Systems and methods for automated vehicle driving that mimic safe driver behaviors

Patent metadata

Field	Value
Publication number	US-10850741-B2
Application number	US-201715709583-A
Country	US
Kind code	B2
Filing date	Sep 20, 2017
Priority date	Sep 20, 2017
Publication date	Dec 1, 2020
Grant date	Dec 1, 2020

Abstract

A system includes a pattern recognizing module that identifies a pattern based on at least one of: (i) a movement of a driver of a vehicle, (ii) an object in front of the vehicle, (iii) a status of the vehicle, and (iv) an action of the vehicle. The pattern corresponds to a pattern response. A safety module compares the pattern response to a safe maneuver database. The pattern response is classified as safe in response to the pattern response matching at least one safe pattern response of the safe maneuver database. A pattern integration module integrates the pattern and the pattern response into a pattern database in response to the pattern response matching the at least one safe pattern response of the safe maneuver database. A vehicle control module performs the pattern response in response to the pattern recognizing module identifying the pattern.

First claim

What is claimed is:

1. A system comprising:
at least one processor and
a non-transitory memory coupled to the at least one processor,
wherein the non-transitory memory stores:
a safe maneuver database,
a pattern database, and
instructions that, when executed by the at least one processor, cause the at least one processor to:

identify a pattern and a pattern response based on at least one of: (i) a movement of a driver of a vehicle, (ii) an object in front of the vehicle, (iii) a status of the vehicle, and (iv) an action of the vehicle, wherein the pattern response occurs in response to the pattern;
compare the pattern response to the safe maneuver database, wherein the pattern response is classified as safe in response to the pattern response matching at least one safe pattern response of the safe maneuver database;
integrate the pattern and the pattern response into the pattern database in response to the pattern response matching the at least one safe pattern response of the safe maneuver database; and
in response to recognizing a first pattern:
identify a first set of pattern responses stored in the pattern database, wherein the first set of pattern responses can safely be performed in response to recognizing the first pattern;
compare each response of the first set of pattern responses to a previously programmed response;
perform a first pattern response from the first set of pattern responses when a first safety score of the first pattern response is equal to or greater than a preset safety score of the previously programmed response; and
perform the previously programmed response when the preset safety score of the previously programmed response is greater than the first safety score of the first pattern response.

2. The system of claim 1 wherein the instructions further cause the at least one processor to:
recognize a behavior of the driver of the vehicle;
monitor the movement of the driver of the vehicle;
identify the object in front of the vehicle; and
determine at least one of (i) the status of the vehicle and (ii) the action of the vehicle.

3. The system of claim 2 wherein the instructions further cause the at least one processor to:
identify the pattern and the pattern response based on the behavior of the driver of the vehicle, and
integrate the pattern and the pattern response into the pattern database after receiving a predetermined amount of data recognizing the behavior of the driver of the vehicle.

4. The system of claim 2 wherein the instructions further cause the at least one processor to identify the pattern after receiving data recognizing the behavior of the driver of the vehicle for a predetermined period.

5. The system of claim 2 wherein the instructions further cause the at least one processor to monitor the movement of the driver of the vehicle by imaging at least one of: (i) an eye of the driver, (ii) a head of the driver, (iii) a neck of the driver, and (iv) an arm of the driver.

6. The system of claim 2 wherein data is received from at least one of (i) a radar sensor, (ii) a sonar sensor, (iii) a LIDAR sensor, and (iv) a camera.

7. The system of claim 2 wherein the instructions further cause the at least one processor to identify a lane marking of a road in front of the vehicle.

8. The system of claim 2 wherein the instructions further cause the at least one processor to determine an actuation of at least one of (i) a right turn signal, (ii) a left turn signal, (iii) a brake of the vehicle, and (iv) a steering wheel of the vehicle.

9. The system of claim 1 wherein the safe maneuver database includes a plurality of predetermined safe pattern responses that the vehicle can perform.

10. The system of claim 1 wherein the first pattern response of is at least one of (i) changing a lane of the vehicle, (ii) changing a position of the vehicle in a current lane of the vehicle, (iii) actuating a brake of the vehicle, and (iv) actuating an accelerator of the vehicle.

11. A method comprising:
identifying a pattern and a pattern response based on at least one of: (i) a movement of a driver of a vehicle, (ii) an object in front of the vehicle, (iii) a status of the vehicle, and (iv) an action of the vehicle, wherein the pattern response occurs in response to the pattern;
comparing the pattern response to a safe maneuver database, wherein the pattern response is classified as safe in response to the pattern response matching at least one safe pattern response of the safe maneuver database;
integrating the pattern and the pattern response into a pattern database in response to the pattern response matching the at least one safe pattern response of the safe maneuver database; and
in response to recognizing a first pattern:
identifying a first set of pattern responses stored in the pattern database, wherein the first set of pattern responses can safely be performed in response to recognizing the first pattern;
comparing each response of the first set of pattern responses to a previously programmed response;
performing a first pattern response from the first set of pattern responses when a first safety score of the first pattern response is equal to or greater than a preset safety score of the previously programmed response; and
performing the previously programmed response when the preset safety score of the previously programmed response is greater than the first safety score of the first pattern response.

12. The method of claim 11 further comprising:
recognizing a behavior of the driver of the vehicle;
monitoring the movement of the driver of the vehicle;
identifying the object in front of the vehicle; and
determining at least one of (i) the status of the vehicle and (ii) the action of the vehicle.

13. The method of claim 12 further comprising:
identifying the pattern and the pattern response based on the behavior of the driver of the vehicle; and
integrating the pattern and the pattern response into the pattern database after receiving a predetermined amount of data recognizing the behavior of the driver of the vehicle.

14. The method of claim 12 further comprising:
identifying the pattern after receiving data recognizing the behavior of the driver of the vehicle for a predetermined period.

15. The method of claim 12 further comprising monitoring the movement of the driver of the vehicle by imaging at least one of: (i) an eye of the driver, (ii) a head of the driver, (iii) a neck of the driver, and (iv) an arm of the driver.

16. The method of claim 12 wherein data is received from at least one of (i) a radar sensor, (ii) a sonar sensor, (iii) a LIDAR sensor, and (iv) a camera.

17. The method of claim 12 further comprising identifying a lane marking of a road in front of the vehicle.

18. The method of claim 12 further comprising determining an actuation of at least one of (i) a right turn signal, (ii) a left turn signal, (iii) a brake of the vehicle, and (iv) a steering wheel of the vehicle.

19. The method of claim 11 wherein the safe maneuver database includes a plurality of predetermined safe pattern responses that the vehicle can perform.

20. The method of claim 11 wherein the first pattern response is at least one of (i) changing a lane of the vehicle, (ii) changing a position of the vehicle in a current lane of the vehicle, (iii) actuating a brake of the vehicle, and (iv) actuating an accelerator of the vehicle.

Assignees

• Denso Int America Inc
• Denso Corp

Inventors

• Alasry Bilal
• Vang Doua

Classifications

• B60W40/09 Primary

  Driving style or behaviour · CPC title

• B60W2556/10

  Historical data · CPC title

• B60W2050/0075

  Automatic parameter input, automatic initialising or calibrating means · CPC title

• B60W2552/53

  Road markings, e.g. lane marker or crosswalk · CPC title

• B60W10/20

  including control of steering systems · CPC title