ON-VEHICLE SITUATION DETECTION APPARATUS AND METHOD

• US 20160009295A1
• Filed: 03/12/2015
• Published: 01/14/2016
• Est. Priority Date: 07/10/2014
• Status: Active Grant

• Current Assignee: Hyundai Mobis Co., Ltd.
• Original Assignee: Hyundai Mobis Co., Ltd.
• Inventors: Chun, In-Sung, Lee, Jun-Han
• Granted Patent: US 9,776,644 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: A61B 5/0077 Devices for viewing the surface of the body, e.g. camera, magnifying lens
• CPC Class Codes: A61B 5/163 by tracking eye movement, gaze, or pupil change
• CPC Class Codes: A61B 5/18 for vehicle drivers or machine operators
• CPC Class Codes: A61B 5/6893 Cars
• CPC Class Codes: A61B 5/7203 for noise prevention, reduction or removal
• CPC Class Codes: A61B 5/7267 involving training the classification device
• CPC Class Codes: B60C 5/005 Ballast tyres
• CPC Class Codes: B60Q 5/005 automatically actuated
• CPC Class Codes: B60W 2040/0818 Inactivity or incapacity of driver
• CPC Class Codes: B60W 2050/0025 Transfer function weighting factor
• CPC Class Codes: B60W 2050/143 Alarm means
• CPC Class Codes: B60W 2050/146 Display means
• CPC Class Codes: B60W 2420/403 Image sensing, e.g. optical camera
• CPC Class Codes: B60W 2420/408 Radar; Laser, e.g. lidar
• CPC Class Codes: B60W 2420/54 Audio sensitive means, e.g. ultrasound
• CPC Class Codes: B60W 2422/90 on bumper, e.g. collision sensor
• CPC Class Codes: B60W 2540/00 Input parameters relating to occupants
• CPC Class Codes: B60W 2540/043 Identity of occupants
• CPC Class Codes: B60W 2540/10 Accelerator pedal position
• CPC Class Codes: B60W 2540/12 Brake pedal position
• CPC Class Codes: B60W 2540/16 : Ratio selector position
• CPC Class Codes: B60W 2540/18 : Steering angle
• CPC Class Codes: B60W 2540/22 : Psychological state; Stress level or workload
• CPC Class Codes: B60W 2540/30 : Driving style
• CPC Class Codes: B60W 2554/00 : Input parameters relating to objects
• CPC Class Codes: B60W 40/02 : related to ambient conditions
• CPC Class Codes: B60W 40/09 : Driving style or behaviour
• CPC Class Codes: B60W 50/14 : Means for informing the driver, warning the driver or prompting a driver intervention
• CPC Class Codes: B60W 50/16 : Tactile feedback to the driver, e.g. vibration or force feedback to the driver on the steering wheel or the accelerator pedal
• CPC Class Codes: G07C 5/0808 : Diagnosing performance data testing of vehicles G01M17/00; testing of electrical installation on vehicles G01R31/005
• CPC Class Codes: G07C 5/0816 : Indicating performance data, e.g. occurrence of a malfunction
• CPC Class Codes: G07C 5/085 : using electronic data carriers
• CPC Class Codes: G16H 50/70 : for mining of medical data, e.g. analysing previous cases of other patients

Abstract

An on-vehicle situation detection apparatus may include a detection unit to identify a driver and acquire driver status data and data about vehicle driving information or vehicle surrounding obstacles, a driving pattern learning unit to learn and store a driving pattern of a driver, based on the data acquired by the detection unit, a weighted value determination unit to determine a weighted value assigned to the information data acquired by the detection unit, based on the driving pattern learned by the driving pattern learning unit, a determination unit to determine a safe driving state of the driver, based on the data to which the weighted value determined by the weighted value determination unit is assigned, and a warning unit to warn the driver when the driver is determined to be not in the safe driving state.

Claims

1. An on-vehicle situation detection apparatus comprising:

a detection unit to identify a driver and acquire driver status data, vehicle driving information data and vehicle surrounding obstacle data;

a driving pattern learning unit to process and store a current driving pattern of a driver, based on the data acquired by the detection unit;

a weighted value determination unit to determine a weighted value assigned to the information data acquired by the detection unit, based on the driving pattern learned by the driving pattern learning unit;

a determination unit to determine a safe driving state of the driver, based on the data; and

a warning unit to warn the driver when the driving state of the driver is determined to be not in the safe driving state by the determination unit.

2. The on-vehicle situation detection apparatus of claim 1, further comprising a memory unit configured to store the data.

3. The on-vehicle situation detection apparatus of claim 1, wherein the detection unit comprises a driver status detection section which comprises one or more of an infrared LED imaging device, a steering wheel speed detection sensor, a steering wheel angle detection sensor, a suspension movement detection sensor, a pedal operation detection sensor, a multifunctional switch operation detection sensor, a voice recognition sensor, an AVN operation detection sensor, an air conditioning device operation detection sensor, a gearbox sensor, a console box operation detection sensor, and a glove box operation detection sensor, and a vehicle surrounding situation detection section which comprises one or more of an SCC (Smart Cruise Control), an LKAS (Lane Keeping Assistant System), an SPAS (Smart Parking Assistant System), an AVM (Around View Monitoring), a camera, and a radar.

4. The on-vehicle situation detection apparatus of claim 1, wherein the determination unit comprises a calculation learning unit to arrange the data, to which the weighted value determined by the weighted value determination unit is assigned, in the order of data causing an integrated risk index to exceed a preset reference risk index and to select only a plurality of high data, a calculation unit to calculate a driver'"'"'s integrated risk index by adding up respective risk indexes which multiply the data selected by the calculation learning unit by a weighted value for each data assigned by the weighted value determination unit, an examination unit to determine whether a calculated result in the calculation unit is valid, and a control unit to determine whether the integrated risk index exceeds a preset reference risk index when the calculated result is determined to be valid in the examination unit.

5. The on-vehicle situation detection apparatus of claim 1, wherein the warning unit comprises one or more of a warning sound output device, a driving load display device, and a vehicle control device.

6. An on-vehicle situation detection method comprising:

performing driver recognition of calling pre-stored driver information to compare whether the driver information coincides with a current driver;

performing driving pattern calling of calling a pre-stored driving pattern of the driver identified by the performing driver identification from a memory unit;

performing detection of collecting driver status information and vehicle driving information or vehicle surrounding obstacle information;

performing driving pattern learning of learning the pre-stored driving pattern called by the performing driving pattern calling and a driving pattern derived from the performing detection to store the learned driving pattern in the memory unit;

performing weighted value determination of determining a weighted value assigned to each data acquired from the performing detection, based on the driving pattern learned in the performing driving pattern learning;

performing determination of determining a safe driving state of the driver, based on the data to which the weighted value determined in the performing weighted value determination is assigned; and

performing warning of warning the driver when the driver is determined to be not in the safe driving state in the performing determination.

7. The on-vehicle situation detection method of claim 6, wherein the performing driver recognition comprises performing driver data acquisition of acquiring image data of pupils or faces through an imaging device, and performing driver identification of comparing the image data of pupils and faces acquired by the performing driver data acquisition with the pre-stored driver information in the memory unit to identify the driver.

8. The on-vehicle situation detection method of claim 6, wherein the performing driving pattern calling calls a pre-stored default driving pattern when a driver coinciding with the pre-stored driver information in the performing driver recognition is not present.

9. The on-vehicle situation detection method of claim 6, wherein the performing detection comprises performing driver status detection of detecting one or more of a driver eyelid, a driver pupils, a steering wheel speed, a steering wheel angle, a suspension movement, whether or not an accelerator pedal is operated, whether or not a brake pedal is operated, whether or not a multifunctional switch is operated, whether or not a driver makes conversation, whether or not an AVN is operated, whether or not an air conditioning device is operated, whether or not a gearbox is operated, whether or not a console box is operated, and whether or not a glove box is operated, and performing vehicle surrounding situation detection of detecting a vehicle surrounding situation using one or more of an SCC (Smart Cruise Control), an LKAS (Lane Keeping Assistant System), an SPAS (Smart Parking Assistant System), an AVM (Around View Monitoring), a camera, and a radar.

10. The on-vehicle situation detection method of claim 6, wherein the performing driving pattern learning comprises:

performing driving pattern comparison of comparing the pre-stored driving pattern of the driver called by the performing driving pattern calling with a current driving pattern by the data acquired from the performing detection;

performing driving pattern determination of determining whether a difference of both in the performing driving pattern comparison is within a preset noise range;

performing driving pattern storage of learning a current driving pattern when the difference of both is equal to or less than the preset noise range in the performing driving pattern determination to store the learned driving pattern in the memory unit; and

performing noise removal of excluding a current driving pattern from a subject to be learned when the difference of both exceeds the preset noise range in the performing driving pattern determination.

11. The on-vehicle situation detection method of claim 6, wherein the performing weighted value determination assigns a weighted value determined according to affecting a driver'"'"'s integrated risk index to the data acquired by the performing detection.

12. The on-vehicle situation detection method of claim 11, wherein the performing weighted value determination compares the acquired information data and the calculated integrated risk index with an information data reference value and an integrated risk index reference value to change a weighting, by feedback of a result from the performing warning.

13. The on-vehicle situation detection method of claim 12, wherein the performing weighted value determination changes a weighted value according to the following equation:

α

(n+1)=α

(n), if W<

d_W and R≧

d_R

α

(n+1)=α

(n)+δ

, if W≧

d_W

α

(n+1)=α

(n)−

δ

, if W<

d_W and R<

d_R,

where R=integrated risk index,

α

=weighting,

α

(n+1)=weighted value changed by feedback,

α

(n)=weighted value before change,

W=acquired information data,

d_R=integrated risk index reference value,

d_W=information data reference value, and

δ

=α

(n)/R.

14. The on-vehicle situation detection method of claim 6, wherein the performing determination comprises performing calculation learning of arranging a great deal of data, to which the weighted value determined in the performing weighted value determination is assigned, in the order of data causing an integrated risk index to exceed a preset reference risk index and of selecting only a plurality of high data.

15. The on-vehicle situation detection method of claim 14, wherein the performing determination comprises performing calculation of calculating a driver'"'"'s integrated risk index by adding up respective risk indexes which multiply the data selected in the performing calculation learning among the data, to which the weighted value determined in the performing weighted value determination is assign, by a weighted value for each data assigned in the performing weighted value determination.

16. The on-vehicle situation detection method of claim 15, wherein the performing determination comprises performing examination of comparing the integrated risk index calculated by the performing calculation with an examination risk index calculated based on the pre-stored driving pattern to determine whether a difference of both indexes is within a preset error range.

17. The on-vehicle situation detection method of claim 16, wherein the performing determination comprises performing control of comparing the integrated risk index with a preset reference risk index when the difference between the integrated risk index and the examination risk index is determined to be within the preset error range in the performing examination, to determine whether or not to inform of warning.

18. The on-vehicle situation detection method of claim 6, wherein the performing warning comprises:

performing first warning of executing one or more of warning sound generation through a speaker, warning display through an AVN or a HUD, and vibration notification through vibration of a steering wheel or a seat when an integrated risk index is equal to or greater than a preset first reference risk index and is less than a preset second reference risk index;

performing second warning of holding functions of the AVN when the integrated risk index is equal to or greater than a preset second reference risk index and is less than a preset third reference risk index;

performing third warning of forcibly stopping a vehicle when the integrated risk index is equal to or greater than a preset third reference risk index; and

performing information transfer of transferring information to the performing weighted value determining for change of the weighted value through feedback.