Network computer system for analyzing driving actions of drivers on road segments of a geographic region

Abstract

Examples include a network computer system and/or service which operates to remotely monitor vehicles to detect and characterize driving actions of drivers with respect to specific road segments of a roadway, enabling driving actions performed by multiple drivers at a specific road segment to be characterized and modeled. Models can inform municipalities about potential traffic hazards or other safety challenges. Individual drivers can also be measured against the model to help understand driver performance. Validating vehicle data against baseline values can also detect spoofing of that data.

What is being claimed is: 
     
         1 . A method for evaluating driver performance, the method being performed by one or more processors and comprising:
 retrieving, for a given road segment of a geographic region, a baseline or model characterization for at least one driving action, wherein generation of the retrieved baseline or model characterization comprises:
 receiving, over one or more networks, vehicle data from a plurality of vehicles that individually traverse the given road segment, the vehicle data of each of the plurality of vehicles including sensor-based vehicle state information and data indicative of one or more attributes of that vehicle's motion while the vehicle is traversing the given road segment; 
 for each of the plurality of vehicles, determining, based on the vehicle data of that vehicle, a characterization of at least one driving action performed using that vehicle at the given road segment; 
 aggregating the characterizations determined for the plurality of vehicles; and 
 determining, for the given road segment, the baseline or model characterization for the at least one driving action based at least in part on the aggregated characterizations; 
   receiving new vehicle data from an additional vehicle, the new vehicle data indicating that the additional vehicle traversed the given road segment;   determining, based on the new vehicle data of the additional vehicle, a characterization of at least one driving action performed using the additional vehicle at the given road segment;   comparing the determined characterization of the at least one driving action performed using the additional vehicle to the retrieved baseline or model characterization; and   evaluating a driver associated with the additional vehicle based on the comparison.   
     
     
         2 . The method of  claim 1 , wherein the evaluating comprises generating a rating for the driver. 
     
     
         3 . The method of  claim 1 , wherein the characterization of at least one driving action performed using the additional vehicle includes a numerical categorization. 
     
     
         4 . The method of  claim 1 , wherein the baseline or model is based on a statistical distribution. 
     
     
         5 . The method of  claim 1 , further comprising:
 communicating information corresponding to the baseline or model characterization to a group of drivers within the geographic region.   
     
     
         6 . The method of  claim 5 , further comprising:
 obtaining contextual information in conjunction with vehicle data that is received from each of the plurality of vehicles; and   wherein determining the baseline or model characterization includes determining the baseline or model characterization based at least in part on a context identified from the contextual information.   
     
     
         7 . The method of  claim 6 , wherein the identified context includes one or more of:
 time of day, day of week, month of year, weather condition, temporary road condition, or a public event in the geographic region.   
     
     
         8 . The method of  claim 6 , wherein the baseline characterization is specific to the identified context. 
     
     
         9 . The method of  claim 1 , further comprising:
 determining, from the baseline or model, one or more road segments of the geographic region which include a road hazard.   
     
     
         10 . The method of  claim 1 , wherein the vehicle data includes vehicle state information determined from a motion measuring component that resides within each of the vehicles. 
     
     
         11 . The method of  claim 10 , wherein the motion measuring component of at least one of the plurality of vehicles includes at least one of an accelerometer or inertial measurement unit (“IMU”) that is provided within a mobile computing device of a driver of that vehicle. 
     
     
         12 . The method of  claim 1 , wherein receiving the vehicle data includes receiving multiple types of vehicle state information from the plurality of vehicles, each type of vehicle state information corresponding to one of Global Positioning System (“GPS”) data, accelerometer data, gyroscopic data, or inertial measurement unit (“IMU”) data. 
     
     
         13 . The method of  claim 12 , wherein determining the characterization of at least one driving action includes determining a magnitude of an acceleration action performed by the driver. 
     
     
         14 . The method of  claim 13 , wherein the acceleration action corresponds to a braking action or a steering action of the driver. 
     
     
         15 . The method of  claim 13 , wherein the acceleration action corresponds to a pedal action of the driver. 
     
     
         16 . The method of  claim 1 , further comprising:
 evaluating a driving performance of a driver of each of the plurality of vehicles based at least in part on a comparison of the characterization of the driving action that is determined for the vehicle of that driver and the baseline of the characterization.   
     
     
         17 . The method of  claim 1 , wherein determining the characterization of the at least one driving action includes:
 (a) communicating with a mobile computing device of a driver of each of the plurality of vehicles to obtain vehicle state information;   (b) determining a characterization of each of plurality of driving actions performed by the driver of each of the plurality of vehicles;   (c) correlating at least one of the multiple driving actions performed by the driver of each of the plurality of vehicles to one of a plurality of road segments for the geographic region.   
     
     
         18 . The method of  claim 1 , wherein determining, from the new vehicle data of the additional vehicle, a characterization of at least one driving action performed using the additional vehicle at the given road segment, comprises determining an associated confidence value indicating a reliability level of the associated characterization, and wherein evaluating the driver is further based on the associated confidence value. 
     
     
         19 . A non-transitory computer-readable medium that stores instructions, which when executed by one or more processors, cause a computing system of the one or more processors to perform operations that include:
 receiving, over one or more networks, vehicle data from a plurality of vehicles that individually traverse a given road segment of a geographic region, the vehicle data of each of the plurality of vehicles including sensor-based vehicle state information and data indicative of one or more attributes of that vehicle's motion while the vehicle is traversing the given road segment;   for each of the plurality of vehicles, determining, based on the vehicle data of that vehicle, a characterization of at least one driving action performed using that vehicle at the given road segment;   aggregating the characterizations determined for the plurality of vehicles;   determining, for the given road segment, a baseline or model characterization for the at least one driving action based at least in part on the aggregated characterizations;   receiving new vehicle data from an additional vehicle, the new vehicle data indicating that the additional vehicle traversed the given road segment;   determining, based on the new vehicle data of the additional vehicle, a characterization of at least one driving action performed using the additional vehicle at the given road segment;   comparing the determined characterization of the at least one driving action performed using the additional vehicle to the determined baseline or model characterization; and   evaluating a driver associated with the additional vehicle based on the comparison.   
     
     
         20 . A method for determining mobile device use at driving action occurrence, the method being performed by one or more processors and comprising:
 receiving, over one or more networks, vehicle data from a plurality of vehicles that individually traverse a given road segment of a geographic region, the vehicle data of each of the plurality of vehicles including sensor-based vehicle state information and data indicative of one or more attributes of that vehicle's motion while the vehicle is traversing the given road segment;   for each of the plurality of vehicles, determining, based on the vehicle data of that vehicle, a characterization of at least one driving action performed using that vehicle at the given road segment;   aggregating the characterizations determined for the plurality of vehicles;   determining, for the given road segment, a baseline or model characterization for the at least one driving action based at least in part on the aggregated characterizations;   receiving new vehicle data from an additional vehicle, the new vehicle data indicating that the additional vehicle traversed the given road segment;   determining, based on the new vehicle data of the additional vehicle, a characterization of at least one driving action performed using the additional vehicle at the given road segment;   receiving application data from a mobile device associated with a driver of the additional vehicle, wherein the application data comprises indicators of non-driving activity; and   determining, based on the received application data and the determined characterization of the at least one driving action performed using the additional vehicle, that the driver performed non-driving activity on the mobile device while the additional vehicle traversed the given road segment.