Situation awareness processor

• US 6,470,272 B2
• Filed: 06/11/2001
• Issued: 10/22/2002
• Est. Priority Date: 06/09/2000
• Status: Expired due to Fees

• Current Assignee: Automotive Systems Laboratory, Incorporated (Ningbo Junsheng Investment Group Co., Ltd.)
• Original Assignee: Automotive Systems Laboratory, Incorporated (Ningbo Junsheng Investment Group Co., Ltd.)
• Inventors: Behr, Leonard W., Ebling, James P., Cong, Shan
• Primary Examiner(s): NGUYEN, TAN QUANG
• Application Number:
  US09/878,644
• Publication Number:
  US 20020019697A1
• Time in Patent Office: 498 Days
• Field of Search: 701/301, 701/300, 701/96, 701/117, 701/118, 701/119, 340/903, 340/435, 340/436, 706/8, 706/905, 706/913
• US Class Current: 701/301
• CPC Class Codes: G01S 13/723 by using numerical data
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks
• CPC Class Codes: Y10S 706/905 Vehicle or aerospace

Abstract

A plurality of events representative of a situation in which the host vehicle is operated are selected, including at least one set of related events. Input data is provided to an inference engine from either a first set of data representative of a target in a field of view of the host vehicle, a second set of data representative of the position or motion of the host vehicle, or a third set of data is representative of an environment of said host vehicle. The inference engine operates in accordance with an inference method to generate an output representative of a probability of occurrence of at least one event of the set of events, responsive to the input data, and possibly to one or more outputs at a past time. A countermeasure may be invoked responsive to one or more outputs from one or more inference engines.

Claims

1. A method of identifying a situation in which a host vehicle is operated, comprising:

a. selecting a plurality of events, wherein each event of said plurality of events is representative of a situation in which the host vehicle is operated, and at least two of said events are different from one another;

b. selecting at least one set of said events that are related to a situation in which the host vehicle is operated;

c. providing for a set of data from at least one of a first set of data, a second set of data and a third set of data, wherein said first set of data is representative of a target in a field of view of the host vehicle, said second set of data is representative of the position or motion of the host vehicle, and said third set of data is representative of an environment of said host vehicle;

d. selecting an inference method for a first inference engine, wherein said inference engine comprises at least one input and an output;

e. selecting as a first input to said inference engine at least one element of said first set of data, said second set of data and said third set of data; and

f. generating a first output from said first inference engine responsive to said first input, wherein said first output is representative of a probability of occurrence of at least one event of said set of said events.

2. A method of identifying a situation in which a host vehicle is operated, as recited in claim 1, wherein a plurality of said events are related to a location of the host vehicle.

3. A method of identifying a situation in which a host vehicle is operated, as recited in claim 2, wherein each of said plurality of said events related to said location of the host vehicle is a situation selected from an operation of the host vehicle in a vicinity of a divided or undivided highway;

an operation of the host vehicle in a vicinity of an intersection, an operation of the host vehicle in a vicinity of a freeway, an operation of the host vehicle in a vicinity of an entrance or exit to a freeway entrance;

an operation of the host vehicle in a vicinity of a parking lot; and

an operation of the host vehicle in an off-highway environment.

4. A method of identifying a situation in which a host vehicle is operated, as recited in claim 1, wherein a plurality of said events are related to a traffic situation.

5. A method of identifying a situation in which a host vehicle is operated, as recited in claim 4, wherein each of said plurality of said events related to a traffic situation comprises operation of the host vehicle in an environment selected from crowded, loose or normal traffic;

a moving or stationary object to the left or right of the host vehicle; and

a moving or stationary object in a lane of the host vehicle.

6. A method of identifying a situation in which a host vehicle is operated, as recited in claim 1, wherein a plurality of said events are related to a relative position change of a target with respect to the host vehicle.

7. A method of identifying a situation in which a host vehicle is operated, as recited in claim 6, wherein each of said plurality of said events related to a relative position change of a target with respect to the host vehicle is selected from an object cutting in a lane of the host vehicle from the left or right of the host vehicle;

the host vehicle changing lanes to the left or right;

a change in speed of traffic to the left or right of the host vehicle;

a change in speed of traffic in the same lane as the host vehicle;

a change in speed of the host vehicle;

a change in direction of traffic to the left or right; and

a change in direction of the host vehicle to the left or right.

8. A method of identifying a situation in which a host vehicle is operated, as recited in claim 1, wherein at least two events of said set of events are mutually exclusive.

9. A method of identifying a situation in which a host vehicle is operated, as recited in claim 1, wherein said first set of data is selected from a count of targets in a field of view of the host vehicle, a target heading, a target speed, and a target location relative to the host vehicle, and at least a portion of said first set of data is generated by a tracker operatively coupled to a radar system.

10. A method of identifying a situation in which a host vehicle is operated, as recited in claim 1, wherein said second set of data is selected from a speed of the host vehicle, a yaw rate of the host vehicle, a heading of the host vehicle, and a location of the host vehicle.

11. A method of identifying a situation in which a host vehicle is operated, as recited in claim 10, further comprising providing for reading said location of the host vehicle from a navigation system.

12. A method of identifying a situation in which a host vehicle is operated, as recited in claim 1, wherein said third set of data is selected from a track map representative of a composite path of targets in an environment of the host vehicle, a curvature or type of a road upon which the host vehicle is operated, data representative of a fixed structure in the field of view of the host vehicle, and a digital map of a road surface, wherein said track map is generated by a track map generator from data is generated by a tracker operatively coupled to a radar system.

13. A method of identifying a situation in which a host vehicle is operated, as recited in claim 1, wherein said inference method is selected from a Dempster-Shafer evidential reasoning method, a fuzzy logic reasoning method, a Bayesian inference method, a neural network and a reasoning method based on random set theory.

14. A method of identifying a situation in which a host vehicle is operated, as recited in claim 1, further comprising:

a. selecting as a second input to said inference engine an output from an inference engine, wherein said output is at a past time relative to said first input; and

b. generating an output from said first inference engine responsive to said first and second inputs.

15. A method of identifying a situation in which a host vehicle is operated, as recited in claim 1, further comprising selecting a countermeasure responsive to at least one said output of at least one said inference engine.