Driver assistance system having a plurality of assistance functions

• US 8,483,906 B2
• Filed: 02/15/2006
• Issued: 07/09/2013
• Est. Priority Date: 03/01/2005
• Status: Active Grant

• Current Assignee: Robert Bosch GmbH
• Original Assignee: Robert Bosch GmbH
• Inventors: Lucas, Bernhard, Wilhelm, Ulf, Randler, Martin
• Primary Examiner(s): Tarcza, Thomas
• Assistant Examiner(s): TISSOT, ADAM D
• Application Number:
  US11/883,969
• Publication Number:
  US 20080188996A1
• Time in Patent Office: 2,701 Days
• Field of Search: 701/29.1, 701/30, 701/32.3, 701/34.1, 701/34.4, 701/36, 701/45, 340/438, 340/439, 180/421, 180/410
• US Class Current: 701/36
• CPC Class Codes: B60T 2201/02 Active or adaptive cruise control system; Distance control
• CPC Class Codes: B60T 2201/12 Pre-actuation of braking systems without significant braking effect; Optimizing brake performance by reduction of play between brake pads and brake disc
• CPC Class Codes: B60T 8/174 characterised by using special control logic, e.g. fuzzy logic , neural computing
• CPC Class Codes: B60W 30/16 Control of distance between vehicles, e.g. keeping a distance to preceding vehicle
• CPC Class Codes: B60W 40/02 related to ambient conditions
• CPC Class Codes: B60W 50/0097 Predicting future conditions

Abstract

A driver assistance system for motor vehicles has a sensor device for measuring data about the environment of the vehicle, at least two assistance functions, and a data processing device, which analyzes the measured data and generates at least one specific environmental hypothesis for each assistance function, which provides output data in a form prepared for the corresponding assistance function, at least one environmental hypothesis which has a structure divided into a plurality of partial hypotheses being predefined in the data processing device, and the partial hypotheses having such a logical relationship with one another that output data of one partial hypothesis flow into the generation of the other partial hypothesis, and at least two assistance functions directly or indirectly use a shared partial hypothesis.

Claims

1. A driver assistance system for a motor vehicle, comprising:

a sensor device for measuring data about an environment of the vehicle;

at least two assistance functions dependent on the measured data; and

a data processing device, which analyzes the measured data and generates at least one specific environmental hypothesis for each assistance function, which provides output data in a form prepared for the corresponding assistance function,

wherein at least one environmental hypothesis which has a structure divided into a plurality of partial hypotheses is predefined in the data processing device, the partial hypotheses having a logical relationship with one another such that output data of one partial hypothesis flow into the generation of another partial hypothesis, and at least two assistance functions directly or indirectly use a shared partial hypothesis,

wherein the at least one environmental hypothesis determines how the measured data is interpreted,

wherein each of the partial hypotheses represents a term described by an aspect of the environment,

wherein the logical relationship between partial hypotheses includes at least one of a subset relation and an implicit relation, and

wherein a warning about leaving a lane is provided as an additional assistance function, wherein an additional sensor provides data which is analyzed according to a second environmental hypothesis, which has an interconnected structure having a plurality of partial hypotheses, wherein the plurality of partial hypotheses is as follows;

(a) the sensor has detected at least one object, and for a plurality of objects, a corresponding plurality of copies of the first partial hypothesis is generated;

(b) the object is a spatial object extending in the vertical direction;

(c) the object is a flat object that defines a left boundary and a right boundary of the lane;

(d) the spatial object which was detected in (b) is within the lane; and

(e) the vehicle is about to cross a lane boundary;

wherein for the second environmental hypothesis, efficient data processing is achieved by partial hypotheses (b) and (c) jointly using the results of partial hypothesis (a), and wherein for partial hypothesis (d), the results of partial hypotheses (b) and (c) are combined.

2. The driver assistance system of claim 1, wherein the hypothesis is “

vehicle ahead.”

3. The driver assistance system of claim 2, wherein the potential hypotheses are “

potential obstacle,” and

“

obstacle.”

4. A method of a driver assistance system for a motor vehicle, comprising:

measuring, at a sensor device, data about an environment of the vehicle based on which at least two assistance functions dependent;

analyzing, at a data processing device, the measured data and generating at least one specific environmental hypothesis for each assistance function, which provides output data in a form prepared for the corresponding assistance function,

wherein at least one environmental hypothesis which has a structure divided into a plurality of partial hypotheses is predefined in the data processing device, the partial hypotheses having a logical relationship with one another such that output data of one partial hypothesis flow into the generation of another partial hypothesis, and at least two assistance functions directly or indirectly use a shared partial hypothesis,

wherein the at least one hypothesis determines how the measured data is interpreted,

wherein each of the partial hypotheses represents a term described by an aspect of the environment,

wherein the logical relationship between partial hypotheses includes at least one of a subset relation and an implicit relation, and

wherein a warning about leaving a lane is provided as an additional assistance function, wherein an additional sensor provides data which is analyzed according to a second environmental hypothesis, which has an interconnected structure having a plurality of partial hypotheses, wherein the plurality of partial hypotheses is as follows;

(a) the sensor has detected at least one object, and for a plurality of objects, a corresponding plurality of copies of the first partial hypothesis is generated;

(b) the object is a spatial object extending in the vertical direction;

(c) the object is a flat object that defines a left boundary and a right boundary of the lane;

(d) the spatial object which was detected in (b) is within the lane; and

(e) the vehicle is about to cross a lane boundary;

wherein for the second environmental hypothesis, efficient data processing is achieved by partial hypotheses (b) and (c) jointly using the results of partial hypothesis (a), and wherein for partial hypothesis (d), the results of partial hypotheses (b) and (c) are combined.

5. The method of claim 4, wherein the hypothesis is “

vehicle ahead.”

6. The method of claim 5, wherein the potential hypotheses are “

potential obstacle,” and

“

obstacle.”

7. The method of claim 5, wherein when generating the environmental hypothesis, it is decided on the basis of the data obtained whether this is an actual obstacle.

8. The method of claim 4, wherein when generating the environmental hypothesis, it is decided on the basis of the data obtained whether this is an actual obstacle, and wherein a decision criterion is whether there is a certain minimum difference between the signal amplitude received by the radar sensor for this object and the noise level.

9. The method of claim 4, wherein a decision criterion is whether there is a certain minimum difference between the signal amplitude received by the radar sensor for this object and the noise level, and wherein signal amplitudes are transmitted by the sensor to a first partial hypothesis and conveyed from there to a second partial hypothesis.

10. The method of claim 4, wherein a decision criterion is that the position of an actual obstacle must be determined in a stable manner over a certain period of time, and it must have a physically possible movement pattern.

11. The method of claim 4, wherein a decision criterion is that the position of an actual obstacle must be determined in a stable manner over a certain period of time, and it must have a physically possible movement pattern, and wherein in the case of a second partial hypothesis, the results of previous measuring cycles must be used, and the object located in the current measuring cycle must be found to be identical to an object located in one of the previous cycles.

12. The method of claim 4, wherein a partial hypothesis data structure is predefined in a data processing device and includes a fixedly stored static part having at least two blocks and a dynamic part for storing variables, and wherein input data are supplied to the at least two blocks of the static part.

13. The method of claim 4, wherein a partial hypothesis data structure is predefined in a data processing device and includes a fixedly stored static part having at least two blocks and a dynamic part for storing variables, and wherein input data are supplied to the at least two blocks of the static part, and wherein the input data are either data of the sensor or output data of a partial hypothesis having precedence in a logical structure.

14. The method of claim 4, wherein a warning about leaving a lane is provided as an additional assistance function, wherein an additional sensor provides data which is analyzed according to an environmental hypothesis, which has an interconnected structure having a plurality of partial hypotheses.

15. The method of claim 4, wherein the results of partial hypothesis (d) contribute to the decision of whether the object is an actual obstacle, so as to reliably differentiate between actual obstacles and apparent obstacles.

16. A driver assistance system for a motor vehicle, comprising:

a sensor device for measuring data about an environment of the vehicle;

at least two assistance functions dependent on the measured data; and

a data processing device, which analyzes the measured data and generates at least one specific environmental hypothesis for each assistance function, which provides output data in a form prepared for the corresponding assistance function,

wherein at least one environmental hypothesis which has a structure divided into a plurality of partial hypotheses is predefined in the data processing device, the partial hypotheses having a logical relationship with one another such that output data of one partial hypothesis flow into the generation of another partial hypothesis, and at least two assistance functions directly or indirectly use a shared partial hypothesis,

wherein the at least one environmental hypothesis determines how the measured data is interpreted,

wherein each of the partial hypotheses represents a term described by an aspect of the environment,

wherein the logical relationship between partial hypotheses includes at least one of a subset relation and an implicit relation,

wherein a warning about leaving a lane is provided as an additional assistance function, and wherein an additional sensor provides data which is analyzed according to a second environmental hypothesis, which has an interconnected structure having a plurality of partial hypotheses, and

wherein the plurality of partial hypotheses is as follows;

(a) the sensor has detected at least one object, and for a plurality of objects, a corresponding plurality of copies of the first partial hypothesis is generated;

(b) the object is a spatial object extending in the vertical direction;

(c) the object is a flat object that defines a left boundary and a right boundary of the lane;

(d) the spatial object which was detected in (b) is within the lane; and

(e) the vehicle is about to cross a lane boundary.

17. The driver assistance system of claim 16, wherein for the second environmental hypothesis, efficient data processing is achieved by partial hypotheses (b) and (c) jointly using the results of partial hypothesis (a).

18. The driver assistance system of claim 16, wherein for partial hypothesis (d), the results of partial hypotheses (b) and (c) are combined.