Real time risk assessment for advanced driver assist system

• US 9,050,980 B2
• Filed: 02/25/2013
• Issued: 06/09/2015
• Est. Priority Date: 02/25/2013
• Status: Active Grant

• Current Assignee: Honda Motor Co., Ltd. (Honda Motor Company)
• Original Assignee: Honda Motor Co., Ltd. (Honda Motor Company)
• Inventors: Dariush, Behzad, Thompson, David A.
• Primary Examiner(s): Olszewski, John R
• Assistant Examiner(s): Wiltey, Nicholas K
• Application Number:
  US13/775,515
• Publication Number:
  US 20140244105A1
• Time in Patent Office: 834 Days
• US Class Current: 1/1
• CPC Class Codes: B60W 2050/0075 Automatic parameter input, automatic initialising or calibrating means
• CPC Class Codes: B60W 2554/00 Input parameters relating to objects
• CPC Class Codes: B60W 2555/20 Ambient conditions, e.g. wind or rain
• CPC Class Codes: B60W 30/0956 the prediction being responsive to traffic or environmental parameters
• CPC Class Codes: B60W 40/04 Traffic conditions
• CPC Class Codes: B60W 50/0098 Details of control systems ensuring comfort, safety or stability not otherwise provided for
• CPC Class Codes: G01S 13/931 of land vehicles

Abstract

A driver assistance system is described that takes as input a number of different types of vehicle environment inputs to provide driver assistance to a driver. To provide the assistance, the driver assistance system synthesizes the inputs. For objects in the vehicle environment detected in the inputs, object risk values are determined by applying a set of rules to the objects. The object risk values are aggregated by quadrant to generate a set of quadrant risk values. A driver assistance system of the vehicle is controlled based on the quadrant risks.

Claims

1. A method comprising:

receiving a plurality of vehicle environment inputs, the inputs comprising a position in two dimensions for each of a plurality of objects located around a vehicle, each object located in one of four quadrants surrounding the vehicle;

determining an object risk value for each of the objects by applying a set of rules to each of the objects, at least a plurality of the object risk values being non-zero, indicating the objects pose a risk to the vehicle;

aggregating the object risk values in a front quadrant to generate a front quadrant risk value;

aggregating the object risk values in a back quadrant to generate a back quadrant risk value;

aggregating the object risk values in a left quadrant to generate a left quadrant risk value;

aggregating the object risk values in a right quadrant to generate a right quadrant risk value,

wherein at least one of the front, back, left, and right quadrant risk values is determined by aggregating at least two of the non-zero object risk values; and

controlling a driver assistance system of the vehicle based on the quadrant risks.

2. The method of claim 1 wherein determining an object risk value for one of the objects comprises:

determining a plurality of memberships by the vehicle environment inputs in a plurality of input membership functions;

combining the memberships into a plurality of permutations of the input membership functions;

mapping the permutations to a plurality of risk membership functions;

aggregating the risk membership functions;

determining the object risk value based on the aggregation.

3. The method of claim 1 wherein the object risk values are all on a same bounded scale, wherein similar risk values correlate to similar perceived risks to the vehicle.

4. The method of claim 1 wherein the set of rules comprises a knowledge base predetermined based on behavior of an expert human driver.

5. The method of claim 1 wherein the vehicle environment inputs additionally comprise a driver attentiveness input, and further comprising:

adjusting each of the quadrant risks value based on the driver attentiveness input.

6. The method of claim 5 wherein adjusting each of the quadrant risk values comprises scaling each of the quadrant risks value upwards or downwards based on the applicability of the driver attentiveness input to the quadrant in which the relevant object is located.

7. The method of claim 5 wherein the driver attentiveness inputs is based on at least one from the group consisting of a driver head pose, a driver eye gaze direction, and a driver'"'"'s hand position.

8. The method of claim 1 wherein the vehicle environment inputs additionally comprise a plurality of global environment inputs, and further comprising:

adjusting the quadrant risk values based on the global environmental inputs.

9. The method of claim 8 wherein adjusting the quadrant risk values comprises scaling the quadrant risk values upwards or downwards together based on the global environmental inputs.

10. The method of claim 8 wherein the global environment inputs are include at least two from group the group consisting of a local weather condition, a local traffic condition, a time of day, a daylight indicator.

11. The method of claim 1 wherein controlling the driver assistance system comprises activating a lane change warning responsive at least one of the left and right quadrant risks exceeding a threshold.

12. The method of claim 1 wherein controlling the driver assistance system comprises activating a blind spot warning responsive to at least one of the left and right quadrant risks exceeding a threshold.

13. The method of claim 1 wherein controlling the driver assistance system comprises activating a collision warning responsive to at least one of the front and back quadrant risks exceeding a threshold.

14. The method of claim 1 wherein controlling the driver assistance system comprises automatically braking the vehicle responsive to the front quadrant risk exceeding a threshold.

15. A system comprising:

a knowledge base comprising a non-transitory computer readable storage medium, the knowledge base storing a set of rules;

an electronic control unit (ECU) comprising a processor and configured to;

receive a plurality of vehicle environment inputs, the inputs comprising a position in two dimensions for each of a plurality of objects located around a vehicle, each object located in one of four quadrants surrounding the vehicle;

determine an object risk value for each of the objects by applying the set of rules to each of the objects, at least a plurality of the object risk values being non-zero, indicating the objects pose a risk to the vehicle;

aggregate the object risk values in a front quadrant to generate a front quadrant risk value;

aggregate the object risk values in a back quadrant to generate a back quadrant risk value;

aggregate the object risk values in a left quadrant to generate a left quadrant risk value;

aggregate the object risk values in a right quadrant to generate a right quadrant risk value

wherein at least one of the front, back, left, and right quadrant risk values is determined by aggregating at least two of the non-zero object risk values; and

control a driver assistance system of the vehicle based on the quadrant risks.

16. The system of claim 15 wherein determining an object risk value for one of the objects comprises:

determining a plurality of memberships by the vehicle environment inputs in a plurality of input membership functions;

combining the memberships into a plurality of permutations of the input membership functions;

mapping the permutations to a plurality of risk membership functions;

aggregating the risk membership functions;

determining the object risk value based on the aggregation.

17. The system of claim 15 wherein the object risk values are all on a same bounded scale, wherein similar risk values correlate to similar perceived risks to the vehicle.

18. The system of claim 15 wherein the vehicle environment inputs additionally comprise a driver attentiveness input, and further comprising:

adjusting each of the quadrant risk values based on the driver attentiveness input.

19. The system of claim 15 wherein the vehicle environment inputs additionally comprise a plurality of global environment inputs, and further comprising:

adjusting the quadrant risk values based on the global environmental inputs.