Automated following based on the driving behavior of a vehicle in front.

Abstract

The invention relates to a method for the automated following of a front vehicle (2) by an ego vehicle (1) comprising the steps: obtaining vehicle data of the front vehicle (2), determining a lateral driving characteristic of the front vehicle (2) from the vehicle data of the front vehicle and automated following of the front vehicle (2) by the ego vehicle (1) depending on the lateral driving characteristic.

Description

[0001] The present invention relates to a method for the automated following of a leading vehicle by an ego vehicle, for which vehicle data from the leading vehicle is acquired. Furthermore, the present invention relates to a motor vehicle with a data processing unit and an assistance system for carrying out such a method.

[0002] Various input variables can be used for the lateral control of driver assistance systems (also referred to here as assistance systems). Each of these input variables, or combinations thereof, offers specific advantages and disadvantages. It has been shown that the path traveled by the vehicle in front is a particularly suitable source for providing robust and smooth control. A significant disadvantage of this source is that the behavior of the driver assistance system becomes dependent on other road users. The vehicle manufacturer can only offer this path to the customer in a meaningful way if the negative influences of other road users on the system's control are eliminated as effectively as possible.

[0003] For this purpose, a method for operating a lane keeping assistance system is known from publication DE 10 2020 214 162 B3. In this method, an optical direction change signal from the turn signal of the vehicle ahead is detected. The trajectory of the vehicle ahead is taken into account, depending on the optical direction change signal, to ensure the vehicle remains in its own lane.

[0004] Besides the undesirable behavior of following vehicles that are signaling or turning, there are other conditions under which the assistance system should not follow the vehicle in front. These include situations where the vehicle in front is not adhering to the applicable traffic regulations (for example, cutting marked curves sharply or repeatedly changing lanes without signaling) or is weaving excessively within its own lane. The latter is the case, for example, with a driver experiencing microsleep, a novice driver, or a driver under the influence of drugs.

[0005] Furthermore, German patent application DE 10 2018 203 376 A1 discloses a method for detecting and taking into account irregular driving behavior of a target vehicle by an ego vehicle. The irregular driving behavior is determined based on an evaluation of the target vehicle's driving behavior within lane boundaries.

[0006] Furthermore, a method for determining the state of inattention of a driver of a target vehicle in the vicinity of an ego-vehicle is disclosed in German patent DE 10 2020 132 431 A1. The driving behavior of the target vehicle is analyzed based on sensor data.

[0007] Furthermore, German patent application DE 10 2022 212 687 A1 describes an autonomous longitudinal control device for a vehicle to follow a target vehicle ahead. Following or not following depends on a suitability assessment based on an analyzed driving behavior of the target vehicle ahead.

[0008] German patent application DE 10 2019 008 894 A1 discloses a method for detecting unsafe driving behavior of a vehicle ahead, using and / or evaluating data recorded by at least one driver assistance sensor and using a control device trained on the movement patterns of drivers with impaired driving ability. The driving behavior is classified and the vehicle distance is adjusted accordingly.

[0009] German patent application DE 10 2016 007 571 A1 describes a method for operating a vehicle in which the vehicle is automatically moved along a target trajectory, wherein the target trajectory is determined based on a vehicle position derived from acquired environmental data relative to at least one lane marking that defines the vehicle's current lane. The target trajectory is determined based on the currently acquired actual trajectory of a preceding vehicle if no lane marking is acquired or recognized.

[0010] Publication DE 10 2020 214 162 B3 describes a procedure by which it can be decided whether, when the vehicle ahead leaves the lane, the movement behavior and / or trajectory of the vehicle ahead should still be taken into account by the vehicle.

[0011] Publication DE 10 2020 215 926 A1 relates to a method for controlling the speed of a vehicle, in particular in the sense of adaptive distance and speed control, wherein data from sensors is fed to the control system and the sensors detect road users ahead of the vehicle. The sensors record the movement parameters of the road users ahead, and these movement parameters are analyzed for conspicuous movement patterns.

[0012] The object of the present invention is to make automated driving more reliable.

[0013] The problem is solved by the subject matter of the independent patent claims. Advantageous embodiments of the invention are described by the dependent patent claims, the following description, and the figures.

[0014] According to the invention, a method is provided for the automated following of a leading vehicle by an ego vehicle. An ego vehicle is thus intended to follow a leading vehicle semi-automatically or fully automatically. If necessary, the driver must intervene manually during this automated driving if fully automated driving is not taking place. The leading vehicle is usually located directly in front of the ego vehicle, but can also be slightly offset.

[0015] In one step of the inventive method, vehicle data from the front vehicle is acquired. This vehicle data is therefore data relating to the front vehicle. It can be detected by the ego vehicle itself, if necessary, or it can be obtained externally, for example, via radio. In the latter case, it could also be data supplied by external systems, possibly even other vehicles. The vehicle data could, for example, be movement data, type data, or the like from the front vehicle.

[0016] In a further step of the inventive method, the lateral driving characteristics of the front vehicle are determined from the vehicle data of the front vehicle. This determination of the lateral driving characteristics can be carried out by the ego-vehicle itself or by an external unit. Determination by the ego-vehicle is particularly advantageous if the vehicle data of the front vehicle can be acquired directly by the ego-vehicle and subsequently processed further. Otherwise, if the vehicle data of the front vehicle is already acquired by an external unit, it may be advantageous for the lateral driving characteristics of the front vehicle to also be determined by the external unit. In a hybrid implementation, it is also possible that the vehicle data of the front vehicle is acquired by the external unit but further processed by the ego-vehicle for determining the lateral driving characteristics.Conversely, the ego vehicle could also acquire the vehicle data of the vehicle in front, but have it further processed by an external unit to determine the lateral driving characteristics of the vehicle in front. In both cases, a communication system for wireless communication between the ego vehicle and the external unit is advantageous.

[0017] At least one lateral driving characteristic of the vehicle in front is determined from the vehicle data. If necessary, several different types of lateral driving characteristics are also determined with respect to the vehicle in front. Different types of lateral driving characteristics are listed below.

[0018] In a further step of the inventive method, the ego vehicle automatically follows the vehicle ahead, depending on its lateral driving characteristics. This automated following can be carried out with the aid of a driver assistance system in the ego vehicle. The manner in which the automated following is performed depends on the determined lateral driving characteristic(s). This dependency can consist of the fact that the manner of automated following is influenced by the lateral driving characteristic. For example, if the vehicle ahead has "poor" lateral driving characteristics (e.g., weaving), the following can only be carried out roughly, whereas if the vehicle ahead has good lateral driving characteristics, it can be carried out very precisely.In extreme cases, the dependence of automated following on the lateral driving characteristics of the vehicle in front may mean that the vehicle in front is followed at all, or not.

[0019] The provided method allows the system to intelligently check whether the vehicle ahead should be considered a reference object or a control object. In other words, it can decide whether the ego vehicle should even follow the vehicle ahead, especially if the vehicle ahead exhibits unusual lateral driving characteristics.

[0020] Automated following can be achieved in particular through a distance control system or a lane keeping system, each of which is a subsystem of a driver assistance system in the self-driving vehicle. Specifically, the lane keeping assist system is either a lane keeping assist or an active lane keeping assist with steering support. In its default setting, the lane keeping assist system warns the driver, for example, if the vehicle in front exhibits poor lateral stability.

[0021] Specifically, the vehicle is currently in motion and is traveling along a lane of a roadway. Specifically, the vehicle is traveling on a country road, a street, a motorway, or a highway.

[0022] If necessary, the vehicle data of the vehicle in front is continuously acquired, provided the vehicle in front is detected at all. In this case, the determination of the lateral driving characteristics of the vehicle in front can also be carried out continuously.

[0023] In one embodiment, the vehicle data includes images of the vehicle ahead captured by a camera on the ego vehicle. The ego vehicle thus possesses a camera or camera system that records the vehicle ahead in order to derive its vehicle data from the corresponding recording data. Generally, the vehicle data can be generated from detection data acquired or detected by a sensor system of the ego vehicle from the vehicle ahead. In addition to the camera, other sensor systems of the ego vehicle can also be used to acquire the corresponding detection data. For example, radar or LiDAR systems can also be employed in this way.

[0024] According to another embodiment, the ego-vehicle acquires environmental data and / or swarm data, and the automated following of the vehicle in front is also dependent on this environmental or swarm data. In addition to the vehicle data directly related to the vehicle in front, data from the surrounding environment or data from a swarm of vehicles is also acquired. This data can be acquired internally or obtained externally. For example, the environmental or swarm data can be provided via the internet. The automated following by the ego-vehicle can therefore be based on additional input data, thus further improving the quality of automated or autonomous driving.

[0025] In a preferred embodiment, the lateral driving characteristic relates to lateral acceleration, steering behavior, behavior towards lane boundaries, or behavior towards a swarm trajectory. Behavior describes the temporal dependence of a physical quantity. Therefore, different types of lateral driving characteristics can be utilized. Optionally, several types of lateral driving characteristics are used to optimize automated following. For example, the lateral acceleration of the vehicle in front can be monitored to decide whether or not to follow the vehicle in front, and if so, how.

[0026] Furthermore, the lateral driving characteristic can also be due to the steering behavior of the vehicle in front. For example, the driver in front might steer abruptly or oversteer in curves. In this case, it may be advantageous not to follow the vehicle in front, or, if following, to smooth out the steering input.

[0027] The lateral driving characteristic can also refer to behavior in relation to lane boundaries. Such lane boundaries could be road markings or physical objects that delineate a particular lane. If, for example, the vehicle in front drives too close to such markings or objects, this fact could be the basis for the decision not to follow the vehicle in front.

[0028] Another lateral driving property could be behavior with respect to (at least) one swarm trajectory. For example, the ego vehicle could have a swarm trajectory available for the currently traveled road. Based on this, the ego vehicle can decide how closely the vehicle in front follows this swarm trajectory, or rather, how large and what kind of deviations the trajectory of the vehicle in front deviates from the swarm trajectory.

[0029] Optionally, several lateral driving characteristics of the vehicle in front can be evaluated. For example, the ego vehicle can monitor the lateral acceleration and the behavior towards lane markings of the vehicle in front. Other groups of the aforementioned lateral driving characteristics, or even additional lateral driving characteristics, can also be used to decide whether or not to follow the vehicle in front, and if so, how.

[0030] The lateral driving characteristic is evaluated by assigning it a value, and based on this value, a decision is made as to whether the ego vehicle automatically follows the vehicle in front or not. Thus, a value (score) is assigned to the detected lateral driving characteristic(s) of the vehicle in front. Based on this value, a decision regarding whether to follow the vehicle in front can be made more easily. This can be implemented, for example, by comparing threshold values.

[0031] The lateral driving characteristic is determined cyclically and evaluated with individual values. These values ​​are summed within a time window to form a total score, and this total score determines whether the autonomous vehicle will automatically follow the vehicle in front. The values ​​for the lateral driving characteristic can be positive or negative. Preferably, they are positive if the lateral driving characteristic of the vehicle in front is desirable. Otherwise, if the lateral driving characteristic is undesirable, the corresponding value for the lateral driving characteristic can be negative. Summing the values ​​into a total score occurs within a time window, which is typically limited. For example, the time window begins with the detection of the vehicle in front that could be followed. The end of the time window usually represents the current time.If there are hardly any negative ratings, the total score can be correspondingly positive, resulting in the vehicle following the lead vehicle. Furthermore, the absence of negative ratings can also be rewarded with actual positive ratings, so that, for example, a positive total score is generated even if no negative ratings are present. The total score can then be compared to one or more threshold values ​​to determine whether the ego vehicle follows the lead vehicle. Preferably, a suitable hysteresis is used.

[0032] In a specific embodiment, the ego vehicle can be configured to automatically follow the vehicle in front only when the sum of the values ​​exceeds a first threshold, and to terminate the automated following only when the sum of the values ​​falls below a second threshold. This allows the aforementioned hysteresis to be implemented. Hysteresis has the advantage that minor deviations above or below a threshold do not trigger a change of decision. This reduces the frequency of such changes.

[0033] According to another embodiment, the lateral driving characteristic is evaluated depending on the presence of a lane boundary, or the decision as to whether the ego vehicle automatically follows the vehicle in front is made depending on the presence of a lane boundary. Thus, both the evaluation itself and the decision-making process can be made dependent on the presence of a lane boundary. For example, the values ​​are higher when a lane boundary is present and lower when no lane boundary is present. This allows for stricter decision criteria when lane boundary lines are detected. Otherwise, the evaluation can be less stringent. The threshold(s) used for the decision regarding vehicle following can also depend on the presence of, for example, lane boundary lines.The lane markings can be made dependent. For example, an assessment can be carried out in a different way, or the scoring factor can be compared with higher or lower threshold values.

[0034] As described above, lateral driving characteristics can refer to lateral acceleration, steering behavior, behavior in relation to lane markings, or behavior in relation to a swarm trajectory. These types of lateral driving characteristics can be specifically determined as follows: In one embodiment, steering behavior is determined based on the number of changes of direction relative to a reference value. For example, the steering behavior corresponds to smooth driving if the number of changes of direction of the vehicle in front is below the specified reference value. In this case, it is advantageous to follow the vehicle in front.

[0035] In another embodiment, the behavior towards lane markings is determined based on the frequency of oscillation between two lane markings. For example, if the oscillation frequency of the vehicle in front between the left and right lane markings is very high, it is advantageous not to follow the vehicle in front.

[0036] In a further embodiment, the behavior towards lane markings is determined based on a lane change without the use of the turn signal. If, for example, the vehicle in front crosses a lane marking without using its turn signal, this indicates dangerous driving behavior on the part of the vehicle in front. For this reason, it may be advantageous not to follow the vehicle in front.

[0037] In another embodiment, the behavior towards lane markings is determined based on the number of times a vehicle crosses them. For example, if the vehicle in front frequently crosses lane markings, it might be advisable not to follow it. Conversely, crossing markings is rarely a reason not to follow the vehicle in front.

[0038] According to another embodiment, the behavior with respect to lane markings is determined based on the extent of any crossing of the markings. Minor crossings of markings may be considered non-critical. However, extensive crossings of markings can be very critical.

[0039] According to another embodiment, the behavior towards lane boundaries is determined based on the distance to other road users. Other road users can also be interpreted as lane boundaries. The lateral distance of the vehicle in front to other road users can thus indicate a lateral driving characteristic. If, for example, the vehicle in front maintains only a small lateral distance to overtaken or parked vehicles, it is certainly advantageous not to follow this vehicle directly.

[0040] In another embodiment, the behavior relative to the swarm trajectory is determined based on a deviation measure. For example, if the vehicle in front deviates significantly from a swarm trajectory, this indicates unusual driving behavior. This may be a reason not to follow the vehicle in front.

[0041] According to a further embodiment, in addition to the lateral driving characteristic, at least one further lateral driving characteristic of the vehicle in front is determined, and the automated following is also dependent on this at least one further lateral driving characteristic. Thus, at least two lateral driving characteristics of the vehicle in front are considered to decide whether or not to follow it. These lateral driving characteristics can be of the types mentioned above, such as lateral acceleration, steering behavior, behavior towards lane boundaries, or behavior in relation to a swarm trajectory. Specifically, these lateral driving characteristics can be determined as described above. The more lateral driving characteristics are used for the decision, the higher the quality of the decision.

[0042] According to another embodiment, the automated following of the vehicle in front is also dependent on the longitudinal acceleration and / or vehicle type of the vehicle in front and / or a violation of a specified traffic regulation and / or a deviation from an average swarm speed. This means that, for example, the acceleration behavior of the vehicle in front is also taken into account when deciding whether to follow automatically. If its acceleration is too high, too low, or too jerky, the system can decide not to follow the vehicle in front. The vehicle type of the vehicle in front can also be considered. For example, it may be advantageous for a passenger car not to follow a motorcycle or a truck.Violating a valid traffic regulation can also be a reason for the ego vehicle to decide not to follow the vehicle in front. Such violations might include exceeding speed limits or driving the wrong way down one-way streets, etc. A deviation from the average swarm speed can also be a reason to not follow a vehicle in front. For example, if the vehicle in front is traveling significantly faster than the usual swarm speed, it is advisable not to follow it. Several of the above criteria can also be used to decide whether the ego vehicle should follow the vehicle in front or not.

[0043] According to the invention, an assistance system is also provided to support the driver of a motor vehicle. The assistance system is configured and designed to carry out the method described above. It comprises a device for acquiring vehicle data from the vehicle in front, a device for determining the lateral driving characteristics of the vehicle in front from the vehicle data of the vehicle in front, and at least one assistance function for the ego vehicle to automatically follow the vehicle in front depending on the lateral driving characteristics. Such an assistance system is, for example, a distance assistant or adaptive cruise control. The assistance system can also be implemented as a lane keeping assistant.

[0044] Furthermore, according to the invention, a motor vehicle is provided which has an assistance system mentioned above, which is designed to carry out the method described above.

[0045] For use cases or application situations that may arise during the procedure and are not explicitly described here, it may be provided that, according to the procedure, an error message and / or a request for user feedback is issued and / or a default setting and / or a predetermined initial state is set.

[0046] The invention also includes a control device or assistance system for the motor vehicle. The control device or assistance system can comprise a data processing device or a processor circuit configured to perform an embodiment of the method according to the invention. For this purpose, the processor circuit can comprise at least one microprocessor and / or at least one microcontroller and / or at least one FPGA (Field Programmable Gate Array) and / or at least one DSP (Digital Signal Processor). In particular, a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), or an NPU (Neural Processing Unit) can be used as the microprocessor. Furthermore, the processor circuit can comprise program code configured to perform the embodiment of the method according to the invention when executed by the processor circuit.The program code can be stored in a data memory of the processor device. The processor device can be based, for example, on at least one circuit board and / or on at least one SoC (System on Chip).

[0047] The invention also includes further developments of the motor vehicle, control device, or assistance system according to the invention, which have features already described in connection with further developments of the method according to the invention. For this reason, the corresponding further developments of the motor vehicle or control device according to the invention are not described again here.

[0048] The motor vehicle according to the invention is preferably designed as a motor vehicle, in particular as a passenger car or truck, or as a passenger bus or motorcycle.

[0049] As a further solution, the invention also includes a computer-readable storage medium comprising program code which, when executed by a computer or a computer network, causes it to execute an embodiment of the method according to the invention. The storage medium can be provided at least partially as a non-volatile data storage medium (e.g., as flash memory and / or as an SSD - solid state drive) and / or at least partially as a volatile data storage medium (e.g., as RAM - random access memory). The storage medium can be located within the computer or computer network. However, the storage medium can also be operated, for example, as an app store server and / or cloud server on the internet. The computer or computer network can provide a processor circuit with, for example, at least one microprocessor.The program code can be provided as binary code, assembly code, source code in a programming language (e.g., C), or a program script (e.g., Python). Alternatively, the computer-readable storage medium can be implemented as a signal containing computer-readable data, such as a time-varying voltage signal or a radio signal.

[0050] The invention also includes combinations of the features of the described embodiments. The invention therefore also includes realizations that each exhibit a combination of the features of several of the described embodiments, provided that the embodiments have not been described as mutually exclusive.

[0051] The following are exemplary embodiments of the invention described. This is illustrated by: Fig. 1 a driving situation in which an ego vehicle follows a vehicle in front; and Fig. 2 a schematic flowchart of an embodiment of a method according to the invention.

[0052] The exemplary embodiments described below are preferred embodiments of the invention. In these exemplary embodiments, the described components each represent individual features of the invention, which can be considered independently of one another and each further develops the invention independently. Therefore, the disclosure is intended to include combinations of features of the embodiments other than those shown. Furthermore, the described embodiments can also be supplemented by further features of the invention already described.

[0053] In the figures, identical reference symbols denote functionally equivalent elements.

[0054] In the embodiment of Fig. Figure 1 schematically depicts a driving situation in which a vehicle 2 is driving in front of an ego-vehicle 1. The roadway is bounded by two lane markings 3 and 4. The ego-vehicle 1 has an assistance system 5, which is, for example, an adaptive cruise control system. The ego-vehicle 1 also has a sensor system 6, which includes, for example, a camera.

[0055] The sensor system 6 acquires detection data, for example, from the vehicle 2 in front and the drivable boundary lines 3, 4. The detection data relating to the vehicle 2 in front can be referred to as vehicle data or used to generate vehicle data. For example, the assistance system 5 of the ego vehicle 1 calculates distances 7, 8 of the vehicle 2 in front to the drivable boundary lines 3, 4 from the detection data. In addition, the assistance system 5 could also, for example, determine a lateral acceleration 9 of the vehicle 2 in front from the detection data.

[0056] The determined data, such as the distances 7, 8 and / or the lateral acceleration 9 or their temporal profiles, represent the lateral driving characteristics of the front vehicle 2. The ego vehicle 1 can determine these or other lateral driving characteristics of the front vehicle 2 in order to decide whether the ego vehicle 1 or its assistance system 5 should follow the front vehicle 2 or not.

[0057] Besides the undesirable behavior of following vehicles that are flashing or turning, there are other conditions under which the assistance system should not follow the vehicle in front. These include, for example, situations where the vehicle in front does not adhere to the applicable traffic regulations (e.g., cutting marked curves sharply or repeatedly changing lanes without signaling), or where it weaves significantly within its own lane (e.g., due to a driver experiencing microsleep, a novice driver, or a driver under the influence of drugs).

[0058] Identifying these aspects presents a major challenge and is addressed by the present invention.

[0059] The schematic flowchart of Fig. Figure 2 shows an embodiment of a method according to the invention. This comprises three levels: an input level 10, an execution level 11 and an output level 12.

[0060] Input level 10 provides input data for executing the procedure, for example, in an assistance system of the ego vehicle. This input data includes, for example, environmental data 13, swarm data 14, and information 15 about the object or vehicle in front. The environmental data relates, for example, to lane boundaries such as lane markings, objects at the edge of the lane, and possibly also objects on the lane. The ego vehicle 1 can acquire this environmental data itself or obtain it from an external source.

[0061] The swarm data 14 can, for example, relate to swarm trajectories, swarm speeds, and the like. The Ego vehicle receives this swarm data, for example, via wireless communication.

[0062] The Ego vehicle typically obtains information 15 about the object in front of it using its own sensor system. This information can include, for example, distances to lane markings, lateral accelerations, vehicle type data, and much more. At least some of this information can also be wirelessly transmitted to the Ego vehicle from external sources.

[0063] In implementation level 11, the actual procedure, an evaluation 16, is carried out, in which the behavior of the vehicle in front is determined, classified, and / or evaluated. For example, the following factors of the vehicle in front are considered: driving behavior (lateral accelerations, longitudinal accelerations, steering behavior), behavior towards lane boundaries, and behavior towards swarm trajectories. If necessary, a distinction is made as to whether lane boundaries can be taken into account when following the vehicle in front.

[0064] In output level 12, for example, a decision 17 can be made as to whether the front object is suitable as a follow object for a driver assistance system or not.

[0065] In a specific implementation example, individual behavioral aspects or other facts of the vehicle in front are evaluated to determine its suitability for automated following. For example, individual aspects are rated positively or negatively using points or percentages. Most of the following criteria relate to the lateral driving characteristics of the vehicle in front, which can arise when road boundaries such as road markings, static objects, and the like are present.

[0066] For example, positive points or scores can be awarded. These are based on a time criterion, specifically whether the vehicle in front has received a negative rating. For instance, if the vehicle in front does not receive a negative rating for any lateral driving characteristic for an extended period, a positive rating can be given. Similarly, a positive rating can be given if the vehicle in front drives "as if in lanes" or consistently stays in the center of the lane or parallel to a marking for a certain period.

[0067] Negative ratings can be issued, for example, for an unexplained, erratic driving behavior between two lane markings. An exception would be obstacles in the driving lane. A negative rating can also be issued for an object that changes lanes without using its turn signal. Such monitoring can occur even before the automated object is being followed automatically.

[0068] Furthermore, a negative rating can be assigned if the object follows a different trajectory than a swarm trajectory. Similarly, high lateral acceleration of the object or the vehicle in front could lead to a negative rating. High lateral accelerations typically occur when a driver corners aggressively. In addition to these lateral driving characteristics, longitudinal driving characteristics such as rapid acceleration or abrupt braking can also be negatively rated.

[0069] Another factor that can lead to negative ratings regarding lateral driving characteristics is the number of times a vehicle crosses a lane marking. For example, if a vehicle repeatedly crosses lane markings and briefly leaves the lane, this would be rated negatively. Furthermore, the extent to which a lane marking is crossed can also be negatively assessed. A smaller crossing will result in a lesser negative rating than a larger one. The type of vehicle in front can also be considered. For example, sports cars, trucks, and motorcycles can be negatively rated in terms of automated following. Another negative factor could be the fact that the vehicle in front comes very close to other road users. For example, the vehicle in front might drive very close to parked vehicles or tailgate, such as when overtaking.

[0070] Furthermore, the vehicle in front can receive a negative rating if it violates traffic regulations, for example by exceeding speed limits or crossing solid lines. A negative rating could also be given if the vehicle travels faster than the average swarm speed.

[0071] In the present example, where a vehicle in front is on a roadway with boundary lines, an assessment can now be made f beg determined and updated according to the following formula. fbeg=fbeg+∑Spos−∑Sneg

[0072] The above-mentioned criteria can, for example, be assessed within fixed time windows (e.g., five seconds or ten seconds) and assigned corresponding ratings. pos or S neg lead.

[0073] In another embodiment, the vehicle in front travels on a roadway without lane markings. In this case, too, an assessment f ohne determined and updated according to the following formula. fohne=fohne+∑Spos−∑Sneg

[0074] Most of the above criteria can also be checked in this case. Exceptions would be the oscillating driving behavior between lane markings, lane changes without using the turn signal, and the number of times lane markings are crossed.

[0075] Finally, the respective determined or updated assessment can be used to... beg or f ohne with a threshold value s oben The assessment will be compared. If the assessment exceeds the threshold, the object should be considered valid for follow-up. If the overall assessment is f beg or f ohne again below a second threshold s untenIf the threshold is exceeded, the object should no longer be valid for following. In principle, however, a single threshold could also be used, which is either undercut or exceeded.

[0076] Overall, the examples show how the driving behavior of a vehicle in front can be assessed with regard to automated following. Reference symbol list 1 Ego vehicle 2 Front vehicle 3 Lane boundary line 4 Lane boundary line 5 Assistance systems 6 Sensor system 7 distance 8 distance 9 Lateral acceleration 10 Input level 11 Implementation level 12 Output level 13 Environmental data 14 swarm data 15 pieces of information 16 reviews 17 Decision

Claims

[1] Method for automated following of a front vehicle (2) by an ego vehicle (1) comprising the steps: - Obtaining vehicle data from the vehicle in front (2), - Determining a lateral driving characteristic of the front vehicle (2) from the vehicle data of the front vehicle and - automated following of the front vehicle (2) by the ego vehicle (1) depending on the lateral driving property, characterized by , that - the lateral driving characteristic is determined cyclically and evaluated with respective values, the values ​​are added up to a total value within a time window, and on the basis of the total value a decision is made as to whether the ego vehicle (1) automatically follows the front vehicle (2) or not. [2] Method according to claim 1, characterized by, that the vehicle data are determined on the basis of detection data detected by a sensor system (6) of the ego vehicle (1) from the front vehicle (2), in particular recordings of the front vehicle (2) by a camera of the ego vehicle (1). [3] Method according to any one of the preceding claims, characterized by , that the ego vehicle (1) acquires environmental data (13) and / or swarm data (14) and that the automated following of the front vehicle (2) also depends on the environmental data (13) or swarm data (14). [4] Method according to any one of the preceding claims, characterized by , that the lateral driving characteristic refers to lateral acceleration, steering behavior, behavior towards road boundaries or behavior towards a swarm trajectory. [5] Method according to any one of the preceding claims, characterized by, that the ego vehicle (1) automatically follows the front vehicle (2) only if the sum value exceeds a first threshold, and the automated following is aborted only if the sum value falls below a second threshold. [6] Method according to any one of the preceding claims, characterized by , that the lateral driving characteristic is evaluated depending on the presence of a lane boundary (3, 4), or the decision (17) whether the ego vehicle (1) automatically follows the front vehicle (2) or not is made depending on the presence of a lane boundary (3, 4). [7] Method according to any one of claims 4 to 6, characterized by , that - the steering behavior is determined based on a number of changes in direction compared to a reference measure, - the behavior towards lane boundaries (3, 4) is determined based on a frequency of oscillation between two lane markings, - the behavior towards lane boundaries (3, 4) is determined on the basis of a lane change without use of the turn signal, - the behavior towards road boundaries (3, 4) is determined on the basis of a number of marking crossings, - the behavior towards road boundaries (3, 4) is determined on the basis of the extent of a marking violation, - the behavior towards lane boundaries (3, 4) is determined on the basis of a distance to other road users, or - the behavior relative to the swarm trajectory is determined based on a deviation measure from the swarm trajectory. [8] Method according to any one of the preceding claims, characterized by , that in addition to the lateral driving characteristic, at least one further lateral driving characteristic of the front vehicle (2) is determined and that automated following also takes place depending on the at least one further lateral driving characteristic. [9] Method according to any one of the preceding claims, characterized by , that the automated following of the vehicle in front (2) also depends on - a longitudinal acceleration and / or - of a vehicle type of the vehicle in front (2) and / or - a violation of a prescribed road traffic regulation and / or - a deviation from the average swarm speed occurs. [10] Assistance system (5) for supporting a driver of a motor vehicle (FZ), wherein the assistance system (5) is set up and designed to carry out the method according to one of the preceding claims, with - a device for obtaining vehicle data from the vehicle in front (2), - a device for determining a lateral driving characteristic of the front vehicle (2) from the vehicle data of the front vehicle (2), and - at least one assistance function for the automated following of the vehicle in front (2) by the ego vehicle (1) depending on the lateral driving characteristic. [11] motor vehicle characterized by an assistance system (5) according to claim 10, which is configured to carry out a method according to any one of claims 1 to 9.

Images