US 12,007,248 B2
Ice thickness estimation for mobile object operation
Arun Dutta, Ann Arbor, MI (US); Nithya Somanath, Farmington Hills, MI (US); Colleen Cauvet, Canton, MI (US); Collin Hurley, Canton, MI (US); David Hamilton, Troy, MI (US); Donald Paul Bilger, Livonia, MI (US); and Javier Onate, Muncie, DE (US)
Assigned to Ford Global Technologies, LLC, Dearborn, MI (US)
Filed by Ford Global Technologies, LLC, Dearborn, MI (US)
Filed on Mar. 3, 2022, as Appl. No. 17/685,443.
Prior Publication US 2023/0280181 A1, Sep. 7, 2023
Int. Cl. G06F 17/00 (2019.01); B60W 40/06 (2012.01); B63B 49/00 (2006.01); B63B 79/15 (2020.01); G01C 21/00 (2006.01); G01C 21/34 (2006.01); G01C 21/36 (2006.01); G06N 3/08 (2023.01); G01B 15/02 (2006.01); G01J 5/00 (2022.01)
CPC G01C 21/3841 (2020.08) [B60W 40/06 (2013.01); B63B 49/00 (2013.01); B63B 79/15 (2020.01); G01C 21/3461 (2013.01); G01C 21/3626 (2013.01); G01C 21/3815 (2020.08); G06N 3/08 (2013.01); B60W 2555/20 (2020.02); B60W 2556/50 (2020.02); G01B 15/02 (2013.01); G01J 2005/0077 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A system, comprising a computer including a processor and a memory, the memory storing instructions executable by the processor programmed to:
upon determining a mobile object is approaching an ice layer above a body of water, obtain a thermal image of the ice layer;
input the thermal image and ambient temperature data to a neural network that outputs a plurality of regions of the ice layer and respective estimated thicknesses for the regions;
determine a classification for each region based on its estimated thickness and the mobile object, wherein the classification is one of preferred or nonpreferred;
predict a future time at which the classification for one region will transition between preferred and nonpreferred based on a characteristic of the mobile object and predicted ambient temperature data; and
output the classifications for the regions.