Method, device and storage medium for operating a vehicle

Abstract

The present invention relates to a method for operating a vehicle (100), in particular a vehicle (100) for highly automated driving. The method comprises a step of reading in input data (121). The input data (121) comprises sensor data (112, 114, 116) and sensor status data (113, 115, 117) of a plurality of sensor devices (101, 104, 106) of the vehicle (100). The method further comprises a step of generating a potential field using the input data (121). The input data (121) is used as the attractive potential and the repulsive potential of the potential field. The method further comprises a step of determining a trajectory through the potential field in order to use the trajectory to generate a fusion signal (129) for fusing the input data (121) to perform sensor data fusion, thereby enabling highly automated driving of the vehicle (100). The present invention also relates to a device and a machine-readable storage medium.

Description

Technical Field

[0001] The present invention proceeds from a device or a method. The present invention also relates to a computer program. Background Art

[0002] Systems for the automated and autonomous guidance of motor vehicles and other vehicles, such as ships, are known. For example, ISR (Tactical Intelligence, Surveillance, and Reconnaissance) capabilities can be expanded from single sensor imaging devices to integrated, comprehensive system architectures. Such systems increasingly include multiple sensing capabilities that can serve as multipliers for the algorithms of such automated and autonomous systems. Traditionally, individual sensors operating largely independently of one another have been used, providing a choice of operating mode. Summary of the Invention

[0003] Against this background, the present invention proposes a method, a device using the method, and finally a corresponding computer program. Advantageous embodiments and improvements of the device according to the invention can be derived from the preferred embodiments.

[0004] According to embodiments, a sensor fusion management system or a sensor fusion management method may be provided that uses an algorithm according to the potential field method, for example, implemented in an evaluation and decision-making unit, to dynamically, scalably, and integratedly manage multiple cooperating sensor systems or sensor devices. Due to its operating principle, such a sensor fusion management system or a sensor fusion management method may be used in particular for highly automated vehicles, in particular motor vehicles.

[0005] Advantageously, depending on the specific embodiment, an integrated and intelligent sensor fusion management system (SFS) or sensor fusion management method can be provided, in particular, to ensure particularly safe and reliable highly automated driving operation of the vehicle. This allows for optimized weighting of sensor information, thereby increasing system safety and availability. It is also possible to extend system reaction times or operator or driver takeover times. In particular, in highly automated or autonomous driving situations, the so-called OODA time (OODA = Observe, Orient, Decide, Act) can be extended or prolonged, where, in theoretically ideal conditions, the OODA time is infinite.

[0006] In this context, the term "in the loop" can be used to describe how a person is connected to a decision-making process, in particular a system decision-making process, an operator takeover process, and / or a driver takeover process. Thus, with increasing levels of automation, the understanding of how the system / person or operator or driver behaves during the preparation phase or "standby phase" (i.e., the so-called "in the loop") can be improved.

[0007] Practical examples of using a sensor fusion management system (SFS) or sensor fusion management method include, for example, reducing system shutdowns due to environmental influences to prevent or minimize performance losses and blindness due to media loads, such as contamination and / or weather influences. System shutdowns due to hardware influences can also be reduced. With regard to safety, this can reduce shutdowns or fallbacks in the event of sensor blindness due to targeted external interference or attacks, such as illuminating a lidar / radar system. With regard to cybersecurity, this can implement fallbacks in the event of a "hostile" system takeover.

[0008] A method for operating a vehicle, in particular a vehicle for highly automated driving, is proposed, wherein the method comprises the following steps:

[0009] reading in input data, wherein the input data includes sensor data and sensor status data of a plurality of sensor devices of the vehicle;

[0010] generating a potential field using the input data, wherein the input data is used as attractive and repulsive potentials of the potential field; and

[0011] A trajectory through the potential field is determined to use the trajectory to generate a fusion signal for fusing input data, so as to perform sensor data fusion for highly automated driving operation of the vehicle.

[0012] The method can be implemented, for example, in software, hardware, or a combination of software and hardware, such as in a controller or device. The vehicle can be a motor vehicle, particularly a land vehicle, watercraft, spacecraft, or aircraft, such as a passenger car or a commercial vehicle. The method can be implemented to perform or control sensor data fusion. When fusing input data, the sensor data can be fused. The steps of the method can be repeated continuously or intermittently.

[0013] According to one specific embodiment, the trajectory determined in the determining step can result in the vehicle's operating state in highly automated driving operation being transferred to a minimally critical state when the fusion signal is used by the system for sensor data fusion of the vehicle. ). The fusion signal may indicate the fusion of sensor data from sensor devices whose sensor status data represents a reliability value that exceeds a reliability threshold. This embodiment has the advantage that reliable sensor data fusion enables safe operation of the vehicle even in highly automated driving.

[0014] In particular, the input data read in during the read-in step may include, as sensor data, environmental data representing environmental conditions in the vehicle's surroundings and driving data representing at least one physical variable of the vehicle's driving operation. The environmental data may represent the vehicle's physical surroundings sensed by at least one sensor device. The environmental data may also include weather data, position data, and additionally or alternatively, other environmental data representing at least one variable condition of the vehicle's surroundings. The driving data may include acceleration, speed, and additionally or alternatively, other driving data representing at least one static or dynamic characteristic of the vehicle. Additionally or alternatively, the input data read in during the read-in step may include, as sensor status data, availability data representing the availability of individual sensor devices. The availability data may include, for at least one of the sensor devices, at least one confidence factor, at least one range parameter, at least one blindness parameter, and additionally or alternatively, at least one safety parameter. This embodiment offers the advantage of providing a comprehensive and robust data base for sensor data fusion.

[0015] Furthermore, in the generation step, a potential field model and, additionally or alternatively, a potential field function can be used to correlate the input data into a three-dimensional potential field. Additionally or alternatively, the potential field can represent at least one predefined relationship between selected input data and criticality, combined in a unique state space. This embodiment offers the advantage that the potential field algorithm is particularly well-suited for the aforementioned application, as it offers analytical representation, low memory consumption, and dynamic adaptation times.

[0016] Furthermore, the potential field can be generated in real time in the generation step. Additionally or alternatively, in the generation step, the potential field can be generated scenario by scenario during the highly automated driving operation of the vehicle. A scenario can represent a traffic activity that includes the vehicle and, optionally, another vehicle within a defined spatial and / or temporal scope. Additionally or alternatively, in the generation step, learned or predefined scenarios can be used and adapted to generate the potential field during the highly automated driving operation of the vehicle. This embodiment offers the advantage that current events and conditions involving the vehicle can be reliably and precisely taken into account during sensor data fusion in order to operate the vehicle safely.

[0017] In particular, the trajectory determined in the determination step can identify minimally critical associations between the sensor state data. Additionally or alternatively, the fusion signal can result in a prolonged highly automated driving operation, a prolonged decision-making time, and additionally or alternatively, a prolonged takeover time before interrupting the highly automated driving operation. This embodiment offers the advantage that highly automated driving operation of the vehicle can be achieved in a safe and stable manner by implementing reliability- and availability-oriented sensor data fusion.

[0018] The method may also include a step of providing a fusion signal for outputting it to an interface with a device of the system for vehicle sensor data fusion. The fusion signal may be designed to cause a weighting of the sensor data when used by the system for sensor data fusion. This embodiment offers the advantage that sensor data from sensor devices assigned to different subsystems of the vehicle can also be used to achieve safety-oriented and optimized fusion.

[0019] The present invention further proposes a device which is designed to implement, control or realize the steps of the variants of the method proposed here in a corresponding device. The object on which the present invention is based can also be achieved quickly and effectively by these embodiment variants of the present invention in the form of a device.

[0020] To this end, the device may include: at least one computing unit for processing signals or data; at least one memory unit for storing signals or data; at least one interface to a sensor or actuator for reading in sensor signals from the sensor or outputting data signals or control signals to the actuator; and / or at least one communication interface for reading in or outputting data embedded in a communication protocol. The computing unit may be, for example, a signal processor, a microcontroller, etc., wherein the memory unit may be a flash memory, an EEPROM, or a magnetic storage unit. The communication interface may be configured for wireless and / or wired reading in or outputting data, wherein a communication interface capable of reading in or outputting wired data may, for example, electrically or optically read in this data from or output this data to a corresponding data transmission line.

[0021] In the present context, a device can be understood as an electrical device that processes sensor signals and outputs control signals and / or data signals accordingly. The device can have an interface that can be implemented in hardware and / or software. In the case of a hardware implementation, the interface can, for example, be part of a so-called system ASIC that contains the various functions of the device. However, it is also possible for these interfaces to be independent integrated circuits or at least partially composed of discrete components. In the case of a software implementation, the interface can be, for example, a software module that exists on a microcontroller in addition to other software modules.

[0022] In one advantageous embodiment, the device controls sensor data fusion for vehicle operation, particularly for highly automated driving. To this end, the device can, for example, access sensor signals such as camera signals, radar signals, lidar signals, and the like. A potential field is generated by signal processing and modeling using suitable algorithms, such as potential field functions. The device is configured to provide a fusion signal as an output suitable for controlling the sensor data fusion.

[0023] A computer program product or a computer program having a program code is also advantageous, which can be stored on a machine-readable carrier or storage medium, such as a semiconductor memory, a hard disk memory or an optical memory, and is used to implement, realize and / or control the steps of the method according to one of the above-mentioned embodiments, in particular when the program product or program is executed on a computer or a device. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] An exemplary embodiment of the present invention is illustrated in the drawings and explained in more detail in the following description.

[0025] Figure 1 A schematic diagram of a vehicle having an apparatus according to one embodiment;

[0026] Figure 2 A flow chart of a method for operating according to one embodiment;

[0027] Figure 3 A schematic diagram of a potential field according to an embodiment;

[0028] Figure 4 A schematic diagram of a potential field according to an embodiment;

[0029] Figure 5 A schematic diagram of a potential field according to an embodiment;

[0030] Figure 6 A schematic diagram of a potential field according to an embodiment;

[0031] Figure 7Schematic diagram of a potential field according to an embodiment.

[0032] In the following description of advantageous exemplary embodiments of the present invention, identical or similar reference numerals are used for similarly acting elements that are shown in the various figures, wherein a repeated description of these elements is omitted. DETAILED DESCRIPTION

[0033] Figure 1 A schematic diagram of a vehicle 100 is shown having a device 120 according to one exemplary embodiment. Device 120 is configured for operating vehicle 100. In other words, device 120 is configured for controlling the operation of vehicle 100. Vehicle 100 is a motor vehicle, such as a land vehicle, in particular a passenger car, truck, or other commercial vehicle. Vehicle 100 is suitable for highly automated driving or highly automated driving operation.

[0034] Vehicle 100 has a plurality of sensor devices 102, 104, 106. Figure 1 In the illustration, only three sensor devices 102, 104, and 106 are shown by way of example. First sensor device 102 is embodied, for example, as a radar sensor for sensing the surroundings of vehicle 100, second sensor device 104 is embodied, for example, as a camera for sensing the surroundings of vehicle 100, and third sensor device 106 is embodied, for example, as a lidar sensor for sensing the surroundings of vehicle 100. First sensor device 102 is configured to provide first sensor data 112, which, according to the exemplary embodiment shown here, represents the surroundings of vehicle 100 sensed by radar. First sensor device 102 is also configured to provide first sensor status data 113, which represents at least one status variable regarding the current state of first sensor device 102. Second sensor device 104 is configured to provide second sensor data 114, which, according to the exemplary embodiment shown here, represents the surroundings of vehicle 100 sensed by camera optics. Second sensor device 104 is further configured to provide second sensor state data 115, which represent at least one state variable regarding the current state of second sensor device 104. Third sensor device 106 is configured to provide third sensor data 116, which, according to the exemplary embodiment shown here, represent the surroundings of vehicle 100 sensed by means of a lidar. Third sensor device 106 is further configured to provide third sensor state data 117, which represent at least one state variable regarding the current state of third sensor device 106.

[0035] Vehicle 100 also has an operating device 120 or operating device 120. Device 120 is connected to sensor devices 102, 104, 106 in a signal-transmitting manner. Device 120 is designed to generate a fusion signal 129 using sensor data 112, 114, 116 and sensor status data 113, 150, 117 as input data 121, which can be used to operate vehicle 100.

[0036] Device 120 is configured to read in sensor data 112, 114, 116 and sensor status data 113, 150, 117 from sensor devices 102, 104, 106 as input data 121. According to the exemplary embodiment shown here, device 120 has a generating device 124 and a determining device 126 as well as an input interface 122 and an output interface 128. In this case, device 120 is configured to read in input data 121 from input interface 122 to sensor devices 102, 104, 106. Generating device 124 is configured to generate a potential field using input data 121. In this case, when generating the potential field, generating device 124 is configured to use input data 121 as attractive and repulsive potentials of the potential field. In particular, generating device 124 is configured to provide potential field data 125 representing the generated potential field to determining device 126. Determining device 126 is configured to generate fusion signal 128 using potential field data 125. To this end, determination device 126 is designed to determine a trajectory through the potential field in order to use this trajectory to generate a fusion signal 129 for fusing input data 121 to perform sensor data fusion for highly automated driving operation of vehicle 100. Within the scope of sensor data fusion, sensor data 112, 114, 116 are weighted using fusion signal 129, for example.

[0037] According to the exemplary embodiment shown here, device 120 is also configured as an output interface 128 for providing a fusion signal 129 for outputting the fusion signal to a device 132 of a system 130 for sensor data fusion of vehicle 100. According to the exemplary embodiment shown here, vehicle 100 also includes system 130. System 130 includes at least device 132. Device 132 is connected to sensor devices 102, 104, and 106 in a signal-transmitting manner. According to one exemplary embodiment, device 120 is implemented as part of system 130. According to another exemplary embodiment, device 120 is implemented separately from system 130 and is connected to system 130 in a signal-transmitting manner.

[0038] Figure 2A flow chart of a method 200 for operation according to an embodiment is shown. The method 200 can be implemented to operate a vehicle, in particular a vehicle for highly automated driving or highly automated driving operation. In particular, the method 200 can be implemented to operate Figure 1 Here, the method 200 can be used Figure 1 device or similar equipment to implement.

[0039] In a read-in step 210 , input data is read in, including sensor data and sensor status data from a plurality of sensor devices of the vehicle. Next, in a generation step 220 , a potential field is generated using the input data read in the read-in step 210 . The input data is used as the attractive and repulsive potentials of the potential field. Next, in a determination step 230 , a trajectory is determined using the potential field generated in the generation step 220 . This trajectory is then used to generate a fusion signal for fusing the input data, thereby performing sensor data fusion for highly automated driving of the vehicle.

[0040] According to one exemplary embodiment, method 200 also has a providing step 240 , which provides the fusion signal generated within the scope of determining step 230 in order to output it to an interface of a device of a system for sensor data fusion of a vehicle.

[0041] Figure 3 A schematic diagram of a potential field 325 according to an embodiment is shown. Here, the potential field 325 corresponds to or is similar to the potential field 325 represented by Figure 1 The potential field represented by the potential field data in . In other words, Figure 3 More accurate representation of the quantitative 3D potential field with fused sensor data and the maximum critical ) 301 to the safest state or the state with the least criticality 303. Maximum criticality 301 may be assigned a value of 1. Minimum criticality 303 may be assigned a value of 0. Potential field 325 shows a first correlation 305 or first relationship 305 between the criticality and the sensor range and / or sensor quality, and a second correlation 307 or second relationship 307 between the criticality and the vehicle speed.

[0042] Figure 4 Schematic diagram of a potential field 325 according to an embodiment is shown. Figure 4 The potential field 325 in FIG. 1 additionally shows a plurality of sensor-specific critical peaks 409 and a reference Figure 1 and 2 The trace 427 shown corresponds to Figure 3 In other words, Figure 4More specifically, a quantitative three-dimensional potential field is shown, which has fused sensor data and a trajectory 427, which serves as an optimized change curve or change path from the state of maximum criticality 301 to the safest state or the state of minimum criticality 303 on the scene, and the quantitative three-dimensional potential field has a sensor-specific critical peak 409.

[0043] Figure 5 A schematic diagram of a potential field 325 is shown according to one embodiment. Figure 5 The potential field 325 in is similar to Figure 4 The potential field in , where Figure 5 The potential field 325 in FIG. 3 is a quantitative three-dimensional potential field 325 with multiple different correlations in three varying fields or planes. In each plane, a trajectory 427 and multiple sensor-specific critical peaks 409 are marked. The first plane shows the potential field 325 generated by Figure 3 The known second correlation 307 between criticality and own speed or vehicle speed, and another correlation 505 between criticality and sensor fusion management. The second plane also shows another correlation 507 between criticality and sensor signal quality or sensor data quality, and an additional correlation 505a between criticality and own trajectory planning. Finally, the third plane also shows an additional correlation 507a between criticality and sensor reliability quality or sensor safety quality, and Figure 3 A second correlation 307 between the critical and the own speed or vehicle speed is known.

[0044] Figure 6 Schematic diagram of a potential field 325 according to one embodiment is shown. More specifically, Figure 6 Shown as a superposition plane in a unique field of change or state space Figure 5 In other words, Figure 6 3 shows a quantitative three-dimensional potential field 325 with fused sensor data and correlations combined in a unique state space. Here, multiple sensor-specific critical peaks 409 and trajectories 427 are also marked as combined trajectories.

[0045] Figure 7 Schematic diagram of a potential field 325 according to an embodiment is shown. Figure 7 The diagram and potential field 325 in Figure 7 In addition to the effect 709 caused by rain, the graph also shows the corresponding Figure 5 In other words, Figure 7 Quantitative three-dimensional potential field 324 is shown with fused sensor data and rain-induced influence 709. In this case, rain-induced influence 709 is shown in particular in the third plane or third variation field.

[0046] With reference to the above-mentioned drawings, the following embodiments are summarized again and briefly explained in a different way.

[0047] To extend the OODA time or maximize system availability, optimal values ​​for all sensor availability characteristics or sensor status data 113 , 115 , 117 , such as blindness, range, confidence factor, etc., are identified by executing method 200 or using device 120 . This results in a virtual 3D region as potential field 325 , which is influenced by external conditions or external influences 709 , such as weather, traffic conditions, dynamic conditions, etc. Input data 121 read in step 210 or using device 120 , in particular, includes, as sensor data 112 , 114 , 116 , environmental data representing environmental conditions in the environment surrounding vehicle 100 and driving data representing at least one physical variable of vehicle 100 's driving operation. Furthermore, the input data 121 includes, in particular, availability data representing the availability of the individual sensor devices 102 , 104 , 106 , as sensor status data 113 , 115 , 117 . The availability data include at least one confidence factor, at least one effective distance parameter, at least one blindness parameter, and / or at least one safety parameter regarding at least one of sensor devices 102 , 104 , 106 .

[0048] In the generation step 220 or with the aid of the generation means 124 of the device 120, these input data 121 are correlated to one another using a potential field model and / or a potential field function to form a three-dimensional potential field 325. Additionally or alternatively, the potential field 325 represents at least one predefined relationship between the selected input data 121 and the criticality in a unique state space, see Figures 3 to 7 305, 307, 505, 505a, 507, 507a in . According to one exemplary embodiment, in generation step 220 or with the aid of generation device 124 of device 120, potential field 325 is generated in real time and / or scenario-by-scenario and / or during highly automated driving operation of vehicle 100 using and adapting learned or predefined scenarios. Such algorithms based on potential field methods are particularly well-suited for intelligent sensor fusion management systems represented by device 120 or method 200 because of the resulting analytical representation, low memory usage, real-time computing power, dynamic adaptability, etc.

[0049] Here, according to one embodiment, the algorithm associates all available sensor information or input data 121 via a potential field model and dynamically generates a potential field 325 as a real-time 3D region. Optionally, the learned scene can also be adapted in a superimposed manner. The potential field 325 or potential field model consisting of a pull-in potential and a push-out potential can be described with the help of a potential field function. The potential field 325 is obtained by superimposing the pull-in potential and the push-out potential (i.e., the basic potential). The potential function can be expressed by the relation U final =U at +U re +U aux To describe. Here, U at represents the pulling or attracting part of the potential function, and U re represents the pushing or repelling part of the potential function. By applying the negative gradient on the right side of the relationship, the relationship becomes: final =F at +F re +F aux This resultant force is also called a virtual force. With this resultant force, an optimal trajectory 427 or a change path through the potential field 325 can be found, because the resultant force indicates the direction and speed relative to the target point.

[0050] Thus, trajectory 427 determined in determination step 230 or by determination device 126 of device 120, particularly using fusion signal 129, by system 130 for sensor data fusion of vehicle 100, shifts the operating state of vehicle 100 in highly automated driving operation to a state of minimal criticality 303. In particular, trajectory 427 identifies minimally critical associations between sensor state data 113, 115, 117. Additionally or alternatively, fusion signal 129 generated in determination step 230 or by determination device 126 of device 120 may result in a prolongation of the highly automated driving operation, a prolongation of the decision-making time, and / or a prolongation of the takeover time before interruption of the highly automated driving operation of vehicle 100.

[0051] According to one embodiment, the approaching potential and the pushing-out potential or the approaching force and the pushing-out force of the potential field 325 are defined in such a way that they optimally reflect the sensor data 112, 114, 116 and the sensor availability characteristics or the sensor status data 113, 115, 117. Thus, customer-specific and vehicle-specific data items can be realized. This also allows for smooth or continuous transitions between the individual states. Additionally, it is possible to freely select the sensor architecture and the system remains scalable, see also Figure 3 and Figure 4 .

[0052] exist Figure 5, a real traffic situation is shown by way of example with three different sensor states or a plurality of dependencies, such as a critical dependency with respect to the own speed, a critical dependency with respect to the sensor effective range, a critical dependency with respect to the own trajectory planning, for example, a dependency for trajectory selection, a critical dependency with respect to the sensor signal quality, for example, a dependency for a blindness indicator in bad weather, a critical dependency with respect to sensor fusion management, for example, a dependency for the number of connected sensor devices 102 , 104 , 106 , a critical dependency with respect to the sensor safety quality, for example, a dependency for creating a fallback layer in the event of a takeover by a “hostile” system. Figure 5 These dependencies 307, 505, 505a, 507, 507a are combined in a unique state space, see Figure 6 . Figure 7 It is also shown by way of example how a change in state due to rain, snow, etc. has an impact 709 on the entire sensor management and how easily a solution can be found with the aid of trajectory 427 .

[0053] If an embodiment includes an "and / or" relationship between a first feature and a second feature, this should be interpreted as: the embodiment includes both the first feature and the second feature according to one embodiment, and has either only the first feature or only the second feature according to another embodiment.

Claims

1. A method (200) for operating a vehicle (100), wherein: The method (200) comprises the following steps: reading in (210) input data (121), wherein the input data (121) comprises sensor data (112, 114, 116) and sensor status data (113, 115, 117) of a plurality of sensor devices (102, 104, 106) of the vehicle (100); generating (220) a potential field (325) using the input data (121), wherein the input data (121) is used as an attractive potential and a repulsive potential of the potential field (325); And determining (230) a trajectory (427) through the potential field (325) so as to use the trajectory (427) to generate a fusion signal (129) for fusing the input data (121) to perform sensor data fusion for highly automated driving operation of the vehicle (100), wherein the potential field is a three-dimensional potential field, the three-dimensional potential field having fused sensor data and the trajectory, which is a change curve from a maximum critical state to a minimum critical state, wherein the minimum critical state is the safest state.

2. The method (200) according to claim 1, characterized in that The trajectory (427) determined in the determination (230) step causes the operating state of the vehicle (100) in highly automated driving operation to transition to the least critical (303) state when the fusion signal (129) is used by the system (130) for sensor data fusion of the vehicle (100).

3. The method (200) according to claim 1 or 2, characterized in that The input data (121) read in the reading-in step (210) have, as sensor data (112, 114, 116), environmental data representing environmental conditions in the surroundings of the vehicle (100) and driving data representing at least one physical variable of the driving operation of the vehicle (100), and / or, have, as sensor status data (113, 115, 117), availability data representing the availability of the individual sensor devices (102, 104, 106), wherein the availability data have at least one confidence factor, at least one effective distance parameter, at least one blindness parameter and / or at least one safety parameter for at least one of the sensor devices (102, 104, 106).

4. The method (200) according to claim 1 or 2, characterized in that In the generating (220) step, the input data (121) are correlated to each other into a three-dimensional potential field (325) using a potential field model and / or a potential field function, and / or, the potential field (325) represents a predefined relationship (305, 307, 505, 505a, 507, 507a) between the selected input data (121) and the criticality combined in a unique state space.

5. The method (200) according to claim 1 or 2, characterized in that In the generation (220) step, the potential field (325) is generated in real time and / or scenario-by-scenario during highly automated driving operation of the vehicle (100) and / or is generated during highly automated driving operation of the vehicle (100) by using and adapting learned or predefined scenarios.

6. The method (200) according to claim 1 or 2, characterized in that The trajectory (427) determined in the determining (230) step identifies an association of the sensor state data (113, 115, 117) with a minimum criticality, and / or wherein, The fusion signal (129) results in a prolongation of the highly automated driving mode, a prolongation of the decision-making time, and / or a prolongation of the takeover time before interruption of the highly automated driving mode.

7. The method (200) according to claim 1 or 2, characterized in that A step of providing (240) the fused signal (129) is provided to output the fused signal to an interface (128) of a device (132) of a system (130) for sensor data fusion of the vehicle (100).

8. The method (200) according to claim 1 or 2, characterized in that The vehicle (100) is a highly automated driving vehicle.

9. A device (120) configured to carry out and / or control the steps of the method (200) according to any one of claims 1 to 8 in corresponding units (124, 126). 10 . A computer program product, configured to carry out and / or control the steps of the method ( 200 ) according to claim 1 .

11. A machine-readable storage medium having stored thereon the computer program product according to claim 10.

Images