Dynamic modeling and simulation of an autonomous vehicle fleet using real-time autonomous vehicle sensor input

Patent metadata

Field	Value
Publication number	US-2019011931-A1
Application number	US-201715645776-A
Country	US
Kind code	A1
Filing date	Jul 10, 2017
Priority date	Jul 10, 2017
Publication date	Jan 10, 2019
Grant date	—

Abstract

Embodiments provide techniques for autonomous vehicle fleet modeling and simulation, such as within a dynamic transportation matching system utilizing one or more vehicle types such as non-autonomous vehicles and autonomous vehicles. An autonomous fleet simulation model may be generated based on real-world parameters of an autonomous vehicle fleet, and the parameters may be modified in a simulation in order to determine optimized values that may be applied to the real-world autonomous vehicle fleet.

First claim

1 . A computer-implemented method comprising:
accessing autonomous fleet data for a geographical region associated with a plurality of autonomous vehicles; determining a plurality of potential locations in the geographical region for an autonomous service entity; determining a plurality of utilization metrics for the plurality of autonomous vehicles based on at least the plurality of potential locations for the autonomous service entity; selecting a location for the autonomous service entity from the plurality of potential locations based on at least the plurality of utilization metrics; generating, for the geographical region, an autonomous fleet simulation model based at least on the autonomous fleet data, the autonomous service entity, and the autonomous service parameters for each of the autonomous service entity; based at least on the autonomous fleet simulation model, determining a pre-position for each of one or more of the plurality of autonomous vehicles to be available for predicted future transportation requests within the geographical region; and causing the one or more of the plurality of autonomous vehicles to travel to their determined pre-positions.

2 . The computer-implemented method of claim 1 , wherein the pre-positions are determined to reduce times en route to pickup locations for predicted future transportation requests.

3 . The computer-implemented method of claim 2 , further comprising:
based at least on the autonomous fleet simulation model, determining according to predicted demand not to make available for rides one or more of the plurality of autonomous vehicles in the geographical region during a certain future time.

4 . The computer-implemented method of claim 3 , further comprising:
based at least on the autonomous fleet simulation model, determining a service schedule for each of one or more of the plurality of autonomous vehicles to increase utilization of the plurality of autonomous vehicles; and causing the one or more of the plurality of autonomous vehicles to be serviced according to their determined service schedules.

5 . The computer-implemented method of claim 1 , wherein the autonomous service entity comprises a charging station, fueling station, parking facility, service facility, or cleaning facility.

6 . The computer-implemented method of claim 1 , wherein one or more of the autonomous service parameters each comprises one or more of: type of service provided, time required for service, or number of autonomous vehicles that can be serviced.

7 . The computer-implemented method of claim 1 , wherein the autonomous fleet simulation model is configured to simulate various autonomous fleet scenarios comprising geographic constraints, autonomous fleet constraints, and infrastructure constraints to predict one or more outcomes with respect to utilization of the plurality of autonomous vehicles.

8 . The computer-implemented method of claim 1 , wherein the autonomous fleet data comprises one or more of autonomous vehicle deployment locations, autonomous vehicle fleet size, current autonomous vehicle utilization, historical autonomous vehicle utilization, autonomous vehicle route data, or autonomous vehicle ride data.

9 . A computer-implemented method comprising:
accessing autonomous fleet data for a geographical region associated with a plurality of autonomous vehicles; determining autonomous service entities in the geographical region to be represented in an autonomous fleet simulation model; determining autonomous service parameters for each of the autonomous service entities in the geographical region; generating, for the geographical region, the autonomous fleet simulation model based at least on the autonomous fleet data, the autonomous service entities, and the autonomous service parameters for each of the autonomous service entities; determining a plurality of potential locations in the geographical region for an additional autonomous service entity; selecting, based at least on the autonomous fleet simulation model, a location from the plurality of potential locations for the additional autonomous service entity to increase utilization of the plurality of autonomous vehicles; updating the autonomous fleet simulation model to include the additional autonomous service entity in accordance with the selected location; and causing at least one of the plurality of autonomous vehicles to travel to a position within the geographical region based on the updated autonomous fleet simulation model.

10 . (canceled)

11 . The computer-implemented method of claim 9 , wherein the additional autonomous service entity comprises a charging station, fueling station, parking facility, service facility, or cleaning facility.

12 . The computer-implemented method of claim 9 , wherein one or more of the autonomous service parameters each comprises one or more of type of service provided, time required for service, or number of autonomous vehicles that can be serviced.

13 . The computer-implemented method of claim 9 , wherein the autonomous fleet simulation model is configured to simulate various autonomous fleet scenarios comprising geographic constraints, autonomous fleet constraints, and infrastructure constraints to predict one or more outcomes with respect to utilization of the plurality of autonomous vehicles.

14 . The computer-implemented method of claim 9 , wherein the autonomous fleet data comprises one or more of autonomous vehicle deployment locations, autonomous vehicle fleet size, current autonomous vehicle utilization, historical autonomous vehicle utilization, autonomous vehicle route data, or autonomous vehicle ride data.

15 . A system comprising:
one or more processors; and one or more computer-readable non-transitory storage media coupled to one or more of the processors and comprising instructions operable when executed by one or more of the processors to cause the system to:
access autonomous fleet data for a geographical region associated with a plurality of autonomous vehicles;
determine a plurality of potential locations in the geographical region for an autonomous service entity;
determine a plurality of utilization metrics for the plurality of autonomous vehicles based on at least the plurality of potential locations for the autonomous service entity;
generate, for the geographical region, an autonomous fleet simulation model based at least on the autonomous fleet data, the autonomous service entity, and the autonomous service parameters for each of the autonomous service entities;
based at least on the autonomous fleet simulation model, determine a pre-position for each of one or more of the plurality of autonomous vehicles to be available for predicted future transportation requests within the geographical region; and
cause the one or more of the plurality of autonomous vehicles to travel to their determined pre-positions.

16 . The system of claim 15 , wherein the pre-positions are determined to reduce times en route to pickup locations for predicted future transportation requests.

17 . The system of claim 16 , wherein the instructions are further operable when executed by one or more of the processors to cause the system, based at least on the autonomous fleet simulation model, to determine according to predicted demand not to make available for rides one or more of the plurality of autonomous vehicles in the geographical region during a certain future time.

18 . A system comprising:
one or more processors; and one or more computer-readable non-transitory storage med

Assignees

• Lyft Inc

Inventors

• Selvam Krishna
• Chamandy Nicholas
• Kelman Jody

Classifications

• G08G1/202 Primary

  Dispatching vehicles on the basis of a location, e.g. taxi dispatching · CPC title

• G05B17/02

  electric · CPC title

• G08G1/123 Primary

  indicating the position of vehicles, e.g. scheduled vehicles; {Managing passenger vehicles circulating according to a fixed timetable, e.g. buses, trains, trams}(transmission of navigation instructions to vehicles G08G1/0968) · CPC title

• G05D1/0291 Primary

  Fleet control (monitoring fleets in traffic control systems for road vehicles G08G1/127, G08G1/127) · CPC title

• G05D1/0088

  characterized by the autonomous decision making process, e.g. artificial intelligence, predefined behaviours (using knowledge based models G06N5/00) · CPC title