US 12,277,095 B2
Approaches for encoding environmental information
Lina Dong, San Francisco, CA (US); Weiyi Hou, Mountain View, CA (US); Somesh Khandelwal, San Jose, CA (US); Ivan Kirigin, Redwood City, CA (US); Shaojing Li, Mountain View, CA (US); Ying Liu, Los Altos, CA (US); David Tse-Zhou Lu, Menlo Park, CA (US); Robert Charles Kyle Pinkerton, Redwood City, CA (US); Vinay Shet, Fremont, CA (US); and Shaohui Sun, San Francisco, CA (US)
Assigned to Lyft, Inc., San Francisco, CA (US)
Filed by Lyft, Inc., San Francisco, CA (US)
Filed on Sep. 2, 2022, as Appl. No. 17/902,490.
Application 17/902,490 is a continuation of application No. 16/457,468, filed on Jun. 28, 2019, granted, now 11,449,475.
Prior Publication US 2023/0110659 A1, Apr. 13, 2023
Int. Cl. G06F 16/21 (2019.01); G06F 16/28 (2019.01); G06N 20/00 (2019.01); G06V 10/762 (2022.01); G06V 10/764 (2022.01); G06V 20/56 (2022.01); G05D 1/00 (2006.01)
CPC G06F 16/211 (2019.01) [G06F 16/285 (2019.01); G06N 20/00 (2019.01); G06V 10/762 (2022.01); G06V 10/764 (2022.01); G06V 20/56 (2022.01); G05D 1/0088 (2013.01); G05D 1/0276 (2013.01)] 18 Claims
OG exemplary drawing
 
1. A computer-implemented method comprising:
encoding, by a computing system, metadata for a map region based on map features that describe agents, actions performed by the agents at different times over a period of time, and environment associated with the map region;
determining, by the computing system, one or more scenarios for the map region based on the metadata;
determining, by the computing system, one or more first frequencies for the one or more scenarios in the map region;
identifying, by the computing system, a second map region associated with one or more second frequencies for the one or more scenarios, wherein the one or more second frequencies are within one or more threshold frequency differences of the one or more first frequencies; and
generating, by the computing system, a risk profile for the map region based on the one or more scenarios, the metadata, and a risk profile for the second map region, wherein the risk profile includes a first level of risk of encountering people and a second level of risk of encountering non-moving objects.