US 12,243,422 B2
Hierarchical transfer learning system
Xuewei Qi, Mountain View, CA (US); Kentaro Oguchi, Mountain View, CA (US); Yongkang Liu, Mountain View, CA (US); and Emrah Akin Sisbot, Menlo Park, CA (US)
Assigned to Toyota Motor Engineering & Manufacturing North America, Inc., Plano, TX (US)
Filed by Toyota Motor Engineering & Manufacturing North America, Inc., Plano, TX (US)
Filed on Feb. 25, 2022, as Appl. No. 17/681,092.
Prior Publication US 2023/0274641 A1, Aug. 31, 2023
Int. Cl. G08G 1/0967 (2006.01); G08G 1/01 (2006.01)
CPC G08G 1/096775 (2013.01) [G08G 1/0129 (2013.01)] 15 Claims
OG exemplary drawing
 
1. A system, comprising:
one or more processors, and
a memory communicably coupled to the one or more processors and storing: a control module including instructions that, when executed by the one or more processors cause the one or more processors to:
receive segments of a model from separate members in a geographic hierarchy;
assemble the segments into the model, wherein the segments include at least a first segment, a second segment, and a third segment, wherein the first segment includes common traffic rules, the second segment includes area specific trends, and the third segment includes local behaviors, wherein the first segment is based at least on an aggregate of trained weights from a plurality of devices within a first region, the second segment is based at least on an aggregate of trained weights from a plurality of devices within a second region, the third segment is based at least on an aggregate of trained weights from a plurality of devices within a third region, wherein the second region is a sub-region of and smaller than the first region, and wherein the third region is a sub-region of and smaller than the second region; and
process sensor data using the model to provide an output for assisting a device.