Map updates based on data captured by an autonomous vehicle

Abstract

The present technology provides a system that can update aspects of an authoritative map portion stored on an autonomous vehicle using low-resolution data from the at least one sensor of the autonomous vehicle, and therefore avoids the need for dispatching the special purpose mapping vehicle for these updates. The captured low-resolution data can be compared with the high-resolution map portion to determine that the sensor data reflects a feature in a way that is inconsistent with how that feature is represented in the authoritative map portion. The sensor data can then be used to relabel the authoritative map portion.

1 . A computer-implemented method comprising:
 receiving data indicating an inconsistency between stored data describing a feature of a location, and current data describing the feature of the location, wherein the stored data comprises semantic labels identifying the feature, and wherein the current data is captured by at least one sensor of an autonomous vehicle;   automatically checking for an availability of pre-existing updates to the semantic labels associated with the stored data based on the inconsistency;   generating revised data based on the current data if no pre-existing updates to the semantic labels are available; and   publishing the revised data.   
     
     
         2 . The computer-implemented method of  claim 1 , wherein the revised data comprises a combination of the stored data the current data. 
     
     
         3 . The computer-implemented method of  claim 1 , wherein the stored data comprises high-resolution point cloud data collected from a Light Detection and Ranging (LiDAR) system of a special purpose mapping vehicle. 
     
     
         4 . The computer-implemented method of  claim 1 , further comprising:
 storing the current data and associating it with an identifier; and   tagging the revised data with the identifier of the current data, whereby a source of the revised semantic labels is indicated by the identifier of the current data.   
     
     
         5 . The computer-implemented method of  claim 1 , wherein the stored data and revised data pertains to a map portion defined by a boundary of location coordinates, wherein the stored data is an earlier version of the map portion, and the revised data is a later, revised version of the map portion. 
     
     
         6 . The computer-implemented method of  claim 5 , comprising:
 publishing a restriction on a use of the map portion upon the receipt of the data indicating the inconsistency between stored data and the current data; and   removing the restriction on the use of the map portion after the revised data has been published.   
     
     
         7 . The computer-implemented method of  claim 1 , wherein the revised data corresponds to a location of a traffic lane line. 
     
     
         8 . A computing system comprising:
 at least one non-transitory computer readable medium comprising instructions stored thereon, wherein the instructions are effective to cause the computing system to:   receive data indicating an inconsistency between stored data describing a feature of a location, and current data describing the feature of the location, wherein the stored data comprises semantic labels identifying the feature, and wherein the current data is captured by at least one sensor of an autonomous vehicle;   automatically check for an availability of pre-existing updates to the semantic labels associated with the stored data based on the inconsistency;   generate revised data based on the current data if no pre-existing updates to the semantic labels are available; and   publish the revised data.   
     
     
         9 . The computing system of  claim 8 , wherein the revised data comprises a combination of the stored data the current data. 
     
     
         10 . The computing system of  claim 8 , wherein the stored data comprises high-resolution point cloud data collected from a Light Detection and Ranging (LiDAR) system of a special purpose mapping vehicle. 
     
     
         11 . The computing system of  claim 8 , further comprising:
 storing the current data and associating it with an identifier; and   tagging the revised data with the identifier of the current data, whereby a source of the revised semantic labels is indicated by the identifier of the current data.   
     
     
         12 . The computing system of  claim 8 , wherein the stored data and revised data pertain to a map portion defined by a boundary of location coordinates, wherein the stored data is an earlier version of the map portion, and the revised data is a later, revised version of the map portion. 
     
     
         13 . The computing system of  claim 8 , wherein the instructions are effective to further cause the computing system to:
 publish a restriction on a use of the map portion upon the receipt of the data indicating the inconsistency between stored data and the current data; and   remove the restriction on the use of the map portion after the revised data has been published.   
     
     
         14 . The computing system of  claim 8 , wherein the revised data corresponds to a location of a traffic lane line. 
     
     
         15 . A non-transitory computer readable medium comprising instructions stored thereon, wherein the instructions are effective to cause an autonomous vehicle to:
 receive data indicating an inconsistency between stored data describing a feature of a location, and current data describing the feature of the location, wherein the stored data comprises semantic labels identifying the feature, and wherein the current data is captured by at least one sensor of an autonomous vehicle;   automatically check for an availability of pre-existing updates to the semantic labels associated with the stored data based on the inconsistency;   generate revised data based on the current data if no pre-existing updates to the semantic labels are available; and   publish the revised data.   
     
     
         16 . The non-transitory computer readable medium of  claim 15 , wherein the revised data comprises a combination of the stored data the current data. 
     
     
         17 . The non-transitory computer readable medium of  claim 15 , wherein the stored data comprises high-resolution point cloud data collected from a Light Detection and Ranging (LiDAR) system of a special purpose mapping vehicle. 
     
     
         18 . The non-transitory computer readable medium of  claim 15 , wherein the instructions are further effective to cause the autonomous vehicle to:
 store the current data and associating it with an identifier; and   tag the revised data with the identifier of the current data, whereby a source of the revised semantic labels is indicated by the identifier of the current data.   
     
     
         19 . The non-transitory computer readable medium of  claim 15 , wherein the stored data and revised data pertain to a map portion defined by a boundary of location coordinates, wherein the stored data is an earlier version of the map portion, and the revised data is a later, revised version of the map portion. 
     
     
         20 . The non-transitory computer readable medium of  claim 15 , wherein the instructions are effective to further cause the computing system to:
 publish a restriction on a use of the map portion upon the receipt of the data indicating the inconsistency between stored data and the current data; and   remove the restriction on the use of the map portion after the revised data has been published.