US 12,235,112 B1
Monitoring map data for validation of vehicle systems
Taylor Andrew Arnicar, Sunnyvale, CA (US); and Christopher James Gibson, Belmont, CA (US)
Assigned to Zoox, Inc., Foster City, CA (US)
Filed by Zoox, Inc., Foster City, CA (US)
Filed on Sep. 30, 2021, as Appl. No. 17/491,009.
Int. Cl. G01C 21/32 (2006.01); G01C 21/00 (2006.01)
CPC G01C 21/32 (2013.01) [G01C 21/3815 (2020.08); G01C 21/3844 (2020.08); G01C 21/387 (2020.08)] 19 Claims
OG exemplary drawing
 
1. A system comprising:
one or more processors; and
one or more non-transitory computer-readable media storing instructions that, when executed by the one or more processors, cause the system to perform operations comprising:
receiving sensor data associated with an environment in which a vehicle is operating;
generating, based at least in part on the sensor data, an estimated map indicating a detected location of a traffic control annotation relative to the vehicle, wherein the estimated map comprises a multi-channel image representing the environment surrounding the vehicle from a top-down perspective, and wherein individual channels of the multi-channel image represent different map features;
receiving, based at least in part on the sensor data, a stored map indicating at least an expected location of the traffic control annotation relative to the vehicle;
comparing the stored map with the estimated map, wherein the comparing comprises analyzing each of the individual channels of the multi-channel image and comparing to a per-channel threshold value;
determining, based at least in part on the comparing, an inconsistency between the detected location of the traffic control annotation and the expected location of the traffic control annotation;
determining, based at least in part on the inconsistency, that a source of the inconsistency is one of three possible sources, wherein at least one of:
determining that a first source of the inconsistency is an error associated with the stored map is based at least in part on determining that a first map element in the estimated map aligns with a first map element in the stored map and that a second map element in the estimated map does not align with a second map element in the stored map,
determining that a second source of the inconsistency is an error associated with a sensor system associated with the vehicle is based at least in part on determining that the first map element in the estimated map does not align with the first map element in the stored map and that the second map element in the estimated map does not align with the second map element in the stored map, and
determining that a third source of the inconsistency is an error associated with a localization system associated with the vehicle is based at least in part on determining that the estimated map can be realigned with the stored map; and
causing the vehicle to perform a remedial action based at least in part on determining that the source of the error is associated with at least one of the stored map, the sensor system, or the localization system.