Adaptive driver workload estimator

• US 20070063854A1
• Filed: 08/02/2005
• Published: 03/22/2007
• Est. Priority Date: 08/02/2005
• Status: Active Grant

• Current Assignee: GM Global Technology Operations LLC (General Motors Company)
• Original Assignee: GM Global Technology Operations Incorporated (Motors Liquidation Co. GUC Trust)
• Inventors: Zhang, Jing, Zhang, Yilu, Owechko, Yuri
• Granted Patent: US 7,394,393 B2
• Time in Patent Office: Days
• US Class Current: 340/576
• CPC Class Codes: B60W 2050/0029 Mathematical model of the driver
• CPC Class Codes: B60W 40/09 Driving style or behaviour

Abstract

A method for adaptive driver workload estimation. A subjective assessment of a driver workload is received from a vehicle driver. A stream of sensor input data is collected from one or more sensors in response to receiving the subjective assessment. A machine learning algorithm is applied to a driver workload estimate model based on the stream of sensor input data and the subjective assessment. The result of the applying is an updated driver workload estimate model.

Claims

1. A method for adaptive driver workload estimation, the method comprising:

receiving a subjective assessment of a driver workload from a vehicle driver;

collecting a stream of sensor input data from one or more sensors in response to receiving the subjective assessment; and

applying a machine learning algorithm to a driver workload estimate model based on the stream of sensor input data and the subjective assessment, the applying resulting in an updated driver workload estimate model.

2. The method of claim 1 further comprising:

receiving sensor input data; and

updating a workload index in response to the sensor input data and to the updated driver workload estimate model.

3. The method of claim 2 wherein the sensor input data is received periodically on a substantially real time basis.

4. The method of claim 1 wherein creation of the subjective assessment is initiated by the vehicle driver.

5. The method of claim 1 wherein creation of the subjective assessment is initiated by logic located on the vehicle.

6. The method of claim 1 wherein the sensor input data includes one or more of vehicle data, driver data and environment data.

7. The method of claim 1 wherein the machine learning algorithm is implemented by a decision tree.

8. The method of claim 1 wherein the machine learning algorithm includes one or more of discriminant analysis, decision tree, artificial neural network, hidden Markov model, Bayesian network, Bayesian belief network, case based reasoning (CBR), genetic algorithm, and support vector machine.

9. A system for adaptive driver workload estimation, the system comprising:

an input device; and

a microprocessor in communication with the input device, the microprocessor including instructions to facilitate;

receiving a subjective assessment of a driver workload from a vehicle driver via the input device;

collecting a stream of sensor input data from one or more sensors in response to receiving the subjective assessment; and

applying a machine learning algorithm to a driver workload estimate model based on the stream of sensor input data and the subjective assessment, the applying resulting in an updated driver workload estimate model.

10. The system of claim 9 further comprising:

receiving sensor input data; and

updating a workload index in response to the sensor input data and to the updated driver workload estimate model.

11. The system of claim 10 wherein the sensor input data is received periodically on a substantially real time basis.

12. The system of claim 9 wherein creation of the subjective assessment is initiated by the vehicle driver.

13. The system of claim 9 wherein creation of the subjective assessment is initiated by logic located on the vehicle.

14. The system of claim 9 wherein the sensor input data includes one or more of vehicle data, driver data and environment data.

15. The system of claim 9 wherein the machine learning algorithm is implemented by a decision tree.

16. The system of claim 9 wherein the machine learning algorithm includes one or more of discriminant analysis, decision tree, artificial neural network, hidden Markov model, Bayesian network, Bayesian belief network, case based reasoning (CBR), genetic algorithm, and support vector machine.

17. A computer program product for adaptive driver workload estimation, the computer program product comprising:

a storage medium readable by a processing circuit and storing instructions for execution by the processing circuit for performing a method comprising;

receiving a subjective assessment of a driver workload from a vehicle driver;

collecting a stream of sensor input data from one or more sensors in response to receiving the subjective assessment; and

applying a machine learning algorithm to a driver workload estimate model based on the stream of sensor input data and the subjective assessment, the applying resulting in an updated driver workload estimate model.

18. The computer program product of claim 17, wherein the method further comprises:

receiving sensor input data; and

updating a workload index in response to the sensor input data and to the updated driver workload estimate model.

19. The computer program product of claim 17 wherein the sensor input data is received periodically on a substantially real time basis.