Computing system implementing traffic modeling using sensor view data from self-driving vehicles

Abstract

A computing system can receive sensor view data from each self-driving vehicle (SDV) in a fleet of SDVs operating throughout a given region. The system may further determine, based on the sensor view data, a set of properties of one or more vehicles external to the SDV. Based on the set of properties of the one or more vehicles, the system can generate traffic models for the given region and generate map data for users that indicate traffic flow for at least part of the given region.

What is claimed is: 
     
         1 . A computing system implementing traffic modeling, the computing system comprising:
 a network communication interface communicating, over one or more networks, with (i) a fleet of self-driving vehicles (SDVs) operating throughout a given region, and (ii) computing devices of users;   one or more processors; and   one or more memory resources storing instructions that, when executed by the one or more processors, cause the computing system to:
 receive, over the one or more networks, sensor view data from each respective SDV in the fleet of SDVs, the sensor view data indicating a surrounding environment of the respective SDV; 
 determine, from the sensor view data, a set of properties of one or more vehicles external to each SDV in the fleet; 
 based on the set of properties of the one or more vehicles external to each SDV in the fleet, generate one or more traffic models for the given region to indicate traffic flow for at least part of the given region; and 
 utilizing the one or more traffic models, generate map data for the computing devices of the users, the map data indicating the traffic flow for the at least part of the given region. 
   
     
     
         2 . The computing system of  claim 1 , wherein the executed instructions cause the computing system to provide estimated time of arrival (ETA) information for the users in conjunction with the map data. 
     
     
         3 . The computing system of  claim 2 , wherein the executed instructions cause the computing system to provide the map data and the ETA data to the users via a designated application executing on the computing devices of the users. 
     
     
         4 . The computing system of  claim 3 , wherein the designated application enables a particular user to input a location on an interactive map interface and view the traffic flow and an ETA of the particular user to the inputted location on the interactive map interface. 
     
     
         5 . The computing system of  claim 1 , wherein the sensor view data from each respective SDV indicates a current lane of a road on which the respective SDV travels and one or more additional lanes in the surrounding environment of the respective SDV, and wherein the set of properties of the one or more vehicles includes a speed of each of the one or more vehicles. 
     
     
         6 . The computing system of  claim 1 , wherein the executed instructions further cause the computing system to generate the one or more traffic models by determining timing data for individual traffic signals throughout the given region based on the traffic flows. 
     
     
         7 . The computing system of  claim 1 , wherein the executed instructions further cause the computing system to:
 receive, over the one or more networks, a transport request from a computing device of a requesting user, the transport request including a pick-up location and a destination location;   select an SDV, from one or more proximate SDVs in relation to a current location of the requesting user, to service the pick-up request; and   transmit, over the one or more networks, confirmation information to the computing device of the requesting user, the confirmation information identifying the selected SDV and ETA data corresponding to the selected SDV arriving at the pick-up location, the ETA data being based on the one or more traffic models.   
     
     
         8 . A non-transitory computing readable medium storing instructions that, when executed by one or more processors of a computing system, cause the computing system to:
 communicate, over one or more networks, with (i) a fleet of self-driving vehicles (SDVs) operating throughout a given region, and (ii) computing devices of users;   receive, over the one or more networks, sensor view data from each respective SDV in the fleet of SDVs, the sensor view data indicating a surrounding environment of the respective SDV;   determine, from the sensor view data, a set of properties of one or more vehicles external to each SDV in the fleet;   based on the set of properties of the one or more vehicles external to each SDV in the fleet, generate one or more traffic models for the given region to indicate traffic flow for at least part of the given region; and   utilizing the one or more traffic models, generate map data for the computing devices of the users, the map data indicating the traffic flow for the at least part of the given region.   
     
     
         9 . The non-transitory computing readable medium of  claim 8 , wherein the executed instructions cause the computing system to provide estimated time of arrival (ETA) information for the users in conjunction with the map data. 
     
     
         10 . The non-transitory computing readable medium of  claim 9 , wherein the executed instructions cause the computing system to provide the map data and the ETA data to the users via a designated application executing on the computing devices of the users. 
     
     
         11 . The non-transitory computing readable medium of  claim 10 , wherein the designated application enables a particular user to input a location on an interactive map interface and view the traffic flow and an ETA of the particular user to the inputted location on the interactive map interface. 
     
     
         12 . The non-transitory computing readable medium of  claim 8 , wherein the sensor view data from each respective SDV indicates a current lane of a road on which the respective SDV travels and one or more additional lanes in the surrounding environment of the respective SDV, and wherein the set of properties of the one or more vehicles includes a speed of each of the one or more vehicles. 
     
     
         13 . The non-transitory computing readable medium of  claim 8 , wherein the executed instructions further cause the computing system to generate the one or more traffic models by determining timing data for individual traffic signals throughout the given region based on the traffic flows. 
     
     
         14 . The non-transitory computing readable medium of  claim 8 , wherein the executed instructions further cause the computing system to:
 receive, over the one or more networks, a pick-up request from a computing device of a requesting user, the pick-up request corresponding to an inputted pick-up location on the interactive map;   select an SDV, from one or more proximate SDVs in relation to a current location of the requesting user, to service the pick-up request; and   transmit confirmation information to the mobile computing device of the requesting user, the confirmation information identifying the selected SDV and ETA data corresponding to the selected SDV arriving at the pick-up location, the ETA data being based on the one or more traffic models.   
     
     
         15 . A computer-executed method of implementing traffic modeling, the method being performed by one or more processors and comprising:
 communicating, over one or more networks, with (i) a fleet of self-driving vehicles (SDVs) operating throughout a given region, and (ii) computing devices of users;   receiving, over the one or more networks, sensor view data from each respective SDV in the fleet of SDVs, the sensor view data indicating a surrounding environment of the respective SDV;   determining, from the sensor view data, a set of properties of one or more vehicles external to each SDV in the fleet;   based on the set of properties of the one or more vehicles external to each SDV in the fleet, generating one or more traffic models for the given region to indicate traffic flow for at least part of the given region; and   utilizing the one or more traffic models, generating map data for the computing devices of the users, the map data indicating the traffic flow for the at least part of the given region.   
     
     
         16 . The method of  claim 15 , wherein the one or more processors provide estimated time of arrival (ETA) information for the users in conjunction with the map data. 
     
     
         17 . The method of  claim 16 , wherein the one or more processors provide the map data and the ETA data to the users via a designated application executing on the computing devices of the users. 
     
     
         18 . The method of  claim 17 , wherein the designated application enables a particular user to input a location on an interactive map interface and view the traffic flow and an ETA of the particular user to the inputted location on the interactive map interface. 
     
     
         19 . The method of  claim 15 , wherein the sensor view data from each respective SDV indicates a current lane of a road on which the respective SDV travels and one or more additional lanes in the surrounding environment of the respective SDV, and wherein the set of properties of the one or more vehicles includes a speed of each of the one or more vehicles. 
     
     
         20 . The method of  claim 15 , wherein the one or more processors generate the one or more traffic models by determining timing data for individual traffic signals throughout the given region based on the traffic flows.