Fleet maintenance management for autonomous vehicles

Patent metadata

Field	Value
Publication number	US-12430960-B2
Application number	US-202318159562-A
Country	US
Kind code	B2
Filing date	Jan 25, 2023
Priority date	Dec 22, 2017
Publication date	Sep 30, 2025
Grant date	Sep 30, 2025

Abstract

In particular embodiments, a computing system may determine a predicted amount of ride requests for a plurality of collectively-managed vehicles and determine an availability of the collectively-managed vehicles to satisfy the predicted amount of ride requests. Subsequent to determining that the availability fails to satisfy one or more predetermined criteria for servicing the predicted amount of ride requests, the system may determine status information associated with the collectively-managed vehicles and determine, based on at least the status information, one or more minimum services for servicing one or more vehicles among the plurality of collectively-managed vehicles at one or more service centers such that the availability satisfies the one or more predetermined criteria. The system may instruct the one or more vehicles that are to receive the one or more minimum services to travel to the one or more service centers to be serviced.

First claim

What is claimed is:

1. A method comprising, by a computing system:
generating an initial predictive supply and demand model for a plurality of collectively-managed vehicles based on historic data associated with supply and demand for the plurality of collectively-managed vehicles;
predicting future events that affect the supply and demand for the plurality of collectively-managed vehicles based on the initial predictive supply and demand model;
generating a prediction of demand for the plurality of collectively-managed vehicles based on the initial predictive supply and demand model and the predicted future events;
receiving current conditions data that affect the supply and demand for the plurality of collectively managed vehicles, and known future events;
receiving captured supply and demand data associated with the plurality of collectively-managed vehicles;
updating the initial predictive supply and demand model based on one or more of the prediction of demand for the plurality of collectively-managed vehicles, the current conditions data, the known future events, or the captured supply and demand data;
generating a second prediction of demand for the plurality of collectively-managed vehicles based on the updated initial predictive supply and demand model; and
instructing a subset of the plurality of collectively-managed vehicles to receive maintenance services in a manner such that a number of available vehicles to fulfill ride requests among the plurality of collectively-managed vehicles exceeds the second prediction of demand for the plurality of collectively-managed vehicles.

2. The method of claim 1 , wherein the plurality of collectively-managed vehicles operate in a particular region.

3. The method of claim 1 , wherein the historic data comprises a volume of ride requests associated with one or more of particular weather events, particular locations, particular days, and particular hours.

4. The method of claim 1 , wherein the initial predictive model corresponds to identified patterns associated with the historic data.

5. The method of claim 1 , wherein the prediction of demand for the plurality of collectively-managed vehicles comprises first predictions of demand for the plurality of collectively-managed vehicles with certain vehicle characteristics, and second predictions of demand for the plurality of collectively-managed vehicles at certain locations within a region in which the plurality of collectively-managed vehicles operate.

6. The method of claim 1 , wherein the current conditions data comprise at least one of collectively-managed vehicle status, service center status, traffic accidents, road construction, weather events, or traffic conditions.

7. The method of claim 1 , wherein the captured supply and demand data comprises data captured by a transportation application running on first computing devices of ride requestors, and data provided by another transportation application running on second computing devices of various service centers.

8. The method of claim 1 , further comprising:
predicting a near-term demand for the plurality of collectively-managed vehicles based on the predicted future events, the current conditions data, the known future events, and the captured supply and demand data;
receiving an indication associated with whether the predicted near-term demand is correct; and
updating the initial predictive supply and demand model based on the indication.

9. The method of claim 8 , wherein near-term demand comprises a demand level and a duration associated with the demand level.

10. 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, the one or more computer-readable non-transitory storage media comprising instructions operable when executed by one or more of the processors to cause the system to perform operations comprising:
generating an initial predictive supply and demand model for a plurality of collectively-managed vehicles based on historic data associated with supply and demand for the plurality of collectively-managed vehicles;
predicting future events that affect the supply and demand for the plurality of collectively-managed vehicles based on the initial predictive supply and demand model;
generating a prediction of demand for the plurality of collectively-managed vehicles based on the initial predictive supply and demand model and the predicted future events;
receiving current conditions data that affect the supply and demand for the plurality of collectively managed vehicles, and known future events;
receiving captured supply and demand data associated with the plurality of collectively-managed vehicles;
updating the initial predictive supply and demand model based on one or more of the prediction of demand for the plurality of collectively-managed vehicles, the current conditions data, the known future events, or the captured supply and demand data;
generating a second prediction of demand for the plurality of collectively-managed vehicles based on the updated initial predictive supply and demand model; and
instructing a subset of the plurality of collectively-managed vehicles to receive maintenance services in a manner such that a number of available vehicles to fulfill ride requests among the plurality of collectively-managed vehicles exceeds the second prediction of demand for the plurality of collectively-managed vehicles.

11. The system of claim 10 , wherein the plurality of collectively-managed vehicles operate in a particular region.

12. The system of claim 10 , wherein the historic data comprises a volume of ride requests associated with one or more of particular weather events, particular locations, particular days, and particular hours.

13. The system of claim 10 , wherein the initial predictive model corresponds to identified patterns associated with the historic data.

14. The system of claim 10 , wherein the prediction of demand for the plurality of collectively-managed vehicles comprises first predictions of demand for the plurality of collectively-managed vehicles with certain vehicle characteristics, and second predictions of demand for the plurality of collectively-managed vehicles at certain locations within a region in which the plurality of collectively-managed vehicles operate.

15. The system of claim 10 , wherein the current conditions data comprise at least one of collectively-managed vehicle status, service center status, traffic accidents, road construction, weather events, or traffic conditions.

16. One or more computer-readable non-transitory storage media including instructions that are operable, when executed by one or more processors, to perform operations comprising:
generating an initial predictive supply and demand model for a plurality of collectively-managed vehicles based on historic data associated with supply and demand for the plurality of collectively-managed vehicles;
predicting future events that affect the supply and demand for the plurality of collectively-managed vehicles based on the initial predictive supply and demand model;
generating a prediction of demand for the plurality of collectively-managed vehicles based on the initial predictive supply and demand model and the predicted future events;
receiving current conditions data that affect the supply and demand for the plurality of collectively managed vehicles, and known future events;
receiving captured supply and demand data associated with the plurality of collectively-managed vehicles;
updating the initial predictive supply and

Assignees

• Lyft Inc

Inventors

• Abari Farzad Cyrus Foroughi
• Friedman Aaron Jacob Levine
• Houston John
• Reis Adam Hart
• Starns Alexander Thomas

Classifications

• G06Q50/40

  Business processes related to the transportation industry (shipping G06Q10/083) · CPC title

• G06Q10/06315

  Needs-based resource requirements planning or analysis · CPC title

• G06Q10/02 Primary

  Reservations, e.g. for tickets, services or events · CPC title

• G06Q10/063

  Operations research, analysis or management · CPC title

• G06Q10/20

  Administration of product repair or maintenance · CPC title