Updating maps based on traffic object detection

Abstract

Systems, methods, and computer-readable media are provided for receiving traffic object data from a plurality of autonomous vehicles, the traffic object data including a geographic location of a traffic object, comparing the traffic object data of each of the plurality of autonomous vehicles with known traffic object data, determining a discrepancy between the traffic object data of each of the plurality of autonomous vehicles and the known traffic object data, grouping the traffic object data of each of the plurality of autonomous vehicles based on the determining of the discrepancy between the traffic object data of each of the plurality of autonomous vehicles and the known traffic object data, determining whether a group of traffic object data of the grouping of the traffic object data of each of the plurality of autonomous vehicles exceeds a threshold; and updating a traffic object map based on the traffic object data of the group that exceeds the threshold.

What is claimed is: 
     
         1 . A computer-implemented method comprising:
 measuring a global position and a global heading of an autonomous vehicle;   imaging, by sensors of the autonomous vehicle, a surrounding of the autonomous vehicle, the surrounding including at least a road surface to obtain road image data;   processing the road image data into at least one of localization data, guidance data, and mapping data; and   generating a local map of road features surrounding the autonomous vehicle based on the at least one of localization data, guidance data, and mapping data, wherein the local map is correlated to a global map, and wherein the global map is a map of features that extends beyond a certain proximity of the autonomous vehicle.   
     
     
         2 . The computer-implemented method of  claim 1 , further comprising:
 measuring a relative heading of the autonomous vehicle relative to a roadway by measuring distortion of a road feature as imaged by a sensor of the autonomous vehicle.   
     
     
         3 . The computer-implemented method of  claim 1 , further comprising:
 receiving pre-existing map data, wherein the pre-existing map data is used to aid in generating the local map; and   refining an initial estimate of location by comparing the road image data to linked position data for matching images of the pre-existing map data to provide a more accurate position estimate than via the initial estimate of location alone.   
     
     
         4 . The computer-implemented method of  claim 1 , wherein refining the initial estimate of location includes image warping techniques to correct for differences in perspective. 
     
     
         5 . The computer-implemented method of  claim 1 , further comprising:
 receiving pre-existing map data, wherein the pre-existing map data is used to aid in generating the local map, and wherein the pre-existing map data provides a first estimate of location that is refined during generation of the local map.   
     
     
         6 . The computer-implemented method of  claim 1 , further comprising:
 receiving pre-existing map data, wherein the pre-existing map data is used to calibrate the sensors of the AV based on a set of road surface images linked to a precise location.   
     
     
         7 . The computer-implemented method of  claim 1 , further comprising:
 receiving pre-existing map data; and   providing predictions by using the pre-existing map data in concert with a rear-facing camera.   
     
     
         8 . The computer-implemented method of  claim 7 , wherein the predictions are lane boundaries in front of the autonomous vehicle based on image data from the rear-facing camera taken from a rear of the autonomous vehicle. 
     
     
         9 . A system comprising:
 a processor; and   a non-transitory memory storing computer-readable instructions, which when executed by the processor, cause the processor to perform operations comprising:   measuring a global position and a global heading of an autonomous vehicle;   imaging, by sensors of the autonomous vehicle, a surrounding of the autonomous vehicle, the surrounding including at least a road surface to obtain road image data;   processing the road image data into at least one of localization data, guidance data, and mapping data; and   generating a local map of road features surrounding the autonomous vehicle based on the at least one of localization data, guidance data, and mapping data, wherein the local map is correlated to a global map, and wherein the global map is a map of features that extends beyond a certain proximity of the autonomous vehicle.   
     
     
         10 . The system of  claim 9 , wherein the computer-readable instructions, when executed by the processor, further cause the processor to perform operations comprising:
 measuring a relative heading of the autonomous vehicle relative to a roadway by measuring distortion of a road feature as imaged by a sensor of the autonomous vehicle.   
     
     
         11 . The system of  claim 9 , wherein the computer-readable instructions, when executed by the processor, further cause the processor to perform operations comprising:
 receiving pre-existing map data, wherein the pre-existing map data is used to aid in generating the local map; and   refining an initial estimate of location by comparing the road image data to linked position data for matching images of the pre-existing map data to provide a more accurate position estimate than via the initial estimate of location alone.   
     
     
         12 . The system of  claim 9 , wherein refining the initial estimate of location includes image warping techniques to correct for differences in perspective. 
     
     
         13 . The system of  claim 9 , wherein the computer-readable instructions, when executed by the processor, further cause the processor to perform operations comprising:
 receiving pre-existing map data, wherein the pre-existing map data is used to aid in generating the local map, and wherein the pre-existing map data provides a first estimate of location that is refined during generation of the local map.   
     
     
         14 . The system of  claim 9 , wherein the computer-readable instructions, when executed by the processor, further cause the processor to perform operations comprising:
 receiving pre-existing map data, wherein the pre-existing map data is used to calibrate the sensors of the AV based on a set of road surface images linked to a precise location.   
     
     
         15 . The system of  claim 9 , wherein the computer-readable instructions, when executed by the processor, further cause the processor to perform operations comprising:
 receiving pre-existing map data; and   providing predictions by using the pre-existing map data in concert with a rear-facing camera.   
     
     
         16 . The system of  claim 15 , wherein the predictions are lane boundaries in front of the autonomous vehicle based on image data from the rear-facing camera taken from a rear of the autonomous vehicle. 
     
     
         17 . A non-transitory computer-readable medium comprising instructions stored therein, which when executed by one or more processors, cause the one or more processors to perform operations comprising:
 measuring a global position and a global heading of an autonomous vehicle;   imaging, by sensors of the autonomous vehicle, a surrounding of the autonomous vehicle, the surrounding including at least a road surface to obtain road image data;   processing the road image data into at least one of localization data, guidance data, and mapping data; and   generating a local map of road features surrounding the autonomous vehicle based on the at least one of localization data, guidance data, and mapping data, wherein the local map is correlated to a global map, and wherein the global map is a map of features that extends beyond a certain proximity of the autonomous vehicle.   
     
     
         18 . The non-transitory computer-readable medium of  claim 17 , wherein the instructions, when executed by the one or more processors, further cause the one or more processor to perform operations comprising:
 measuring a relative heading of the autonomous vehicle relative to a roadway by measuring distortion of a road feature as imaged by a sensor of the autonomous vehicle.   
     
     
         19 . The non-transitory computer-readable medium of  claim 17 , wherein the instructions, when executed by the one or more processors, further cause the one or more processor to perform operations comprising:
 receiving pre-existing map data, wherein the pre-existing map data is used to aid in generating the local map; and   refining an initial estimate of location by comparing the road image data to linked position data for matching images of the pre-existing map data to provide a more accurate position estimate than via the initial estimate of location alone.   
     
     
         20 . The non-transitory computer-readable medium of  claim 17 , wherein
 refining the initial estimate of location includes image warping techniques to correct for differences in perspective.