US 12,118,883 B2
Utilization of reflectivity to determine changes to traffic infrastructure elements
Nestor Grace, San Francisco, CA (US); Dogan Gidon, Berkeley, CA (US); Diego Plascencia-Vega, San Francisco, CA (US); Srishti Iyer Koduvayur, Emeryville, CA (US); and Hooman Barekatain, San Francisco, CA (US)
Assigned to GM Cruise Holdings LLC, San Francisco, CA (US)
Filed by GM Cruise Holdings LLC, San Francisco, CA (US)
Filed on Apr. 15, 2020, as Appl. No. 16/849,657.
Prior Publication US 2021/0327269 A1, Oct. 21, 2021
Int. Cl. G08G 1/0967 (2006.01); G01C 21/30 (2006.01); G01S 17/89 (2020.01); G05D 1/00 (2024.01)
CPC G08G 1/096725 (2013.01) [G01C 21/30 (2013.01); G01S 17/89 (2013.01); G05D 1/0088 (2013.01); G05D 1/0274 (2013.01); G05D 1/0285 (2013.01)] 21 Claims
OG exemplary drawing
 
1. A computer-implemented method comprising:
analyzing sensor data returned from a traffic infrastructure element, wherein the sensor data includes LiDAR intensity information corresponding to visual characteristics of the traffic infrastructure element;
determining reflectivity information of the traffic infrastructure element based on the analyzing of the sensor data;
comparing the reflectivity information of the traffic infrastructure element with semantic map information of the traffic infrastructure element, wherein:
the semantic map information is part of a semantic map that is generated based on sensor data captured by a plurality of vehicles and is provided to the plurality of vehicles in response to the sensor data matching across the plurality of vehicles; and
the semantic map information includes blacklisted road segment information indicating degraded infrastructure that is identified from reflectivity information of the degraded infrastructure in the sensor data captured by the plurality of vehicles;
determining that the reflectivity information of the traffic infrastructure element does not match the semantic map information of the traffic infrastructure element based on a detection that the traffic infrastructure element has been tampered with based on the reflectivity information indicating a change in material of the traffic infrastructure element;
providing instructions to an autonomous vehicle based on the reflectivity information of the traffic infrastructure element not matching the semantic map information of the traffic infrastructure element, wherein the instructions are effective to cause the autonomous vehicle to operate based on the semantic map information instead of the reflectivity information; and
controlling the autonomous vehicle to operate based on the semantic map information according to the instructions and a road utilization quality index that is identified based on the blacklisted road segment information included in the semantic map information.