Autonomous vehicle fleet management for reduced traffic congestion

Abstract

Techniques are provided for autonomous vehicle fleet management for reduced traffic congestion. A request is received for a vehicular ride. The request includes an initial spatiotemporal location and a destination spatiotemporal location. A processor is used to generate a representation of lane segments. Each lane segment is weighted in accordance with a number of other vehicles on the lane segment. A vehicle located within a threshold distance to the initial spatiotemporal location is identified such that the identified vehicle has at least one vacant seat. The processor is used to determine a route for operating the identified vehicle from the initial spatiotemporal location to the destination spatiotemporal location. The route includes one or more lane segments of the lane segments. An aggregate of weights of the one or more lane segments is below a threshold value. The received request and the determined route are transmitted to the identified vehicle.

1 - 20 . (canceled) 
     
     
         21 . A method comprising:
 generating, using one or more processors, a representation of a plurality of lane segments for operating a plurality of vehicles;   receiving, using the one or more processors, from each vehicle of the plurality of vehicles, telemetry data specifying at least one parameter for operating the vehicle;   identifying, using the one or more processors, for each vehicle of the plurality of vehicles, a corresponding portion of the representation, wherein the portion comprises one or more lane segments of the plurality lane segments for operating the vehicle in accordance with the telemetry data received from the vehicle.   receiving, using the one or more processors, from a user device, a request for a vehicular ride, wherein the request specifies an initial spatiotemporal location and a destination spatiotemporal location; and   identifying, using the one or more processors, a vehicle of the plurality of vehicles, such that the initial spatiotemporal location and the destination spatiotemporal location are both located within the portion of the representation corresponding to the identified vehicle.   
     
     
         22 . The method of  claim 21 , wherein the representation of the plurality of lane segments for operating the plurality of vehicles is at least one of a weighted graph, a linked list, or a multi-dimensional array. 
     
     
         23 . The method of  claim 21 , further comprising:
 generating a route for operating the identified vehicle, wherein the route comprises a subset of the one or more lane segments of the corresponding portion of the representation.   
     
     
         24 . The method of  claim 23 , wherein the telemetry data comprises a spatiotemporal location that must be included within the generated route, and wherein the generated route further comprises the spatiotemporal location. 
     
     
         25 . The method of  claim 21 , wherein the request is received from the user device at a first time, and wherein the request for the vehicular ride further specifies a start time later than the first time. 
     
     
         26 . The method of  claim 25 , further comprising:
 determining, at the first time, that an operating state of the identified vehicle is busy.   
     
     
         27 . The method of  claim 26 , further comprising:
 determining that the operating state of the identified vehicle at the specified start time will be available.   
     
     
         28 . The method of  claim 27 , further comprising:
 transmitting, to the identified vehicle, the generated route for operating the identified vehicle at the specified start time in accordance with the telemetry data received from the identified vehicle.   
     
     
         29 . The method of  claim 23 , further comprising:
 determining, using the portion of the representation corresponding to the identified vehicle, that a level of traffic congestion on the generated route is higher than a threshold value.   
     
     
         30 . The method of  claim 29 , further comprising:
 generating, for the identified vehicle, an updated route comprising a second subset of the one or more lane segments of the corresponding portion of the environment, wherein a level of traffic congestion on the updated route is less than the threshold value.   
     
     
         31 . The method of  claim 21 , wherein at least one parameter comprises a maximum speed limit. 
     
     
         32 . The method of  claim 21 , wherein at least one parameter comprises one or more operating times. 
     
     
         33 . The method of  claim 21 , wherein at least one parameter comprises one or more operating weather conditions. 
     
     
         34 . The method of  claim 21 , wherein at least one parameter comprises one or more roadways. 
     
     
         35 . The method of  claim 21 , wherein at least one parameter comprises one or more regions denoted by geofences. 
     
     
         36 . The method of  claim 21 , wherein the telemetry data further comprises at least one of a video or an image captured by a sensor of the vehicle. 
     
     
         37 . The method of  claim 21 , wherein the telemetry data further comprises an indication of a classification of an object located on the one or more lane segments of the plurality of lane segments. 
     
     
         38 . The method of  claim 21 , wherein the telemetry data further comprises textual data indicating the location of the object relative to the vehicle. 
     
     
         39 . The method of  claim 38 , wherein the textual data further comprises one or more data items in a JavaScript Object Notation (JSON) format. 
     
     
         40 . A computer system comprising:
 one or more computer processors; and   one or more non-transitory storage media storing instructions which, when executed by the one or more computer processors, cause the one or more computer processors to perform operations comprising:   generating a representation of a plurality of lane segments for operating a plurality of vehicles;   receiving, from each vehicle of the plurality of vehicles, telemetry data specifying at least one parameter for operating the vehicle;   identifying, for each vehicle of the plurality of vehicles, a corresponding portion of the representation, wherein the portion comprises one or more lane segments of the plurality lane segments for operating the vehicle in accordance with the telemetry data received from the vehicle.   receiving, from a user device, a request for a vehicular ride, wherein the request specifies an initial spatiotemporal location and a destination spatiotemporal location; and   identifying a vehicle of the plurality of vehicles, such that the initial spatiotemporal location and the destination spatiotemporal location are both located within the portion of the representation corresponding to the identified vehicle.   
     
     
         41 . One or more non-transitory storage media storing instructions which, when executed by one or more computing devices, cause the one or more computing devices to perform operations comprising:
 generating a representation of a plurality of lane segments for operating a plurality of vehicles;   receiving, from each vehicle of the plurality of vehicles, telemetry data specifying at least one parameter for operating the vehicle;   identifying, for each vehicle of the plurality of vehicles, a corresponding portion of the representation, wherein the portion comprises one or more lane segments of the plurality lane segments for operating the vehicle in accordance with the telemetry data received from the vehicle.   receiving, from a user device, a request for a vehicular ride, wherein the request specifies an initial spatiotemporal location and a destination spatiotemporal location; and   identifying a vehicle of the plurality of vehicles, such that the initial spatiotemporal location and the destination spatiotemporal location are both located within the portion of the representation corresponding to the identified vehicle.