Map Uncertainty and Observation Modeling

Abstract

Systems and methods are described that provide measures of uncertainty for map features provided in association with a vehicle map service. A vehicle map service may include a vehicle map model that is configured to provide map data for a geographic area in association with a vehicle map service. The vehicle map model can have an entity schema that includes a first address space configured to represent a plurality of entities associated with the vehicle map model. The vehicle may service may include an uncertainty model that is configured to represent a plurality of uncertainties associated with the plurality of entities. The uncertainty model can have an uncertainty schema that includes a second address space that is separate from the first address space. Uncertainties in the second address space can point to one or more entities in the first address space.

1 .- 20 . (canceled) 
     
     
         21 . A computing system for a vehicle map service, comprising:
 one or more non-transitory computer-readable media that collectively store:
 a vehicle map model including a plurality of entities defined according to an entity schema of the vehicle map model, and 
 an uncertainty model, separate from the vehicle map model, configured to represent a plurality of uncertainties associated with the plurality of entities and including an uncertainty schema; and 
   one or more processors configured to:
 apply an uncertainty measure from the uncertainty model to an entity among the plurality of entities from the vehicle map model, according to a mapping between the uncertainty model and the vehicle map model, and 
 determine information about map data for the vehicle map service according to the application of the uncertainty measure to the entity. 
   
     
     
         22 . The computing system of  claim 21 , wherein the one or more processors are configured to:
 obtain sensor data from one or more sensors of a vehicle, the sensor data associated with a geographic area; and   generate the map data based on the sensor data by:
 generating, based on the vehicle map model and the sensor data, a first entity among the plurality of the entities, wherein the first entity is defined according to the entity schema of the vehicle map model; and 
 generating, based on the uncertainty model and the sensor data, one or more uncertainty relations with respect to the first entity, wherein the one or more uncertainty relations are defined according to the uncertainty schema of the uncertainty model. 
   
     
     
         23 . The computing system of  claim 21 , wherein:
 the plurality of entities include a plurality of unique entities and a plurality of hypothesized entities.   
     
     
         24 . The computing system of  claim 23 , wherein:
 at least one of the plurality of uncertainties relates a first unique entity among the plurality of unique entities with a first hypothesized entity among the plurality of hypothesized entities.   
     
     
         25 . The computing system of  claim 23 , wherein:
 each of the plurality of unique entities is unique among the plurality of unique entities; and   each of the plurality of hypothesized entities can lack uniqueness among the plurality of unique entities and among the plurality of hypothesized entities.   
     
     
         26 . The computing system of  claim 23 , wherein:
 the entity schema comprises one or more first map layers, and   the uncertainty schema is configured to point to unique entities in the one or more first map layers and hypothesized entities in the one or more first map layers.   
     
     
         27 . The computing system of  claim 23 , wherein:
 the entity schema comprises one or more first map layers, and   the one or more first map layers include a unique entity address space corresponding to the plurality of unique entities and a hypothesized entity address space corresponding to the plurality of hypothesized entities.   
     
     
         28 . The computing system of  claim 23 , wherein:
 the plurality of hypothesized entities include a first hypothesized entity and a second hypothesized entity; and   the uncertainty model includes one or more uncertainty relations that model one or more joint existence relations between the first hypothesized entity and the second hypothesized entity.   
     
     
         29 . The computing system of  claim 23 , wherein:
 the uncertainty schema comprises a clustering relation configured to reference two or more hypothesized entities that are taken to be a same real-world entity.   
     
     
         30 . The computing system of  claim 29 , wherein:
 the clustering relation includes a respective weight for each of the two or more hypothesized entities.   
     
     
         31 . The computing system of  23 , wherein:
 the uncertainty schema comprises a mutual exclusion relation configured to reference two or more hypothesized entities that are not a same real-world entity.   
     
     
         32 . The computing system of  claim 21 , wherein:
 the entity schema includes a plurality of properties associated with at least one entity among the plurality of entities; and   the uncertainty schema includes one or more uncertainty relations that point to one or more of the plurality of properties of the at least one entity to describe one or more error functions on or between the one or more of the plurality of properties associated with the at least one entity.   
     
     
         33 . The computing system of  claim 21 , wherein:
 the plurality of entities includes a first entity and a second entity; and   the uncertainty model includes one or more uncertainty relations that associate one or more properties of the first entity with one or more properties of the second entity.   
     
     
         34 . The computing system of  claim 21 , wherein:
 the uncertainty model includes one or more uncertainty relations associated with at least one entity of the plurality of entities;   the one or more uncertainty relations include a context; and   the context of the one or more uncertainty relations includes a unique address space that attaches to the one or more uncertainty relations to indicate a source of the one or more uncertainty relations.   
     
     
         35 . The computing system of  claim 21 , wherein:
 the entity schema comprises one or more first map layers,   the uncertainty schema comprises one or more second map layers, separate from the one or more first map layers, and   at least one of the plurality of uncertainties in the one or more second map layers relates to two or more of the plurality of entities in the one or more first map layers.   
     
     
         36 . The computing system of  claim 21 , wherein:
 the uncertainty schema comprises a pose relation;   the pose relation includes a reference to at least a first entity among the plurality of entities as a base entity; and   the pose relation includes a reference to at least a second entity among the plurality of entities as a relative entity whose pose is uncertain relative to the base entity.   
     
     
         37 . The computing system of  claim 36 , wherein:
 the pose relation is a first pose relation and the base entity is a first base entity;   the uncertainty schema comprises a second pose relation;   the second pose relation includes a reference to at least a third entity among the plurality of entities as a second base entity; and   the pose relation includes a reference to at least the second entity among the plurality of entities as the relative entity whose pose is uncertain relative to the second base entity.   
     
     
         38 . The computing system of  claim 37 , wherein:
 the pose relation includes a velocity model of a velocity vector or velocity tensor of the relative entity with respect to the base entity.   
     
     
         39 . A computer-implemented method of operating a vehicle map service, the method comprising:
 accessing, by one or more computing devices, a map model comprising a plurality of entities defined according to an entity schema of the vehicle map model;   accessing, by the one or more computing devices, an uncertainty model configured to represent a plurality of uncertainties associated with the plurality of entities and including an uncertainty schema;   applying, by the one or more computing devices, an uncertainty measure from the uncertainty model to an entity among the plurality of entities from the vehicle map model, according to a mapping between the uncertainty model and the vehicle map model; and   determining, by the one or more computing devices, information about map data for the vehicle map service according to the application of the uncertainty measure to the entity.   
     
     
         40 . One or more non-transitory computer-readable media that store instructions that, when executed by one or more processors, cause the one or more processors to perform operations, the operations comprising:
 accessing, by one or more computing devices, a map model comprising a plurality of entities defined according to an entity schema of the vehicle map model;   accessing, by the one or more computing devices, an uncertainty model configured to represent a plurality of uncertainties associated with the plurality of entities and including an uncertainty schema;   applying, by the one or more computing devices, an uncertainty measure from the uncertainty model to an entity among the plurality of entities from the vehicle map model, according to a mapping between the uncertainty model and the vehicle map model; and determining, by the one or more computing devices, information about map data for the vehicle map service according to the application of the uncertainty measure to the entity.