18/2148 (2023.01); G06N 20/00 (2019.01); G08G 5/0013 (2013.01)] 17 Claims
OG exemplary drawing
 
1. A process comprising:
receiving into a computer processor a first dataset of vehicle trajectories comprising a plurality of individual vehicle tracks forming a first track density;
receiving into the computer processor a vehicle track density profile;
receiving into the computer processor a target spatio-temporal coverage metric that is an indication of a user-specified vehicle track density profile;
receiving into the computer processor a track model comprising a plurality of Heaviside functions encoding track time origins and durations for the plurality of individual vehicle tracks and comprising locations for the plurality of individual vehicle tracks;
minimizing an approximation of the Heaviside functions as a function of the target spatio-temporal coverage metric;
optimizing the first dataset of vehicle trajectories as a function of the vehicle track density profile and the minimized approximation of the Heaviside functions;
reshaping each individual vehicle track start time and start location in the first dataset of vehicle trajectories as a function of the optimizing, thereby generating a second dataset of vehicle trajectories having a second track density; and
training a vehicle resources machine learning algorithm using the second dataset of vehicle trajectories.