Automatic driver modeling for integration of human-controlled vehicles into an autonomous vehicle network

• US 9,361,409 B2
• Filed: 01/10/2013
• Issued: 06/07/2016
• Est. Priority Date: 01/10/2013
• Status: Active Grant

• Current Assignee: DoorDash, Inc.
• Original Assignee: International Business Machines Corporation
• Inventors: Kozloski, James R., Lynar, Timothy M., VECCHIOLA, Cristian
• Primary Examiner(s): Rivas, Omar Fernandez
• Assistant Examiner(s): Khan, Iftekhar
• Application Number:
  US13/738,317
• Publication Number:
  US 20140195213A1
• Time in Patent Office: 1,244 Days
• Field of Search: 703/8
• US Class Current: 1/1
• CPC Class Codes: B60W 2540/30 Driving style
• CPC Class Codes: B60W 2556/45 External transmission of data to or from the vehicle
• CPC Class Codes: B60W 2556/65 Data transmitted between vehicles
• CPC Class Codes: B60W 2756/10 Involving external transmission of data to or from the vehicle
• CPC Class Codes: G05D 1/0088 characterized by the autonomous decision making process, e.g. artificial intelligence, predefined behaviours using knowledge based models G06N5/00
• CPC Class Codes: G06F 30/15 Vehicle, aircraft or watercraft design
• CPC Class Codes: G06F 30/20 Design optimisation, verification or simulation optimisation, verification or simulation of circuit designs G06F30/30
• CPC Class Codes: G08G 1/0112 from the vehicle, e.g. floating car data [FCD]
• CPC Class Codes: G08G 1/0129 for creating historical data or processing based on historical data
• CPC Class Codes: H04W 4/70 Services for machine-to-machine communication [M2M] or machine type communication [MTC]

Abstract

Automatic driver modeling is used to integrate human-controlled vehicles into an autonomous vehicle network. A driver of a human-controlled vehicle is identified based on behavior patterns of the driver measured by one or more sensors of an autonomous vehicle. A model of the driver is generated based on the behavior patterns of the driver measured by the one or more sensors of the autonomous vehicle. Previously stored behavior patterns of the driver are then retrieved from a database to augment the model of the driver. The model of the driver is then transmitted from the autonomous vehicle to nearby vehicles with autonomous interfaces.

Claims

1. A computer-implemented method, comprising:

identifying, with a processing device, a driver of a human-controlled vehicle based on behavior patterns of the driver measured by one or more sensors of an autonomous vehicle, wherein the human-controlled vehicle is not an autonomous vehicle, and wherein the driver identification comprises;

interrogating the human-controlled vehicle for the driver identification data;

receiving the driver identification data in response,

analyzing registration information of the human-controlled vehicle, and

identifying the driver using a pattern matching algorithm;

generating a model of the driver of the human-controlled vehicle by the autonomous vehicle based on the behavior patterns of the driver;

retrieving previously stored behavior patterns of the driver to augment the model of the driver; and

transmitting the model of the driver of the human-controlled vehicle by the autonomous vehicle to other nearby autonomous vehicles.

2. The computer-implemented method of claim 1, wherein an autonomous vehicle probes a nearby vehicle on a roadway for the presence of autonomous interfaces, the autonomous interfaces communicating vehicle parameters comprising a vehicle'"'"'s location, a vehicle'"'"'s speed, and a subsequent action of the vehicle.

3. The computer-implemented method of claim 1, wherein the autonomous vehicles are configured to anticipate actions of the driver of the human-controlled vehicle based on the model of the driver.

4. The computer-implemented method of claim 1, wherein the retrieving of previously stored behavior patterns of the driver further comprises:

accessing a remote server using a unique identifier of the driver; and

uploading recently measured behavior patterns of the driver to the remote server.

5. The computer-implemented method of claim 4, wherein the model of the driver is generated using a processing device onboard the human-controlled vehicle or a processing device of the remote server.

6. The computer-implemented method of claim 1, wherein the model of the driver, which includes previously stored behavior patterns of the driver, is further augmented with present measurements of driver behavior patterns.

7. The computer-implemented method of claim 1, wherein the one or more sensors comprise optical sensors and audio sensors for identifying the behavior patterns of the driver, the behavior patterns including a vehicle measurement selected from a group comprising a speed, an acceleration, a directional change, a movement, a brake frequency, and a variation in speed over a predetermined time.

8. The computer-implemented method of claim 1, wherein the transmitting of the model of the driver from the human-controlled vehicle to the autonomous vehicles is implemented through a wireless antenna onboard the human-controlled vehicle.

9. The computer-implemented method of claim 4, wherein the accessing of the remote server is implemented through a cellular antenna onboard the human-controlled vehicle.

10. The computer-implemented method of claim 4, wherein behavior patterns of the driver stored in the remote server is accessible via the Internet.

11. A method comprising:

equipping autonomous vehicle with an onboard processor, the onboard processor executing a computer-implemented method comprising;

identifying, with the onboard processor, a driver of a human-controlled vehicle based on behavior patterns of the driver measured by one or more sensors coupled to the onboard processor of the autonomous vehicle, wherein the human-controlled vehicle is not an autonomous vehicle, and wherein the driver is identified using a pattern matching algorithm by;

interrogating the human-controlled vehicle for driver identification wherein the driver identification comprises;

receiving driver identification data, and

analyzing registration information of the human-controlled vehicle;

generating a dynamically updated model of the driver using the behavior patterns measured by the one or more sensors; and

transmitting an identification of the driver and the model of the driver of the human-controlled vehicle to other nearby vehicles with autonomous interfaces and to a remote server to store the generated model.

12. The method of claim 11, wherein the onboard processor of the autonomous vehicle receives information from a second onboard processor installed on the human-controlled vehicle, and wherein the installation of the second onboard processor grants special driving privileges on roadways to the driver of the human-controlled vehicle.