Method and system for determining the driving situation

• US 7,386,389 B2
• Filed: 05/22/2006
• Issued: 06/10/2008
• Est. Priority Date: 11/20/2003
• Status: Active Grant

• Current Assignee: Bayerische Motoren Werke AG
• Original Assignee: Bayerische Motoren Werke AG
• Inventors: Salzmann, Christian, Stolle, Uwe
• Primary Examiner(s): WOLFE JR, WILLIS RAY
• Application Number:
  US11/437,807
• Publication Number:
  US 20060271269A1
• Time in Patent Office: 750 Days
• Field of Search: 701101-106, 701/110, 701/111, 701/115, 706/2, 706/15, 706/16, 706/23, 706/25, 706/41, 706/44, 706/45, 706/48, 700 28- 32
• US Class Current: 701/106
• CPC Class Codes: G05B 13/027 using neural networks only
• CPC Class Codes: G08G 1/0104 Measuring and analyzing of parameters relative to traffic conditions

Abstract

A method and a system for ascertaining the driving situation of a motor vehicle by using data provided in the vehicle indicating the value of at least one state variable of the vehicle are provided. To relieve the burden on the driver a data record providing the history of the at least one state variable is supplied. In a neural network in the motor vehicle is supplied by a suitably programmed computer. The neural network has at least one input layer and one output layer, each of the layers having a plurality of perceptrons. The respective value of the at least one state variable of the respective point in time, preferably a normalized value, is supplied to a perceptron of the neural network. After the neural network has been trained, the current driving situation is output by the perceptrons of the output layer of the neural network.

Claims

1. A processor programmed to execute machine-readable code to perform the acts of:

receiving a data record of a history of the at least one state variable;

generating, by a programmed computer, a neural network in the motor vehicle, the neural network having at least one input layer and one output layer, each of the layers having a plurality of perceptrons;

supplying, to a perceptron of the neural network, a respective value of the at least one state variable of a respective point in time; and

outputting the current driving situation by the perceptrons of the output layer of the neural network after it has been trained, wherein a current driving state of the vehicle is set and/or defined from a chronological sequence of driving situations ascertained.

2. A method for ascertaining a driving situation of a motor vehicle by using data provided in the vehicle indicating the value of at least one state variable of the vehicle, the method comprising the acts of:

receiving a data record of a history of the at least one state variable;

generating, by a programmed computer, a neural network in the motor vehicle, the neural network having at least one input layer and one output layer, each of the layers having a plurality of perceptrons;

supplying, to a perceptron of the neural network, a respective value of the at least one state variable of a respective point in time; and

outputting the current driving situation by the perceptrons of the output layer of the neural network after it has been trained, wherein a current driving state of the vehicle is set and/or defined from a chronological sequence of driving situations ascertained.

3. The method of claim 2, wherein instead of an earlier driving state, a new driving state is ascertained only when the new driving state has been set and/or determined repeatedly within an interval of time that has elapsed.

4. The method of claim 2, wherein at least one device of the vehicle is adapted to the driving situation ascertained, the driving state ascertained, or the extent of the information forwarded to the driver of the motor vehicle is based on the driving state ascertained.

5. The method of claim 2, wherein the respective value of the at least one state variable of the respective point in time is a normalized value.

6. The method of claim 2, wherein the neural network is a sigmoid network.

7. The method of claim 6, wherein the neural network has three layers.

8. A method for ascertaining a driving situation of a motor vehicle by using data provided in the vehicle indicating the value of at least one state variable of the vehicle, the method comprising the acts of:

receiving a data record of a history of the at least one state variable;

generating, by a programmed computer, a neural network in the motor vehicle, the neural network having at least one input layer and one output layer, each of the layers having a plurality of perceptrons;

supplying, to a perceptron of the neural network, a respective value of the at least one state variable of a respective point in time; and

outputting the current driving situation by the perceptrons of the output layer of the neural network after it has been trained, wherein a current driving state is assigned to a chronological sequence of driving situations ascertained, this assignment being made on the basis of at least one allocation procedure.

9. The method of claim 8, wherein at least one device of the vehicle is adapted to the driving situation ascertained, the driving state ascertained, or the extent of the information forwarded to the driver of the motor vehicle is based on the driving state ascertained.

10. The method of claim 8, wherein the respective value of the at least one state variable of the respective point in time is a normalized value.

11. The method of claim 8, wherein the neural network is a sigmoid network.

12. The method of claim 11, wherein the neural network has three layers.

13. A method for ascertaining a driving situation of a motor vehicle by using data provided in the vehicle indicating the value of at least one state variable of the vehicle, the method comprising the acts of:

receiving a data record of a history of the at least one state variable;

generating, by a programmed computer, a neural network in the motor vehicle, the neural network having at least one input layer and one output layer, each of the layers having a plurality of perceptrons;

supplying, to a perceptron of the neural network, a respective value of the at least one state variable of a respective point in time; and

outputting the current driving situation by the perceptrons of the output layer of the neural network after it has been trained, wherein a different driving situation is assigned to each perceptron of the output layer or its output signal and the maximum output signal of all output signals of the perceptrons of the output layer indicates the current situation of the motor vehicle.

14. The method of claim 13, wherein the driving situation is considered indefinite if the difference between the value of the maximum output signal of all perceptrons of the output layer and the value of a next smaller output signal of the respective perceptron is less than 20% or the value of the greatest output signal of all perceptrons of the output layer is less than 10% of its maximum value.

15. The method of claim 13, wherein the output signals of the perceptrons are standardized.

16. The method of claim 13, wherein at least one device of the vehicle is adapted to the driving situation ascertained, the driving state ascertained, or the extent of the information forwarded to the driver of the motor vehicle is based on the driving state ascertained.

17. The method of claim 13, wherein the respective value of the at least one state variable of the respective point in time is a normalized value.

18. The method of claim 13, wherein the output signal of the first perceptron of the output layer of the neural network indicates a “

stop and go”

, of the second perceptron of the output layer of the neural network indicates a “

city driving”

driving situation, of the third perceptron of the output layer of the neural network indicates a “

cruising”

driving situation, or of the fourth perceptron of the output layer of the neural network indicates a “

sporty”

driving situation.

19. The method of claim 18, wherein the output signal is a signal maximum.

20. The method of claim 13, wherein the neural network is a sigmoid network.

21. The method of claim 20, wherein the neural network has three layers.