PERSONALIZED DRIVER STRESS PREDICTION USING GEOGRAPHICAL DATABASES

• US 20030097047A1
• Filed: 11/21/2001
• Published: 05/22/2003
• Est. Priority Date: 11/21/2001
• Status: Active Grant

• Current Assignee: Mind Fusion, LLC (Ascend Innovation Management, LLC)
• Original Assignee: DaimlerChrysler AG (Mercedes-Benz Group AG)
• Inventors: Woltermann, Bernd, Schroedl, Stefan
• Granted Patent: US 6,599,243 B2
• Time in Patent Office: Days
• US Class Current: 600/300
• CPC Class Codes: A61B 5/165 Evaluating the state of mind, e.g. depression, anxiety
• CPC Class Codes: A61B 5/18 for vehicle drivers or machine operators
• CPC Class Codes: B60W 2050/0029 Mathematical model of the driver
• CPC Class Codes: B60W 2540/22 Psychological state; Stress level or workload
• CPC Class Codes: B60W 2540/221 Physiology, e.g. weight, heartbeat, health or special needs
• CPC Class Codes: B60W 2556/50 of positioning data, e.g. GPS [Global Positioning System] data
• CPC Class Codes: G01C 21/3697 Output of additional, non-guidance related information, e.g. low fuel level G01C21/3679 takes precedence
• CPC Class Codes: G08B 21/06 indicating a condition of sleep, e.g. anti-dozing alarms

Abstract

A system installed in a motor vehicle for inferring a vehicle operator'"'"'s stress level from body sensors and from environmental data related to the position and operation of the vehicle. The system functions in a training phase using machine learning techniques to derive a model of an individual operators stress reaction to the environment in which the vehicle is operated and, using the results of this training phase, the system is subsequently used to predict stress levels to be expected when certain traffic conditions are imminent based on a projection of the driver'"'"'s physiolocial state. The result of this prediction of stress level for the individual driver is used to control or warn the driver with respect to operation and scheduling of attention diverting devices such as cellular phones.

Claims

1. A system for providing an indication of a vehicle operators stress reaction to a future change in the environment in which said vehicle is being operated;

said system comprising;

at least one sensor for sensing a respective at least one physical parameter of said operator;

a processing device receiving the outputs of said at least one sensor and providing a training signal;

a vehicle positioning system for determining a position of said vehicle and outputting a position signal;

at least one vehicle sensor for determining at least one vehicle operation parameter and outputting at least one vehicle parameter signal;

a derived environment device having at least one first input receiving respective ones of said at least one vehicle parameter signal and a second input receiving said position signal and providing a vehicle environment output signal;

a machine statistical learning module having a first input for receiving said vehicle environmental output signal wherein said machine statistical learning module is controlled by said training signal in order to derive a statistical relationship between a physical condition of said operator and an operational environment of said vehicle.

2. A system according to claim 1 wherein said derived environment device further provides an updated vehicle environment signal to said statistical learning module wherein said statistical module compares said updated vehicle environment signal with a stored set of data in said statistical learning module to provide a predicted operator condition output as a function of said updated vehicle environment signal.

3. The system according to claim 2 further comprising a navigation system providing an output to a map database in order to modify said updated vehicle environmental signal on the basis of an anticipated predetermined route to be followed by said vehicle.

9. The system according to claim 1, wherein said at least one sensor for sensing a physical parameter includes at least one of an electrocardiogram measuring device, a pulse measuring device and a blood pressure measuring device.

10. The system according to claim 1, wherein said at least one vehicle sensor includes at least one of a speed measuring device, a traction measuring device, an anti-lock brake measuring device and an electronic stability program.

11. The system according to claim 1, wherein said machine statistical learning module includes one of a neural net, a polynomial classifier and a support vector machine.

12. The system according to claim 1, wherein said at least one sensor for sensing a physical parameter includes an infrared device integrated into the vehicle and proximal to the vehicle operator.

13. The system according to claim 1, wherein said vehicle positioning system includes at least one of a digital map and a global positioning system (“

GPS”

).

4. A system for predicting operator stress during operation of the vehicle, comprising:

means for sensing physical data related to at least one parameter of said operator;

means for collecting and arranging said physical data to provide a continuous operator stress condition output signal;

vehicle positioning means for determining the position of said vehicle;

vehicle operation means for determining operating characteristics of said vehicle;

means responsive to an output of said vehicle positioning means and said vehicle operation means in order to provide an environmental information signal concerning said vehicle; and

a statistical learning device receiving the vehicle environment information signal as an input, wherein said statistical learning device utilizes said continuous operator stress condition output signal as a teaching signal in order to provide a stored statistical learning model relating a physical condition of said operator with the environment of said vehicle.

5. The system according to claim 4, further including a navigation means for indexing said vehicle positioning means to provide an indication of the future environment of said vehicle and outputting a future environment signal as an additional input to said statistical learning device wherein said statistical learning device outputs a future operator stress condition signal.

14. The system according to claim 4, further including a prediction means for providing a predicted stress level and a comparing means for comparing said predicted stress level with an actual stress level provided by said continuous stress condition output signal in order to update said stored statistical learning model.

6. A method for predicting vehicle operator stress reaction to a future change in the environment in which said vehicle is being operated, said method comprising the steps of:

sensing at least one physical parameter of said operator;

processing sensed outputs related to said at least one physical parameter and providing a training signal;

determining a position of said vehicle and outputting a position signal;

determining at least one vehicle operating parameter and outputting a corresponding at least one vehicle operating parameter signal;

determining a vehicle environment as a function of said at least one vehicle operating parameter signal and said position signal to provide a vehicle environment output signal; and

deriving a statistical relationship between a physical condition of said operator and an operational environment of said vehicle as a function of said vehicle environment output signal controlled by said training signal.

7. A method according to claim 6 comprising the further steps of providing an updated vehicle environment signal and comparing said updated vehicle environment signal with a stored set of data concerning said statistical relationship in order to provide a predicted operator condition output as a function of said updated vehicle environment signal.

8. A method according to claim 7 including the further step of supplying a map database in order to modify said updated vehicle environment signal on the basis of an anticipated predetermined route to be followed by said vehicle.