METHOD AND SYSTEM FOR ANTICIPATORY DEPLOYMENT OF AUTONOMOUSLY CONTROLLED VEHICLES

• US 20160209220A1
• Filed: 01/20/2015
• Published: 07/21/2016
• Est. Priority Date: 01/21/2014
• Status: Active Grant

• Current Assignee: Xinda International Corp.
• Original Assignee: Tribal Rides Incorporated (Xinda International Corp.)
• Inventors: Laetz, Kurt R.
• Granted Patent: US 9,984,574 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06Q 10/02 Reservations, e.g. for tickets, services or events
• CPC Class Codes: G06Q 10/047 Optimisation of routes or paths, e.g. travelling salesman problem
• CPC Class Codes: G08G 1/202 Dispatching vehicles on the basis of a location, e.g. taxi dispatching

Abstract

A method and system for management and anticipatory deployment of autonomously controlled vehicles are disclosed. According to one embodiment, a method may include calculating the geographic locations and periods of time where self-driving vehicles might experience the greatest probability of being requested to provide transportation services to passengers or cargo, and then communicating the resulting locations and times to self-driving vehicles, causing the vehicles to deploy themselves to those certain locations at those certain times, all prior to and in anticipation of specific requests being initiated by users or entities for such transport.

Claims

1. A computerized method for enabling the deployment of autonomously controlled vehicles in a manner that anticipates the time and location at which the vehicles will most likely be needed by one or more users, comprising:

determining the geographical locations and times of day where users that request transportation services are most likely to require the transportation services as a function of multiple variables that indicate one or more geographic locations and times where the highest probability exists that users will require transportation services; and

causing selected vehicles to be pre-deployed proximate in both time and location to those users requesting transportation services.

2. The method set forth in claim 1, wherein determining the geographical locations and times of day where users are most likely to require transportation services comprises:

determining for each user in a group the locations and times where the user is most likely to require transportation services and tabulating the resulting data for all users in a group and for each location and time so that each location and time has a corresponding value representing the likelihood that transportation services will be requested by a member of the user group;

calculating as a function of a multitude of weighted variables, the likelihood that transportation services will be required at a location and time by a user, and assigning a value for such anticipated demand, and including both known and unknown values where the unknown values are assigned a value employing heuristic calculations where the heuristic calculations employ judgmental rules that are learned and stored in memory.

3. The method as recited in claim 2, wherein determining locations and times where users are most likely to require transportation services comprises:

obtaining collaboration data pertaining to shared use preferences by the users via an electronic device, the shared use preferences including data preferences selected from the group consisting of ride sharing preferences, schedule adjusting preferences, and route adjusting preferences.

4. The method as recited in claim 1, wherein determining the geographical locations and times of day where users are most likely to require transportation services comprises:

determining a dynamic forward looking matrix of values for anticipated requests for transportation services at different times and locations so that the supply of autonomous vehicles is dynamically positioned for better servicing the requests being anticipated, and then instructing the self driving vehicles to deploy accordingly, causing the vehicles to pre-deploy based on anticipated requests for transportation services.

5. The method as recited in claim 1, wherein determining the geographical locations and times of day where users are most likely to require transportation services comprises:

determining the cost of providing those transportation services based upon the fractional cost of ownership and the direct variable costs for each rider on every trip, so that the probability of a user requesting transportation services can be adjusted to reflect a user'"'"'s price sensitivities as recorded in a user profile based on historical user data and stated user preferences.

6. The method as recited in claim 1, wherein determining the geographical locations and times of day comprises:

determining locations and times of day where historical user transportation services have been recorded by users and are then used to predict future demand for services.

7. The method as recited in claim 1, wherein determining the geographical locations and times of day comprises:

determining locations and times of day where current user requests for services, scheduled service requests, and otherwise planned or reserved service requests are used to predict demand for services.

8. The method as recited in claim 1, wherein determining the geographical locations and times of day comprises:

determining locations and times of day where data comprising user'"'"'s preferences, individually or collectively, are used to predict demand for services, said preferences to include the type and kind of transportation, the level of social interaction and privacy, price, routes, and any other variation in service.

9. The method as recited in claim 1, wherein determining the geographical locations and times of day comprises:

determining locations and times of day where current and anticipated human and natural events are used to predict demand for services, including weather events, sporting events and normal commuting.

10. A computer-accessible medium comprising program instructions, wherein the program instructions are computer-executable to:

determine the probability that users will require transportation services at respective geographical areas at respective times by using input data including prior use patterns, user behaviors, and a plurality of real-time input factors weather;

determine hierarchical matrices of geographic locations and times by highest probability of users requiring transportation services at respective geographical areas at respective times;

determine the optimum distribution of autonomously driven vehicles by geographic locations and times so that vehicles can be pre-deployed to those geographic locations and times where transportation services are most anticipated to be needed.

11. The computer-accessible medium as recited in claim 10, wherein the optimum distribution of autonomously driven vehicles is determined by:

factoring in pricing data obtained via an on-line, live, electronic marketplace where bidding for services occurs between buyers and sellers and, factoring in pricing to include using real time pricing data generated from an electronic marketplace, to adjust the distribution of the vehicles.

12. The computer-accessible medium as recited in claim 10, wherein the optimum distribution of autonomously driven vehicles is determined by factoring in routing data obtained from user defined routing data generated through a user interface on a digital media, including user defined routing data created to facilitate route preferences, ride sharing, and flexible scheduling.

13. The computer-accessible medium as recited in claim 11, wherein factoring in pricing data comprises determining a cost associated with the anticipatory deployment of autonomous vehicles to provide transportation services at the lowest cost.

14. A computer system for deploying autonomously controlled vehicles, comprising:

a database for storing profiles of users of the system, the profiles comprising information regarding a plurality of user preferences, and user travel history;

a vehicle deployment module for determining routes of the vehicles as a function of the profiles, the routes including start and end points for each route, and a time corresponding to each start and end point; and

a communications module for causing vehicle control information to be transmitted to the vehicles, the vehicle control information comprising the start and end points for the corresponding vehicle.

15. The computer system of claim 14 wherein the profiles comprise:

information pertaining to ride sharing preferences;

information pertaining to vehicle preferences;

information pertaining to price preferences; and

information pertaining to route preferences.

16. The computer system of claim 14 wherein the vehicle deployment module determines routes of the vehicles by employing a computer generated matrix of anticipatory vehicle demand values calculated as a function of probability employing mapping data.

17. The computer system of claim 16 wherein the vehicle deployment module determines routes of the vehicles by employing a computer generated matrix of anticipatory vehicle demand values calculated as a function of probability employing mapping data and historical data on trips taken by the users and generating groupings for the users and calculating a net-sum of probabilities by zone for the group that a trip will be initiated by a user within any given time zone and location.

18. The computer system of claim 14 wherein the vehicle control information further comprises route preference information.