Map change detection

Abstract

The present technology provides systems, methods, and devices that can update aspects of a map as an autonomous vehicle navigates a route, and therefore avoids the need for dispatching a special purpose mapping vehicle for these updates. As the autonomous vehicle navigates the route, data captured by at least one sensor of an autonomous vehicle can indicate an inconsistency between pre-mapped from a high-resolution sensor system describing a location on a map, and current data describing a new feature of the location. The current data can be clustered together based on a threshold spatial closeness, where the clustering describes the new feature, and semantic labels of the pre-mapped data from the high-resolution sensor system can be updated based on the new feature described by the clustered current data.

What is claimed is: 
     
         1 . A method comprising:
 receiving current data captured by at least one sensor on an autonomous vehicle as the autonomous vehicle navigates a route, wherein the current data is received when the autonomous vehicle identifies an inconsistency between pre-mapped data describing a location on a map and the current data;   accessing sensor data used to generate the pre-mapped data;   comparing the sensor data and the current data to confirm the inconsistency; and   determining whether the inconsistency renders autonomous driving associated with the autonomous vehicle unsafe.   
     
     
         2 . The method of  claim 1 , further comprising:
 sending an instruction to the autonomous vehicle to stop based on the inconsistency rendering the autonomous driving associated with the autonomous vehicle unsafe.   
     
     
         3 . The method of  claim 1 , further comprising:
 updating semantic labels related to autonomous navigation of the map based on the current data.   
     
     
         4 . The method of  claim 1 , further comprising:
 adding semantic labels related to autonomous navigation of the map based on the current data; and   storing the current data with the pre-mapped data.   
     
     
         5 . The method of  claim 1 , further comprising:
 after receiving the current data, receiving second current data captured by a different autonomous vehicle as the different autonomous vehicle navigates a different route, wherein the second current data is received when the different autonomous vehicle identifies an inconsistency between the pre-mapped data describing the location on the map and the second current data; and   updating the map based on the current data and the second current data identifying the inconsistency.   
     
     
         6 . The method of  claim 1 , further comprising:
 after receiving the current data, receiving second current data captured by a different autonomous vehicle as the different autonomous vehicle navigates a different route, wherein the second current data is received when the different autonomous vehicle identifies a different inconsistency between the pre-mapped data describing the location on the map and the second current data,   wherein the map is not updated based on the different inconsistency identified by the different autonomous vehicle.   
     
     
         7 . The method of  claim 1 , wherein the inconsistency comprises a traffic configuration object that provides visual driving information. 
     
     
         8 . The method of  claim 1 , wherein the inconsistency comprises a lane marker change that is painted onto a road. 
     
     
         9 . The method of  claim 8 , wherein the lane marker comprises at least one of a pedestrian crossing or a stop marker. 
     
     
         10 . The method of  claim 1 , further comprising:
 providing instruction for a mapping vehicle to remap the location associated with the map.   
     
     
         11 . A system comprising:
 a storage configured to store instructions;   a processor configured to execute the instructions and cause the processor to:
 receive current data captured by at least one sensor on an autonomous vehicle as the autonomous vehicle navigates a route, wherein the current data is received when the autonomous vehicle identifies an inconsistency between pre-mapped data describing a location on a map and the current data; 
 access sensor data used to generate the pre-mapped data; 
 compare the sensor data and the current data to confirm the inconsistency; and 
 determine whether the inconsistency renders autonomous driving associated with the autonomous vehicle unsafe. 
   
     
     
         12 . The system of  claim 11 , wherein the processor is configured to execute the instructions and cause the processor to:
 send an instruction to the autonomous vehicle to stop based on the inconsistency rendering the autonomous driving associated with the autonomous vehicle unsafe.   
     
     
         13 . The system of  claim 11 , wherein the processor is configured to execute the instructions and cause the processor to:
 update semantic labels related to autonomous navigation of the map based on the current data.   
     
     
         14 . The system of  claim 11 , wherein the processor is configured to execute the instructions and cause the processor to:
 add semantic labels related to autonomous navigation of the map based on the current data; and   store the current data with the pre-mapped data.   
     
     
         15 . The system of  claim 11 , wherein the processor is configured to execute the instructions and cause the processor to:
 after receiving the current data, receive second current data captured by a different autonomous vehicle as the different autonomous vehicle navigates a different route, wherein the second current data is received when the different autonomous vehicle identifies an inconsistency between the pre-mapped data describing the location on the map and the second current data; and   update the map based on the current data and the second current data identifying the inconsistency.   
     
     
         16 . The system of  claim 11 , wherein the processor is configured to execute the instructions and cause the processor to:
 after receiving the current data, receive second current data captured by a different autonomous vehicle as the different autonomous vehicle navigates a different route, wherein the second current data is received when the different autonomous vehicle identifies a different inconsistency between the pre-mapped data describing the location on the map and the second current data,   wherein the map is not updated based on the different inconsistency identified by the different autonomous vehicle.   
     
     
         17 . The system of  claim 11 , wherein the inconsistency comprises a traffic configuration object that provides visual driving information. 
     
     
         18 . The system of  claim 11 , wherein the inconsistency comprises a lane marker change that is painted onto a road. 
     
     
         19 . The system of  claim 18 , wherein the lane marker comprises at least one of a pedestrian crossing or a stop marker. 
     
     
         20 . The system of  claim 11 , wherein the processor is configured to execute the instructions and cause the processor to:
 provide instruction for a mapping vehicle to remap the location associated with the map.