APPARATUS AND METHOD FOR DETERMINING CARELESS DRIVING

• US 20150081605A1
• Filed: 12/06/2013
• Published: 03/19/2015
• Est. Priority Date: 09/13/2013
• Status: Active Grant

• Current Assignee: Hyundai Motor Company (Hyundai Motor Group)
• Original Assignee: Hyundai Motor Company (Hyundai Motor Group)
• Inventors: Im, Seong Su, Kim, Jin Hak, You, Byung Yong, Yang, Seok Youl, Lee, Cheol Ha
• Granted Patent: US 9,415,778 B2
• Time in Patent Office: Days
• US Class Current: 706/15
• CPC Class Codes: B60W 2050/0005 Processor details or data handling, e.g. memory registers or chip architecture
• CPC Class Codes: B60W 2050/0045 using databus protocols
• CPC Class Codes: B60W 2510/205 Steering speed
• CPC Class Codes: B60W 2540/18 Steering angle
• CPC Class Codes: B60W 40/09 Driving style or behaviour
• CPC Class Codes: G06N 3/08 Learning methods

Abstract

An apparatus and a method for determining careless driving are provided and determine more reliable careless driving by generating normal driving patterns using driving performance data for a reference time at the beginning of driving. In addition, careless driving patterns greater than a predetermined number are detected using the normal driving pattern and a boundary between the normal driving and the careless driving is determined using a supervised learning method. The careless driving of the driver is then determined based on the determined boundary.

Claims

1. An apparatus for determining careless driving, comprising:

a memory configured to store program instructions; and

a processor configured to execute the program instructions, the program instructions when executed configured to;

collect driving performance data;

generate driving patterns using the collected driving performance data;

store normal driving patterns and careless driving patterns;

detect the careless driving patterns from the driving patterns, based on the normal driving patterns and store the detected careless driving patterns;

decide boundary values between the normal driving patterns and the careless driving patterns using an artificial neural network (ANN) technique;

determine whether the driving patterns within a threshold time unit are the careless driving patterns, based on the decided boundary values; and

store the driving patterns generated within a reference time at a beginning of driving as the normal driving patterns.

2. The apparatus for determining careless driving according to claim 1, wherein the driving performance data are a steering angle and a steering speed.

3. The apparatus for determining careless driving according to claim 1, wherein a Mahalanobis distance is used to detect driving patterns that exceed a first threshold value as the careless driving patterns.

4. The apparatus for determining careless driving according to claim 1, wherein the program instructions when executed are further configured to determine an average of ANN result values as the boundary values between the normal driving patterns and the careless driving patterns.

5. The apparatus for determining careless driving according to claim 4, wherein the program instructions when executed are further configured to determine a driving as the careless driving when a ratio of the ANN result values exceeding the boundary values exceeds a second threshold value.

6. The apparatus for determining careless driving according to claim 5, wherein the program instructions when executed are further configured to:

calculate the ANN result values by applying the ANN technique to the driving patterns; and

determine the driving as the careless driving when the ratio of the ANN result values exceeding the boundary values exceeds the second threshold value.

7. The apparatus for determining careless driving according to claim 1, wherein the program instructions when executed are further configured to collect the driving performance data via a vehicle network selected from a group consisting of:

a controller area network (CAN), a local interconnect network (LIN), FlexRay, and media oriented system transport (MOST).

8. A method for determining careless driving, comprising:

collecting, by a controller, driving performance data;

storing, by the controller, driving patterns generated within a reference time at a beginning of driving as normal driving patterns;

detecting, by the controller, careless driving patterns from the driving patterns, based on the normal driving patterns;

determining, by the controller, boundary values between the normal driving patterns and the careless driving patterns using an artificial neural network (ANN) technique; and

determining, by the controller, whether driving patterns within a threshold time unit are the careless driving patterns, based on the boundary values.

9. The method for determining careless driving according to claim 8, wherein the driving performance data are a steering angle and a steering speed.

10. The method for determining careless driving according to claim 8, wherein in detecting the careless driving patterns, a Mahalanobis distance is used to detect driving patterns that exceed a first threshold value as the careless driving patterns.

11. The method for determining careless driving according to claim 8, wherein in determining the boundary, an average of ANN result values is decided as the boundary values between the normal driving patterns and the careless driving patterns.

12. The method for determining careless driving according to claim 11, wherein in determining the careless driving, a driving is determined as the careless driving when a ratio of the ANN result values exceeding the boundary values exceeds a second threshold value.

13. A non-transitory computer readable medium containing program instructions executed by a controller, the computer readable medium comprising:

program instructions that collect driving performance data;

program instructions that store driving patterns generated within a reference time at a beginning of driving as normal driving patterns;

program instructions that detect careless driving patterns from the driving patterns, based on the normal driving patterns;

program instructions that determine boundary values between the normal driving patterns and the careless driving patterns using an artificial neural network (ANN) technique; and

program instructions that determine whether driving patterns within a threshold time unit are the careless driving patterns, based on the boundary values.

14. The non-transitory computer readable medium of claim 13, wherein the driving performance data are a steering angle and a steering speed.

15. The non-transitory computer readable medium of claim 13, wherein a Mahalanobis distance is used to detect driving patterns that exceed a first threshold value as the careless driving patterns.

16. The non-transitory computer readable medium of claim 13, further comprising:

program instructions that decide an average of ANN result values as the boundary values between the normal driving patterns and the careless driving patterns.

17. The non-transitory computer readable medium of claim 16, further comprising:

program instructions that determine a driving as the careless driving when a ratio of the ANN result values exceeding the boundary values exceeds a second threshold value.