US 11,741,724 B2
Configuring a neural network to produce an electronic road map that has information to distinguish lanes of a road
Shunsho Kaku, Mountain View, CA (US); Jeffrey M. Walls, Ann Arbor, MI (US); and Ryan W. Wolcott, Ann Arbor, MI (US)
Assigned to Toyota Research Institute, Inc., Los Altos, CA (US)
Filed by Toyota Research Institute, Inc., Los Altos, CA (US)
Filed on Feb. 25, 2021, as Appl. No. 17/184,773.
Prior Publication US 2022/0269891 A1, Aug. 25, 2022
Int. Cl. G06N 3/08 (2023.01); G06F 18/21 (2023.01); G06N 3/047 (2023.01); G06V 20/56 (2022.01); G06V 20/52 (2022.01); G06V 30/194 (2022.01)
CPC G06V 20/588 (2022.01) [G06F 18/21 (2023.01); G06N 3/047 (2023.01); G06N 3/08 (2013.01); G06V 20/52 (2022.01); G06V 30/194 (2022.01)] 20 Claims
OG exemplary drawing
 
1. A system, comprising:
a processor; and
a memory storing:
a preliminary processing module including instructions that when executed by the processor cause the processor to:
detect a feature in an image that was produced at a current time, the image being of a road; and
determine that the feature in the image corresponds to a feature, of a plurality of features, in a feature map that was produced at a prior time from at least one image, wherein the image includes another feature, but the other feature in the image lacks a corresponding other feature in the feature map; and
a neural network training module including instructions that when executed by the processor cause the processor to:
produce, from the feature in the image and the plurality of features in the feature map, a labeled training map that has information to distinguish lanes of the road; and
train a neural network to produce, in response to a receipt of the image and the feature map, the labeled training map.