Map prior layer

Abstract

Systems, methods, and devices are disclosed for mapping historical information about behaviors of objects (vehicles, bicycles, pedestrians, etc.) at a location. Based on the mapped historical information, a prediction is determined about a behavior of an object proximate to an autonomous vehicle at the location, where the prediction is based on a statistical analysis of the historical information that is applied to the object. One or more behaviors of the AV are affected based on the prediction.

What is claimed is: 
     
         1 . A method comprising:
 performing a statistical analysis of historical information applied to an object proximate to an autonomous vehicle at a location to determine a statistical probability of the object performing a maneuver that would violate a semantic layer of a map that is utilized by the autonomous vehicle, wherein the semantic layer defines allowed maneuvers;   assigning the statistical probability as semantic data for the maneuver in the semantic layer of the map;   determining, based on the statistical analysis, a prediction of the object performing the maneuver; and   affecting a behavior of the autonomous vehicle based on the prediction.   
     
     
         2 . The method of  claim 1 , wherein determining the prediction is further based on a time of day. 
     
     
         3 . The method of  claim 1 , wherein determining the prediction is further based on a surrounding environment of the location. 
     
     
         4 . The method of  claim 3 , wherein the surrounding environment includes at least one of a school zone, a bus route, a fire station, and a police station. 
     
     
         5 . The method of  claim 1 , wherein determining the prediction is further based on a type of the object. 
     
     
         6 . The method of  claim 1 , wherein the semantic map identifies lanes that are legally coupled to other lanes, and wherein the maneuver results in the object taking a path from a lane that is not legally coupled to another lane. 
     
     
         7 . The method of  claim 1 , wherein the maneuver is one of going straight through an intersection instead of turning, a lane change performed mid-intersection, and an illegal turn. 
     
     
         8 . A non-transitory computer-readable medium storing instructions thereon, wherein the instructions, when executed by one or more processors, cause the one or more processors to perform operations comprising:
 performing a statistical analysis of historical information applied to an object proximate to an autonomous vehicle at a location to determine a statistical probability of the object performing a maneuver that would violate a semantic layer of a map that is utilized by the autonomous vehicle, wherein the semantic layer defines allowed maneuvers;   assigning the statistical probability as semantic data for the maneuver in the semantic layer of the map;   determining, based on the statistical analysis, a prediction of the object performing the maneuver; and   affecting a behavior of the autonomous vehicle based on the prediction.   
     
     
         9 . The non-transitory computer-readable medium of  claim 8 , wherein determining the prediction is further based on a time of day. 
     
     
         10 . The non-transitory computer-readable medium of  claim 8 , wherein determining the prediction is further based on a surrounding environment of the location. 
     
     
         11 . The non-transitory computer-readable medium of  claim 10 , wherein the surrounding environment includes at least one of a school zone, a bus route, a fire station, and a police station. 
     
     
         12 . The non-transitory computer-readable medium of  claim 8 , wherein determining the prediction is further based on a type of the object. 
     
     
         13 . The non-transitory computer-readable medium of  claim 8 , wherein determining the prediction is further based on a type of the object. 
     
     
         14 . The non-transitory computer-readable medium of  claim 8 , wherein the maneuver is one of going straight through an intersection instead of turning, a lane change performed mid-intersection, and an illegal turn. 
     
     
         15 . A system comprising:
 a processor; and   a non-transitory memory storing computer-executable instructions thereon, wherein the computer-executable instructions, when executed by the processor, cause the processor to perform operations comprising:   performing a statistical analysis of historical information applied to an object proximate to an autonomous vehicle at a location to determine a statistical probability of the object performing a maneuver that would violate a semantic layer of a map that is utilized by the autonomous vehicle, wherein the semantic layer defines allowed maneuvers;   assigning the statistical probability as semantic data for the maneuver in the semantic layer of the map;   determining, based on the statistical analysis, a prediction of the object performing the maneuver; and   affecting a behavior of the autonomous vehicle based on the prediction.   
     
     
         16 . The system of  claim 15 , wherein determining the prediction is further based on a time of day. 
     
     
         17 . The system of  claim 15 , wherein determining the prediction is further based on a surrounding environment of the location. 
     
     
         18 . The system of  claim 17 , wherein the surrounding environment includes at least one of a school zone, a bus route, a fire station, and a police station. 
     
     
         19 . The system of  claim 15 , wherein determining the prediction is further based on a type of the object. 
     
     
         20 . The system of  claim 15 , wherein determining the prediction is further based on a type of the object.