WO2009013052A2

WO2009013052A2 - Method and device for sensing a lane with a driver assistance system

Info

Publication number: WO2009013052A2
Application number: PCT/EP2008/056774
Authority: WO
Inventors: Lutz Buerkle; Tobias Rentschler; Thomas App
Original assignee: Robert Bosch Gmbh
Priority date: 2007-07-23
Filing date: 2008-06-02
Publication date: 2009-01-29
Also published as: DE102007034196A1; WO2009013052A3

Abstract

The invention relates to a method for sensing a lane with a driver assistance system, comprising a sensor system for lane detection, of a vehicle (33), in which driver assistance system measuring points MP which represent lane markings are sensed with the sensor system for lane detection in a region of a traffic space (30) in front of the vehicle (33). An ideal number of measuring points MP is determined on the basis of a reference model. A measure of plausibility of the look-ahead distance is determined from a comparison between the number of measuring points which are actually sensed and the ideal number of measuring points.

Description

title

Method and device for track detection with a driver assistance system

State of the art

The invention relates to a method and apparatus for the track detection with a driver assistance system according to the preamble of claim 1. There are already

Driver assistance systems with assistance functions known as ACC (Adaptive Cruise Control) and Night Vision (Night Vision). For this purpose, detection sensors are used, in particular video sensors, radar sensors and lidar sensors, which are able to detect the distance and / or speed of objects in the surroundings of a vehicle and / or lane boundaries. Furthermore, assistance functions such as LDW (Lane Departure Warning) and LKS (Lane Keeping Support) are known in connection with a driver assistance system. The assistance function LDW warns the driver against unintentionally leaving the lane of his own vehicle. For this purpose, at least the traffic space in front of the own vehicle is detected by means of video sensors, in order in particular to detect lane markings and to detect the position of the own vehicle with respect to such lane markings. Depending on the position of the own vehicle with respect to the detected lane markings as well as its predicted direction of travel, an acoustic, visual, haptic warning or a combination of such warnings generated to warn the driver of the vehicle from accidental leaving the lane. In the assistance function LKS, the driver is assisted by steering intervention of the driver assistance system when guiding the vehicle in the lane.

From DE 103 49 631 A1, a driver assistance method and a driver assistance device are known which operate on the basis of lane information. Depending on the weather conditions, the lane information is measured from an image recorded by a video sensor and / or estimated on the basis of objects in this image. In this case, the traffic lane information from at least two, the lane characterizing

Derived information. From the image contrast, a quality measure for the track data acquisition is derived, with which the respectively determined track data are weighted and taken into account during the fusion of the driver assistance system provided track data from the individual track data. In this case, the formation of a Gesamtgütemaßes for the track data acquisition from the Einzelgütemaßen is provided, the driver assistance system is turned off when this Gesamtgütemaß falls below a certain value. The quality measure can also be derived from a comparison of an estimate with a measurement, in particular the deviation of the measurement points from the estimation line being used.

From DE 197 20 764 Al a method for detecting the preceding road course for motor vehicles is also known, in which detects the vehicle's own speed and by rigid, oriented in the direction of search antennas via a radar sensor, the position and speed of objects ahead be determined, which allows a simple predictive road course detection by special evaluation of the existing position and speed measurement data. From the fixed targets, the roadside-specific targets are filtered out by threshold comparison of the fixed-target amplitudes, and the actual distances between the vehicle and the roadway edge in discrete angular ranges are determined by order filtering. The lane edge distances estimated for each angular range are supplied as characteristics to a classifier for prediction of the forward curve type and used as fulcrums for a curve regression to obtain a curve curvature parameter.

From DE 197 49 086 Cl a device for determining lane course-indicative data is known, which detects a lane detection sensor system, an object position sensor system which detects at least the distance of an object located in front of the vehicle and its directional angle with respect to the vehicle movement direction

Vehicle own motion sensor includes. According to the invention, an estimation device is provided to which the lane detection measurement data, the object position measurement data and the vehicle intrinsic movement measurement data are supplied and which determines the lane curvature and / or the transverse position of a respective object in front of the vehicle relative to the lane by estimation by means of a predefinable, dynamic vehicle movement model-containing estimation algorithm , For this purpose, the device preferably includes a Kalman filter. The device is e.g. used in road vehicles.

From DE 103 54 650 Al a lane device and a method for determining first lane course data of a lane course for a first vehicle based on Lane data of the first vehicle ahead of the second vehicle known. A detection of lane data of a plurality of measurement positions of the second vehicle and a determination of second lane course data for describing a lane course of the second vehicle based on the lane data are proposed.

From DE 10 2006 040 334.7 a method for the track detection with a driver system comprising a sensor system for lane detection driver assistance system of a vehicle is further known.

In this case, lane markings are detected with the sensor system for lane detection in a lying in front of the vehicle area of a traffic area. The lane markings are assigned to nodes with at least coordinates of a first coordinate system. The coordinates of

Support points are converted into a second coordinate system. The course of lane markings and / or lanes is reconstructed from the position of the interpolation points in the second coordinate system.

Disclosure of the invention

Technical task

The invention is based on the object

Driver assistance system with an assistance function supporting the lateral guidance of the vehicle, such as in particular LKS (Lane Keeping Support), to further improve.

Technical solution

This object is achieved in that the detected by sensors of the driver assistance system information about the course of lane markings Plausibility measure is assigned. This plausibility measure enables the driver assistance system to assess whether the acquired information is suitable for a successful and safe lateral guidance of the vehicle, in particular with the assistance function LKS.

Advantageous effects

The core of the invention is a model-based method, which compresses the criteria relevant for assistance function for the assessment of information about the course of a lane, or their markers, to an integrated plausibility measure. Relevant criteria for this are, in particular, the distance in front of the vehicle, up to which information about the course of a traffic lane or its marking is available. This distance is also referred to as a look-ahead range in the present description of the invention. Another criterion is the quality of the track information. On the basis of the plausibility measure obtained according to the invention, the

Driver assistance system decide whether the detected lane markings are sufficiently clear for a successful work of the assistance function. It can also be decided whether individual functionalities can no longer be guaranteed, or whether the entire

Assistance function, at least temporarily, must be disabled.

Further advantages will become apparent from the description, the dependent claims and the drawings.

Brief description of the drawings

Embodiments of the invention are explained below with reference to the drawing. It shows Figure 1 is a plan view of a traffic area with a

Vehicle;

FIG. 2 shows a measuring point history with measuring points of a video sensor;

Figure 3 is a diagram showing the

Plausibility measure as a function of time.

Embodiments of the invention

Figure 1 shows a plan view of a traffic space 30 with a vehicle 33, which moves along a lane 31. The vehicle 33 comprises an evaluation device 1, in particular a microcomputer, a driver assistance system, whose multiple sensors 2.1, 2.2,

2.3 record measuring points MP along the lane 31 located in front of the vehicle 33 and derive therefrom the course of the lane 31 and the position of the vehicle 33 with respect to this lane 31. The evaluation device 1 receives the information from the sensors and evaluates them by determining the lane course. In the application DE 10 2006 040 334.7 it is proposed to convert measuring points detected by sensors over the course of lanes or their markings into a stationary coordinate system and to carry them over a certain period of time by storing them in a measuring point memory in a so-called measuring point history. In order to evaluate the look-ahead range based on the measurement points in the measurement point history, an idealized reference model of the measurement point history is now used according to the invention. With an assumed optimal _look- ahead range of the various sensors, this model maps the optimum number of measurement points n _ldea i (t _k ) that would have to be in the measurement point history at some point in time. The model practically describes the "level" of the measurement point history Level is compared with the actual prevailing level by quotient formation, the real number of measuring points is in the numerator of the quotient and the ideal number in the denominator of the quotient. If the ideal number is smaller than the real number, these are equated. Thus, the quotient gives the value one.

If, on the other hand, the real number of measuring points is smaller than the ideal number, a value of the quotient of less than one results. The ideal number of measurement points is determined according to this model idea as follows. One or more arbitrary enveloping sensors provide, in time-constant time steps .DELTA.t, a parametric lane description, for example in the form of a polynomial, which is calculated back into corresponding measuring points. Alternatively, it is also possible to directly detect measuring points which describe the course of the lane ahead of the driver's own vehicle. These measuring points are added to the measuring point history. In the same train, measuring points located behind the vehicle are deleted from the measuring point history. The number of measuring points to be deleted depends on the distance traveled in a time step and the number of measuring points already contained in the measuring point history. In the exemplary embodiment which will be explained in more detail below, the ideal number of measuring points is given by way of example for the use of a single video sensor. When using a plurality of sensors, sensor 1, sensor 2, sensor 3, sensor x, the values determined for each sensor would still have to be added as follows:

Sensor 3 rn _ic eal, sensor x

With reference to FIG. 2, this reference model will now be described on the basis of the measurements of a video sensor of the Driver assistance system shown. The diagram shown in FIG. 2 shows a measuring point history with measuring points MP of a video sensor of the

Driver assistance system, wherein each of the parallel to the y-axis lines represents a new measurement of the video sensor of the driver assistance system 1 of a vehicle 33 in a subsequent time step t _L. The x-axis of the diagram is the time axis (time t). On the y-axis of the diagram, a distance dx in front of the vehicle 33 is indicated. The crosses on the lines drawn parallel to the y-axis of the diagram represent measuring points MP detected by the video sensor of the vehicle 33. A first measurement takes place at the time t ₀ at the distance dx _S ta _r t. Further measurements are then carried out in subsequent times ti, t ₂ , t _ir t _k . Measurement interval to measurement interval, the vehicle covers the distance 33 Δdx _Fah rzeug back. The distance between measuring points MP is Δdx _M esspunkte • The maximum predicted distance or measuring distance dx _En d, max is.

At time t ₀ provides the recalculation of the detected from the video sensor lane markings in the measuring points MP, with a maximum predicted distance of the video sensor of dx _En d, max and esspunkte a distance of the measuring points of Δdx _M _Λ a number of measuring points MP of

; D

The number of measuring points MP in the measuring point history is thus:

(2) ⁿ ₁ deal (h) = ⁿ r ₁ deo ( ^t θ)

Due to the assumed maximum foresight distance and the constant distance of the measuring points MP remains also the number of newly added measuring points MP is constant in each measuring cycle. The number of measuring points in the measuring point history

(3) n _ideal (t _k )

Increases thus in each measurement cycle to

dx Εnd, especially & x

^ X ^' ' measuring points

Depending on the speed v (t _k ), which _is assumed to be constant between two measuring cycles dTVi _d eo, the vehicle lays the following route

(5) _vehicle Δdx (t _k) = v (t _k) _l dT _Vιdeo back,

With

(6) dT _rideo = t _k - t _k _ _γ .

Measuring points can be carried along in the measuring point history until they are in front of the vehicle in a defined distance X _d ei> 0, are being run over by the vehicle (X _d ei ⁼ 0) or spatially a defined distance x _de i <0 behind the vehicle.

Depending on the requirements of the assistance function of the driver assistance system, one of the variants with associated distance X _d ei can be selected. Subsequently, the measuring points are deleted from the measuring point history. The number of measuring points that are deleted from the measuring point history depends on how many measuring points from past measuring cycles lie on the track, which is the Vehicle has crossed over between the last and the current measurement cycle. Based on the reference model, it is possible to implicitly determine the number of measurement points on the route traveled by the vehicle, knowing the speeds which the vehicle has traveled in past measurement cycles. For this purpose, the current speed in each measuring cycle is stored in a vector v. The number of measuring points that must be in the measuring point history at a certain time t _k results from the inflow and outflow of measuring points. The inflow is given by the number of measuring points that were recorded during the period t ₀ t _k . The outflow is given by the measuring points which were crossed during the period or which correspond to the criteria of the route X _d ei. From inflow and outflow, the following ideal number of measurement points result:

with n _Vιdeo {t ^ = COHSt.

The core area of the present invention is that, based on the ideal number of measuring points n _ldea i determined on the basis of the reference model and taking into account the actually recorded number of measuring points n _rea i, a plausibility measure of the foresight distance PEntfemung is determined according to the following relationship:

'Q) _n _ ⁿ reaMk) κ' y distance nιdeal

In an advantageous embodiment of the invention, this plausibility measure can be normalized to a certain range of values, which is particularly useful for further processing. For example, the plausibility measure can be normalized to a value range [0 ... 1].

Taking into account the plausibility measure, an assistance function of the driver assistance system can advantageously decide when information about the course of the lane detected by the driver assistance system is to be regarded as plausible or implausible and consequently an activation or deactivation is to be undertaken. This will be explained below with reference to the diagram shown in FIG. 3, which shows a plausibility measure P as

Represents the function of time t. As a result of the standardization described, the plausibility measure can assume the value one at most. When a predetermined threshold value P _A ACTIVATION activation takes place. In the diagram shown in FIG. 3, this is the case at the point in time t _A. Deactivation takes place at a further threshold value _D deactivation. This is _Deact i _v i _ng the case at time t. A hysteresis is advantageous in this case introduced characterized in that the threshold value P _D eaktivierung is smaller than the threshold value P • _A ACTIVATION

Advantageously, furthermore, with known measurement inaccuracy of the sensors used in the driver assistance system, an error model can be stored for each sensor and from this a measurement uncertainty X measurement point can be obtained for each measurement point

Be calculated. Particularly advantageously, the measurement uncertainties of the measuring points are already determined by the sensors themselves and made available to the driver assistance system. The measurement uncertainties of all measuring points can be particularly advantageous for another To summarize the plausibility measure that describes the plausibility of the measurements per se. It is expedient to note here that the measurement uncertainties of the measurements of different sensors can have different accuracy classes from each other and therefore must not be mixed directly with each other. For measurements with sensors of different accuracy classes for each measuring point, it is therefore advantageously determined from the measurement uncertainty of the measuring point and from the maximum measurement uncertainty of the respective sensor that a standardized weighting factor w _{M inkt} G [0 l] is determined.

Subsequently, the weights of all measuring points can then be compressed into a further plausibility measure PMess points, for example based on a simple averaging:

(-LU) PMess points ~ ^W measurement points

From both plausibility measures, a total plausibility measure can be determined and made available to an assistance function of the driver assistance system, for example the LKS assistance function. In this case, a weighting factor is additionally introduced for each plausibility measure. This weighting factor will, depending on the requirements of each

Assistance function, adapted to the lane information.

(1 1) P total ~ "'^ KY ¹ ' pRemove ^' P distance ^' ^ PMesspoints ^' PMesspoints)"

In an advantageous further embodiment of the invention, the Gesamtplausibilitätsmaß can consist of only one of the partial plausibilities.

Furthermore, additional plausibilities can be included, if they are for an assistance function of the driver assistance system are relevant. As such plausibilities come in particular the measurement uncertainty of a measurement point or a plausibility into consideration, which results from a comparison of measurement points based on their distances to a reference, such as the calculated from the measurement points parametric track description.

The evaluation device 1 is designed to carry out the above-described method.

Claims

claims

1. A method for tracking detection with a sensor system for lane detection (sensors 2.1, 2.2, 2.3) comprehensive driver assistance system of a vehicle (33), in which with the sensor system for lane detection (2.1, 2.2,

2.3) in a front of the vehicle (33) lying area of a traffic space (30) lane markings representing measuring points (MP) are detected, characterized in that based on a reference model, an ideal number of measuring points (MP) is determined, and that from a comparison between the number of the actually detected measurement points (MP) and the ideal number of measuring points (MP) (p ntfernung _e) a plausibility of the predicted distance is determined.

2. The method according to claim 1, characterized in that the plausibility measure (p _E removal) according to the relationship

P _Ent f _ernung = """^ st be IMMT wi rd.

3. The method according to any one of the preceding claims, characterized in that the plausibility measure

(PEntfemung) is normalized to a certain range of values, in particular to the value range [0 ... 1].

4. The method according to any one of the preceding claims, characterized in that the measurement uncertainty

(x measuring point) of the measuring points is detected.

5. The method according to any one of the preceding claims, characterized in that derived from the measurement uncertainties of the measurement points another plausibility measure

5 becomes.

6. The method according to any one of the preceding claims, characterized in that in a measurement with sensors of different accuracy classes for0 each measuring point (MP) from the measurement uncertainty of the respective measuring point (MP) and from the maximum measurement uncertainty of the respective sensor, a normalized weighting factor ^ W _{M kt} G [0 1] is determined.

7. The method according to any one of the preceding claims, characterized in that the weights of all measuring points (MP) to a plausibility measure (pluses) 0 are compressed.

8. The method according to any one of the preceding claims, characterized in that an assistance function of the driver assistance system on reaching a threshold value 5 (activation) of the Plausibi1itatsmaßes activated and at

Reaching a threshold value (P _D eaktivierung) is disabled.

9. The method according to any one of the preceding claims, 0 characterized in that the threshold value (P _D deactivation) is lower than the threshold value (P _A ktivierung) _r so that there is a hysteresis between activation and deactivation.

10. The method according to any one of the preceding claims, characterized in that the plausibility measure (PMesspunkte) is determined according to the following relationship:

r measuring points measuring points ^r

where ^ _{measuring points of} the mean value of the _{measurement points} (MP) assigned weighting factors W _{measuring point} i st.

11.Vorrichtung for track detection, with a

Evaluation device (1), the information from sensors (2.1, 2.2, 2.3) receives and evaluates, characterized in that the evaluation device for performing one of the methods according to claim 1 to 10 is configured.