DE102017106349A1 - A driver assistance system for a vehicle for predicting a traffic lane area, vehicle and method ahead of the vehicle - Google Patents

Abstract

Driver assistance system (2) for an own vehicle (1) for predicting a lane area ahead of the own vehicle (1) to determine if an object (14) is in the predicted lane area, the driver assistance system (2) comprising at least one environment sensor (3) for Detecting lane markings (4) of a lane (5) traveling with the own vehicle (1), at least one detection means (6) for detecting at least two intrinsic motion parameters of the own vehicle (1), and a control device (7) designed to in accordance with a first determination method, to determine a first lane area (12) ahead of the own vehicle (1) as a function of the at least two eigenmotion parameters of the own vehicle (1). Furthermore, the control device (7) is designed according to a second determination method to determine a second lane area (13) ahead of the own vehicle (1) as a function of sensor data of the at least one surroundings sensor (3), which concern the detection of the lane markings (4). and predict the leading lane area in response to the first lane area (12) and / or the second lane area (13).

Description

The invention relates to a driver assistance system for a vehicle, which is also referred to below as an own vehicle, for predicting a driving lane area ahead of the own vehicle in order to determine whether an object, such as a vehicle driving ahead of the own vehicle, is located in the predicted lane area. In this case, the driver assistance system has at least one environment sensor for detecting lane markings of a roadway traveled by the own vehicle, at least one detection means for detecting at least two own motion parameters of the own vehicle, and a control device, which is designed according to a determination method a lane area ahead of the own vehicle in dependence from the at least two eigenmotion parameters of the own vehicle to determine. Furthermore, the invention also relates to a vehicle having such a driver assistance system, and to a method for predicting a lane area ahead of an own vehicle in order to determine whether an object is in the predicted lane area.

Various driver assistance systems are known from the prior art. Such driver assistance systems can have a wide variety of automation levels, ranging from level 1, such as the ACC (Adaptive Cruise Control), to level 5, fully autonomous driving. In order to implement these driver-assisting or even fully autonomous driving functions, it is necessary for such systems to be able to detect objects, obstacles or other road users ahead. Moreover, in most systems, it is also important to assess whether such objects or obstacles are within the lane or range of traffic likely to be traveled by the subject vehicle, for example, to adjust the speed and / or maintain a certain safety distance from a preceding vehicle. For example, if a vehicle in front is detected, but this is not in the lane of the driver's vehicle, so it is not necessary in such a case to warn the driver or to automatically delay the vehicle. Therefore, it is necessary not only to determine whether objects lying ahead, such as preceding vehicles, are basically present, but also to determine as reliably as possible whether or not a vehicle ahead of the own vehicle is located on the traffic lane area to be traveled by the own vehicle. This process is also called "target selection". The target can represent any object preceding the own vehicle. Thus, if such a "destination" is selected, this means that this destination is located on the lane area to be traveled by the own vehicle. If no destination is selected, preceding road users are not on the lane to be traveled by their own vehicle. If there are several vehicles on the lane traveled by the own vehicle, then ideally only that of the vehicles is selected as the target for which the time to collision is the shortest, based on the position, speed, and acceleration of the preceding vehicles as well as the Own vehicle can be determined.

In order to be able to make such an assignment, in turn the lane area to be traveled or probably to be traveled must be determined or predicted. For such a prediction, it is also known to use eigenmotion parameters of the own vehicle. These represent, for example, the current speed, steering angle, or similar parameters that describe the current self-motion of the own vehicle. On the basis of the current proper motion of the own vehicle, it is thus possible, at least for a certain distance, to predict the lane area likely to be traveled by the driver's own vehicle.

A generic driver assistance system is for example in the US 8,577,552 B1 disclosed. In this case, on the basis of intrinsic motion parameters of an own vehicle, a lane area to be traveled in the future can be predicted and, based on this, it can be determined whether a vehicle driving ahead of the own vehicle lies in this lane area or not. Environment sensors of the own vehicle can be used for detecting and determining the position of the vehicle in front. It is further disclosed that camera based lane marker recognition systems can be used to provide lane departure warnings.

Also the US 2011/0270466 A1 describes determining a predicted lane area based on intrinsic motion parameters of the subject vehicle.

However, the prediction of the preceding lane area of the own vehicle on the basis of intrinsic motion parameters has the great disadvantage that such a prediction is sometimes reliable only for very short distances. Especially on a winding route a reliable prediction is limited to an extremely short range in front of the own vehicle. For example, if the own vehicle on a right lane drives straight ahead to a right turn, then in this situation, based on the eigenmotion parameters the predicted lane area run straight ahead so that, for example, road users located on the left-hand lane and already located in the right-hand bend would erroneously be recognized as directly preceding vehicles. Conversely, even vehicles in front and in the same lane that are already in the right-hand bend would not be recorded as targets.

It is therefore an object of the present invention to provide a driver assistance system for a vehicle for forecasting a traffic lane area ahead of the vehicle, a vehicle, and a method by means of which a more reliable prediction of the lane area ahead is made possible for greater distances to the vehicle.

This object is achieved by a driver assistance system, a vehicle and a method having the features according to the respective independent claims. Advantageous embodiments of the invention are the subject of the dependent claims, the description and the figures.

An inventive driver assistance system for an own vehicle for predicting a lane area ahead of the own vehicle to determine whether an object, for example a vehicle ahead of the own vehicle, is located in the predicted lane area, has at least one environment sensor for detecting lane markings of a lane traveled by the own vehicle at least one detecting means for detecting at least two self-motion parameters of the own vehicle and a control device, which is designed according to a first determination method to determine a first lane area ahead of the own vehicle in dependence on the at least two proper motion parameters of the own vehicle. Furthermore, the control device is configured to determine, according to a second determination method, a second lane area adjacent to the own vehicle as a function of sensor data of the at least one surroundings sensor relating to the detection of the lane markings and the forward lane area depending on the first lane area and / or the second Predict lane area.

In addition to the first method, according to which the first lane area is determined on the basis of the at least two intrinsic motion parameters of the vehicle, a second method for determining the second lane area can advantageously be used according to the invention, according to which this second preceding lane area is determined on the basis of the detected lane markings , The possibility of combining these two determination methods can significantly increase the accuracy and reliability of the prediction of the preceding driving range. In particular, this means that the driving range to be traveled can be forecast much more accurately for further sections ahead. Even in curve situations for which the traffic lane area to be traveled alone according to the first method is predictable only very inaccurate or only for a very short distance with respect to the own vehicle, now the lane area ahead by the detection of the lane markings can be clearly be described in more detail and long-range. Although there is the problem in the prediction of driving ranges lying ahead through environment detection, in principle, an environment detection per se can be very inaccurate and can therefore lead to a very unreliable prediction of the preceding driving area. For example, if cameras are used for lane mark recognition, it may for example be the case that lane markings can be very poorly recognized in bad weather conditions, such as rain. It may also happen that lane markings are basically difficult to recognize, or partially on roads are not even available. Also, lane markings may be obscured by other road users close to or in front of the own vehicle. In addition, environmental sensors can be polluted, which impairs their detection accuracy. It can also dazzle effects occur, for example, by direct sunlight or various reflections, so that the environment detection and accordingly derived therefrom results such as a predicted ahead driving range depending on the situation more or less accurate. However, the invention makes use of the knowledge that the possibility exists precisely through a combination of these two methods, that is to say the prediction of the first lane area on the basis of the at least two eigenmovement parameters and the prediction of a second lane area on the basis of the surroundings detection, in particular the detection of the lane markings provides just to exploit the strengths of these respective methods in a particularly advantageous manner and at the same time to compensate for their weaknesses. As a result, it is advantageously possible to achieve enormous advantages in terms of both accuracy and range. By the combination possibility of the first determination method and the second determination method provided by the invention, a significantly better situation adaptation can be achieved. For example, the lane area to be forecasted can also be at long intervals to the own vehicle by the second determination method are described in much greater detail and the advantages of the first method in terms of very short distances to the own vehicle can continue to be used. This means that the lane area to be traveled can be forecast much more accurately on very winding lanes.

The object can be any type of object, such as a moving object or even a static object. For example, the object may represent a vehicle ahead of the subject vehicle, such as a car, a motorcycle, a truck, a bicycle, or even a pedestrian, an animal, or any obstacle on the road, such as a fallen from a truck on the road Object.

In general, the own vehicle may also represent any vehicle, such as a car, for example a passenger car, a motorcycle, a truck. The term "self" vehicle is used herein merely to more easily distinguish between that vehicle and objects, such as one or more preceding vehicles.

The driver assistance system may further include one or more environmental sensors, such as a camera, a ToF (Time of Flight) camera, a stereo camera, or the like, to detect lane markings. Other environment sensors, such as radars, ultrasonic sensors, laser scanners, or the like may also be provided. By means of such sensors it is also possible, for example, to detect road boundaries, crash barriers, edge structures, and so on, which can be used to determine the traffic lane area, in particular the second traffic lane area. When the lane markings are detected, lane markings running both to the left in the direction of travel from the driver's own vehicle as well as lane markings running to the right of the own vehicle can be detected and used to determine the second lane course. Sense, for example, only on one side of the driver's vehicle lane markings detectable because they are present, for example, only on one side, it can be assumed to calculate the lane course, in particular its width perpendicular to the direction of a predetermined standard width.

For determining the first lane area on the basis of the at least two eigenmotion parameters, a plurality of eigenmovement parameters are preferably used, such as the current speed of the own vehicle, the current steering angle, a yaw angle or yaw rate, an actual acceleration, acceleration change, and so on. On the basis of one or more of these parameters, by extrapolation of the proper motion described by these parameters, the first lane area can be calculated, again for its width in the course direction a default value or also the width of the own vehicle, optionally plus a lateral, fixed value. Preferably, at least one of the at least two eigenmotion parameters represents a parameter describing a longitudinal movement of the own vehicle, such as the longitudinal velocity of the subject vehicle, and at least one of the at least two intrinsic motion parameters represents a parameter describing a lateral behavior of the own vehicle, such as the yaw rate or the front wheel angle of the own vehicle. In particular, the eigenmotion parameters used for the determination of the first lane area are coupled to each other via a dynamic model of the own vehicle. In addition, the more eigenmotion parameters are used, the more accurate the prediction becomes.

In an advantageous embodiment of the invention, the control device is designed to calculate the predicted lane area as a predeterminable averaging of the first lane area and the second lane area for predicting the forward lane area as a function of the first lane area and the second lane area. In this way, advantageously both the results of the first determination method and those of the second determination method can be taken into account and advantageously combined when forecasting the traffic lane area. Such averaging does not necessarily mean the results, i. consider the first lane area and the second lane area, these two methods of determination in the same way but, for example, also weighted, so that it is thereby made possible to take advantage of the strengths of the respective determination method and to compensate for their weaknesses. The predeterminable averaging can also be calculated dynamically, for example as a function of the speed of the own vehicle, as a function of the dynamic behavior of the sensor, as a function of the infrastructural environment, us and so forth, depending on a parameter, such as the speed, of the behavior , and so on, predeterminable.

It is particularly advantageous if the control device is designed to determine at least a first reliability value for the first lane area and to determine at least one second reliability value for the second lane area. Furthermore, the control device is preferably designed to be pre-definable Averaging as a function of the at least one first reliability value and the at least one second reliability value weighted averaging of the first lane area and the second lane area to calculate.

By the respective reliability values, the reliability of the individual calculated traffic lane areas, i. of the first and second lane areas. Thus, in the averaging, the respective first and second lane area can be weighted accordingly by their reliability. This advantageously makes it possible to maximize the overall reliability of the ultimately predicted lane area. By such a weighting, it can thus be realized with particular advantage that the strengths and advantages of the respective methods are maximally utilized in different situations and their weaknesses eradicated.

The respective reliability values give an estimated value for the extent to which the respective calculated first lane area and second lane area coincide with an actual lane area to be traveled. With respect to the second determination method in which the second lane area is calculated based on the sensor data, this reliability value significantly describes the accuracy and reliability of this sensor data. In this case, the reliability value can be calculated, for example, as a function of an image quality of the recorded camera image for lane marking recognition, in particular as a function of different image areas, which correspond, for example, to different distances or distances from the own vehicle. The image quality per se can in turn be determined on the basis of parameters such as contrast, intensity, contrast progressions, intensity gradients, resolution, and the like. Results of the data interpretation can also be included in the second reliability value, such as whether lane markings in the first place could be recognized or classified as such, with which likelihood the identified lane markings are actually lane markings, and so on. For high reliability, the curvature of the lane markings, their lateral position and their orientation must also be precisely determined, so that uncertainties in the determination of these variables can also be taken into account in the calculation of the at least one second reliability value. All of these quantities are suitable in order to evaluate the reliability of the second lane area calculated on the basis of the environment data or sensor data, in particular by the corresponding at least one second reliability value. The at least one first reliability value for the first lane area can be significantly described on the basis of dynamic parameters of the own vehicle, and will be explained in more detail later. Furthermore, the higher the reliability of the lane area evaluated by the latter, the higher the respective reliability value can be. Such a reliability value may for example include between zero and one, or alternatively between 0% and 100%.

In a further advantageous embodiment of the invention, the driver assistance system is designed to determine a distance of the object to the own vehicle, and to determine the at least one first and the at least one second reliability value in each case depending on the determined distance. As already indicated, the reliability of the respective determination methods varies, inter alia, with the distance or the distance to the own vehicle. For example, the first lane area based on the intrinsic motion of the own vehicle can be determined very accurately, especially in the vicinity, while this is only very imprecisely possible for long distances to the own vehicle. By the above-described advantageous consideration of the distance of the object to the own vehicle this fact can be taken into account in a particularly advantageous manner. In this way, therefore, the at least one reliability value, both for the first lane area and thus for the calculation of the second lane area, can be determined specifically for the distance at which the object is currently located. As a result, the lane area can be predicted particularly accurately and reliably precisely at the location of the object. Thus, the subsequent determination as to whether the object is located on the predicted lane area or not can be provided with particularly high accuracy and low error rate. If, for example, several vehicles are detected in front of the own vehicle in the direction of travel, the corresponding reliability values can also be calculated for the respective distances.

Thus, it can advantageously be accomplished that, for example, in a proximity to the own vehicle, the predicted lane area is generally influenced by the values of the first lane area, since in the vicinity the prediction of the lane area based on the intrinsic motion of the vehicle of the own vehicle usually significantly better is as a prediction based on environmental data. In contrast, in a far-away area, in which usually a lane area calculation based on the self-motion of the own vehicle is significantly less accurate than a prediction based on the environment detection, the predicted lane area significantly influenced by the values of the calculated second lane area.

Due to this distance-dependent calculation of the respective reliability values, an optimal adaptation to the respective situation can be achieved with the best possible result. These advantages can be accomplished in the same way by the following embodiment of the invention.

According to this further advantageous embodiment of the invention, the first and the second lane area is divided into a plurality of contiguous, specific distance ranges with respect to the own vehicle, wherein the control device is designed to determine a plurality of first reliability values for the first traffic lane area and a plurality of second reliability values for the first lane area second lane area to determine. In this case, a respective one of the plurality of first and second reliability values is assigned to one, in particular exactly one, of the plurality of defined distance ranges. Furthermore, the control device is configured to calculate the predeterminable averaging for a respective one of the plurality of distance ranges as a weighted averaging of the first lane area and the second lane area for a respective distance range depending on the respective first and second reliability values associated with the respective distance range ,

Thus, firstly the first and the second lane area can be calculated, and then these calculated lane areas can be assigned a plurality of reliability values as a function of the distances of the respective partial areas, ie the distance areas, of the respective lane areas to the own vehicle. The predicted lane area then results from an averaging of these two first and second lane areas, which enter into this averaging for respective distance ranges according to their reliability values. This also advantageously enables a spatially resolved reliability evaluation of the first and second lane areas, so that the predicted lane area in respective distance ranges is dominated by the most reliable data of these respective individual first and second lane areas. Then, positions of detected objects may then be compared with the thus-predicted lane area to determine if the one or more of the objects are in the predicted lane area.

In a further advantageous embodiment of the invention, the control device is designed to determine the at least one first reliability value, and in particular also in the case of a plurality of first reliability values as described in the last example, as a function of at least one of the following parameters: a speed of the own vehicle, Navigation data relating to a preceding route, and detecting an initiation of a predetermined automatic driving maneuver, which includes a lateral offset of the own vehicle with respect to the currently traveled roadway.

For example, the higher the speed of the own vehicle, the higher the reliability can be assessed, since at higher speeds the trajectory can not be changed so fast because the wheel angle or steering angle and also the speed per se can not change abruptly. In contrast, changing driving maneuvers are possible at a very low speed much faster, ie shorter driving distance, so that correspondingly at lower speeds the reliability of the lane area calculated on the basis of the vehicle's own motion is lower. It is also possible to use navigation data, for example a navigation device, which may comprise a GPS receiver or another position-determining device, as well as map data, which may be stored in a memory, in order to evaluate the reliability. As mentioned at the outset, the reliability of the self-motion based lane area calculation is relatively small for a curvy road, whereas for a straight road it is very high. Whether the currently traveled lane or the preceding route runs straight or curved can thus be determined on the basis of the corresponding navigation data. In this case, it is not absolutely necessary to obtain the curvature profile of the route section lying directly from the navigation data; for example, it is possible to deduce such on the basis of the type of roadway currently being traveled. For example, highways are typically more straightforward than highways or even urban roads. Such a road type or regional information, such as whether the own vehicle is currently in town or out of town, can be obtained from the navigation data and used to calculate the at least one first reliability value. Furthermore, it can also be provided that the driver assistance system is designed to allow the driver to set a desired lateral offset, which specifies which lateral distance, for example as a safety margin for overtaking or to vehicles parked at the roadside or to the road boundary itself, to be kept by the own vehicle. If such a lateral or lateral offset is predetermined by the driver to the driver assistance system, the driver assistance system can regulate or correct the lateral offset of the driver's vehicle while driving in order to comply with this specification. If, for example, a driver changes this specification while driving, this leads to the driver assistance system, in implementing this changed specification, causing a lateral offset of the own vehicle with respect to the currently traveled roadway in order to adapt to the new specification. Such a lateral offset inevitably results in a steering angle correction or a resulting curved trajectory, which, however, is not due to a curvature of the currently traveled traffic lane area or the roadway currently being traveled. Thus, the initiation of such a predetermined automatic driving maneuver also leads to a reduced reliability of the first traffic lane area calculated during such a driving maneuver.

Thus, by the above examples, it is possible to consider various different situations in evaluating the reliability of the first lane area. As a result, the reliability of the first lane area can be estimated particularly accurately. Of course, other parameters may also be taken into account when determining the first or several first reliability values, such as the dynamics of the longitudinal system or the like.

In a further embodiment of the invention, the control device is designed to determine the at least one second reliability value as a function of at least one of the following parameters: an environmental condition, such as day or night, sun or rain, and so on, a sensor state of the at least one environmental sensor a quality of the lane markers, particularly on the right and / or left side of the lane in the direction of travel, and whether or not a vehicle having a size larger than a predetermined size is in front of the own vehicle, such as a vehicle which tracks the lanes can cover. Also many more parameters can be considered.

Alternatively or in combination with the aforementioned examples, the lane area to be forecasted can not be provided only by weighted combination of the first and second lane area, but there are numerous other possibilities, both the first and the second determination method advantageously and simply for one To use particularly accurate determination of the predictable lane area, which are described in more detail below.

In this case, according to a further advantageous embodiment of the invention, it is provided that the control device is designed to predict the forward lane area depending on the first lane area and / or the second lane area, the first and / or second lane area depending on at least one predetermined parameter than to select the predicted lane area. The predicted lane area can thus be equated with the calculated first lane area in a first situation specified by the predetermined parameter and, for example, in another situation specified by the predetermined parameter with the calculated second lane area. Thus, no averaging of the values of the first and second lane area is required to calculate the predicted lane area, but the first or second lane area may be selected as the predicted lane area depending on the situation. As a result, the computational effort is simplified enormously and yet a particularly good situation adaptation can be achieved by the predetermined parameter which determines or at least influences the selection. It may also be that for the relevant area, i. the location where the object is located, the first and the second lane area coincide, or at least with respect to the result of whether the object is in the lane area or not, so also both lane area, that is, the first and the second than the predicted lane area can be provided. Thus, the strengths of the respective determination methods in adaptation to a respective situation can in turn be used selectively by the at least one predetermined parameter and at the same time compensate for their respective weaknesses.

It is particularly advantageous if the at least one predetermined parameter represents a determined distance of the object to the own vehicle. Since the qualities of the individual determination methods depend on the distance to the own vehicle, in turn the selection of the first and / or second traffic lane area as a function of the determined distance of the object is particularly advantageous. In order to describe the qualities or reliability of the first and second lane area, it is not necessary to determine the reliability values described above. The decision criteria can be based on experience and empirical calculations. In principle, there is still the possibility provide the reliability values described above as the at least one predetermined parameter so that, for example, the lane area is selected from the first and second lane areas having the higher reliability. This in turn would be additionally combinable with a distance-dependent calculation of the reliability values.

In a further advantageous embodiment of the invention, the at least one predetermined parameter represents a result of a time-prior determination as to whether the object is in the predicted lane area. This also makes it possible, for example, to use previous results from areas with higher accuracy or reliability, for example. Such previous results may also be used to verify the current decision or determine the decision between the first and second calculated lane areas. For example, both the first and second lane areas may be calculated and checked as to whether the object is within the respective lane area or not, and in case of contradictory results, the temporally previous result may be used for the decision.

The parameters described above can also be combined with one another in any desired manner and can be used to select between the first and / or second lane area as the predicted lane area in order to enable a particularly good situation adaptation and a particularly high reliability of the finally predicted lane area.

According to a further advantageous embodiment of the invention, a short range located in front of the own vehicle in the direction of travel is defined, which extends starting from the own vehicle in a predetermined direction up to a predetermined first distance to the own vehicle. Furthermore, a remote area located in front of the own vehicle is defined, which extends from the first distance or from a second distance, which is greater than the first distance to the own vehicle, in the predetermined direction up to a third distance to the own vehicle. Further, the controller is configured to check whether the object is in the near or far range, and if the object is in the vicinity, to provide the first lane area as the predicted lane area, and if the object is in the far area, the second Lane area as the predicted lane area. This advantageous embodiment of the invention is based in turn on the knowledge that the calculation of the lane area based on the current proper motion of the own vehicle is much better, especially at close range, and has a significantly higher accuracy than the calculation of this lane area in the vicinity on the basis of Umweisfassung. However, the lane in the far range calculated on the basis of the surroundings detection clearly dominates a lane area calculated on the basis of the own movement of the own vehicle with regard to its quality. Therefore, it is particularly advantageous to provide the first lane area as the predicted lane area in the vicinity, and to provide the second lane area as the predicted lane area in the far area.

In this procedure, the position or the distance of the object to the own vehicle is preferably first determined, and if this is, for example, in the vicinity, the first lane area is calculated and equated with the predicted lane area. In this case, for example, the second lane area does not have to be calculated first. Conversely, this is also the case for the long-range. This can save enormous computational effort and still provide the predicted lane area with high accuracy. The area ahead of the own vehicle can, for example, be divided into only two partial areas, the near area and the far area, which represents a particularly simple embodiment of this method. But it can also be provided significantly more subdivisions, which in turn provides much more flexible customization options.

Accordingly, it is an advantageous embodiment of the invention that an intermediate area between the near area and the far area is defined, wherein the control device is designed to check whether the object is in the intermediate area, and if the object is located in the intermediate area to determine whether the object is in the first lane area and to provide a result of the determination as a first result. Furthermore, the control device is configured to determine whether the object is in the second lane area and to provide a result of this determination as a second result, wherein the control device is further adapted to compare the first result with the second result, and in the case a match, the first and second results, respectively, which in this case represent the same result, as an overall result of determining whether the object is in the predicted lane area. This intermediate area thus advantageously allows significantly more differentiation possibilities. Especially the comparison between the Results ie the first and second results, allows for additional verification and thus a much higher safety and reliability of the overall result.

However, if there is no match between these two results, i. Thus, for example, if the object is by comparison with the respective calculated first and second lane area, for example, in the first lane area, but not in the second lane area or vice versa, there are in turn several particularly advantageous ways to make decisions in such a situation, both are optimized in terms of safety and ride comfort, and are explained in more detail below.

According to a variant of the invention, the control device is furthermore designed to provide, in the event that the first result does not match the second result, as an overall result that the object is in the predicted lane area. This is a particularly conservative solution in terms of safety. This has the background that the false assumption that the object is in the same lane area as the own vehicle can have significantly less serious consequences than the false assumption that the object is not in the lane area of the own vehicle, although that is the case. In the first case, for example, the own vehicle is falsely braked or the driver warned unnecessarily, while in the second case worst case, a rear-end collision can result. This conservative decision criterion thus leads to a particularly high level of security.

• - für den Fall, dass sich das Objekt im ersten Teilbereich befindet, die Steuereinrichtung dazu ausgelegt ist,
  • • wenn das erste Ergebnis beinhaltet, dass sich das Objekt in dem ersten Fahrspurbereich befindet, das erste Ergebnis als das Gesamtergebnis bereitzustellen;
  • • wenn das erste Ergebnis beinhaltet, dass sich das Objekt nicht im ersten Fahrspurbereich befindet, ein Gesamtergebnis einer zeitlich vorhergehenden, insbesondere den zweiten Teilbereich betreffenden, Ermittlung, ob sich das Objekt im prognostizierten Fahrspurbereich befindet, als das aktuelle Gesamtergebnis bereitzustellen; und
• - für den Fall, dass sich das Objekt im zweiten Teilbereich befindet, die Steuereinrichtung dazu ausgelegt ist,
  • • wenn das zweite Ergebnis beinhaltet, dass sich das Objekt im zweiten Fahrspurbereich befindet, das zweite Ergebnis als das Gesamtergebnis bereitzustellen; und
  • • wenn das zweite Ergebnis beinhaltet, dass sich das Objekt nicht im zweiten Fahrspurbereich befindet, ein Gesamtergebnis einer zeitlich vorhergehenden, insbesondere den ersten Teilbereich betreffenden, Ermittlung, ob sich das Objekt im prognostizierten Fahrspurbereich befindet, als das Gesamtergebnis bereitzustellen.

In a further advantageous embodiment of the invention, the intermediate region is defined such that it has a first subregion and a second subregion adjoining the first subregion, wherein the first subregion continues to adjoin the short region and the second subregion adjoins the remote region. Furthermore, the control device is designed to check whether the object is in the first partial area or in the second partial area, and in the case that the first result does not match the second result, and

• in the case where the object is in the first subarea, the control device is designed to
  • If the first result includes the object being in the first lane area to provide the first result as the overall result;
  • If the first result includes that the object is not in the first lane area, an overall result of a temporally preceding, in particular the second section, determining whether the object is in the predicted lane area to provide as the current overall result; and
• in the case where the object is located in the second subarea, the control device is designed to
  • If the second result includes the object being in the second lane area, providing the second result as the overall result; and
  • If the second result includes that the object is not in the second lane area, an overall result of a temporally preceding, in particular the first partial area, determining whether the object is in the predicted lane area to provide as the overall result.

In the first subarea, which is thus closer to the near range, it can therefore be assumed that the results of the first determination method, based on the own movement of the own vehicle, have a higher reliability than the results of the second determination method. If, therefore, the result of the first determination method, that is to say the first result, is conservative, it is thus determined that the object is located on the first lane area, then this result is assumed to be the overall result. This overall result is then in all likelihood also true, as this is based on the more reliable data. If this is not the case, however, the conservative result can avoid even worse consequences such as construction accidents. The same applies to the second section. For this, the result of the second determination method on the basis of the environment detection is generally more accurate than the calculation based on the eigenmovement. If the result of the second calculation determination method therefore fails conservatively in this second subarea, that is to say it is determined that the object is located on the second traffic lane area, then this is assumed to be the overall result. Correspondingly, the likelihood that this overall result is also correct is high, and otherwise worse consequences such as accidents can be avoided.

However, in another case, when the first sub-area in which the results based on the self-movement are usually more accurate, it is determined that the object is not in the first traffic lane area but the second result based on the second determination method is different can advantageously for additional verification of the first Result the overall result of a temporally preceding determination, whether the preceding vehicle is in the predicted lane area, are used. For example, if this previous result indicates that the object did not previously also lie in the predicted lane area, then the first result can be set as the overall result. Otherwise, the overall result is assumed to be on the predicted lane area. This also applies analogously to the second subarea, so that here as well, in the case of conflict, the overall result of a previous investigation, in particular also from a different distance range, can be used. This approach can provide much more differentiated and therefore more accurate decisions. The likelihood of a wrong decision is reduced in the same way and thus leads less often to unnecessary braking or unnecessary warning messages.

Furthermore, the invention also relates to a vehicle, in particular the vehicle previously referred to as an own vehicle, which is preferably designed as a motor vehicle, in particular as a passenger car. The vehicle according to the invention has a driver assistance system according to the invention or one of its refinements. The features, feature combinations and their advantages mentioned for the inventive driver assistance system in its embodiments apply in the same way to the own vehicle according to the invention and its embodiments.

The invention further relates to a method for forecasting a lane area ahead of an own vehicle in order to determine whether a vehicle ahead of the driver's vehicle is in the predicted lane area. In this case, according to a first determination method, a first lane area ahead of the own vehicle is determined as a function of at least two detected intrinsic motion parameters of the own vehicle, and according to a second determination method a second lane area ahead of the own vehicle is determined as a function of detected lane markings. The preceding lane area is further predicted in dependence on the first lane area and / or the second lane area.

The advantages mentioned for the driver assistance system according to the invention and its embodiments apply in the same way to the method according to the invention. Furthermore, the subject features mentioned in connection with the driver assistance system according to the invention and its embodiments allow the development of the method according to the invention by further method steps.

Further features of the invention will become apparent from the claims, the figures and the description of the figures. The features and combinations of features mentioned above in the description as well as the features and feature combinations mentioned below in the description of the figures and / or shown alone in the figures can be used not only in the respectively specified combination but also in other combinations, without departing from the scope of the invention , Thus, embodiments of the invention are to be regarded as encompassed and disclosed, which are not explicitly shown and explained in the figures, but which emerge and can be produced by separated combinations of features from the embodiments explained. Embodiments and combinations of features are also to be regarded as disclosed, which thus do not have all the features of an originally formulated independent claim. Moreover, embodiments and combinations of features, in particular by the embodiments set out above, are to be regarded as disclosed, which go beyond or deviate from the combinations of features set out in the back references of the claims.

• 1 eine schematische Darstellung eines Fahrzeugs mit einem Fahrerassistenzsystem zum Prognostizieren eines dem Eigenfahrzeug vorausliegenden Fahrspurbereichs gemäß einem Ausführungsbeispiel der Erfindung;
• 2 eine schematische Darstellung eines auf Basis einer Eigenbewegung eines Fahrzeugs berechneten Fahrspurverlaufs in einer Kurvensituation;
• 3 eine schematische Darstellung eines Fahrzeugs gemäß einem Ausführungsbeispiel der Erfindung sowie der gemäß dem ersten und zweiten Bestimmungsverfahren berechneten Fahrspurbereiche;
• 4 eine tabellarische Darstellung eines Verfahrens zum Prognostizieren eines vorausliegender Fahrspurbereichs auf Basis des ersten und zweiten berechneten Fahrspurbereichs gemäß einem Ausführungsbeispiel der Erfindung;
• 5 ein Ablaufdiagramm zur Veranschaulichung eines Verfahrens zum Prognostizieren eines dem Eigenfahrzeug vorausliegenden Fahrspurbereichs gemäß einem Ausführungsbeispiel der Erfindung;
• 6 eine schematische Darstellung des Eigenfahrzeugs und der berechneten ersten und zweiten Fahrspurbereiche mit einer Veranschaulichung von jeweiligen Zuverlässigkeitswerten für verschiedene Abstandsbereiche gemäß einem ersten Anwendungsfall zur Berechnung des prognostizierten Fahrspurbereichs gemäß einem Ausführungsbeispiel der Erfindung;
• 7 eine schematische Darstellung des Eigenfahrzeugs sowie der berechneten ersten und zweiten Fahrspurbereiche mit einer Veranschaulichung von zugeordneten Zuverlässigkeitswerten für verschiedene Abstandsbereiche für einen zweiten Anwendungsfall gemäß einem weiteren Ausführungsbeispiel der Erfindung; und
• 8 ein Ablaufdiagramm zur Veranschaulichung eines Verfahrens zum Prognostizieren eines Fahrspurbereichs gemäß einem weiteren Ausführungsbeispiel der Erfindung.

Showing:

• 1 a schematic representation of a vehicle with a driver assistance system for predicting a lane area ahead of the own vehicle according to an embodiment of the invention;
• 2 a schematic representation of a calculated based on a self-motion of a vehicle lane course in a curve situation;
• 3 a schematic representation of a vehicle according to an embodiment of the invention and the calculated according to the first and second determination method lane areas;
• 4 a tabular representation of a method for predicting a preceding lane area based on the first and second calculated lane area according to an embodiment of the invention;
• 5 a flowchart for illustrating a method for predicting a lane area ahead of the own vehicle according to an embodiment of the invention;
• 6 a schematic representation of the own vehicle and the calculated first and second lane areas with an illustration of respective reliability values for various distance ranges according to a first application for calculating the predicted traffic lane area according to an embodiment of the invention;
• 7 a schematic representation of the own vehicle and the calculated first and second lane areas with an illustration of associated reliability values for different distance ranges for a second application according to another embodiment of the invention; and
• 8th a flowchart for illustrating a method for predicting a lane area according to another embodiment of the invention.

1 shows a schematic representation of a vehicle 1 with a driver assistance system 2 according to an embodiment of the invention. The vehicle 1, which subsequently also as an own vehicle 1 is referred to, further comprises at least one environmental sensor, in which case four environment sensors 3, such as cameras, are shown here by way of example. These sensors 3 can also be arranged in other places as well. For example, a video sensor may be disposed in the center of the windshield, one or two laser scanners in the front bumper, a video sensor in the center of the front bumper, a video sensor in each exterior mirror, and a video sensor at the rear of the driver's vehicle 1. The environmental sensors 3 are designed to at least part of the vehicle environment, and especially lane markings 4 a currently used carriageway 5 capture. Also, a navigation device, such as a GPS sensor and an associated map, may be another environment sensor 3 be provided, for example, to determine if the own vehicle 1 driving straight on a straight road or a winding road. Furthermore, the vehicle 1 at least one detection means 6, which is designed to at least two eigenmotion parameters of the vehicle 1 capture. It can also several such detection means 6 be provided, which may be formed, for example, as a steering angle sensor, speed sensor, and so on. Preferably, by the detection means 6 Own motion parameters, such as the vehicle speed, the current steering angle, a yaw rate or a yaw angle, an acceleration, or the like detected. Furthermore, the vehicle 1 , in particular the driver assistance system 2 , a control device 7 on, which is designed to the detected variables, ie on the one hand from the environment sensors 3 recorded sensor data and by the detection means 6 evaluate recorded eigenmotion parameters.

The control device 7 is designed to, according to a first determination method a first the own vehicle 1 leading lane area 12 (cf. 3 . 6 and 7 ) as a function of the at least two eigenmotion parameters of the own vehicle 1 to be determined, and on the other hand, according to a second determination method, a second lane area ahead of a second own vehicle 1 13 (see 3 . 6 and 7 ) as a function of sensor data of the at least one environment sensor 3 that captures the lane markings 4 be determined. For determining the first lane area, the control device 7 For example, based on the current eigenmotion parameters a current trajectory of the vehicle 1 determine and by extrapolation the first lane area 12 predict. As the width of this first lane area 12 For example, the vehicle width, possibly plus a predetermined value, or even a predetermined default value can be assumed. To determine the first lane area, the detected lane markings may 4 be evaluated accordingly. For this purpose, for example, a curvature of the lane markings 4 as well as their lateral position and orientation are determined in order to determine therefrom the second lane course 13. Although the lane markings 4 here on the left side of the own vehicle 1 can also show lane markings 4 on the right side of the own vehicle 1 by means of the sensors 3 be detected, in particular additionally or alternatively.

Furthermore, the control device 7 configured as a function of the first lane area 12 and / or the second lane area 13 , the own vehicle 1 in the direction of travel ahead and to be driven lane area to predict. Furthermore, the control device 7 designed to determine whether an object, such as a preceding vehicle, is based on the travel range ultimately predicted for a respective time step 14 (see 3 . 6 and 7 ), lies in this predicted lane area. If this is the case, the control device 7 selects this vehicle 14 as a goal, otherwise not. Based on this, the driver assistance system 2 perform additional driver assistance functions, such as the speed of the own vehicle 1 depending on the selected target to keep a minimum distance, warn of a collision with the target, or the like.

Both determination methods for determining the first and second lane area 12 . 13 have weaknesses in themselves. The determination of the second traffic lane area on the basis of the environmental data, for example, is very dependent on corresponding environmental conditions and Environmental influences, such as visibility, weather conditions, the nature of the lane markings and their contrast to the ground, ie the road 5 , dependent. Also the quality of the environment sensor 3 in itself and the quality of the evaluation and interpretation procedures play a role. However, especially due to strong dependence on environmental conditions, which can sometimes be inferior to very strong fluctuations, a prognosis of the lane area based on the environment detection alone is not very reliable. Above all, it can not be predicted so far when the environment detection, in particular the detection of the lane markings, is better or worse, which would make it very risky to rely solely on a lane range predicted by the surroundings detection. In the same way, the first determination method itself has problems, as will be explained in more detail with reference to FIG. 2.

2 shows a schematic representation of a not belonging to the invention vehicle 8 and one based on the proper motion of the vehicle 8th calculated lane course 9 using the example of a very winding roadway 5 , Continue to be on this lane 5 even more road users 10a . 10b . 10c in the same direction, which is indicated by the arrow 11 illustrated, drive like the vehicle 8th , In this example, the vehicle is still in front of the curve and is driving straight ahead at this moment. Accordingly, the calculation of the lane results 9 based on the self-movement of the vehicle 8th straighten yourself in front of the vehicle 8th extend range. Should now based on this determined lane 9 Target selection, this results in a false selection in this example, which can have critical consequences. In general, a destination selection means that another road user is selected who is immediately ahead of the lane, which is likely to be traveled by the driver's own vehicle. In which 2 example shown would be the road user 10a as such a destination, which is on the determined lane 9 is to be selected. In fact, this road user is 10a however, on a different lane, not from the vehicle 8th will be driven. In contrast, the other road users 10b and 10c However, for which there is a risk of collision, since they are at least partially on the vehicle 8th to be traveled lane, wrongly not selected. Such mis-selections, corresponding to an erroneous prediction of the lane 9 can sometimes have very critical consequences.

The inventions of their embodiments now advantageously provides the possibility of the two described methods, ie the lane area based on the intrinsic motion as well as on the basis of environmental sensors 3 to identify, to combine, which in total can predict a particularly reliably determinable traffic lane area, probably from the own vehicle 1 will be driven. A selection of these different combination options will be explained in more detail with reference to the following examples. Although the following example is for illustrative purposes only to a preceding vehicle 14 As an example of an object, the invention and its embodiments, in particular those described below, apply equally to any type of object, such as pedestrians, obstacles, moving or static objects, in addition to or alternatively to the preceding vehicle 14 ,

3 shows a schematic representation of an own vehicle 1 , like that too 1 and that according to the first determination method on the basis of the intrinsic motion parameters of the vehicle 1 calculated first preceding lane area 12 , and the second lane area calculated according to the second determination method based on the surroundings detection, in particular the lane marker detection 13 , Furthermore, the vehicle 1 preceding vehicle 14 , here in chronological order, that is, for several different time steps, shown at different positions.

The usual situation is that the first lane area course 12 for small distances or distances to the own vehicle 1 provides very good and reliable results. For non-straight road course, however, the first lane area 12 at a greater distance to the own vehicle 1 only a very low reliability. The second lane area 13, which is calculated on the basis of the environmental data, is subject to large reliability fluctuations due to the dependency on the surroundings detection, so that it is primarily used for short distances to the own vehicle 1 basically considered to be significantly less reliable than the first calculated lane area 12 , For longer distances to the vehicle 1 however, and in particular in a curved lane, it can be assumed that the reliability of the second lane area 13 is significantly higher than that of the first lane area 12 , This knowledge can now be used advantageously to the predicted lane area from the first lane area 12 and / or the second lane area 13 depending on the distance to the own vehicle 1 select.

For this purpose, the area in the direction of travel in front of the own vehicle 1 in several Distance ranges are subdivided. In particular, a short-range N may be provided here, as well as a long-range range F. In the short-range N, the first traffic lane area will then be correspondingly the lane area to be predicted 12 is provided, while in the far area F as the lane area to be forecasted, the second lane area 13 is provided. So is the preceding vehicle 14 in the vicinity N, so is the position of this preceding vehicle 14 with the course of the first lane area 12 compared, for example, as shown here, that the preceding vehicle 14 on the first lane area 12 located. Is the preceding vehicle 14 For example, in the far range F, the determined position of the preceding vehicle 14 with the calculated second lane area 13 compared and as shown in this example found that the vehicle ahead 14 located on the second lane area. In both cases, therefore, the vehicle ahead 14 correctly selected as destination.

In addition, in order to avoid an abrupt transition of this selection concept, it is advantageous to provide at least one intermediate region. In this example, this intermediate region is subdivided into two subregions Z1 and Z2. In order to define these individual distance ranges, it may be provided, for example, to specify a distance d, such as 20 m, for example. The boundary between the near zone N and the first subregion Z1 can then be defined, for example, by the distance d minus a percentage value relative to the distance value d, which in 3 is represented by x%, and the boundary between the second portion and the far range has a second percentage value with respect to the distance value d, here represented by y%. The distance d thus defines the boundary between the first partial area Z1 and the second partial area Z2, while the value dx% defines the boundary between the near zone N and the first partial area Z1, and the value d + y% defines the boundary between the second partial area Z2 and the far range F. The percentages x and y may be the same or different. In the case where x% y% are each 20% of the distance d, and the distance d is, for example, 20 m, the boundary between the near area N and the first area Z1 is 16 m and the boundary between the second area Z2 and the long range F at 24 m. The boundaries themselves may be assigned to one of the adjacent areas as desired. The distances to the vehicle 1 can also by the environment sensors 3 of the vehicle 1 be determined. The distance may also be, for example, the smallest distance, for example, as the crow flies between a point of the environment and a selected point of the vehicle 1 be defined. Correspondingly, for example, the limits dx%, d and d + y% shown here would then be circular around the vehicle 1 run. However, distances may also be defined differently as desired, for example along one of the calculated traffic lane areas 12, 13 or as a distance perpendicular to a transverse axis of the vehicle 1 , However, preferably the same distance definition is used for the determination of these distance ranges N, Z1, Z2, F and for the determination of the distance of the preceding vehicle 14 based on. This is especially true for those related to 6 and 7 Spacing ranges A1, A2, A3, A4 described in detail later.

The provision of these intermediate regions, that is to say of the first subregion Z1 and of the second subregion Z2, provides significantly more flexibility and adaptation possibilities, which as a whole enable a more reliable and accurate prediction of the forward travel range. An example of how to make the decision for these four defined distance ranges, i. The local area N, the first partial area Z1, the second partial area Z2 and the far range F can fail, will now be described in more detail with reference to FIG. 4.

4 1 shows a table for illustrating a method for forecasting a lane area ahead on the basis of the first and / or second lane area 12 . 13 according to an embodiment of the invention. In this table, N again denotes the near range, Z1 the first portion, Z2 the second portion and F the far range. E1 hereby denotes the result of a check as to whether the preceding vehicle is moving 14 on the first lane area 12 while E2 denotes the result of a check as to whether the vehicle in front is moving 14 on the second lane area 13 located. Furthermore, "+" means that the preceding vehicle 14 is located on the lane area concerned and thus selected as the destination, while "-" means that the vehicle in front is moving 14 not on the lane area concerned and therefore not selected as the destination. E continues to designate the overall result, ultimately by the driver assistance system 2 is provided for further use. Is the preceding vehicle 14 for example, in the vicinity N, so only the first lane area 12 calculated, since this is usually in the vicinity of N clearly more accurate than the second lane area 13. Accordingly, the position of the preceding vehicle 14 with the first lane area 12 compared. If it is determined as the first result E1 that the vehicle 14 on the first lane area 12 is located, then this first result E1 is set equal to the total result E. Is the preceding vehicle 14 not on the first one lane area 12 , so in the close range N here too the first result E1 is set equal to the overall result. This is illustrated by the third and fourth lines of the illustrated table. The following two lines describe the situation in the far range F. Here, only the second lane area is relevant 13, and the position of the vehicle located in the far range F 14 becomes corresponding to this second lane area 13 compared. This review reveals that the vehicle 14 is in the second lane area 13, so this also represents the overall result E. Does the second result E2, that I the vehicle 14 not on the second lane area 13 This is also the final final result E. The further four subsequent lines of the table describe the situation in the first subarea Z1. So is the vehicle 14 in the first partial area Z1, both the first lane area 12 and the second lane area become 13 calculated, as well as the respective results E1 and E2 of the target selection. If these match, as shown in lines seven and eight, then these results E1, E2 also count as final result or overall result E.

With differing first and second results E1 and E2, there are now several possibilities. Of these, a variant will be explained below. If, for example, it is determined for the first subarea Z1 that the vehicle is moving 14 on the first lane area 12 but not in the second lane area 13 , so the overall result is that the vehicle 14 is on the predicted lane area and thus selected as the destination. This has the background that in the former subarea Z1 still higher accuracy of the first lane area 12 can be assumed, and also the first result E1 also represents the conservative result, in which no safety risks are to be expected in the event of an error. Otherwise, it is determined for the first partial area Z1 that the vehicle 14 is not on the first lane area 12 but is on the second lane area 13, so can be used for the decision between these two conflicting results E1 and E2 to a total result E in a time-previous investigation. For example, the previous determination in the area Z2 can be used, in particular if the distance between the own vehicle 1 and the preceding vehicle decreases. For example, has the vehicle 14 previously found in the second partial area Z2, and it was found as the overall result E that the vehicle was previously on the predicted lane area, which in the table with "(+)" is designated, then the overall result E is also assumed in this case in that the vehicle 14 is currently on the predicted lane area. Returns the time-previous result E against the fact that the vehicle 14 was previously not on the predicted lane area, which is indicated in the table with "(-)", then it is assumed at the current time that I as the overall result E the vehicle 14 also not on the predicted lane area.

As an alternative to this procedure, the conservative result could simply always be set as end result E, ie "+". In other words, an alternative approach is to always adopt a conservative "or" outcome when the vehicle is in use 14 is in the intermediate ranges Z1 or Z2: If the vehicle 14 either by the result E1 or the result E2 in the corresponding respective lane area 12 or 13 is detected, then this is selected as the overall result E. The situation is similar in the second subarea Z2. If the results E1 and E2 match, these results are also set equal to the final result E. In the event that the results E1 and E2 do not correspond in this second subarea Z2, and it has further been determined that the vehicle 14 on the second lane area 13 This is also set as the final result E. On the other hand, it is determined that the vehicle 14 not on the second lane area 13 but on the first lane area 12 Once again, previous overall results E can be taken into account. For example, they say that the vehicle is 14 which was previously located in the first subarea Z1, for example, has not been on the predicted driving range, this is set as the final result E, if so, this is again set as the current final result E.

This procedure, in which the time-consuming overall result E is taken into account, is in 5 again illustrated as a flow chart. Here, first in step S1, a preceding vehicle 14 through environmental sensors 3 of the vehicle 1 recorded, and its distance to the own vehicle 1 determined, for example, as the shortest distance. Furthermore, it is checked in step S2 whether this determined distance is in the near range N, in the first subrange Z1, in the second subrange Z2 or in the far range F. If the distance is close to N, the first lane area is determined in step S3 according to the first determination method 12 calculates and in step S4 the determined vehicle position of the vehicle 14 compared with the first lane area 12. If it is determined in step S5 as the result of this comparison that the vehicle 14 in the first lane area 12 is located, so in step S6, the vehicle 14 otherwise selected in step S7.

If, on the other hand, it is determined in step S2 that the vehicle in front is moving 14 is in the far range F, the second lane area will be in step S8 according to the second determination method 13 calculated and in step S9, the calculated second lane area 13 with the vehicle position of the vehicle 14 compared. If it is then determined in step S10 that the vehicle 14 on the second lane area 13 is located, the vehicle is in step S11 14 otherwise selected in step S12.

If it is determined in step S2 that the vehicle 14 is located in the first partial area Z1, so in step S 14, both the first lane area 12 according to the first determination method as well as the second lane area 13 is calculated according to the second determination method, and in step S15 the vehicle position of the vehicle 14 is calculated with the respective lane areas 12 and 13 compared. Furthermore, it is checked in step S16 whether the results relating to whether the vehicle 14 on the corresponding lane area 12 respectively 13 is, match. If so, and it is determined in step S17 that the vehicle 14 on both lane areas 12 and 13 is located, so will the vehicle 14 otherwise selected in step S18 as the destination, otherwise not in step S19. On the other hand, if it is determined in step S16 that the results do not coincide, it is checked in step S20 if the result according to the first determination method is affirmative, and if so, the vehicle 14 is selected as the target in step S21. Otherwise, a temporally preceding overall result is used in step S22, and if this was positive, the vehicle is in step S23 14 is selected as the destination, and otherwise not in step S24

If it is determined in step S2 that the vehicle 14 is in the second partial area Z2, then in step S25, in turn, both the first lane area 12 as well as the second lane area 13 calculated and in step S26 with the position of the vehicle 14 compared. If the results in step S27 match, in step S28 in the case of positive results, ie the vehicle 14 is located on both the first and the second lane area 12 . 13 so will the vehicle 14 otherwise, in step S29, it is selected as the destination, otherwise not in step S30. On the other hand, if the results do not coincide in step S27, it is checked in step S31 whether the result according to the second determination method with respect to the second lane area 13 was positive, and if so, the vehicle is in step S32 14 selected as the destination. Otherwise, in step S33, a time-previous overall result is again used, and if this was positive, the vehicle is in step S34 14 is selected as the destination and otherwise not in step S35.

By the examples described above can be predicted on a particularly simple and computationally particularly costly way the lane ahead on reliable. However, there are still numerous other possibilities for the lane area to be forecast as a function of the first lane area 12 and / or the second lane area 13 to provide with high accuracy. One of these possibilities will now be described by means of 6 . 7 and 8th described.

6 again shows a schematic representation of a roadway 5 with an own vehicle 1 and an own vehicle 1 preceding vehicle 14 , Furthermore, in turn, the first lane area 12 calculated according to the first determination method and the lane area 13 calculated according to the second determination method are shown, in particular again for a specific time. In this example, it is now possible to continue for a particular lane area 12 . 13 respective reliability values W1, W2 are calculated. For this purpose, the area in the direction of travel in front of the own vehicle 1 and, correspondingly, the first and second lane areas 12, 13 are also divided into a plurality of adjoining predetermined distance areas A1, A2, A3, A4, four in this example. However, it can also be provided near arbitrary more or less distance ranges. The first distance range A1 can, for example, starting from the own vehicle 1 between 0 m and 5 m, the second distance range A2 between 5 m and 15 m, the third distance range A3 between 15 m and 30 m, and the fourth distance range A4 between 30 m and 50 m. These distance ranges are given only as an order of magnitude and can also be defined differently. This also applies to the distance ranges in 7 are shown.

Although the boundary lines between the respective distance ranges A1, A2, A3, A4 are also illustrated in a straight line, these limits can in turn be based, for example, on circular lines around an excellent point of the own vehicle 1 with respect to which these respective distances are measured. For the first lane area 12, corresponding reliability values W1 are then calculated correspondingly for a respective distance range A1, A2, A3, A4. For a relatively fast driving own vehicle 1 , For example, for 70 km / h, the reliability of the first lane area 12 in the first distance range A1 is very good, and in particular given here by way of example with 100%. As distance increases, the reliability of the first lane area decreases 12 Here, by way of example, over 75% in the second distance range A2, 50% in the third Distance range A3 up to 25% in the fourth distance range A4.

Also for the second lane area 13 For each distance range A1, A2, A3, A4, respective reliability values W2 are calculated. By way of example, the reliability for the first distance range A1 is 80%, for the second distance range A2 75%, for the third distance range 70% and for the fourth distance range 50%. Again, the reliability of the second lane area 13 increases with increasing distance to the own vehicle 1 but not as dramatic as this for the first lane area 12 the case is. The lane area to be predicted can now advantageously be an averaging of the first and second lane areas 12 . 13 are calculated for the respective distance ranges A1, A2, A3 and A4 with a weighting corresponding to the respective reliability values W1, W2 assigned to the distance ranges A1, A2, A3, A4. By doing so, to provide the predicted lane area, the overall reliability can be maximized. Finally, the determined position of the vehicle 14 then compared with the predicted traffic lane area calculated in this way, and it is determined on the basis of this comparison whether the vehicle in front is approaching 14 located on the predicted lane area or not.

7 shows again another illustration of the 6 described method, only in this case for a lower speed of the own vehicle 1 for example, 30 km / h, and for another application than the in 6 shown. Furthermore, in this example, in turn, that of the own vehicle 1 busy roadway 5 , one's own vehicle 1 preceding vehicle 14 and the first lane area calculated according to the first determination method 12 and the lane area calculated according to the second determination method 13 shown. Again, for the respective distance ranges A1, A2, A3, A4, the respective reliability values W1 are for the first lane area 12 and the reliability values W2 for the second lane area 13 shown.

Also in this situation is the reliability of the first determination method or the resulting first lane area 12 for the first distance range A1 very high, in particular 100%. However, the reliability falls with increasing distance to the own vehicle 1 due to the lower speed of the own vehicle 1 significantly faster and is in the fourth distance range A4, for example, only 5%. At a speed of 30 km / h, a distance of 30 m is covered within about 3 seconds, so that the probability of changing the odometric data within these 3 seconds is very high, so for this fourth distance range A4, the calculation of the first lane area 12 is very unreliable, while in this area the reliability of the lane recognition is relatively high, at 50%, due to the reliability of the recognition algorithm itself.

Also results for the second lane area 13 another course of the reliability values W2 for the respective distance ranges A1, A2, A3, A4. These other values are not necessarily due to the lower speed of the own vehicle 1, but are to demonstrate the situation dependency of the environment detection. The lower reliability values W2 for the first and second distance ranges A1, A2 can be due, for example, to the fact that, for example, for short distances to the own vehicle 1 of one of the environmental sensors 3, such as the cocoon camera, which is typically a short-range detection of lane markers 4 provides no information regarding the lane markings 4 can be provided. Thus, in the present disclosure, if the cocoon camera can not provide information, for example, if this sensor is out of service, only the lane mark detection of other sensors, such as the windshield camera, is available, but for a range of about 10 meters to about 50 m. The lane area to be predicted can now again be an averaging of the first and second lane area 12 . 13 for the respective distance ranges A1, A2, A3 and A4 are calculated with a weighting corresponding to the respective reliability values W1, W2 associated with the distance ranges A1, A2, A3, A4, and then a target selection based thereon is performed. This procedure is repeated, for example periodically, in respective successive time steps.

8th shows a flowchart illustrating the method just described according to an embodiment of the invention. Here, in step S40, according to the first determination method, the first lane area 12 calculated and according to the second determination method, the second lane area 13 , Furthermore, for a respective defined distance range A1, A2, A3, A4 in step S41 for the respective calculated lane areas 12 . 13 a reliability value W1, W2 calculated. Further, in step S42, for each of the distance ranges A1, A2, A3, A4, the first lane area becomes 12 and the second lane area 13 weighted correspondingly according to their respective reliability values W1, W2. The result of this averaging is provided as the predicted lane area in step S43 and it is checked in step S44 whether the measured position of the preceding vehicle 14 in the predicted lane range or not. If this is the case, then the vehicle ahead 14 in step S 45 is selected as the destination, otherwise not in step S 46. Again, this method is again repeated in successive time steps.

Thus, overall a driver assistance system, a vehicle and a method are provided, which make it possible by the combination possibilities of two different methods for determining a lane area ahead to provide the lane area lying ahead with particularly high reliability and especially adapted to the situation.

QUOTES INCLUDE IN THE DESCRIPTION

This list of the documents listed by the applicant has been generated automatically and is included solely for the better information of the reader. The list is not part of the German patent or utility model application. The DPMA assumes no liability for any errors or omissions.

Cited patent literature

• US 8577552 B1 [0004]
• US 2011/0270466 A1 [0005]

Claims (15)

Driver assistance system (2) for an own vehicle (1) for predicting a lane area ahead of the own vehicle (1) to determine whether an object (14) is in the predicted lane area, the driver assistance system (2) comprising: - at least one environment sensor ( 3) for detecting lane markings (4) of a roadway (5) traveling with the own vehicle (1); - At least one detection means (6) for detecting at least two eigenmotion parameters of the own vehicle (1); and - a control device (7) which is designed, according to a first determination method, to determine a first lane area (12) ahead of the own vehicle (1) in dependence on the at least two proper motion parameters of the own vehicle (1), characterized in that the control device (7) is designed to - according to a second determination method, determine a second lane area (13) ahead of the own vehicle (1) as a function of sensor data of the at least one surroundings sensor (3) which concern the detection of the lane markings (4); and - predict the leading lane area in dependence on the first lane area (12) and / or the second lane area (13). Driver assistance system (2) after Claim 1 characterized in that the control means (7) is adapted to predict the forward lane area depending on the first lane area (12) and the second lane area (13), the forward lane area as a predeterminable averaging of the first lane area (12) and of the second lane area (13). Driver assistance system (2) after Claim 2 , characterized in that the control device (7) is designed to determine at least a first reliability value (W1) for the first lane area (12) and to determine at least one second reliability value (W2) for the second lane area (13), and predeterminable averaging as a function of the at least one first reliability value (W1) and the at least one second reliability value (W2) weighted averaging of the first lane area (12) and the second lane area (13). Driver assistance system (2) according to one of Claims 2 to 3 characterized in that the first and second lane areas (12, 13) are divided into a plurality of contiguous, predetermined pitch areas (A1, A2, A3, A4) with respect to the subject vehicle (1), the control means (7) being arranged therefor is to determine a plurality of first reliability values (W1) for the first lane area (12) and to determine a plurality of second reliability values (W2) for the second lane area (13), wherein a respective one of the plurality of first and second reliability values (W1, W2) is one of is assigned to a plurality of specific distance ranges (A1, A2, A3, A4), and wherein the control device (7) is adapted to the predeterminable averaging for a respective one of the plurality of distance ranges (A1, A2, A3, A4) in the form of one the weighted averaging of the first lane area (12) and of the first and second reliability values (W1, W2) associated with the respective range of distances (A1, A2, A3, A4) second lane area (13) for a respective distance range (A1, A2, A3, A4) to calculate. Driver assistance system (2) according to one of Claims 3 to 4 , characterized in that the control device (7) is adapted to determine the at least one first reliability value (W1) as a function of at least one of the following parameters: - a speed of the own vehicle (1); - navigation data relating to a preceding route; - Detecting an initiation of a predetermined automatic driving maneuver, which includes a lateral offset of the own vehicle (1) with respect to the currently traveled lane (5). Driver assistance system (2) according to one of Claims 3 to 5 , characterized in that the control device (7) is adapted to determine the at least one second reliability value (W2) as a function of at least one of the following parameters: an environmental condition; a sensor state of the at least one environment sensor (3); - a quality of the lane markings (4); whether or not a vehicle having a size larger than a predetermined size is in front of the own vehicle (1). Driver assistance system (2) according to one of the preceding claims, characterized in that the control device (7) is designed to predict the forward lane area in dependence on the first lane area (12) and / or the second lane area (13) the first and / or or second lane area (12, 13) in response to at least one predetermined parameter as the predicted lane area. Driver assistance system (2) after Claim 7 , characterized in that the at least one predetermined parameter represents a determined distance of the object (14) to the own vehicle (1). Driver assistance system (2) according to one of Claims 7 or 8th , characterized in that the at least one predetermined parameter represents a result (E) of a time-prior determination as to whether the object (14) is in the predicted lane area. Driver assistance system (2) according to one of the preceding claims, characterized in that in the direction of travel in front of the own vehicle (1) located Nahbereich (N) is defined, starting from the own vehicle (1) in a predetermined direction up to a predetermined first distance ( dx%) to the own vehicle (1), and wherein a remote area (F) located in front of the own vehicle (1) is defined, which starts from the first distance (dx%) or from a second distance (d + y%) is greater than the first distance (dx%) to the own vehicle (1), extends in the predetermined direction up to a third distance to the own vehicle (1), and wherein the control device (7) is adapted to check whether the object (14) is in the near range (N) or far range (F), and if the object (14) is in the near range (N), providing the first lane area (12) as the predicted lane area, and if the object ( 14) in the far range (F) is to provide the second lane area (13) as the predicted lane area. Driver assistance system (2) after a Claim 10 characterized in that an intermediate region (Z1, Z2) is defined between the near region (N) and the far region (F), and wherein the control device (7) is adapted to check whether the object (14) is in the intermediate region (Z1, Z2), and if the object (14) is located in the intermediate area (Z1, Z2), to determine whether the object (14) is in the first lane area (12) and a result (E1) of the determining as a first result (E1), and to determine whether the object (14) is in the second lane area (13) and to provide a result (E2) of the determination as a second result (E2), the control means (7) is further adapted to compare the first result (E1) with the second result (E2) and, in the case of a match, the first and the second result (E1, E2) as an overall result (E) of determining whether the object (14) is in the predicted lane area, above eitzustellen. Driver assistance system (2) after Claim 11 characterized in that the control means (7) is further adapted, in the event that the first result (E1) does not coincide with the second result (E2), to provide as the overall result (E) that the object (14) in the predicted lane area is located. Driver assistance system (2) after Claim 11 , characterized in that the intermediate region (Z1, Z2) is defined such that it has a first partial region (Z1) and a second partial region (Z2) adjacent to the first partial region (Z1), the first partial region (Z1) continuing to abut the near zone (N) adjoins and the second partial zone (Z2) adjoins the far zone (F), the control device (7) being designed to check whether the object (14) is in the first partial zone (Z1) or in the second zone Subregion (Z2), and in the event that the first result (E1) does not correspond to the second result (2) and, in the case where the object (14) is located in the first subregion (Z1), the control device (Z1) 7) is arranged to: • if the first result (E1) includes the object (14) being in the first lane area (12) to provide the first result (E1) as the overall result (E); If the first result (E1) includes that the object (14) is not located in the first lane area (12), an overall result (E) of a temporally preceding, in particular the second partial area (Z2) determining whether the object (14) is in the predicted lane area to provide as the current total score (E); and - in the event that the object (14) is located in the second partial area (Z2), the control device (7) is designed to, • if the second result (E2) includes the object (14) in the second lane area (13) to provide the second result (E2) as the overall result (E); and if the second result (E2) includes that the object (14) is not located in the second lane area (13), an overall result (E) of a time-related, in particular the first partial area (Z1) determining whether the Object (14) is in the predicted lane area to provide as the overall result (E). Vehicle (1) with a driver assistance system (2) according to one of the preceding claims. A method of predicting a lane area ahead of an own vehicle (1) to determine if an object (14) is in the predicted lane area, wherein: - according to a first determination method, a first lane area (12) ahead of the own vehicle (1) depending on at least two detected proper motion parameters of the own vehicle (1) is determined, characterized in that - according to a second determination method, a second lane area (13) ahead of the own vehicle (1) is determined as a function of detected lane markings; and - the preceding lane area is predicted in dependence on the first lane area (12) and / or the second lane area (13).

Images