Lateral guidance of a vehicle using environmental data collected from other vehicles

Abstract

Method for laterally guiding a vehicle (10), comprising: - Recording environmental data of a vehicle (10) when driving along a route, - Obtaining stored environmental data that was recorded by a plurality of other vehicles (10) that are not currently traveling on the route while traveling on the route; - Plausibility check of the stored environmental data based on the recorded environmental data; - Carrying out a lateral guidance of the vehicle (10) based on the plausibility-checked stored environmental data.

Description

[0001] The invention relates to a method and an arrangement for transversely guiding a vehicle, in particular a motor vehicle, such as a passenger car or a truck.

[0002] Modern vehicles, and especially motor vehicles, utilize various driver assistance systems. These often enable autonomous driver control of vehicle movements and / or autonomous driver interventions in vehicle operation, for example, to adjust speed or steering angle. One example is a so-called lane departure warning system. In a conventional manner, the course of the road (or lane) ahead of the vehicle is detected by sensors. The system then ensures that the vehicle does not unintentionally depart from this lane, for example, by autonomous driver countersteering upon reaching a lane boundary.

[0003] To provide such functions, the vehicle's surroundings are recorded using sensors. This process generates so-called environmental data. This environmental data contains analyzable or analyzed information about the environment and, in particular, about predetermined environmental properties. For example, it can indicate the course and / or coordinates of lane boundaries along a section of road ahead. One option for capturing environmental data is camera sensors, which can determine the desired environmental properties by analyzing the captured camera images.

[0004] A typical application area for the driver assistance functions described here and / or the driver-autonomous control of a vehicle based on environmental data is lateral guidance of the vehicle. This can be understood, for example, to mean that the vehicle is to be held in position and / or guided in a desired manner in the lateral direction (which generally runs horizontally and transversely to a vehicle's longitudinal axis), in particular autonomously by the driver. For example, a permissible movement corridor in the lateral direction can be specified that corresponds to the width of the roadway. As part of the lateral guidance, care can be taken to ensure that this (virtual) movement corridor is not exceeded. If this is threatened, a driver-autonomous steering intervention can take place as part of the lateral guidance. Solutions and in particular control units and furthermore in particular controllers that enable such lateral guidance are available on the market.

[0005] However, sensor-based environmental data acquisition may not always be reliable in certain situations. For example, the sensor may fail, be dirty, or malfunction in other ways. Furthermore, the environmental characteristics to be captured may not always be recognizable, for example, if the road surface is dirty or other environmental conditions exist that cannot be interpreted, or at least not correctly, based on the sensor data.

[0006] There is therefore a need to improve the lateral guidance of vehicles, especially with regard to the not always reliable sensory detection of the environment.

[0007] DE 10 2014 216 018 A1 discloses a solution in which sensor data from a vehicle's environmental sensors are checked for plausibility against each other or against sensor data from other vehicles. This teaching can be considered obvious, but does not disclose that environmental data from vehicles not currently traveling on the route are used, and that the vehicle's lateral guidance is carried out based on these previously stored environmental data, provided they are checked for plausibility.

[0008] DE 10 2013 208 521 A1 discloses a solution for collectively learning a high-precision road model in which perception data is collected from a plurality of vehicles.

[0009] DE 10 2017 207 097 A1 discloses the autonomous control of a vehicle with the help of environmental information from environmental sensors and with environmental information from a digital map.

[0010] DE 10 2016 220 647 A1 discloses a solution in which an actual road surface configuration recorded by a camera is compared with a target road surface configuration, a difference in road surface configuration is determined if necessary and this difference is displayed in at least one display field in a vehicle.

[0011] WO 2017 / 012743 A1 discloses a solution for checking the plausibility of an activation decision for safety devices of a vehicle, in which a regulatory standardized feature of a collision object is detected by means of the vehicle's environmental sensors and the activation decision is released depending on the detected feature.

[0012] This object is achieved by a method and an arrangement according to the appended independent claims. Advantageous further developments are specified in the dependent claims. It is understood that all of the introductory features and embodiments can also be provided in or apply to the present solution.

[0013] In principle, the solution according to the invention (i.e. the method according to the invention and the arrangement according to the invention) does not limit itself to sensor-captured data for lateral guidance. Instead, data from other vehicles that have already traveled the same route in the past should also be taken into account. In particular, so-called swarm data can be used, which contains and stores data from a large number of vehicles over a longer period of time. This stored data (primarily environmental data) serves as a type of reference, as it indicates the form in which the environment along a current route has already been captured by other vehicles. In this respect, the vehicle's own sensor data and, in particular, environmental data can be compared with the stored environmental data.

[0014] In particular, the stored data can be checked for plausibility, or in other words, verified, using the system's own recorded sensor data. It can then be generally specified that the already stored environmental data, if verified, will be used in addition to or alternatively to the environmental data recorded by the vehicle for the (driver-autonomous) lateral guidance of the vehicle. If the plausibility check fails and, for example, the stored environmental data differs significantly from the environmental data recorded by the sensors, these stored environmental data can be omitted for the (driver-autonomous) lateral guidance. Instead, the vehicle's own sensor data can be used, e.g., to react to short-term environmental changes.

[0015] One advantage is that the multitude of already recorded environmental data, which are expected to have a high and / or already verified accuracy, can be used by default for lateral guidance of the vehicle (if plausible). This data can be prioritized over the potentially error-prone and less accurate sensor detections of the own vehicle. On the other hand, it is possible to react to short-term changes in the vehicle's environment that have not yet been detected by vehicles that have previously traveled the route, as it is then possible to switch to the environmental data recorded by the vehicle currently traveling the route. Such a discrepancy between the stored and recorded environmental data can lead to a failure of the plausibility check, whereupon the own environmental data recorded by the vehicle is then preferentially selected by default.

[0016] Overall, a solution is provided in which the more accurate or less error-prone environmental data for lateral guidance are automatically selected with an increased probability, which increases the operational safety of the vehicle.

[0017] In detail, a method for laterally guiding a vehicle is proposed, comprising: - Recording environmental data of a vehicle when driving along a route, - Obtaining stored environmental data collected by a plurality of other vehicles not currently traveling on the route while traveling on the route; - Plausibility check of the stored environmental data based on the recorded environmental data; - Carrying out lateral guidance of the vehicle (preferably exclusively) based on (or using) the plausibility-checked (stored) environmental data.

[0018] The environmental data can, in particular, relate to data relating to the road environment and, in particular, to a road section ahead. They can specify and / or quantify environmental properties explained below. The detection is advantageously carried out autonomously by the driver, e.g., using detection sensors. In particular, a camera, an ultrasonic sensor, a lidar sensor, or the like can be used as detection sensors.

[0019] Any environmental data described herein may be provided with location information. This allows inferences to be made about the location where the corresponding environmental information or data was acquired. The data may be digital data records and / or stored in electronic or digital storage devices.

[0020] Environmental data can be output data from sensors for environmental detection or can be determined based on such output data (or output signals). For example, the environmental data can be data on predetermined environmental properties, whereby these environmental properties are determined from image data (as output data) of a camera sensor. This determination can generally be performed by a control unit or control device of the vehicle, as can the storage of the detected environmental data. In principle, any method steps or method measures described herein can be performed by a control device of the vehicle, as will be explained in more detail below.

[0021] The stored environmental data can be stored in a storage device of the vehicle. For example, this can be a navigation memory or, in other words, the memory of a navigation device. Additionally or alternatively, the environmental data can be stored in a storage device external to the vehicle, for example on a server (in particular a cloud server). The vehicle can then access this server selectively or as needed and request the environmental data relevant to a currently traveled, planned, or probable route. A communication connection to the vehicle-external storage device and in particular to the server can generally be non-wired. In particular, it can be a cellular connection or an internet connection. At least some of the environmental data stored external to the vehicle can be temporarily stored in the vehicle.This part may be the environmental data relating to a currently travelled, planned or probable route.

[0022] The stored environmental data may already have been at least partially pre-evaluated. For example, it may be an average value for a predetermined environmental property, determined from all stored environmental data transmitted by individual vehicles. Such an evaluation of expected values and / or average values for predetermined environmental properties based on the total stored or, in other words, collected or accumulated environmental data can, in principle, also be performed in the vehicle itself. An environmental property may be the coordinates of predetermined environmental features, such as a center line or lane boundary.

[0023] Raw data and / or previously evaluated data can therefore be stored as environmental data.

[0024] The vehicles that recorded and delivered the stored environmental data cannot currently travel the route. Rather, it may be a vehicle fleet or vehicle population that has already traveled the route in the past. This can occur over a longer period of time, particularly several days, weeks, or months. This creates a collection of environmental data from a large number of vehicles that has been recorded over a longer period of time and serves as a kind of knowledge base or knowledge database for environmental detection. This differs from solutions in which sensor-recorded data is only exchanged between vehicles that are currently in the same environment and traveling a common route. Such real-time data exchange presupposes that another vehicle is actually present in the area.If this is not the case, no improvement in driving safety can be achieved. Furthermore, the problem may arise that this additional vehicle suffers from the same environmental sensor detection problems as the own vehicle, for example, due to heavy snowfall or a dirty road. Therefore, it cannot always be guaranteed that, even if another vehicle is in the vicinity, the environmental data collected by this vehicle will be of better quality than the environmental data collected by the own vehicle.

[0025] According to the invention, however, it is also possible, for example, to take into account, in addition to stored environmental data, environmental data from other vehicles that are also currently traveling the same route.

[0026] Checking the plausibility of the stored environmental data based on the acquired environmental data may include comparing these data with each other. In particular, at least one environmental property of this environmental data may be compared with each other.

[0027] The plural use of environmental data herein does not necessarily mean that multiple environmental properties must be recorded. It is also possible to record only one environmental property, but this is recorded continuously depending on the location and / or along a route ahead. Since this location-dependent environmental property is updated multiple times while traveling along the route, a corresponding plurality of individual environmental data is also obtained when traveling along the route (e.g., data on an environmental property present at that location for each location or route section ahead).

[0028] In particular, during plausibility checks, a discrepancy between the stored environmental data and the recorded environmental data can be determined. The greater the discrepancy, the more likely the stored environmental data will be deemed implausible. In particular, a maximum permissible discrepancy threshold can be defined that may not be exceeded for plausibility checks. As explained in more detail below, comparisons and / or discrepancies can be made based on quantified variables that are described in the environmental data but are described by them, which can in particular be the environmental properties already mentioned.

[0029] The lateral guidance of the vehicle can generally be carried out autonomously by the driver. In particular, the aforementioned guidance can be carried out within a permissible movement corridor, including any driver-autonomous steering interventions. Known control algorithms can be used to determine an impermissible lateral movement of the vehicle based on current movement variables and, if necessary, to initiate (driver-autonomous) countermeasures based on this. Implementing lateral guidance based on the plausibility-checked environmental data (or, in the following case, based on the environmental data acquired by the vehicle) can include defining a permissible movement corridor and / or at least one limit in the lateral direction that must not be exceeded based on the environmental data.For example, lane markings or lane boundaries can be determined based on the surrounding data, and these can define a maximum permissible lateral position for the vehicle. Accordingly, as part of the lateral guidance, it can be monitored whether the vehicle is in danger of exceeding this limit and can then be counter-steered, for example, autonomously by the driver.

[0030] A further development provides that the stored environmental data is swarm data. Swarm data can be understood as data recorded by a large number of vehicles (e.g. more than 10 or more than 100) over a period of several days (e.g. at least 10, at least 30 or at least 365) or over several journeys along the route. The large number of these vehicles can act independently of one another, but can nevertheless be collectively referred to as a fleet or swarm. The environmental data individually recorded by the vehicles in the fleet or swarm can be collectively referred to as swarm data and can preferably be summarized accordingly and / or stored together, for example in a central database. A common feature of the vehicles is that they have traveled the same route, which can be determined using location information from the environmental data.Within the swarm data, environmental data is available for a large number of journeys along the route. Preferably, the vehicles have determined environmental data for preferred common predetermined environmental characteristics. The swarm data can also be stored externally to the vehicle, e.g., on the servers described above.

[0031] A further development provides that if the plausibility check fails (for example because the quality of the recorded environmental data does not meet a required minimum quality), (preferably only) the environmental data recorded by the vehicle are used as environmental data for the lateral guidance or, in other words, are taken into account.

[0032] In general, it should be noted that, within the scope of this disclosure, plausibility can be understood as determining and confirming the quality of the environmental data and / or its meaningfulness, suitability for consideration, accuracy, or general usability. For this purpose, the acquired environmental data can serve as a reference within the scope of this invention.

[0033] If the stored environmental data fails to verify its plausibility, this may indicate that, for example, short-term changes have occurred along the route. In this case, the system can switch to the environmental data recorded by the vehicle for safety reasons.

[0034] According to a further embodiment, the environmental data relate to different environmental properties, and an independent plausibility check is performed for each environmental property. Subsequently, the vehicle's lateral guidance can be based on the verified environmental properties. Those environmental properties that have not been verified can, however, be detected by the vehicle, so that even mixed forms of stored environmental properties and detected environmental properties can be used for vehicle lateral guidance, depending on the plausibility check result. This increases safety and accuracy, since each property is separately checked to determine whether it actually reflects a current state.

[0035] In general, it can be provided that an environmental property that is recorded with or determined from the environmental data is one of the following: - a lane marking or lane boundary on the left from the perspective of the vehicle (i.e. in the direction of travel); - a lane marking or lane boundary on the right from the vehicle's point of view; - at least one outer edge of the road.

[0036] A carriageway can also be understood here as a single lane of a multi-lane road or a multi-lane roadway. A road marking can accordingly be a lane marking. In general, a road marking can be a center line or side line, which can be applied to the road surface in a conventional manner. The road boundary can be a physical obstacle that can at least locally prevent a vehicle from leaving the roadway or can represent a collision obstacle when leaving the roadway, e.g., in the form of a bollard, a delineator post, or a guardrail.

[0037] An outer road edge can correspond to a road edge and / or a transition area to, for example, an unpaved environment.

[0038] A further development provides for information about a route traveled by the other vehicles to be stored. This information is preferably used to check the plausibility of the stored environmental data with environmental data recorded by the vehicle. For example, only environmental data from those vehicles that traveled along the same or a comparable route (or stretch) can be considered. For example, it can be checked whether a route traveled by the vehicles corresponds to an actual route or road course ahead according to the environmental data recorded by the (own) vehicle. If this is not the case, the environmental data of these corresponding vehicles can be disregarded or, more precisely, the environmental data recorded by these vehicles cannot be checked for plausibility.

[0039] The route information may be stored in the form of location coordinates and / or GPS data or other positioning data or be defined based on these.

[0040] According to a further embodiment, for the plausibility check, a quality of the stored environmental data is determined based on the acquired environmental data. In particular, it can be determined to what extent the environmental data agree with and / or deviate from the acquired environmental data. Depending on this, the quality of the stored environmental data can then be determined. The greater the agreement or the smaller the deviation, the higher the quality can be. In particular, a quantifiable value can be determined as a quality or, in other words, a quality criterion. As explained below, this can be compared with a minimum quality, which can also be defined as a quantifiable value, and the environmental data can only be plausibility checked if the minimum quality is met.

[0041] In particular, in this context, it can be provided that the quality is determined based on a comparison of the stored environmental data and the detected environmental data over (i.e. along) a defined and preferably upcoming section of road. Location information for the upcoming section of road can be determined from a currently detected position of the vehicle and known detection ranges of the vehicle sensors. For example, within the scope of this invention, it is generally possible to determine a considered upcoming section of road, for example whether the detected environmental data are detected within a range of 0 to 20 m, 0 to 40 m, or 0 to 60 m (in the direction of travel) in front of the vehicle.From the stored environmental data, environmental data with identical location information can then be determined and compared with the recorded (ahead) environmental data along the upcoming route, and in particular within a defined forward route section of, for example, 0 to 20 m or 0 to 40 m. This represents an effective means of promptly detecting any inadmissible deviations from the stored and recorded environmental data.

[0042] The invention may further provide for determining a minimum quality that the stored environmental data must meet in order to be considered plausible or evaluated as plausible. The minimum quality may be determined depending on at least one of the following (and, more precisely, depending on one of the following variables): - A section of road ahead of the vehicle within which recorded environmental data is compared with stored environmental data. This can take into account, for example, whether the detection range for environmental data ahead is 0 to 20 m, 0 to 40 m or 0 to 60 m. The larger the section of road ahead or the length of road ahead under consideration, the lower the requirements that can be placed on the minimum quality. This is based on the idea that detections in areas far ahead or far away from the vehicle can generally be less accurate than in areas closer to the vehicle. Therefore, the smaller the size or length of the specified section of road, the higher the requirements that can be placed on the minimum quality to be met.In general, the minimum quality can define and, in particular, quantify a minimum level of compliance to be met or a permissible maximum deviation from the stored and recorded environmental data. High minimum quality requirements can be synonymous with low permissible deviations or a high required level of compliance. Low minimum quality requirements can be synonymous with high permissible deviation and low compliance. - A type of environmental property that is recorded and compared as (or as part of) environmental data. Here, consideration can be given to the degree of accuracy with which the corresponding properties can actually be recorded. For example, recording road boundaries or road markings may be easier than recording a road edge (e.g., the transition from asphalt to natural surface). The higher the theoretically measurable accuracy of the environmental property, the higher the requirements for the minimum quality to be met can be. The lower this accuracy, the lower the requirements for the minimum quality can be. - The detection conditions during the detection of environmental data, whereby particular reference can be made to the environmental data detected by the vehicle. The detection conditions can be determined by vehicle sensors. This can include, for example, brightness, precipitation level, visibility, general visibility conditions or road surface contamination. The detection conditions can be saved as part of the environmental data and / or as additional information. If the detection conditions are to be classified as critical, i.e. if they do not allow highly precise detection of the environment, which can be automatically determined and / or evaluated accordingly by a vehicle control unit, correspondingly low requirements for the minimum quality can apply. Conversely, the requirements for the minimum quality can be increased if the detection conditions are non-critical. - A region within which the vehicle is located. This can be a geographical region, defined, for example, based on geographical characteristics and / or map data. However, it can also be a radius with a predetermined number of kilometers. For this region, it can be determined to what extent stored environmental data is available for it and / or what quality the environmental data in this region has (historically) had. If the region is characterized by a small amount of stored environmental data and / or a low quality of this environmental data, the requirements for the minimum quality to be met can be correspondingly low, since a high detection uncertainty can generally be assumed. Conversely, if a large amount of stored environmental data and / or a high quality of this environmental data is present in this region, the requirements for the minimum quality can be increased. - A historical quality of the stored environmental data. This allows previously determined environmental data qualities to be considered, regardless of any connection to specific regions and, for example, with respect to the currently viewed vehicle and / or the route. If these qualities are comparatively high, the minimum quality requirements can be increased; otherwise, they can be reduced. - A property of the comparison carried out to determine the quality. Here, for example, the generally expected accuracy of the comparison method used and / or a (e.g. statistical) accuracy value determined during the comparison can be considered. In general, the requirements for the minimum quality can be reduced for less precise or error-prone methods. For example, a comparison based on least squares may have different (in particular lower) requirements for the minimum quality to be met than a general consideration of the correlation between stored and recorded environmental data. With the least squares method, a constant deviation in the data (e.g. a parallel offset between recorded and stored road surfaces) is known to lead to high deviations, which can be assessed as being inaccurate.The correlation may be less affected by such a constant deviation and therefore preferentially requires higher minimum quality requirements. Another example of a comparison method is the determination of the Hausdorff distance, for which, as with correlation, high minimum quality requirements may apply.

[0043] Depending on the number of variables considered, the minimum quality can be a multi-dimensional characteristic map or be determined based on one, with the dimension being determined, for example, by the number of variables. The variables can be weighted or weightable. The weighting can be flexibly adjusted. In this way, a minimum quality can be determined, for example, based on a linear combination of possibly weighted individual values, with each individual value being determined as and / or based on an individual variable. The individual value can be a scale value that is obtained depending on current values of a corresponding variable (e.g. a rating scale of historical quality from 0 (unusable) to 10 (very good)).

[0044] In general, it can also be stipulated that stored environmental data is only considered valid to a limited extent. If a maximum permissible age is exceeded, it can be automatically assessed as implausible, preferably without taking into account other (e.g., quality) characteristics.

[0045] The invention also relates to an arrangement for transversely guiding a vehicle, comprising: a detection device for detecting environmental data of the vehicle and a control device which is configured to: - to check the plausibility of stored environmental data recorded by a number of other vehicles while driving along a route using the recorded environmental data; - to carry out lateral guidance of the vehicle based on the plausibility-checked environmental data.

[0046] The detection device may be a sensor device or a sensor according to any of the variants described herein and generally provided in a vehicle, with which environmental data can be detected.

[0047] The control device can be distributed throughout the vehicle and, for example, comprise or access several individual control components and / or control units. However, it can also be a single structurally and / or functionally integrated control unit of the vehicle. Accessing environmental data can be achieved by accessing a vehicle bus that is connected to the control device and the detection device. The detected environmental data can be processed by the control device and / or the detection device, for example to determine the environmental properties to be detected as described herein. To access the stored environmental data, the control device can access a vehicle-external storage device (e.g.via mobile phone connection) or can read this environmental data from a (temporary) memory of the vehicle, for example if it is temporarily stored in the vehicle after being read from a memory external to the vehicle. The control device can therefore generally be set up to read out, request and / or receive the stored environmental data, in particular from or from a memory device external to the vehicle. To check the plausibility of this stored environmental data, a comparison of any of the types explained above can be carried out, for example, and / or a quality of this stored environmental data, preferably also a minimum quality to be met, can be determined by the control device.

[0048] To implement lateral guidance of the vehicle, the control device can provide known control functions and, in particular, use the environmental data to determine transverse positions that must not be exceeded and / or to define a permissible (virtual) movement corridor. Furthermore, the control device can compare the vehicle's current transverse positions with a corresponding movement corridor or a general movement limit and, if there is a risk of leaving this corridor or exceeding this limit, initiate driver-autonomous countermeasures, in particular driver-autonomous steering interventions.

[0049] In general, the arrangement may include any further feature and any further component to provide and / or execute all of the functions, operating states, defects, steps, and measures described herein. In general, the arrangement may be configured to carry out a method according to any of the types described herein. In particular, all refinements of and embodiments of the method features may also apply to the identical arrangement features or be provided for them.

[0050] The invention is explained below with reference to the attached schematic figures: Fig. 1 shows a vehicle comprising an arrangement according to an embodiment of the invention, the arrangement carrying out a method according to an embodiment; and Fig. 2 shows a flow chart of the process that is carried out by the arrangement Fig. 1 is executed.

[0051] In the following, the same reference symbols can be used for similar or equivalent features across all figures.

[0052] In Fig. 1 shows a vehicle 10 traveling along a road 12 (or route) in the direction of travel F. The vehicle 10 comprises an arrangement 1 according to an exemplary embodiment of the invention. The arrangement 1 comprises a control device 14, which in the example shown is embodied as a single control unit. The control unit 14 is wirelessly connected to a server external to the vehicle, and more precisely, to a cloud server 16, via a mobile radio connection.

[0053] The arrangement 1 also includes a detection device 15, which in the example shown is a camera sensor. This is arranged in the vehicle 10 in such a way that it detects a road section ahead and outputs image data of the road according to a detection frequency. This image data can be evaluated in the camera sensor itself or by the control device 14, specifically in such a way that predetermined environmental properties are determined therein.

[0054] These environmental characteristics are a left lane boundary LF and a right lane boundary RF, viewed from the perspective of the vehicle and in the direction of travel F. In the case shown, a roadway is equated with a single lane for vehicle 10. The left lane boundary LF is a median strip, and the right lane boundary RF is a shoulder. The right lane boundary RF can also be marked by a transition area of road 12 to the surroundings or nature.

[0055] The control device 14 is also configured to determine a current vehicle position, e.g., based on GPS data or other position detection data. The environmental properties LF, RF can be stored accordingly in a location-based or location-dependent manner. This can be done in a memory device (not shown) of the control device 14.

[0056] In general, it should be noted that the control device 14 may comprise at least one processor device, in particular a computer processor. This processor can execute program instructions stored, for example, in a memory device (also not shown) of the control device 14. By executing these program instructions, the control device can be prompted to perform or initiate all of the functions and / or steps and / or measures described herein.

[0057] Within the scope of this disclosure, it is generally possible, and not limited to further details of the exemplary embodiments, to determine and store position information, in particular in the transverse direction, of the determined environmental properties and in particular of the lane boundaries LF, RF in an absolute and / or vehicle-external coordinate system. For this purpose, GPS coordinates or other global coordinates can be used, for example. Thus, coordinates of the detected lane boundaries LF, RF can be determined and stored in an absolute (e.g., global) coordinate system, preferably for each vehicle location, but in principle also independently thereof.

[0058] Also shown is a route R that the vehicle will still travel in the depicted state. Route R can be determined based on the actual vehicle positions of the vehicle that exist when the vehicle 10 travels along the road 12.

[0059] The solution shown assumes that several other vehicles have already traveled along road 12 in the past along a comparable route R and have also recorded the same environmental characteristics LF, RF. It is further assumed that these vehicles have transmitted the corresponding environmental data to the vehicle-external storage device 16. This environmental data can be stored there, for example, location-dependently, as generally explained above. The routes R actually traveled by the respective vehicles can also be stored.

[0060] If the currently viewed vehicle 10 is traveling along road 12, the environmental data currently recorded by the detection device 16 or control device 14 can be determined. Likewise, the stored environmental data of those vehicles that have previously traveled along road 12 in this area (i.e., in the same section of road) can be determined from the storage device 16. Relevant environmental data can be determined, for example, based on the routes R traveled and / or a vehicle position, which should match the position and route R of the vehicle 10 currently traveling along road 12 as closely as possible.

[0061] The stored environmental data is then compared with the currently acquired environmental data. Specifically, each of the environmental properties LF, RF under consideration is individually compared with the corresponding stored environmental properties. If it is determined that the stored environmental data, or more precisely environmental properties, do not correspond to the currently acquired ones, which can be determined by the control device 14 by performing corresponding comparison and evaluation steps, the stored environmental data can be assessed as implausible. The currently acquired environmental data can then be used for lateral guidance instead, and preferably exclusively this acquired environmental data. If, on the other hand, plausibility is determined, the stored environmental data can be used for lateral guidance, and preferably exclusively this stored environmental data.

[0062] In Fig. 2, this procedure is explained again separately using a flowchart. In a step S0, which can be carried out continuously and is an optional component of the method according to the invention, a large number of environmental data recorded by vehicles of a (swarm) population or fleet are stored location-dependently in the vehicle-external storage device 16. In a step S1, a road 12 is then driven on by a specific vehicle 10. This vehicle 10 also continuously records environmental data and, in particular, the same environmental properties LF, RF that have already been recorded by the vehicles whose environmental data were stored in the vehicle-external storage device 16.

[0063] In a step S2, the stored environmental data are read or requested by the control device 14 depending on the current location of the vehicle 10. Subsequently, at least one or any combination of the plausibility check measures explained below can be performed.

[0064] First, it can optionally be determined whether a route R of those vehicles that have generated the corresponding stored environmental data matches a route R ahead of the currently viewed vehicle 10. For this purpose, information about the route R can be stored as part of this stored environmental data during the acquisition of the stored environmental data and can be determined by the control device 14. A current route R can be determined, for example, using known image analysis algorithms, in particular as the center line between the left and right lane boundaries LF, RF. The comparison of a route R ahead according to stored environmental data (or swarm data) and the acquired route R ahead is carried out in Fig.2 is performed in step S2a. If a sufficient match is found, the environmental data can be assessed as plausible. A match can be expressed, for example, as a deviation in the horizontal plane and / or in location coordinates of the corresponding routes R, or can be determined based on these.

[0065] Additionally or alternatively, in a step S2b, the respectively determined environmental properties LF, RF can be compared with the currently detected environmental properties LF, RF. For this purpose, for example, a coordinate value of the left lane boundary LF, as detected by the detection device 16, can be recorded over a certain distance. Furthermore, the coordinate value of this lane boundary LF can be determined for the same route section from the stored environmental data. Figuratively speaking, two graphs can be generated in this way, and a correlation and / or a distance between these graphs can be evaluated.

[0066] For example, mathematical comparison methods, such as the method of individual least squares or a general correlation method, can be applied to determine the agreement (or deviation) between the stored and the recorded environmental data, preferably for each individual environmental property. As a result, a quality G of the stored environmental data can be determined, with the quality being higher the smaller the deviation and / or the greater the agreement with the actually recorded environmental data or environmental properties.

[0067] In step S3, this quality G can then be used to perform the actual plausibility check.

[0068] For this purpose, a minimum quality M to be met is preferably first determined, which can be carried out at any time and, for example, also before step S2b. The minimum quality M enables, in the manner generally explained above, to determine, depending on various circumstances, which quality G can realistically be expected for the current driving scenario and / or the general operating situation. If a high level of accuracy for the acquisition of environmental data cannot be expected for the location under consideration or the operating situation under consideration in general, the minimum quality M to be met can be selected accordingly low. If the opposite is the case, the minimum quality M to be met can be correspondingly high.

[0069] In step S4, it is then determined whether a comparison of the determined quality and the minimum quality M to be met in step S3, or the comparison of route R in step S2a, has shown that the stored environmental data is plausible or not. If this is not the case, it is determined in step S4 that the lateral guidance of the vehicle with the control device 14 should be carried out on the basis of the environmental data acquired by the vehicle 10 itself. If, however, the stored environmental data were assessed as plausible, the lateral guidance is carried out taking into account this stored environmental data and preferably exclusively on the basis of this stored environmental data and not the currently acquired data. List of reference symbols 1 arrangement 10 vehicles 12 Street 14 Control device 15 Recording device 16 vehicle-external storage device F Direction of travel LF left lane boundary RF right lane boundary G quality M Minimum quality R Route

Claims

[1] Method for the lateral guidance of a vehicle (10), comprising: - Recording environmental data of a vehicle (10) when driving along a route, - Obtaining stored environmental data that was recorded by a plurality of other vehicles (10) that are not currently traveling on the route while traveling on the route; - Plausibility check of the stored environmental data based on the recorded environmental data; - Carrying out a lateral guidance of the vehicle (10) based on the plausibility-checked stored environmental data. [2] Method according to claim 1, characterized by that the stored environmental data is swarm data. [3] Method according to claim 1 or 2, characterized by that if the plausibility check fails, the environmental data recorded by the vehicle (10) are taken into account as environmental data for the lateral guidance. [4] Method according to one of the preceding claims, characterized bythat the environmental data relate to different environmental properties and that an independent plausibility check is carried out for each environmental property. [5] Method according to one of the preceding claims, characterized by that the environmental data captures at least one of the following environmental properties: - a lane marking (LF) or lane boundary on the left from the vehicle's point of view; - a right-hand lane marking (RF) or lane boundary from the vehicle's point of view; - at least one outer edge of the road. [6] Method according to one of the preceding claims, characterized by that information about a route (R) traveled by the other vehicles is also stored and this information is used to check the plausibility of the stored environmental data with environmental data recorded by the vehicle (10). [7] Method according to one of the preceding claims, characterized bythat for the plausibility check, a quality (G) of the stored environmental data is determined on the basis of the recorded environmental data, in particular wherein the quality (G) is determined on the basis of a comparison between the stored environmental data and the recorded environmental data along a defined route section. [8] Method according to claim 7, characterized by that a minimum quality (M) is determined which the stored environmental data must meet in order to be verified. [9] Method according to claim 8, characterized by that the minimum quality (M) is determined depending on at least one of the following: - a length of the route section ahead of the vehicle (10), within which recorded environmental data are compared with stored environmental data; - a type of environmental property that is captured and compared as environmental data; - Acquisition conditions during the acquisition of environmental data; - a region within which the vehicle (10) is located; - a characteristic of the comparison carried out to determine the quality; - a historical quality of the stored environmental data. [10] Arrangement (1) for transversely guiding a vehicle (10), comprising: a detection device (15) for detecting environmental data of the vehicle (10) and a control device (14) which is configured to: - to check the plausibility of stored environmental data which were recorded by a plurality of other vehicles (10) when traveling along a route using the recorded environmental data; - to carry out lateral guidance of the vehicle (10) based on the plausibility-checked stored environmental data.

Images