DE102020118640A1 - Method and vehicle system for determining a driving corridor for a vehicle - Google Patents

Abstract

A vehicle system for determining a traffic corridor for a motor vehicle is described. The vehicle system is set up, based on image data from at least one camera of the vehicle, to determine a camera-based lane hypothesis for a lane of a lane that the vehicle can drive in, and to determine a map-based lane based on a digital map in relation to the lane - to determine the hypothesis for the lane that can be driven in by the vehicle. The vehicle system is also set up to determine an overlapping area of the camera-based lane hypothesis and the map-based lane hypothesis, and to determine the drivable driving corridor on the basis of the overlapping area.

Description

The invention relates to a method and a corresponding vehicle system for determining a driving corridor for driving a vehicle.

A vehicle can include one or more environment sensors that make it possible to capture environment data relating to the environment of the vehicle. Based on the environmental data, it can be determined, for example, which lane of a possibly multi-lane roadway the vehicle is in. Alternatively or additionally, the transverse position of the vehicle can be determined within a lane in which the vehicle is traveling. Alternatively or additionally, the course of the lane traveled by the vehicle can be determined or predicted. This information can be used to guide the vehicle longitudinally and/or laterally along a travel corridor in an at least partially automated manner.

When evaluating the surroundings data, contradictions can arise with regard to the position and/or course of the lane in which the vehicle is driving, which can impair the operation of the vehicle, in particular the automated operation of the vehicle.

The present document deals with the technical task of providing a method and a vehicle system with which the driving corridor available for a vehicle on a roadway can be determined with particularly high accuracy and reliability.

The object is solved by each of the independent claims. Advantageous embodiments are described inter alia in the dependent claims. It is pointed out that additional features of a patent claim dependent on an independent patent claim without the features of the independent patent claim or only in combination with a subset of the features of the independent patent claim can form a separate invention independent of the combination of all features of the independent patent claim, which can be made the subject of an independent claim, a divisional application or a subsequent application. This applies equally to the technical teachings described in the description, which can form an invention independent of the features of the independent patent claims.

According to one aspect, a vehicle system for determining a trafficable driving corridor for a motor vehicle is described. The vehicle system is set up to determine a camera-based lane hypothesis for a lane in which the vehicle can drive (or for the lane in which the vehicle is driving) on the basis of image data from at least one camera of the vehicle. The camera-based lane hypothesis can be determined using an image analysis of the images captured by the camera, in particular to determine lane markings of the lane in which the vehicle can travel. The camera-based lane hypothesis can include the predicted course of the lane that the vehicle can drive in.

The camera-based lane hypothesis can be associated with a confidence for the lane hypothesis, in particular for the predicted course of the lane. In particular, the vehicle system can be set up to determine camera confidence data in relation to the confidence of the camera-based lane hypothesis. The camera confidence data can be determined on the basis of the image analysis algorithm for determining the camera-based lane hypothesis. The camera confidence data can be taken into account when determining the trafficable driving corridor.

The vehicle system can also be set up to determine a map-based lane hypothesis for the lane in which the vehicle can travel on the basis of a digital map in relation to the lane. For this purpose, the vehicle can be localized within the digital map (e.g. based on position data from a position sensor, such as a GPS receiver, of the vehicle). The map-based lane hypothesis can include the predicted course of the lane in which the vehicle can travel.

The map-based lane hypothesis can be associated with a confidence for the lane hypothesis, in particular for the predicted course of the lane. In particular, the vehicle system can be set up to determine map confidence data in relation to the confidence of the map-based lane hypothesis. The map confidence data can be determined on the basis of the age or the topicality of the digital map. The map confidence data can be taken into account when determining the trafficable driving corridor.

The vehicle system can also be set up to determine an overlapping area of the camera-based lane hypothesis and the map-based lane hypothesis. In other words, an intersection between the camera-based lane hypothesis and the map-based lane hypothesis can be determined. In particular, the overlapping area between the predicted course of the lane can be determined from the camera-based lane hypothesis and from the map-based lane hypothesis.

The driving corridor that can be traveled by the vehicle can then be determined on the basis of the overlapping area. The vehicle system may be configured to determine that the camera-based lane hypothesis differs from the map-based lane hypothesis. In this case in particular, the drivable driving corridor can be determined on the basis of the overlapping area.

The vehicle can then be guided longitudinally and/or laterally at least partially automatically, in particular according to SAE level 3 or higher, depending on the determined driving corridor.

The vehicle system thus makes it possible to determine a suitable driving corridor for longitudinal and/or lateral guidance of the vehicle, even in the case of at least partially contradicting lane hypotheses. In this way, the reliability and availability of the automated longitudinal and/or lateral guidance of the vehicle can be increased.

The vehicle system can be set up to determine the value of a deviation measure between the course of the lane indicated by the camera-based lane hypothesis and the course of the lane indicated by the map-based lane hypothesis. Depending on the value of the deviation measure, in particular if the value of the deviation measure is greater than or equal to a predefined deviation threshold value, it can then be determined that the camera-based lane hypothesis differs from the map-based lane hypothesis deviates. By taking into account a deviation measure (e.g. a mean square deviation), a deviation in the determined lane hypotheses can be reliably detected.

The vehicle system can be set up to issue a takeover request (in particular a so-called take-over request, TOR) for driving the vehicle to the driver of the vehicle if it is determined that the camera-based lane hypothesis differs from the map-based lane hypothesis differs. The (automated) longitudinal and/or lateral guidance of the vehicle can take place during the takeover period until the driver takes over based on the determined driving corridor. Reliable, automated longitudinal and/or lateral guidance of the vehicle can thus be brought about.

The vehicle system may be configured to verify that the camera-based lane hypothesis is supported by sensor data from one or more motion sensors (e.g., a yaw sensor, a speed sensor, etc.) of the vehicle. A cross-check or a cross-check of the camera-based lane hypothesis can thus be carried out. The driving corridor can then be determined on the basis of the course of the lane indicated by the camera-based lane hypothesis, in particular as the course, if it is recognized that the camera-based lane hypothesis is based on the sensor data from one or more motion sensors of the Vehicle is supported.

In a corresponding manner, it can be checked whether the map-based lane hypothesis is supported by sensor data from one or more cameras and/or from one or more movement sensors of the vehicle. A cross-check or a cross-check of the map-based lane hypothesis can thus be carried out. The driving corridor can then be determined on the basis of the course of the lane indicated by the map-based lane hypothesis, in particular when it is recognized that the map-based lane hypothesis is based on the sensor data from one or more cameras and /or supported by the vehicle's one or more motion sensors. The accuracy and/or the reliability of the determined driving corridor can be further increased by carrying out a cross-check or a cross-check.

As already explained above, the vehicle system can be set up to determine the driving corridor as a function of the camera confidence data and the map confidence data. In particular, the vehicle system can be set up to determine based on the camera confidence data and based on the map confidence data whether the camera-based lane hypothesis and the map-based lane hypothesis have confidences that differ by at most a predefined difference value . In other words, it can be determined whether the confidences of the two lane hypotheses are nearly equal. If this is the case, in particular only if this is the case, then the trafficable driving corridor can be determined on the basis of the overlapping area, in particular as the overlapping area.

On the other hand, the vehicle system can be set up to determine on the basis of the camera confidence data and on the basis of the map confidence data that the camera-based lane hypothesis has a significantly greater confidence, in particular by a factor of 2 or higher, than the map ten-based lane hypothesis. If this is the case, the driving corridor can be determined on the basis of the course of the lane indicated by the camera-based lane hypothesis (in particular as the course of the lane).

Alternatively, it can be determined on the basis of the camera confidence data and on the basis of the map confidence data that the map-based lane hypothesis has a significantly greater confidence, in particular by a factor of 2 or higher, than the camera-based lane hypothesis . In this case, the driving corridor can be determined on the basis of the course of the lane indicated by the map-based lane hypothesis (in particular as the course of the lane). By taking the confidence data into account, the reliability of the determined driving corridor can be further increased.

The vehicle system can be set up to determine an updated camera-based lane hypothesis and an updated map-based lane hypothesis at successive points in time. The driving corridor can then be updated at the different times based on the updated camera-based lane hypothesis and the updated map-based lane hypothesis. The respectively updated driving corridor can then be used for (automated) longitudinal and/or lateral guidance of the vehicle. In this way, the reliability and availability of the (automated) longitudinal and/or lateral guidance of the vehicle can be further increased.

The vehicle system can be set up to determine that the driving corridor is not large enough, in particular not wide enough, for the vehicle. A driving trajectory can then be determined for the vehicle, which causes the vehicle to remain on the roadway and/or which creates the largest possible, in particular maximum large, distance between the vehicle and one or more other road users the roadway is effected. In this way, the reliability of the (automated) longitudinal and/or lateral guidance of the vehicle can be further increased.

According to a further aspect, a (further) vehicle system for determining a drivable driving corridor for a motor vehicle is described. The aspects described in this document can also be used alone or in combination for this vehicle system.

The vehicle system is set up, on the basis of image data from at least one camera of the vehicle, to determine a camera-based lane hypothesis for a lane of a roadway that the vehicle can drive in. Furthermore, the vehicle system is set up to determine a map-based lane hypothesis for the lane in which the vehicle can travel on the basis of a digital map in relation to the lane.

Furthermore, the vehicle system can be set up to determine camera confidence data in relation to a confidence in the camera-based lane hypothesis and/or to determine map confidence data in relation to a confidence in the map-based lane hypothesis. The driving corridor can then be determined as a function of the camera confidence data and the map confidence data. In particular, the driving corridor (possibly alone) can be determined on the basis of the map-based lane hypothesis if the confidence of the map-based lane hypothesis is significantly higher, for example by a factor of 2 or more, than the confidence of the camera based lane hypothesis. Alternatively, the driving corridor (possibly alone) can be determined on the basis of the camera-based lane hypothesis if the confidence of the camera-based lane hypothesis is significantly higher, e.g. by a factor of 2 or more, than the confidence of the map based lane hypothesis. Alternatively, the driving corridor can be determined based on the camera-based lane hypothesis and based on the map-based lane hypothesis (e.g. in combination, in particular based on the overlapping area of the two lane hypotheses) if the confidence of the camera -based lane hypothesis and the confidence of the map-based lane hypothesis are similar (e.g. deviate from each other by less than a factor of 2).

By taking into account confidence data, the available or drivable driving corridor for a vehicle can be determined in a particularly precise manner.

The vehicle system may be configured to issue a takeover request to drive the vehicle to the driver of the vehicle if the camera confidence data indicates that the confidence of the camera-based lane hypothesis is less than a confidence threshold, and/or if the maps -Confidence data indicating that the confidence of the map-based lane hypothesis is less than a confidence threshold. A particularly safe operation of the vehicle can be made possible in this way.

The vehicle system can be set up, for example, to decide in a first step based on the map confidence data and/or based on the camera confidence data whether the driving corridor based on the map-based lane hypo thesis and/or is determined on the basis of the camera-based lane hypothesis. Furthermore, on the basis of the card confidence data and/or on the basis of the camera confidence data, a decision can be made as to whether a takeover request is issued to the driver of the vehicle. This can be output, for example, if the map-based lane hypothesis and/or the camera-based lane hypothesis deviate from one another and/or if the confidences of the hypothesis are less than the confidence threshold value.

If it is decided that the driving corridor is to be determined based on the map-based lane hypothesis and on the basis of the camera-based lane hypothesis (e.g. because both lane hypotheses have a similarly high level of confidence), the driving corridor can be reliably determined based on or as the overlapping area of the two lane hypotheses.

The lane hypotheses can be determined repeatedly at consecutive points in time. An overlapping area of the two lane hypotheses can then be determined in each case. As long as the overlapping area is sufficient as a travel corridor for the vehicle, a trajectory of the vehicle that causes the vehicle to remain within the overlapping area can be determined. If the overlapping area becomes too small for the vehicle, the trajectory of the vehicle can be determined in order to avoid a collision with other road users and/or to stay on the roadway currently being driven on. The trajectory can be determined on the basis of the sensor data from one or more sensors surrounding the vehicle. The trajectory can be determined within the takeover period, until the driver takes over control of the vehicle and/or until the vehicle has been brought to a standstill. In this way, a particularly safe and reliable operation of the vehicle can be made possible.

According to a further aspect, a (road) motor vehicle (in particular a passenger car or a truck or a bus or a motorcycle) is described which comprises the vehicle system described in this document.

According to a further aspect, a method for determining a trafficable driving corridor for a motor vehicle is described. The method includes determining, on the basis of image data from at least one camera of the vehicle, a camera-based lane hypothesis for a lane of a roadway that the vehicle can drive in. The method also includes determining, on the basis of a digital map in relation to the roadway, a map-based lane hypothesis for the lane in which the vehicle can travel. The method also includes determining an overlapping area of the camera-based lane hypothesis and the map-based lane hypothesis, and determining the trafficable driving corridor based on the overlapping area (in particular as the overlapping area).

According to a further aspect, a further method for determining a trafficable driving corridor for a motor vehicle is described. The method includes determining, on the basis of image data from at least one camera of the vehicle, a camera-based lane hypothesis for a lane of a roadway that the vehicle can drive in. The method also includes determining, on the basis of a digital map in relation to the roadway, a map-based lane hypothesis for the lane in which the vehicle can travel. Furthermore, the method includes determining camera confidence data relating to a confidence of the camera-based lane hypothesis and determining map confidence data relating to a confidence of the map-based lane hypothesis. The method also includes determining the driving corridor as a function of the camera confidence data and the map confidence data.

According to a further aspect, a software (SW) program is described. The SW program can be set up to be executed on a processor (e.g. on a vehicle's control unit) and thereby to carry out the method described in this document.

According to a further aspect, a storage medium is described. The storage medium can comprise a SW program which is set up to be executed on a processor and thereby to carry out the method described in this document.

In the context of the document, the term "automated driving" can be understood as driving with automated longitudinal or lateral guidance or autonomous driving with automated longitudinal and lateral guidance. Automated driving can be, for example, driving on the freeway for a longer period of time or driving for a limited time as part of parking or manoeuvring. The term "automated driving" includes automated driving with any degree of automation. Exemplary degrees of automation are an assisted, partially automated, highly automated or fully automated driving. These degrees of automation were defined by the Federal Highway Research Institute (BASt) (see BASt publication "Research compact", issue 11/2012). With assisted driving, the driver constantly performs longitudinal or lateral guidance, while the system takes over the other function within certain limits. With semi-automated driving (TAF), the system takes over longitudinal and lateral guidance for a certain period of time and/or in specific situations, whereby the driver has to constantly monitor the system, as with assisted driving. With highly automated driving (HAD), the system takes over longitudinal and lateral guidance for a certain period of time without the driver having to constantly monitor the system; however, the driver must be able to take control of the vehicle within a certain period of time. With fully automated driving (VAF), the system can automatically handle driving in all situations for a specific application; a driver is no longer required for this application. The four levels of automation mentioned above correspond to SAE levels 1 to 4 of the SAE J3016 standard (SAE - Society of Automotive Engineering). For example, highly automated driving (HAF) corresponds to level 3 of the SAE J3016 standard. Furthermore, SAE J3016 also provides SAE Level 5 as the highest degree of automation, which is not included in the BASt definition. SAE Level 5 corresponds to driverless driving, in which the system can automatically handle all situations like a human driver throughout the journey; a driver is generally no longer required. The aspects described in this document relate in particular to a vehicle with SAE level 3 and higher.

It should be noted that the methods, devices and systems described in this document can be used both alone and in combination with other methods, devices and systems described in this document. Furthermore, any aspects of the methods, devices and systems described in this document can be combined with one another in a variety of ways. In particular, the features of the claims can be combined with one another in many different ways.

• 1 beispielhafte Komponenten eines Fahrzeugs;
• 2 eine beispielhafte mehrspurige Fahrbahn;
• 3 einen beispielhaften Fahr-Korridor für ein Fahrzeug; und
• 4 ein Ablaufdiagramm eines beispielhaften Verfahrens zur Ermittlung eines Fahr-Korridors für ein Fahrzeug.

The invention is described in more detail below using exemplary embodiments. show it

• 1 exemplary components of a vehicle;
• 2 an exemplary multi-lane roadway;
• 3 an exemplary driving corridor for a vehicle; and
• 4 a flowchart of an exemplary method for determining a driving corridor for a vehicle.

As explained at the outset, the present document deals with the precise and reliable determination of a driving corridor for a vehicle on the roadway traveled by the vehicle.

1 12 shows exemplary components of a vehicle 100. The vehicle 100 includes one or more surroundings sensors 102 which are set up to record surroundings data relating to the surroundings of the vehicle 100. Exemplary environment sensors 102 are a camera, a radar sensor, a lidar sensor, an ultrasonic sensor, etc. In particular, at least one camera 102 of vehicle 100 can capture image data relating to the roadway traveled by vehicle 100 . On the basis of the image data, for example, lane markings on the roadway can be recognized and evaluated in order to determine the lane in which vehicle 100 is located.

The vehicle 100 further includes a position sensor 103 (e.g. a GPS receiver) configured to acquire position data relating to the position of the vehicle 100 . The position data can be determined using a satellite-based positioning system. The position data can be evaluated in connection with a digital map, the digital map showing the position of the roadway and the individual lanes of the roadway. The position data can thus be used (in connection with the digital map) to determine the lane in which vehicle 100 is located.

A control unit 101 (or an evaluation device or a vehicle system) of vehicle 100 can be set up to determine based on the surroundings data (in particular based on the image data) and/or based on the position data (in connection with the digital map). , in which lane the vehicle 100 is located. Alternatively or additionally, the course of the lane traveled by vehicle 100 can be determined and/or predicted. In this way, a precise lane hypothesis with respect to the ego lane of the vehicle 100 can be determined. The lane hypothesis can show the current and/or future course of the ego lane. Alternatively or additionally, the lane hypothesis may indicate the lateral position of vehicle 100 within the ego lane. Alternatively or additionally, the lane hypothesis can indicate which lane of a multi-lane roadway vehicle 100 is in.

Furthermore, control unit 101 may be set up to control a longitudinal and/or lateral guidance actuator 105 of vehicle 100 (e.g. a drive motor, a braking device and/or a steering device) as a function of the determined lane hypothesis, in particular as a function of a one or more lane hypotheses determined driving corridor. In particular, the one or more determined lane hypotheses can be used to guide vehicle 100 at least partially or fully automatically (eg according to SAE level 3 or more).

2 shows an exemplary lane 200 for a vehicle 100 with different (in particular with three) lanes 201, 202, 203. The individual lanes 201, 202, 203 are divided by lane markings 205 or delimited from one another and/or each limited. In other words, a lane marking 205 can be designed as a marking between two lanes 201, 202 or as a delimitation marking for delimiting the roadway 200.

• • auf Basis der Anzahl von Bildkameras 102, mit der die Kamera-basierte Fahrspur-Hypothese ermittelt wurde (wobei die Konfidenz typischerweise mit steigender Anzahl von Bildkameras 102 ansteigt); und/oder
• • auf Basis von Auswertedaten, die von dem Bildanalyse-Algorithmus zur Ermittlung der Kamera-basierten Fahrspur-Hypothese bereitgestellt werden.

The device 101 can be set up to ascertain confidence data relating to the reliability, the accuracy and/or the confidence of a camera-based lane hypothesis ascertained on the basis of the image data from at least one image camera 102 . The confidence data can be determined, for example,

• • on the basis of the number of imaging cameras 102 with which the camera-based lane hypothesis was determined (with the confidence typically increasing as the number of imaging cameras 102 increases); and or
• • based on evaluation data provided by the image analysis algorithm for determining the camera-based lane hypothesis.

• • auf Basis von Daten in Bezug auf die Genauigkeit und/oder die Aktualität der digitalen Karte, wie z.B. das letzte Aktualisierungsdaten und/oder Rückmeldungen von ein oder mehreren Verkehrsteilnehmern in Bezug auf die Genauigkeit und/oder die Aktualität der digitalen Karte; und/oder
• • auf Basis von Daten in Bezug auf die Genauigkeit und/oder die Konfidenz der von dem Positionssensor 103 angezeigten Position des Fahrzeugs 100.

Furthermore, the device 101 can be set up to determine confidence data in relation to the reliability, the accuracy and/or the confidence of a map-based lane hypothesis determined on the basis of a digital map. The confidence data can be determined, for example,

• • based on data related to the accuracy and/or the timeliness of the digital map, such as the last update data and/or feedback from one or more road users related to the accuracy and/or the timeliness of the digital map; and or
• • based on data relating to the accuracy and/or the confidence of the position of the vehicle 100 indicated by the position sensor 103.

The device 101 can be set up, a driving corridor on a roadway 200 on which the vehicle 100 can drive (eg on which the vehicle 100 can be guided automatically), based on the confidence data of the camera-based lane hypothesis and the maps -based lane hypothesis to determine. In this way, the quality of a determined driving corridor can be increased.

In particular, device 101 (or the vehicle system) can be set up to take into account the confidence data of the individual lane hypotheses if the individual lane hypotheses at least partially contradict one another. 3 shows an exemplary driving situation in which there is a contradiction between the camera-based lane hypothesis 301 and the map-based lane hypothesis 302 .

Device 101 can be set up to determine a driving corridor 303 for vehicle 100 on the basis of the two lane hypotheses 301, 302. In particular, the device 101 can be set up to select one of the available lane hypotheses 301, 302 as the driving corridor 303 as a function of the confidence data of the individual lane hypotheses 301, 302, in particular if the confidence for the selected lane hypothesis 301, 302 is significantly greater than the confidence for the one or more other lane hypotheses 301, 302. If necessary, a cross check can also be carried out. In particular, it can be checked whether further sensor data from one or more sensors 102, 103 of vehicle 100 are present, which confirm one of the lane hypotheses 301, 302. For example, it can be checked whether the sensor data of a camera 102 of the vehicle 100 are compatible with the map-based lane hypothesis 302 or not. Alternatively or additionally, it can be checked whether one of the available lane hypotheses 301, 302 is confirmed by the sensor data from one or more other (movement) sensors 102, 103 of the vehicle 100 or not. Based on this, one of the available lane hypotheses 301, 302 can then be selected in order to determine the driving corridor 303. The driving corridor 303 can then correspond to the predicted course of the lane 202 of the selected lane hypothesis 301, 302.

The device 101 can be set up to check on the basis of the confidence data whether the individual lane hypotheses 301, 302 each have a specific, predefined, minimum confidence. A lane hypothesis 301, 302 becomes possibly only selected as the basis for the driving corridor 303 if the lane hypothesis 301, 302 has at least the minimum confidence.

As already explained above, a contradiction between the camera-based lane hypothesis 301 and the map-based lane hypothesis 302 can be recognized at a specific point in time. In particular, it can be recognized that the camera-based lane hypothesis 301 and the map-based lane hypothesis 302 predict an at least partially different course of the lane 202 .

In response to this, the device 101 can cause the automated longitudinal and/or lateral guidance of the vehicle 100 (e.g. according to SAE level 3 or higher) to be terminated. This can be effected, for example, by issuing a TOR (take-over request) to the driver of the vehicle 100 . The driver should then take over the driving task within a certain takeover period (e.g. between 5 and 10 seconds). If the driver does not take over within the takeover period, the device 101 can cause the vehicle 100 to be automatically transferred to a safe state (in particular to a standstill, for example at the edge of the roadway 200).

Consequently, it may be necessary for vehicle 100 to continue to be automatically longitudinally and/or laterally guided for a specific period of time, in particular for the takeover period, even after contradictory lane hypotheses 301, 302 have been detected. For this purpose, a driving corridor 303 can be determined by the device 101 on the basis of the available lane hypotheses 301, 302. The vehicle 100 can then, as in 3 shown as an example, are guided along a driving trajectory 310 that runs within the determined driving corridor 303 .

As already explained, one of the available lane hypotheses 301, 302 can be selected as the driving corridor 303 if the confidence of the selected lane hypothesis 301, 302 is significantly (e.g. by a factor of 2 or more, or 5 or more, or 10 or more) above the confidences of the one or more other lane hypotheses 301, 302.

Alternatively or additionally, the intersection or the overlapping areas of the available lane hypotheses 301, 302 as a basis for the driving -Corridor 303, in particular as a driving corridor 303, can be selected (as exemplified in 3 represented by the shaded area). The area of roadway 200 that is compatible with both (in particular with all) determined lane hypotheses 301, 302 can thus be determined as driving corridor 303. Vehicle 100 can then be guided safely along determined driving corridor 303 .

Device 101 is typically set up to repeatedly, in particular periodically, determine current lane hypotheses 301, 302 at successive times on the basis of current sensor data. The driving corridor 303 can be updated on the basis of the respectively current lane hypotheses 301, 302 at the successive points in time. In particular, the respective current overlapping area of the available lane hypotheses 301, 302 can be determined. If necessary, it can also be determined at a specific point in time that the contradiction in the lane hypotheses 301, 302 recognized at the point in time of the contradiction has been resolved again. In this way, a safe driving corridor 303 for vehicle 100 can also be reliably determined after the objection point in time.

If, on the other hand, it is recognized at a point in time that the overlapping area between the contradictory lane hypotheses 301, 302 is too small, in particular too narrow, to be used as a driving corridor 303 for vehicle 100, then a driving traj ector 310 are selected for the vehicle 100, through which the collision probability for the vehicle 100 is reduced, in particular minimized. For example, a driving trajectory 310 can be selected or determined, which increases the distance to one or more other road users and/or causes vehicle 100 to move away from one or more other road users. Alternatively or additionally, a driving trajectory 310 that runs on the current lane 200 can be selected or determined.

The device 101 (or the vehicle system) can thus be set up to determine a driving corridor 303 or a driving trajectory 310 by making a decision at a point in time (if there is a contradiction between the determined lane hypotheses 301, 302). which decision will result in the smallest possible and/or least dangerous error in relation to a possible collision.

4 FIG. 12 shows a flow chart of an exemplary (possibly computer-implemented) method 400 for determining a trafficable driving corridor 303 for a motor vehicle 100. The method 400 includes determining 401, on the basis of image data from at least one camera 102 of the vehicle 100, a camera-based lane hypothesis 301 for a lane 202 of a lane 200 that the vehicle 100 can drive in. The camera-based lane hypothesis 301 can, for example be determined based on the detection of lane markings 205 of lane 202. The camera-based lane hypothesis 301 can display or describe the course (up ahead) of the lane 202 .

The method 400 further includes determining 402, on the basis of a digital map in relation to the lane 200 (in particular in relation to the lane network traveled by the vehicle 100), a map-based lane hypothesis 302 for the lane in which the vehicle 100 can travel 202. The map-based lane hypothesis 302 can be described on the basis of position data from a position sensor 103 of the vehicle 100. In particular, the map-based lane hypothesis 302 can be determined based on a localization of the vehicle 100 within the digital map. The map-based lane hypothesis 302 can display or describe the course (up ahead) of the lane 202 .

Furthermore, the method 400 includes determining 403 an overlapping area of the camera-based lane hypothesis 301 and the map-based lane hypothesis 302. In particular, the overlapping area of the lane indicated by the camera-based lane hypothesis 301 (up ahead). 202 and the (ahead) lane 202 indicated by the map-based lane hypothesis 302 can be determined. In other words, the intersection between the camera-based lane hypothesis 301 and the map-based lane hypothesis 302 can be determined.

The method 400 also includes determining 404 the trafficable driving corridor 303 based on the overlapping area or based on the intersection between the camera-based lane hypothesis 301 and the map-based lane hypothesis 302. The vehicle 100 can then possibly be guided longitudinally and/or transversely within the determined travel corridor 303 in an automated manner.

With the measures described in this document, a reliable and safer operation of a vehicle 100 can be brought about even if there is a contradiction between determined lane hypotheses 301, 302.

The present invention is not limited to the exemplary embodiments shown. In particular, it should be noted that the description and the figures are only intended to illustrate the principle of the proposed methods, devices and systems by way of example.

Claims (15)

Vehicle system (101) for determining a drivable driving corridor (303) for a motor vehicle (100); wherein the vehicle system (101) is set up, - On the basis of image data from at least one camera (102) of the vehicle (100) to determine a camera-based lane hypothesis (301) for a vehicle (100) driveable lane (202) of a roadway (200); - to determine a map-based lane hypothesis (302) for the lane (202) that can be driven on by the vehicle (100) on the basis of a digital map in relation to the lane (200); - determine an overlapping area of the camera-based lane hypothesis (301) and the map-based lane hypothesis (302); and - to determine the passable driving corridor (303) on the basis of the overlapping area. Vehicle system (101) according to claim 1 , wherein the vehicle system (101) is set up - to determine that the camera-based lane hypothesis (301) deviates from the map-based lane hypothesis (302); and - in response thereto, determining the drivable driving corridor (303) on the basis of the overlapping area. Vehicle system (101) according to claim 2 , wherein the vehicle system (101) is set up, - a value of a deviation measure between a course of the lane (202) indicated by the camera-based lane hypothesis (301) and a course indicated by the map-based lane hypothesis (302). determine the lane (202); and - to determine as a function of the value of the deviation measure, in particular if the value of the deviation measure is greater than or equal to a deviation threshold value, that the camera-based lane hypothesis (301) differs from the map-based lane hypothesis (302). Vehicle system (101) according to one of claims 2 until 3 , wherein the vehicle system (101) is set up to issue a takeover request for driving the vehicle (100) to a driver of the vehicle (100) if it is determined that the camera-based lane hypothesis (301) from the map-based lane hypothesis (302) differs. Vehicle system (101) according to one of claims 2 until 4 , wherein the vehicle system (101) is set up - to check whether the camera-based lane hypothesis (301) is supported by sensor data from one or more motion sensors (102) of the vehicle (100); and - to determine the driving corridor (303) on the basis of the course of the lane (202) indicated by the camera-based lane hypothesis (301), in particular as the course of the lane (202), if it is recognized that the Camera-based lane hypothesis (301) is supported by sensor data from one or more motion sensors (102) of the vehicle (100). Vehicle system (101) according to one of claims 2 until 4 , wherein the vehicle system (101) is set up - to check whether the map-based lane hypothesis (302) is corrected by sensor data from one or more cameras (102) and/or from one or more motion sensors (102) of the vehicle (100 ) is supported; and - to determine the driving corridor (303) on the basis of the course of the lane (202) indicated by the map-based lane hypothesis (302), in particular as the course of the lane (202), if it is recognized that the Map-based lane hypothesis (302) is supported by sensor data from one or more cameras (102) and/or from one or more motion sensors (102) of the vehicle (100). Vehicle system (101) according to one of the preceding claims, wherein the vehicle system (101) is set up - determine camera confidence data related to a confidence of the camera-based lane hypothesis (301); - map confidence data relating to a confidence of the map-based lane hypothesis (302); and - to determine the driving corridor (303) as a function of the camera confidence data and the map confidence data. Vehicle system (101) according to claim 7 , wherein the vehicle system (101) is set up - to determine on the basis of the camera confidence data and on the basis of the map confidence data that the camera-based lane hypothesis (301) and the map-based lane hypothesis (302) have confidences have, which deviate from each other by at most a predefined difference value; and - in response thereto, determining the drivable driving corridor (303) on the basis of the overlapping area. Vehicle system (101) according to one of Claims 7 until 8th , wherein the vehicle system (101) is set up - to determine on the basis of the camera confidence data and on the basis of the map confidence data that the camera-based lane hypothesis (301) is significantly larger, in particular by a factor of 2 or more has confidence than the map-based lane hypothesis (302); and - in response to this, to determine the driving corridor (303) on the basis of the course of the driving lane (202) displayed, in particular as the course of the driving lane (202) indicated by the camera-based driving lane hypothesis (301); or - to determine on the basis of the camera confidence data and on the basis of the map confidence data that the map-based lane hypothesis (302) has a significantly greater confidence, in particular by a factor of 2 or higher, than the camera-based lane hypothesis (301); and - in response to this, to determine the driving corridor (303) on the basis of the course of the lane (202) indicated, in particular as the course of the lane based on the map-based lane hypothesis (302). Vehicle system (101) according to any one of the preceding claims, wherein the vehicle system (101) is set up, at successive points in time, - to determine an updated camera-based lane hypothesis (301) and an updated map-based lane hypothesis (302) in each case; and - update the driving corridor (303) on the basis of the updated camera-based lane hypothesis (301) and the updated map-based lane hypothesis (302). Vehicle system (101) according to one of the preceding claims, wherein the vehicle system (101) is set up - to determine that the driving corridor (303) is not sufficiently large, in particular not sufficiently wide, for the vehicle (100); and - In response to this, a driving trajectory (310) for the vehicle (100) to be determined by which - It is caused that the vehicle (100) remains on the roadway (200); and - The vehicle (100) is spaced as large as possible, in particular as large as possible, from one or more other road users on the roadway (200). Vehicle system (101) according to one of the preceding claims, wherein the vehicle system (101) is set up to automate the vehicle (100) at least partially, in particular according to SAE level 3 or higher, depending on the determined driving corridor (303) and/or cross. Vehicle system (101) for determining a drivable driving corridor (303) for a motor vehicle (100); wherein the vehicle system (101) is set up, - based on image data from at least one camera (102) of the vehicle (100), a camera-based lane hypothesis (301) for a lane (202) in which the vehicle (100) can drive to determine roadway (200); - to determine a map-based lane hypothesis (302) for the lane (202) that can be driven on by the vehicle (100) on the basis of a digital map in relation to the lane (200); - determine camera confidence data related to a confidence of the camera-based lane hypothesis (301); - map confidence data relating to a confidence of the map-based lane hypothesis (302); and - to determine the driving corridor (303) as a function of the camera confidence data and the map confidence data. Vehicle system (101) according to Claim 13 , wherein the vehicle system (101) is set up to issue a takeover request to drive the vehicle (100) to a driver of the vehicle (100) if - the camera confidence data indicate that the confidence of the camera-based lane hypothesis (301) is less than a confidence threshold, and/or - the map confidence data indicates that the confidence of the map-based lane hypothesis (302) is less than a confidence threshold. Method (400) for determining a drivable driving corridor (303) for a motor vehicle (100); the method (400) comprising - Determining (401), on the basis of image data from at least one camera (102) of the vehicle (100), a camera-based lane hypothesis (301) for a lane (202) of a roadway (200 ); - determining (402), on the basis of a digital map in relation to the roadway (200), a map-based lane hypothesis (302) for the vehicle (100) navigable lane (202); - determining (403) an overlapping region of the camera-based lane hypothesis (301) and the map-based lane hypothesis (302); and - Determination (404) of the drivable driving corridor (303) on the basis of the overlapping area.

Images