Adaptive vehicle control system with driving style recognition

• US 8,260,515 B2
• Filed: 07/24/2008
• Issued: 09/04/2012
• Est. Priority Date: 07/24/2008
• Status: Expired due to Fees

• Current Assignee: GM Global Technology Operations LLC (General Motors Company)
• Original Assignee: GM Global Technology Operations LLC (General Motors Company)
• Inventors: Huang, Jihua, Chin, Yuen-Kwok, Lin, William C.
• Primary Examiner(s): Tran, Khoi
• Assistant Examiner(s): Sample, Jonathan L
• Application Number:
  US12/179,048
• Publication Number:
  US 20100023223A1
• Time in Patent Office: 1,503 Days
• Field of Search: None
• US Class Current: 701/70
• CPC Class Codes: B60K 2031/0033 Detecting longitudinal speed or acceleration of target vehicle
• CPC Class Codes: B60W 2510/20 Steering systems
• CPC Class Codes: B60W 2520/10 Longitudinal speed
• CPC Class Codes: B60W 2520/14 Yaw
• CPC Class Codes: B60W 2540/18 Steering angle
• CPC Class Codes: B60W 2540/30 Driving style
• CPC Class Codes: B60W 2552/05 Type of road, e.g. motorways, local streets, paved or unpaved roads
• CPC Class Codes: B60W 2552/10 Number of lanes
• CPC Class Codes: B60W 2552/40 Coefficient of friction
• CPC Class Codes: B60W 2555/20 Ambient conditions, e.g. wind or rain
• CPC Class Codes: B60W 2556/50 of positioning data, e.g. GPS [Global Positioning System] data
• CPC Class Codes: B60W 30/12 Lane keeping
• CPC Class Codes: B60W 30/16 Control of distance between vehicles, e.g. keeping a distance to preceding vehicle
• CPC Class Codes: B60W 40/09 Driving style or behaviour

Abstract

An adaptive vehicle control system that classifies a driver'"'"'s driving style based on characteristic curve-handling maneuvers and road and traffic conditions. The system includes a plurality of vehicle sensors that detect various vehicle parameters. A maneuver identification processor receives the sensor signals to identify a characteristic maneuver of the vehicle and provides a maneuver identifier signal of the maneuver. The system also includes a traffic and road condition recognition processor that receives the sensor signals, and provides traffic condition signals identifying traffic conditions and road condition signals identifying road conditions. A style characterization processor receives the maneuver identifier signals, sensor signals from the vehicle sensors and the traffic and road condition signals, and classifies driving style based on the signals to classify the style of the driver driving the vehicle.

Claims

1. A system for classifying a driver'"'"'s driving style of a vehicle, said system comprising:

a plurality of vehicle sensors providing sensor measurement signals;

a maneuver identification processor responsive to the sensor signals from the plurality of vehicle sensors, said maneuver identification processor identifying characteristic maneuvers of the vehicle and providing maneuver identifier signals identifying the type of the characteristic maneuvers;

a traffic and road condition recognition processor responsive to the sensor signals, said traffic and road condition recognition processor providing traffic and road condition signals identifying traffic conditions and road conditions;

a vehicle-to-infrastructure communications system providing communications signals to the traffic and road condition recognition processor so as to enhance the traffic and road condition signals;

a data selection processor responsive to the sensor signals, the maneuver identifier signals and the traffic and road condition signals, said data selection processor storing data for the maneuvers and the traffic and road conditions;

a style characterization processor responsive to the maneuver identifier signals, the stored data from the data selection processor and the traffic and road condition signals from the traffic and road condition recognition processor, said style characterization processor classifying driving style based on the signals and providing driving style classification signals that identify the type of driver driving the vehicle;

a style profile trip-logger responsive to the maneuver identifier signals and the driving style signals, said trip-logger storing the style classification signals; and

a decision fusion processor responsive to the style classification signals from the style characterization processor and the stored driving style classification signals from the trip-logger, said decision fusion processor integrating the most recent style classification signals with past style classification signals stored in the trip-logger, and providing integrated driving style classification signals, wherein the decision fusion processor employs a level-1 combination that combines style classification signals from different classifiers based on a single maneuver.

2. The system according to claim 1 wherein the decision fusion processor employs a decision fusion technique selected from the group consisting of Bayesian fusion and Dempster-Shafer fusion.

3. The system according to claim 1 wherein the decision fusion processor employs a level-2 combination that combines style classification signals based on multiple maneuvers that are of the same type.

4. The system according to claim 1 wherein the decision fusion processor employs a level-3 combination that combines style classification signals based on different types of maneuvers.

5. The system according to claim 1 further comprising a vehicle position processor responsive to the sensor signals and location signals, said vehicle position processor outputting vehicle position signals to the traffic and road condition recognition processor to incorporate vehicle position in the traffic and road condition signals.

6. The system according to claim 5 wherein the vehicle position processor receives information about vehicle position from a global positioning system or an electronic digital map.

7. The system according to claim 1 further comprising a surround sensing processor providing surround fusion signals to the traffic and road condition recognition processor so as to enhance the traffic and road condition signals.

8. The system according to claim 1 further comprising a signal processor responsive to the sensor signals and processing the sensor signals to be in a format suitable for the maneuver identification processor, the traffic and road condition recognition processor and the data selection processor.

9. The system according to claim 1 further comprising a driver identification processor that identifies a particular driver of the vehicle, and a style profile database processor that updates a style profile of a particular driver based on a driver identification signal and the style classification signals.

10. The system according to claim 9 further comprising a trend analysis processor that receives style profile values from the style profile database processor and the style classification signals, and determining whether there is a change in the driving style.

11. The system according to claim 1 wherein the characteristic maneuvers include vehicle following maneuvers, lane-change maneuvers, U-turn maneuvers, left/right-turn maneuvers, highway on/off ramp maneuvers, passing maneuvers, vehicle launching maneuvers and curve-handling maneuvers.

12. The system according to claim 1 wherein the traffic condition signals are determined based on the number of lanes in the roadway, the number of vehicle tracks being monitored, the range from the vehicle to a preceding vehicle and the speed of the vehicle.

13. The system according to claim 12 wherein the traffic condition signals are also determined based on the range from the vehicle to a trailing vehicle.

14. The system according to claim 1 wherein the traffic condition signals are determined based on the average distance between the vehicle and other vehicles travelling in the same direction.

15. The system according to claim 1 wherein the roadway condition signals include roadway conditions for roadway type, roadway surface and ambient conditions.

16. The system according to claim 15 wherein the roadway type is identified for each of an urban freeway, a rural freeway, an urban local road, a rural local road and other road-way types.

17. The system according to claim 15 wherein the roadway surface is identified as surfaces with various levels of friction coefficients and various degrees of roughness.

18. The system according to claim 15 wherein the ambient conditions include light level, rain or snow and fog detection.

19. The system according to claim 1 wherein the style characterization processor uses a classification processes selected from the group comprising fuzzy logic, clustering, neural networks, self-organizing maps and threshold-based logic.

20. The system according to claim 1 wherein the style characterization processor includes an input switch responsive to the maneuver identifier signals, the stored data from the data selection processor, the traffic condition signals and the road condition signals, said style characterization processor further includes a separate classification processor for each different type of characteristic maneuver, wherein the input switch directs the stored data, the traffic condition signals and the road condition signals to the proper style classification processor based on the maneuver identifier signal, each style classification processor providing the style classification signals for the specific type of maneuver.

21. The system according to claim 1 wherein the style characterization processor uses discriminant features to classify the driving style.

22. The system according to claim 21 wherein the discriminant features are derived or obtained from the group comprising vehicle yaw rate, vehicle lateral acceleration, vehicle speed, brake pedal position, brake pedal force, throttle percentage, distance to a preceding vehicle and distance to a following vehicle and signals processed and derived from same.

23. The system according to claim 1 wherein the style characterization processor employs a process of feature extraction and feature selection to classify the driving style.

24. The system according to claim 23 wherein the style characterization processor includes an original features processor, a feature extraction processor, a feature selection processor and a classifier processor for each different type of characteristic maneuver, said original features processor being responsive to the stored data and providing original features of the stored data to the feature extraction processor, said feature extraction processor further being responsive to the traffic condition signals and the road condition signals, said feature extraction processor extracting discriminant features from the original features and providing the extracted features to the feature selection processor, said feature selection processor selecting certain ones of the extracted discriminant features and providing the selected features to the classifier processor, said classifier processor providing the style classification signals.

25. The system according to claim 23 wherein the style characterization processor includes an original features processor, a feature extraction processor, a feature selection processor and a classifier processor for each separate characteristic maneuver, said original features processor being responsive to the stored data and providing original features of the storage data to the feature extraction processor, said feature extraction processor extracting discriminant features from the original features and providing the extracted features to the feature selection processor, said classifier processor being responsive to the traffic condition signals and the road condition signals, said classifier processor providing the style classification signals.

26. The system according to claim 1 wherein the style characterization processor includes an input switch responsive to the traffic condition signals, the road index condition signals and the stored data from the data selection processor, said traffic index signal identifying either light traffic or moderate traffic and said road index signal identifying either good road conditions or moderate road conditions, said characterization processor including four channels one for light traffic and good road conditions, one for moderate traffic and good road conditions, one for light traffic and moderate road conditions and one for moderate traffic and moderate road conditions, said input switch sending the recorded data to the appropriate channel based on the traffic and road conditions.

27. The system according to claim 1 wherein the style characterization processor uses a select/switch incorporation to include traffic/road conditions in the classification of the driving style.

28. The system according to claim 1 wherein the style characterization processor uses decoupled-scaling to incorporate traffic/road conditions in the classification of the driving style.

29. The system according to claim 1 wherein the style characterization processor uses a driver'"'"'s headway control between the vehicle and a preceding vehicle to classify the driving style.

30. The system according to claim 1 wherein the style characterization processor includes a maneuver qualification and identification processor for qualifying and identifying data from the vehicle, a maneuver index and parameter processor for creating a maneuver index and for identifying irrelevant vehicle parameters, a path reconstruction processor that reproduces a vehicle path for each maneuver, a maneuver model processor for modeling the maneuver, and a driving style diagnosis processor that provides the driving style signals based on the maneuver model and the driver input data.

31. The system according to claim 30 wherein the driving style diagnosis processor converts the maneuver model signals and driver command input signals to the frequency domain, said driver style diagnosis processor providing a difference between the frequency domain of the maneuver model signals and the driver command signals to provide frequency content discrepancy analysis.

32. The system according to claim 1 wherein the system is part of an active front steer variable gear ratio control system on the vehicle.

33. The system according to claim 1 wherein the plurality of sensors include a hand-wheel angle sensor, a yaw rate sensor, a vehicle speed sensor, wheel speed sensors, longitudinal accelerometer, a lateral accelerometer, a headway distance sensor, a forward-looking radar/lidar camera, a throttle opening sensor and brake pedal position/force sensors.

34. A system for classifying a driver'"'"'s driving style of a vehicle, said system comprising:

a plurality of vehicle sensors providing sensor measurement signals;

a maneuver identification processor responsive to the sensor signals from the plurality of vehicles sensors, said maneuver identification processor identifying characteristic maneuvers of the vehicle and providing maneuver identifier signals identifying the characteristic maneuvers;

a style characterization processor responsive to the maneuver identifier signals, said style characterization processor classifying driving style based on the maneuver identifier signals using discriminant features, where the style characterization processor includes a separate classification processor for each different type of characteristic maneuver, said style characterization processor providing driving style classification signals that identify the type of driver driving the vehicle;

a style profile trip-logger responsive to the maneuver identifier signals and the driver style signals, said trip-logger storing the style classification signals; and

a decision fusion processor responsive to the style classification signals from the style characterization processor and the stored driving style classification signals from the trip-logger, said decision fusion processor integrating the most recent style classification signals with past style classification signals stored in the trip-logger, and providing integrated driving style classification signals.

35. The system according to claim 34 further comprising a traffic and road condition recognition processor responsive to the sensor signals, said traffic and condition recognition processor providing traffic and road condition signals identifying traffic conditions and road conditions, said style characterization processor receiving the traffic and road condition signals to be used for classifying the driving style.

36. The system according to claim 34 wherein the style characterization processor employs a process of feature extraction and feature selection to classify the driving style.

37. The system according to claim 34 wherein the plurality of sensors include a hand-wheel angle sensor, a yaw rate sensor, a vehicle speed sensor, wheel speed sensors, longitudinal accelerometer, a lateral accelerometer, a headway distance sensor, a forward-looking radar/lidar camera, a throttle opening sensor and brake pedal position/force sensors.

38. The system according to claim 34 wherein the system is part of an active front steer variable gear ratio control system on the vehicle.

39. The system according to claim 34 wherein the style characterization processor uses a select/switch incorporation to include traffic/road conditions in the classification of the driving style.

40. The system according to claim 34 wherein the style characterization processor uses decoupled-scaling to incorporate traffic/road conditions in the classification of the driving style.

41. The system according to claim 34 wherein the style characterization processor uses a driver'"'"'s headway control between the vehicle and a preceding vehicle to classify the driving style.

42. The system according to claim 34 wherein the style characterization processor uses a classification processes selected from the group comprising fuzzy logic, clustering, neural networks, self-organizing maps and threshold-based logic.

43. A system for classifying a driver'"'"'s driving style of a vehicle, said system comprising:

a plurality of vehicle sensors providing sensor measurement signals;

a signal processor responsive to the sensor signals and processing the sensor signals to be in a format suitable for the classification;

a maneuver identification processor responsive to the sensor signals from the signal processor, said maneuver identification processor identifying characteristic maneuvers of the vehicle and providing maneuver identifier signals identifying the characteristic maneuvers;

a traffic and road condition recognition processor responsive to the sensor signals from the signal processor, said traffic and road condition recognition processor providing traffic and road condition signals identifying traffic conditions and road conditions;

a vehicle position processor responsive to the sensor signals from the signal processor and location signals, said vehicle position processor outputting vehicle position signals to the traffic and road condition recognition processor to incorporate vehicle position in the traffic and road condition signals;

a data selection processor responsive to the sensor signals from the signal processor, the maneuver identifier signals and the traffic and road condition signals, said data selection processor storing data for the maneuvers and the traffic and road conditions;

a style characterization processor responsive to the maneuver identifier signals, the stored data from the data selection processor and the traffic and road condition signals from the traffic and road condition recognition processor, said style characterization processor classifying driving style based on the signals and providing driving style classification signals that identify the type of driver driving the vehicle, where the style characterization processor uses a select/switch incorporation to include traffic/road conditions in the classification of the driving style;

a style profile trip-logger responsive to the maneuver identifier signals and the driver style signals, said trip-logger storing the style classification signals; and

a decision fusion processor responsive to the style classification signals from the style characterization processor and the stored driving style classification signals from the trip-logger, said decision fusion processor integrating the most recent style classification signals with past style classification signals stored in the trip-logger, and providing integrated driving style classification signals.

44. The system according to claim 43 further comprising a surround sensing processor providing surround fusion signals to the traffic and road condition recognition processor so as to enhance the traffic and road condition signals.

45. The system according to claim 43 further comprising a vehicle-to-infrastructure/vehicle communications system providing communications signals to the traffic and road condition recognition processor so as to enhance the traffic and road condition signals.

46. The system according to claim 43 further comprising a driver identification processor that identifies a particular driver of the vehicle, and a style profile database processor that updates a style profile of a particular driver based on a driver identification signal and the style classification signals.

47. The system according to claim 46 further comprising a trend analysis processor that receives style profile values from the style profile database processor and the style classification signals, and determining whether there is a change in the driving style.

48. The system according to claim 43 wherein the characteristic maneuvers include vehicle following maneuvers, lane-change maneuvers, U-turn maneuvers, left/right-turn maneuvers, highway on/off ramp maneuvers, passing maneuvers, vehicle launching maneuvers and curve-handling maneuvers.

49. The system according to claim 43 wherein the style characterization processor uses decoupled-scaling to incorporate traffic/road conditions in the classification of the driving style.

50. The system according to claim 43 wherein the system is part of an active front steer variable gear ratio control system on the vehicle.

51. The system according to claim 43 wherein the plurality of sensors include a hand-wheel angle sensor, a yaw rate sensor, a vehicle speed sensor, wheel speed sensors, longitudinal accelerometer, a lateral accelerometer, a headway distance sensor, a forward-looking radar/lidar camera, a throttle opening sensor and brake pedal position/force sensors.

52. The system according to claim 43 wherein the decision fusion processor employs a decision fusion technique selected from the group consisting of Bayesian fusion and Dempster-Shafer fusion.

53. The system according to claim 43 wherein the style characterization processor uses a classification processes selected from the group comprising fuzzy logic, clustering, neural networks, self-organizing maps and threshold-based logic.

54. The system according to claim 43 wherein the style characterization processor uses discriminant features to classify the driving style.

55. The system according to claim 54 wherein the discriminant features are derived or obtained from the group comprising vehicle yaw rate, vehicle lateral acceleration, vehicle speed, brake pedal position, brake pedal force, throttle percentage, distance to a preceding vehicle and distance to a following vehicle and the signals processed and derived from same.