초록 ▼

An adaptive vehicle control system that classifies a drivers driving style based on highway on/off ramp maneuvers. Once the maneuver has been determined to be an on-ramp maneuver or an off-ramp maneuver, a style characterization processor can classify the maneuver using selected discriminant feature

An adaptive vehicle control system that classifies a drivers driving style based on highway on/off ramp maneuvers. Once the maneuver has been determined to be an on-ramp maneuver or an off-ramp maneuver, a style characterization processor can classify the maneuver using selected discriminant features obtained or derived from the maneuver.

대표청구항 ▼

1. A method for identifying whether a vehicle maneuver may be an on-ramp or off-ramp maneuver, said method comprising: reading a vehicle speed signal and a vehicle yaw rate signal from vehicle sensors;determining whether the vehicle is turning by determining whether the vehicle yaw rate signal is gr

1. A method for identifying whether a vehicle maneuver may be an on-ramp or off-ramp maneuver, said method comprising: reading a vehicle speed signal and a vehicle yaw rate signal from vehicle sensors;determining whether the vehicle is turning by determining whether the vehicle yaw rate signal is greater than a first yaw rate threshold and, if so, determining that the vehicle has entered a curve that may be a curve portion of a highway on/off ramp;determining whether the vehicle has exited the curve by determining whether the vehicle yaw rate signal is less than a second yaw rate threshold;determining whether the difference between the vehicle speed at the beginning of the curve and at the end of the is less than a first vehicle speed threshold and, if so, determining that the curve-handling maneuver is an off-ramp maneuver;determining whether the increase in vehicle speed during a predetermined time window is less than a second speed threshold;determining whether the vehicle speed during a predetermined time window of the maneuver is greater than a third speed threshold;determining whether a difference of the vehicle speed during the time window minus the speed at the start time is greater than a fourth speed threshold; anddetermining that the maneuver may be an on-ramp maneuver if the increase in the vehicle speed becomes less than the second speed threshold and the speed of the vehicle during the predetermined time window is greater than the third speed threshold and the difference in the vehicle speed during the time window minus the speed of the vehicle at the start time is greater than the fourth speed threshold. 2. The method according to claim 1 further comprising determining that the maneuver is not an off-ramp maneuver if the time the vehicle spends on the curve is greater than a first time period. 3. The method according to claim 1 further comprising determining that the off-ramp maneuver has ended if the vehicle speed is less than a fifth speed threshold. 4. The method according to claim 1 further comprising determining that the maneuver is not an off-ramp maneuver if the vehicle speed is not reduced enough during the maneuver. 5. The method according to claim 1 wherein the first yaw rate threshold is about 2 degrees per second, the second yaw rate threshold is about 1 degree per second, the first speed threshold is about 25 mph, the second speed threshold is about 55 mph, and the fourth speed threshold is about 3 mph. 6. The method according to claim 1 further comprising classifying the vehicle maneuver to determine a driver's driving style if the maneuver is an on-ramp or an off-ramp maneuver. 7. The method according to claim 6 wherein classifying the on-ramp or off-ramp maneuver to determine a driver's driving style includes using selected discriminant features derived or obtained from the maneuver. 8. The method according to claim 7 wherein the discriminant features are derived or obtained from the group comprising a maximum lateral acceleration, a maximum yaw rate, an average acceleration, a maximum throttle opening and an array of throttle indices for an on-ramp maneuver and a maximum lateral acceleration, a maximum yaw rate, an average deceleration, a maximum brake pedal force and an array of braking indices for an off-ramp maneuver. 9. The method according to claim 7 wherein obtaining the discriminant features includes using a linear discriminant analysis process. 10. The method according to claim 7 wherein obtaining the discriminant features includes using a technique selected from the group comprising principal component analysis, linear discriminant analysis, kernel principal component analysis and generalized discriminant analysis, and selecting the discriminant features includes using a technique selected from the group comprising exhaustive search, branch-and-bound search, sequential forward/backward selection and sequential forward/backward floating search. 11. The method according to claim 6 wherein classifying the maneuver includes using a support vector machine. 12. The method according to claim 6 wherein classifying the maneuver includes using a technique selected from a group comprising fuzzy logic, clustering, neural networks, support vector machines and threshold-based logics. 13. A method for identifying whether a vehicle maneuver may be an on-ramp or off-ramp maneuver, said method comprising: reading a vehicle speed signal and a vehicle yaw rate signal in vehicle sensors;determining whether the vehicle is turning by determining whether the vehicle yaw rate signal is greater than a first yaw rate threshold and, if so, determining that the vehicle has entered a curve that may be a curve portion of a highway on/off ramp;determining whether the vehicle has exited the curve by determining whether the vehicle yaw rate signal is less than a second yaw rate threshold;determining whether the difference between the vehicle speed at the beginning of the curve and at the end of the is less than a first vehicle speed threshold and, if so, determining that the curve-handling maneuver is an off-ramp maneuver;determining whether the increase in vehicle speed during a predetermined time window is less than a second speed threshold;determining whether the vehicle speed during a predetermined time window of the maneuver is greater than a third speed threshold;determining whether a difference of the vehicle speed during the time window minus the speed at the start time is greater than a fourth speed threshold;determining that the maneuver may be an on-ramp maneuver if the increase in the vehicle speed becomes less than the second speed threshold and the speed of the vehicle during the predetermined time window is greater than a third speed threshold and a difference in the vehicle speed during the time window minus the speed of the vehicle at the start time is greater than the fourth speed threshold; andclassifying the vehicle maneuver to determine a driver's driving style if the maneuver is an on-ramp or an off-ramp maneuver using selected discriminant features obtained or derived from the maneuver. 14. The method according to claim 13 further comprising determining that the off-ramp maneuver has ended if the vehicle speed is less than a fifth speed threshold. 15. The method according to claim 13 further comprising determining that the maneuver is not an off-ramp maneuver if the vehicle speed is not reduced enough during the maneuver. 16. The method according to claim 13 wherein the first yaw rate threshold is about 2 degrees per second, the second yaw rate threshold is about 1 degree per second, the first speed threshold is about 25 mph, the second speed threshold is about 55 mph, and the fourth speed threshold is about 3 mph. 17. The method according to claim 13 wherein the discriminant features are obtained or derived from the group comprising a maximum lateral acceleration, a maximum yaw rate, an average acceleration, a maximum throttle opening and an array of throttle indices for an on-ramp maneuver and a maximum lateral acceleration, a maximum yaw rate, an average deceleration, a maximum brake pedal force and an array of braking indices for an off-ramp maneuver. 18. The method according to claim 13 wherein obtaining the discriminant features includes using a linear discriminant analysis process. 19. The method according to claim 13 wherein classifying the maneuver to determine a driver's driving style includes using a support vector machine. 20. A system for identifying a vehicle maneuver as a possible on-ramp or off-ramp maneuver, said system comprising: vehicle sensors that provide a vehicle speed signal and a vehicle yaw rate signal;means for determining whether the vehicle is turning by determining whether the vehicle yaw rate signal is greater than a first threshold and, if so, determining that the vehicle has entered a curve that might be a curve portion of a highway on/off ramp;means for determining whether the vehicle has exited the curve by determining whether the vehicle yaw rate signal is less than a second yaw rate threshold;means for determining whether the difference between vehicle speed at the beginning of the curve and at the end of the curve is less than a first vehicle speed threshold and, if so, determining that the curve-handling maneuver is an off-ramp maneuver;means for determining whether the increase in vehicle speed during a predetermined time window is less than a second speed threshold;means for determining whether the vehicle speed during a predetermined time window of the maneuver is greater than a third speed threshold;means for determining whether a difference of the vehicle speed during the time window minus the speed at the start time is greater than a fourth speed threshold; andmeans for determining that the maneuver may be an on-ramp maneuver if the increase in the vehicle speed becomes less than the second speed threshold and the speed of the vehicle during the predetermined time window is greater than the third speed threshold and the difference in the vehicle speed during the time window minus the of the vehicle at the start time speed is greater than the fourth speed threshold. 21. The system according to claim 20 further comprising means for determining that the maneuver is not an off-ramp maneuver if the time during the curve-handling maneuver is greater than a first time period. 22. The system according to claim 20 further comprising means for determining that the off-ramp maneuver has ended if the vehicle speed is less than a fifth speed threshold. 23. The system according to claim 20 further comprising means for determining that the maneuver is not an off-ramp maneuver if the vehicle speed is not reduced enough during the maneuver. 24. The system according to claim 20 wherein the first yaw rate threshold is about 2 degrees per second, the second yaw rate threshold is about 1 degree per second, the first speed threshold is about 25 mph, the second speed threshold is about 55 mph, and the fourth speed threshold is about 3 mph. 25. The system according to claim 20 further comprising means for classifying the vehicle maneuver to determine a driver's driving style if the maneuver is an on-ramp or an off-ramp maneuver. 26. The system according to claim 25 wherein the means for classifying the on-ramp or off-ramp maneuver includes means for using selected discriminant features obtained or derived from the maneuver. 27. The system according to claim 26 wherein the discriminant features are obtained or derived from the group comprising a maximum lateral acceleration, a maximum yaw rate, an average acceleration, a maximum throttle opening and an array of throttle indices for an on-ramp maneuver and a maximum lateral acceleration, a maximum yaw rate, an average deceleration, a maximum brake pedal force and an array of braking indices for an off-ramp maneuver. 28. The system according to claim 26 wherein the means for obtaining or deriving the discriminant features uses a linear discriminant analysis process. 29. The system according to claim 26 wherein the means for obtaining or deriving the discriminant features uses a technique selected from the group comprising principal component analysis, linear discriminant analysis, kernel principal component analysis and generalized discriminant analysis, and the means for selecting the discriminant features is selected from the group comprising exhaustive search, branch-and-bound search, sequential forward/backward selection and sequential forward/backward floating search. 30. The system according to claim 25 wherein the means for classifying the maneuver to determine a driver's driving style includes using a support vector machine.