Autonomous vehicle fleet management for improved computational resource usage
Systems and methods for evaluating and deploying fleets of autonomous in operational domains are described. A computing system may obtain data indicative of one or more capabilities of at least one autonomous vehicle, data indicative of vehicle service dynamics in an operational domain over a period of time, and determining a plurality of resource performance parameters respectively for a plurality of autonomous vehicle fleets associated with potential deployment in the operational domain. Each autonomous vehicle fleet can be associated with a different number of autonomous vehicles The resource performance parameter for each autonomous vehicle fleet can be based at least in part on the one or more capabilities of the at least one autonomous vehicle and the vehicle service dynamics in the operational domain. The computing system can initiate an action associated with the operational domain based at least in part on the plurality of resource performance parameters.
1 . A computer-implemented method for determining autonomous vehicle (AV) fleets, comprising:
obtaining, by a computing system comprising one or more computing devices, data indicative of one or more capabilities of at least one AV;
obtaining, by the computing system, data indicative of vehicle service dynamics in an operational domain over a period of time;
determining, by the computing system, one or more resource performance parameters for a vehicle fleet associated with potential deployment in the operational domain, the one or more resource performance parameters being based at least in part on the one or more capabilities of the at least one AV and the vehicle service dynamics in the operational domain;
determining, by the computing system, a measure of breakeven utilization for the vehicle fleet, the measure of breakeven utilization being based at least in part on a number of AVs having a total resource outflow per unit that is equal to a total resource outflow per unit for a fleet of non-autonomous vehicles; and
initiating, by the computing system, an action associated with the operational domain based at least in part on the one or more resource performance parameters, the action resulting in the at least one AV utilizing one or more sensors of the at least one AV to autonomously navigate the at least one AV along a route to at least one location by controlling one or more vehicle controls.
2 . The computer-implemented method of claim 1 , wherein:
the one or more resource performance parameters include a plurality of measures of resource return, respectively, for the vehicle fleet, the vehicle fleet comprising one or more AVs and one or more non-autonomous vehicles.
3 . The computer-implemented method of claim 2 , wherein:
the measure of resource return for the vehicle fleet is a measure of fleet-level return, the action resulting in the at least one AV generating a motion plan and executing the motion plan.
4 . The computer-implemented method of claim 2 , wherein:
the measure of resource return is a measure of marginal resource return associated with individual vehicles of the vehicle fleet.
5 . The computer-implemented method of claim 1 , wherein:
the one or more resource performance parameters include a plurality of measures of efficiency for the vehicle fleet.
6 . The computer-implemented method of claim 5 , wherein:
the measure of efficiency includes a measure of time efficiency associated with the vehicle fleet.
7 . The computer-implemented method of claim 5 , wherein:
the measure of efficiency includes a measure of predicted mileage efficiency.
8 . The computer-implemented method of claim 1 , further comprising:
obtaining, by the computing system, data indicative of a resource outflow associated with the at least one AV.
9 . The computer-implemented method of claim 8 , wherein the resource outflow is based on at least one of operation or deployment of the at least one AV.
10 . The computer-implemented method of claim 1 , wherein:
the data indicative of vehicle service dynamics includes data indicative of usage associated with one or more vehicle service types.
11 . The computer-implemented method of claim 10 , wherein:
the usage includes a supply and a demand associated with the one or more vehicle service types.
12 . The computer-implemented method of claim 1 , further comprising:
obtaining, by the computing system, data associated with a plurality of potential travel routes within the operational domain of the at least one AV.
13 . The computer-implemented method of claim 12 , further comprising:
determining, by the computing system, a level of addressability of the operational domain based at least in part on the one or more capabilities of the at least one AV and the plurality of potential travel routes within the operational domain of the at least one AV, wherein the one or more resource performance parameters are based at least in part on the level of addressability of the operational domain.
14 . The computer-implemented method of claim 13 , further comprising:
determining data indicative of vehicle service requests that are serviceable by the at least one AV in the operational domain based on the plurality of potential travel routes and the vehicle service dynamics;
wherein the one or more resource performance parameters are based at least in part on the vehicle service requests that are serviceable by the at least one AV.
15 . The computer-implemented method of claim 1 , wherein the one or more capabilities of the at least one AV are indicative of at least one of an ability of the at least one AV to operate in a weather condition, a vehicle operating condition, or a vehicle maneuverability.
16 . The computer-implemented method of claim 1 , wherein initiating, by the computing system, the action comprises:
generating, by the computing system, data indicative of the one or more resource performance parameters; and
outputting, by the computing system, the data indicative of the one or more resource performance parameters.
17 . The computer-implemented method of claim 1 , wherein:
the one or more resource performance parameters include a first one or more resource performance parameters based on a first profile, the first profile including at least one of a first set of capabilities of the at least one AV or a first set of vehicle service dynamics.
18 . The computer-implemented method of claim 17 , wherein;
the one or more resource performance parameters include a second one or more resource performance parameters based on a second profile, the second profile including at least one of a second set of capabilities of the at least one AV or a second set of vehicle service dynamics.
19 . A computing system comprising:
one or more processors; and
one or more tangible, non-transitory, computer-readable media that collectively store instructions that when executed by the one or more processors cause the computing system to perform operations comprising:
obtaining data indicative of one or more capabilities of at least one autonomous vehicle (AV);
obtaining data indicative of vehicle service dynamics in an operational domain over a period of time;
determining one or more resource performance parameters for a vehicle fleet associated with potential deployment in the operational domain, the one or more resource performance parameters being based at least in part on the one or more capabilities of the at least one AV and the vehicle service dynamics in the operational domain;
determining a measure of breakeven utilization for the vehicle fleet, the measure of breakeven utilization being based at least in part on a number of AVs having a total resource outflow per unit that is equal to a total resource outflow per unit for a fleet of non-autonomous vehicles; and
initiating an action associated with the operational domain based at least in part on the one or more resource performance parameters, the action resulting in the at least one AV utilizing one or more sensors of the at least one AV to autonomously navigate the at least one AV along a route to at least one location by controlling one or more vehicle controls.
20 . One or more tangible, non-transitory, computer-readable media that collectively store instructions that, when executed by one or more processors, cause the one or more processors to perform operations, the operations comprising:
obtaining data indicative of one or more capabilities of at least one autonomous vehicle (AV);
obtaining data indicative of vehicle service dynamics in an operational domain over a period of time;
determining one or more resource performance parameters for a vehicle fleet associated with potential deployment in the operational domain, the one or more resource performance parameters being based at least in part on the one or more capabilities of the at least one AV and the vehicle service dynamics in the operational domain;
determining a measure of breakeven utilization for the vehicle fleet, the measure of breakeven utilization being based at least in part on a number of AVs having a total resource outflow per unit that is equal to a total resource outflow per unit for a fleet of non-autonomous vehicles; and
initiating an action associated with the operational domain based at least in part on the one or more resource performance parameters, the action resulting in the at least one AV utilizing one or more sensors of the at least one AV to autonomously navigate the at least one AV along a route to at least one location by controlling one or more vehicle controls.