Method for navigating a motor vehicle with at least partially automated driving functionality by means of an electronic computing device, a computer program product, a computer-readable storage medium and an electronic computing device

Abstract

The invention relates to a method for navigating a motor vehicle (12) with at least partially automated driving functionality by means of an electronic computing device (44) of the motor vehicle (12). The method comprises the steps: Receiving (S1) object recognition data (42) relating to the environment (38) of the motor vehicle (12) by the electronic computing device (44); Generating (S2A) a topographic map (10) of the environment (38) by the electronic computing device (44), wherein a topographic content of the topographic map (10) is derived from the object recognition data (42); Determining (S2B) a drivable space (14) of the topographic map (10) by the electronic computing device (44) according to at least one height criterion (48);The invention relates to the adaptation (S4) of a virtual destination rectangle (34) within the drivable space (14) by the electronic computing device (44) according to an adaptation loss function (52) of the electronic computing device (44); and the generation (S5) of a control signal (54) for the motor vehicle (12) by the electronic computing device (44) to move the motor vehicle (12) depending on the adaptation to a position in the environment (38) corresponding to the virtual destination rectangle (34). The invention further relates to a computer program product, a non-volatile computer-readable storage medium, and an electronic computing device (44).

Description

AREA OF INVENTION

[0001] The present invention relates to the field of motor vehicles. In particular, the present invention relates to a method for navigating a motor vehicle with at least partially automated driving functionality by means of an electronic computing device of the motor vehicle. Furthermore, the present invention relates to a corresponding computer program product, a corresponding non-volatile computer-readable storage medium, and a corresponding electronic computing device. BACKGROUND INFORMATION

[0002] According to the state of the art, as exemplified in document US 2023 / 0041498A1, systems and methods can be used to assist a driver while navigating a lane of a facility in autonomous operation. In one example method, a processor in a vehicle determines the vehicle's position within a lane in various ways, such as based on objects located near the lane, based on spatial coordinates, and / or based on a geofence defined around the facility. The vehicle then moves autonomously through the lane in a stop-and-go motion at a controlled speed, while maintaining lane centering and avoiding collisions. SUMMARY OF THE INVENTION

[0003] It is an object of the present invention to provide automated navigation of a motor vehicle in a narrow area, such as a lane through which motor vehicles are only allowed to drive in a line.

[0004] The object of the present invention is achieved by a method, a corresponding computer program product, a corresponding non-volatile, computer-readable storage medium, and a corresponding electronic computing device according to the independent claims. Advantageous embodiments are described in the dependent claims, the following description, and the figures.

[0005] One aspect of the invention relates to a method for navigating a motor vehicle with at least partially automated driving functionality by means of an electronic computing device of the motor vehicle. The electronic computing device acquires object detection data relating to the motor vehicle's surroundings. The electronic computing device generates a topographic map of the surroundings. Topographic content of the topographic map is derived from the object detection data. A navigable area of ​​the topographic map is determined by the electronic computing device according to at least one elevation criterion. A virtual destination rectangle is fitted into the navigable area by the electronic computing device according to a loss-of-fit function of the electronic computing device.The electronic computing device generates a control signal for the motor vehicle in order to move the motor vehicle to a position in the environment corresponding to the virtual destination rectangle, depending on the fit.

[0006] Examples of object detection data include optical sensor data, such as photos or videos from at least one optical sensor, e.g., a camera operating at at least one wavelength; acoustic sensor data, e.g., from an ultrasonic sensor; radar data; LiDAR data; information about the field of view and / or range of the at least one sensor; and geometric information about the extent and location of a transmitting vehicle itself. Examples of object detection data also include combinations of the above examples, which are also known in the prior art as data fusion products. Examples of data relevant to the object detection task also include the results of analyses performed on sensor data, regardless of whether that sensor data is still available.For example, a detection system in one vehicle can transmit inferences about a detected object to a second vehicle without transmitting sensor information about the object. In this case, the independent inferences are still object recognition data.

[0007] The term "environment" here encompasses, but is not limited to, all physical locations that are relevant to the current trajectory of the motor vehicle. In particular, the environment includes all physical features relevant to the vehicle's navigation, such as other motor vehicles, pedestrians, cyclists, poles, curbs, road markings, signs, buildings, and traffic cones.

[0008] A topographic map is a digital structure containing spatially resolved elevation information. The topographic map may be an intermediate product of a process that is not accessible to the vehicle user.

[0009] However, the topographic map can, for example, be presented to a human occupant of the vehicle via a display device. In this case, the topographic map may include at least one display feature intended to convey information to a human viewer or to improve accessibility for them, but which is not necessary for the execution of the procedure by the electronic computing device. Examples of display features include a colored map indicating elevation and / or visibility levels associated with various physical features of the environment, a fixed orientation of the map relative to the vehicle, or a dashed box on the map indicating the physical extent of the vehicle.

[0010] The drivable space encompasses any section of the environment that the electronic computing device determines to be suitable for traversing by the motor vehicle, provided that traversing the vehicle does not require exceeding the manufacturer's intended operating parameters. For example, an unpaved, off-road road may not be designated as a drivable space by the electronic computing device because its surface may be so uneven that it poses a contact risk to the vehicle's chassis. Similarly, a sidewalk may not be designated as a drivable space by the electronic computing device because traffic regulations apply at the vehicle's current location. Furthermore, the drivable space must be directly accessible to the vehicle from its current position.For example, if the motor vehicle is traveling on a road that is passable in both directions and has a median strip, a section of the road that is allocated to traffic traveling in the opposite direction of the motor vehicle cannot be determined by the electronic computing device as a passable space, unless the motor vehicle turns around at an intersection, for example.

[0011] The electronic computing device uses at least the elevation criterion to determine whether a space in the environment, as depicted on the topographic map, can be included in the drivable space. For example, the electronic computing device can apply an elevation threshold according to which certain physical features are classified as too abrupt and / or with too great an elevation difference to be traversed. In this example, a sidewalk might be classified as non-drivable according to the threshold because a curb / street boundary associated with the sidewalk has too great a height difference to the actual surface on which the vehicle is currently traveling.

[0012] The drivable space can be derived, for example, by starting with an elevation value associated with a current surface on which the vehicle is located. The derivation can then be performed by iteratively enlarging a drivable space radially outward from the vehicle's current position. In each iteration, the electronic computing device can test an additional distance of, say, 25 cm extending in a specific direction from a boundary of the drivable space as updated in one of the previous iterations of the derivation. If, for example, a detected elevation of the additional distance deviates from that of the previous boundary by more than a predefined tolerance level, the derivation can stop for that specific direction and consider another direction.For example, the derivation can divide the vehicle's orientation into a predefined number of angles (e.g., 18 angles), separated by, say, twenty degrees, each of which can be taken into account in this derivation. In this way, areas that are too high or too low for the vehicle to pass through according to the manufacturer's specifications can be identified and excluded from the drivable space.

[0013] During this iterative derivation, the electronic computing device can require that the expansion of the drivable space does not lead to regions that are too narrow for the vehicle. For example, the electronic computing device can exclude the space to the left and right of a second vehicle on a single-lane road. However, the exclusion of excessively narrow areas can also occur during the step of adjusting the virtual destination rectangle.

[0014] Adapting the virtual destination rectangle to the drivable space may involve the electronic computing device examining at least one virtual destination candidate rectangle. Each virtual destination candidate rectangle may vary in offset (i.e., position) and rotation, but must have fixed proportions that correspond to those of the vehicle. Alternatively, the virtual destination may be slightly enlarged, for example, by inserting buffer zones around its perimeter. Including these buffer zones can, for instance, enable the detection of unfavorable bottlenecks, as the buffer zones must not lie within the drivable space.

[0015] The at least one candidate rectangle can be tested using the loss of fit function. For each of the at least one current candidate rectangle, the loss of fit function can output a loss value that can be minimized to find the candidate rectangle best suited to the procedure.

[0016] The at least one candidate rectangle can also be examined using one or more filters, whereby certain undesirable features of the at least one candidate rectangle can lead to its automatic disqualification, possibly without any loss calculation. For example, a filter can require that all candidate rectangles lie entirely within the traversable space. This filter can, for example, automatically prevent the electronic computing device from attempting to lay a path through a too narrow area of ​​the traversable space because at least one side of the candidate rectangle lies outside the traversable space.

[0017] The generation and testing of the at least one candidate rectangle can be performed alternately. For example, the electronic computing device can execute an iterative process in which one candidate rectangle is generated and tested before a subsequent candidate rectangle is generated. This process might initially involve generating candidate rectangles near or at the vehicle's location, followed by generating candidate rectangles that move progressively further away from the vehicle in the direction of a navigation destination. This iteration can offer the advantage of automatically ensuring that the vehicle can reach the candidate rectangle. In contrast, for example, starting the generation of candidate rectangles at the navigation destination might result in the evaluation of at least one candidate rectangle that is separated from the vehicle's current position by impassable space.

[0018] The invention includes further developments with additional advantages.

[0019] One example of a loss-of-fit function penalizes candidate rectangles according to their distance from a programmed destination of the vehicle. By applying this loss-of-fit function, the electronic computing device can prioritize movement toward the programmed destination. A second example of a loss-of-fit function penalizes candidate rectangles according to a user-friendliness heuristic. By applying this loss-of-fit function, the electronic computing device can prioritize maintaining a current orientation over turning, especially when the physical extent of the area corresponding to the drivable space is small compared to the physical extent of the vehicle.

[0020] A loss of fit function can also be a composite of different loss of fit functions. For example, the loss of fit functions described in the two previous examples can be summed in quadrature to produce a loss of fit function that represents a compromise between their two priorities.

[0021] As a result of applying the above procedure, the electronic computing device can optimize the movement of the motor vehicle according to at least one navigation goal, as encoded in the appropriate loss function, while complying with the limitations imposed by the surrounding topography. In this way, the motor vehicle's automatic navigation can be improved, thereby achieving the previously formulated goal.

[0022] In a further development of the invention, when adapting the virtual destination rectangle, at least a portion of the drivable space is discretized into at least one candidate rectangle whose virtual extent corresponds to a physical extent of the vehicle. In other words, each candidate rectangle generated according to this development lies entirely within the drivable space. However, at least one area of ​​the drivable space can be excluded from a specific discretization, for example, if the area exceeds a stored maximum distance or falls below a stored minimum distance to the vehicle.

[0023] The positions of the candidate rectangles into which the part of the drivable space is discretized can be calculated mathematically, e.g. using a Minkowski difference algorithm that uses a Minkowski difference between a rectangle that bounds a current position of the motor vehicle and a polygon that bounds the part of the drivable space.

[0024] If the application of the expansion results in at least two candidate rectangles, the candidate rectangles can overlap, at least partially. For example, a first candidate rectangle can represent a westward shift of a second candidate rectangle by a quarter of a meter, while an eastward extension of each rectangle corresponds to a physical distance of three meters. Another example: The first candidate rectangle can represent a 180-degree rotation of the second candidate rectangle without any shift being involved.

[0025] In a further development stage, the step of generating the topographic map and / or the step of inserting the virtual destination rectangle is triggered when the electronic computing device detects that the motor vehicle has crossed at least one geofence boundary.

[0026] A digital map used by the electronic computing device can employ geofences to identify areas of the map that belong to specific businesses, for example. A fast-food restaurant's lane, for instance, can be geofenced to associate the lane with the restaurant's primary building. By detecting geofences, a vehicle with at least partially automated driving functionality can, for example, automatically switch to a different self-driving navigation process, such as one designed for navigating a highway.

[0027] In a further development stage, the process steps are carried out in an endless loop until the electronic computing device terminates the loop upon detecting the fulfillment of a stored loop termination criterion.

[0028] For example, if the vehicle's electronic computer and / or other onboard navigation system is programmed with a specific destination, the stored criterion for completing the loop can be the vehicle's arrival at that destination. Upon arrival, the self-driving mode can be terminated.

[0029] If the method is configured to be used by the electronic computing device in conjunction with at least one other autonomous navigation process, the detection of the fulfillment of the stored loop closure criterion can also trigger a switch to the at least one other autonomous navigation process. An example of a suitable stored loop closure criterion for this case could be a driving environment criterion. In particular, if the electronic computing device is configured to use the inventive method for navigating the vehicle in a narrow and / or low-traffic area, such as a throughway, the stored loop closure criterion could be a detection that the vehicle has left the throughway.

[0030] In a further development stage, at least some of the object recognition data will be received by the electronic computing device from a map information server.

[0031] For example, the map information server can contain at least one topographic map that can be downloaded by the electronic computing device. This development can offer the advantage that the electronic computing device is supplied with object recognition data that cannot be detected by at least one sensor of the vehicle at a given time, for example, if the line of sight of the at least one sensor to a particular object is blocked by another vehicle.

[0032] In a further development stage, at least some of the object recognition data will be received from at least one other motor vehicle in the vicinity of the electronic computing device.

[0033] For example, at least one other nearby vehicle can exchange sensor data and / or sensor data analysis products with the vehicle. This development can be advantageous for a similar reason to the previously mentioned development. In particular, with a larger amount of sensor data available to the electronic computing device, the accuracy of object detection and / or classification can be improved.

[0034] In a further embodiment, the method includes the additional step of generating a control signal by the electronic computing device to perform at least one stop at at least one interaction point. The term "interaction point" is used here to denote a location where a human occupant of the motor vehicle interacts with at least one unit located outside the motor vehicle and situated at the interaction point.

[0035] For example, a fast-food drive-thru can contain multiple interaction points. These include microphones where orders can be placed, windows where orders can be paid for, and windows where the food items can be picked up. This approach offers the advantage of allowing a vehicle user to interrupt their navigation without having to take over the vehicle's navigation. An interaction point can be detected automatically, for example, when the vehicle's detection system detects a payment window. Alternatively or additionally, an interaction point can also be specified by the user. For instance, during a multi-hour drive, the user can specify a stop at a particular gas station.

[0036] In particular, the method is a computer-implemented method. Therefore, one aspect of the invention relates to a computer program product consisting of computer-readable instructions for carrying out a method according to the preceding aspect.

[0037] One aspect of the invention relates to a non-volatile, computer-readable storage medium containing the computer program product according to the preceding aspect.

[0038] One aspect of the invention relates to an electronic computing device of a motor vehicle, wherein the electronic computing device is configured to carry out a method according to the preceding aspect. In particular, the method is carried out by the electronic computing device.

[0039] An "electronic computing device" can be understood to mean, in particular, a data processing device that includes processing circuits. The electronic computing device can therefore, in particular, process data in order to perform arithmetic operations. This can also include operations for performing indexed access to a data structure, e.g., a lookup table (LUT).

[0040] In particular, the electronic computing device may comprise one or more computers, one or more microcontrollers, and / or one or more integrated circuits, such as one or more application-specific integrated circuits (ASICs), one or more field-programmable gate arrays (FPGAs), and / or one or more systems-on-a-chip (SoCs). The electronic computing device may also include one or more processors, such as one or more microprocessors, one or more central processing units (CPUs), one or more graphics processing units (GPUs), and / or one or more signal processors, in particular one or more digital signal processors (DSPs) or neural processing units (NPUs). The electronic computing device may also comprise a physical or virtual group of computers or other units of the aforementioned type.

[0041] In various embodiments, the electronic computing device comprises one or more hardware and / or software interfaces and / or one or more storage units.

[0042] A storage unit can be a volatile data storage device, e.g., a dynamic random access memory (DRAM) or static random access memory (SRAM), or a non-volatile data storage device, e.g., a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a flash memory or flash EEPROM, a ferroelectric random access memory (FRAM), a magnetoresistive random access memory (MRAM), or a phase-change random access memory (PCRAM).

[0043] Furthermore, the present invention relates to a vehicle comprising the electronic computing device according to the preceding aspect.

[0044] Further advantages, features, and details of the invention will become apparent from the following description of preferred embodiments and from the drawings. The features and combinations of features mentioned above in the description, as well as those mentioned in the following description of the figures and / or illustrated in the figures alone, can be used not only in the combinations specified, but also in any other combination or on their own, without departing from the scope of the invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] The new features and properties of the disclosure are set forth in the accompanying claims. The accompanying drawings, which form part of this disclosure, illustrate exemplary embodiments and, together with the description, serve to explain the disclosed principles. The same numbers are used in the figures to refer to identical features and components. Some embodiments of systems and / or methods according to the embodiments of the present subject matter are described below only by way of example and with reference to the accompanying figures.

[0046] The drawings show in: Fig. 1. An example of a topographic map that can be generated during the execution of the procedure; Fig. 2 a three-part schematic top view of the movement of a motor vehicle controlled by an electronic computing device performing an embodiment of the method; Fig. 3 a schematic top view of a motor vehicle with an electronic computing device according to one aspect of the invention; Fig. 4 a supplementary view to Fig. 3, which outlines various areas to which reference is made during the execution of an embodiment of the method; Fig. 5 a supplementary view to Fig. 3 and Fig. 4, which represents an example of the discretization of a drivable space into multiple virtual destinations; and Fig. 6 a schematic flowchart according to one embodiment of the method.

[0047] In the figures, identical elements or elements with the same function are indicated by the same reference symbols. DETAILED DESCRIPTION

[0048] The following detailed description of exemplary embodiments of the disclosure refers to the accompanying drawings, which form part of this document and illustrate specific embodiments in which the disclosure can be implemented. These embodiments are described in sufficient detail to enable those skilled in the art to put the disclosure into practice, and it is understood that other embodiments may also be used and modifications made without affecting the scope of this disclosure. The following description is therefore not to be understood as restrictive.

[0049] Although the disclosure permits various modifications and alternative forms, certain embodiments are illustrated by way of example in the drawings and described in detail below. It should be understood, however, that the disclosure is not intended to be limited to the specific forms disclosed, but rather, on the contrary, to cover all modifications, equivalents, and alternatives that fall within the scope of the disclosure.

[0050] Fig. Figure 1 shows an example of a topographic map 10 that can be generated during the execution of the procedure. A rectangular outline in the center indicates a motor vehicle 12 containing an electronic computing device that generates the topographic map 10, which is not shown here. The motor vehicle 12 may currently be located along a flat, slightly curved road, which in this example can represent a drivable space 14.

[0051] The topographic map 10 can, in this example, display variations in surface elevation through a series of contour lines 16, 18, 20, 22, 24, and 26. The two lines 16, which delineate the drivable space 14, can, in this example, correspond to a curb, representing a height difference of six inches relative to the drivable space 14. Furthermore, lines 18 and 20, in this example, can represent elevation differences associated with the physical features of a fast-food drive-through area. Examples of such features include menu signs, buildings, and trash cans.

[0052] On the other side of the vehicle 12, contour lines 22, 24, and 26 can represent different elevations along a descending hill. The density of contour lines 22, 24, and 26 above the feature can be predetermined by a stored spacing rule. For example, the electronic computing device can automatically place a new contour line for every six-inch change in elevation compared to a previous contour line.

[0053] In the example of Fig. 2. The steps of the procedure are executed in an endless loop until the electronic computing device terminates the loop after detecting the fulfillment of a stored loop termination criterion. Specifically, in Fig. 2 the topographic maps 10 from three successive executions of the procedure are shown, wherein Fig. 2a a first time step and Fig. 2c describes a third time step.

[0054] In the center of each topographic map 10 is the rectangular outline which, as in Fig. 1, which displays vehicle 12, also referred to in this example as first vehicle 12. In this example, first vehicle 12 can navigate through a drive-through area of ​​a pharmacy.

[0055] In this example, the topographic maps can be compared to 10. Fig. 1 can be simplified insofar as only two topographical levels are specified: the drivable space 14 and the inaccessible space 28. In this example, the definition of the drivable space 14 can also include spaces that are inaccessible to the motor vehicle 12 due to their narrowness, such as the spaces above in Fig. 2a. In this example, impossibly narrow spaces can be automatically excluded in a later step, for example when fitting a virtual destination rectangle into the drivable space 14.

[0056] Some sections of the non-vehicular space 28 may be dynamic and change their extent and / or position relative to the first motor vehicle 12 when it is stationary. For example, a rectangle at the top in Fig. 2a in this example corresponds to a second motor vehicle 30. Fig. 2b the movement of the second motor vehicle 30 can be recognized if the corresponding rectangle moves relative to a stationary feature 32, here a pair of projections.

[0057] In each topographic map 10, a virtual destination rectangle 34 is marked by a second outline 34. The virtual destination rectangle 34 represents a planned navigation step for the electronic computing device that steers the motor vehicle 10 towards a longer-term navigation destination. In this example, the longer-term navigation destination can be a point at which the vehicle leaves the drive-in area. Fig. Figure 2b shows the motor vehicle 10, which has moved approximately to where the destination rectangle 34 is located. Fig. 2a was located, and Fig. 2c similarly shows the motor vehicle 10, which has moved approximately to where the destination rectangle 34 is located. Fig. 2b was located.

[0058] In Fig. Figure 3 depicts the first vehicle 12 in the queue behind the second vehicle 30 in a drive-through area of ​​a fast-food restaurant 36. The environment 38 of the first vehicle 12 is sketched. In this example, an optical sensor 40, here a camera, of the first vehicle 12 can acquire object recognition data 42, from which the electronic computing device 44 can determine the environment 38. Alternatively or additionally, the environment 38 can be determined, for example, based on the location of the first vehicle 12, e.g., encoded in coordinates of the Global Positioning System (GPS coordinates), within a map with street and terrain features.

[0059] In this example, at least some of the object recognition data 42 can be received by the electronic computing device 44 from a map information server 46. In this example, the object recognition data 42 can be a set of polygons describing the drivable space 14 and the non-drivable space 28 of the drive-through area, and the map information server 46 can be a manufacturer-provided backend database that is automatically accessed by a network device, such as a Wi-Fi card, of the electronic computing device 44.

[0060] For simplicity, the map information server 46 is shown to be located near the first vehicle 12. However, the map information server 46 does not necessarily have to be physically located in the vicinity 38. For example, the map information server 46 could be located at the headquarters of a manufacturer of the first vehicle 12 and communicate with the first vehicle 12 via a mobile phone mast.

[0061] In this example, the electronic computing device 44 can receive at least some of the object recognition data 42 from at least one other motor vehicle in the vicinity 38. In this example, the electronic computing device 44 can receive some object recognition data 42 from the second motor vehicle 30, which relates to an area of ​​the vicinity 38 that cannot currently be perceived by the optical sensor 40, for example, an area directly in front of the second motor vehicle 30. In this example, the second motor vehicle 30 can transmit at least some of the object recognition data 42 via a cellular network.

[0062] The electronic computing device 44 generates the topographic map 10 based on the object recognition data 42, in this example from the optical sensor 40. Furthermore, the electronic computing device 44 determines the drivable space 14 according to at least one height criterion 48, in this example one stored in the electronic computing device 44.

[0063] The drivable space 14, in which the first motor vehicle 12 in the queue is located, is bounded by a pair of curbs 50. The curbs can be identified by the electronic computing device 44 as areas of the non-drivable space 28. In this example, however, the surrounding area 38 can be defined to extend, for example, twenty meters beyond the nearest approach to the non-drivable space 28 in order to monitor cyclists and pedestrians who may be approaching the drivable space 14.

[0064] The electronic computing device 44 adapts the virtual destination rectangle 34 within the drivable space 14 according to an adaptation loss function 52 of the electronic computing device 44. The electronic computing device 44 generates a control signal, here referred to as the first control signal 54, to move the first motor vehicle 12 to a position in the environment 38 that corresponds to the virtual destination rectangle 34.

[0065] In this example, the loss of fit function 52 can prioritize proximity to at least one interaction point 56, 58. In particular, in this example, the fast-food restaurant 36 can be a sufficiently large establishment in which two customer interaction windows 56, 58 are occupied: a first window 56 for accepting payments and a second window 58 for dispensing the ordered food. The loss of fit function 52 can therefore lead the electronic computing device 44 to a Fig. At the time shown in point 2, a candidate is preferentially selected for a virtual destination rectangle that is not only further down the road, but also further to the left.

[0066] In this example, the electronic computing device 44 can generate a stop control signal 60 to terminate at least one stop at at least one interaction point 56, 58. This is further illustrated in Fig. At the time shown in 3, the electronic computing device 44 may in particular have generated the stop control signal 60 in order to stop at the first interaction point 56 until, for example, an occupant of the first motor vehicle 12 interacts with a resume button of the electronic computing device 44.

[0067] Fig. Figure 4 shows a supplementary view of Fig. 3 with different areas defined for the procedure. In this example, the drivable space 14 can correspond to a section of a road within the passage area, where the section can begin near the bumper of the second motor vehicle 30 and extend upwards out of sight. In this example, the drivable space 14 must not include areas that are too narrow to allow passage with the first motor vehicle 12.

[0068] The virtual destination rectangle 34, selected by the electronic computing device 44 after applying the matching loss function 52 to various virtual destination candidate rectangles, is shown near the first interaction point 56. Within the framework of the first control unit 54, the first motor vehicle 12 can be controlled in various ways, for example by braking, turning, and activating an acceleration mechanism.

[0069] In this example, the step of generating the topographic map 10 and / or the step of adjusting the virtual destination rectangle 34 is triggered when the electronic computing device 44 detects that the first motor vehicle 12 has crossed at least one boundary of the geofence 62. In this example, the geofence 62 can encompass the entire fast-food restaurant 36, including the drive-through area.

[0070] In this example, geofence 62 can be specified as an area of ​​global positioning coordinates (GPS coordinates) that are downloaded by the electronic computing device 44 from the map information server 46. In this example, the electronic computing device 44 can detect a crossing of a boundary of geofence 62 by comparing the GPS coordinates of the first motor vehicle 12 with the area assigned to geofence 62.

[0071] Fig. Figure 5 shows an example of how the electronic computing device 44 is used in the Fig. 3 and Fig. In the situation depicted in Figure 4, the drivable space 14 can be discretized into virtual destination candidate rectangles. For simplicity, in this representation, each candidate rectangle is visualized by a point corresponding to a midpoint of the candidate rectangle and by an arrow corresponding to an orientation of that candidate rectangle. Each arrow represents the direction in which the front of the first vehicle 12 could point if the first vehicle 12 were positioned according to that candidate rectangle. Therefore, the points do not extend to the edges of the drivable space 14, as points near the edges of the drivable space 14 would correspond to candidate rectangles that are not entirely contained within the drivable space 14.

[0072] In this example, the electronic computing device 44 can attempt to conserve computing resources by sampling regions of the traversable space 14 with a density proportional to its proximity to the first interaction point 56. For example, in the upper left area of Fig. 5 more candidate rectangles than in any other area of Fig. 5.

[0073] Fig. Figure 6 shows a schematic flowchart that describes an exemplary control flow of the procedure.

[0074] In a first step S1, the electronic computing device 44 receives the object recognition data 42 from at least one sensor. Examples of sensors are optical sensors such as cameras, LiDAR sensors, and radar sensors.

[0075] In a second step S2, the electronic computing device 44 generates the topographic map 10, which is referred to here as the local topographic map 10. In this example, the electronic computing device 44 can identify interaction points 56, 58 as part of a labeling step in the generation of the local topographic map 10.

[0076] In a first part S2A of the second step S2, the electronic computing device 44 detects obstacles in the environment 38 by calculating the heights of different areas of the environment 38 from the object recognition data 42. In a second part S2B of the second step S2, the electronic computing device 44 determines the drivable space 14 according to at least the height criterion 48, in this example by detecting at least one lane on which the first motor vehicle 12 can drive.

[0077] In a third part S2C of the second step S2, the electronic computing device 44 in this example can identify three interaction points. In addition to the payment window 56 and the food pickup window 58 introduced in a previous example, the electronic computing device 44 can identify a location where the occupant of the first motor vehicle 12 can place an order for specific food items. This location might, for example, include a microphone positioned near a menu board.

[0078] In a fourth part S2D of the second step S2, the electronic computing device 44 in this example can perform an additional computer vision step to detect and read at least one sign in the environment 38. The at least one sign could, for example, be a speed limit sign indicating a maximum permissible speed of eight km / h. The electronic computing device 44 can then, in this example, incorporate this speed limit into its motion planning.

[0079] In a third step S3, the electronic computing device 44 can receive at least some of the object recognition data 42 from a map information server 46. In particular, in this example, the electronic computing device 44 can download a topographic auxiliary map from the map information server 46. The electronic computing device 44 can then compare the topographic auxiliary map with the local topographic map 10 to identify potential blind spots and inaccuracies that affect the local topographic map 10.

[0080] In a fourth step S4, the electronic computing device 44 plans the path of the first motor vehicle 12 by adjusting the virtual destination rectangle 34 within the drivable space 14 according to the matching loss function 52.

[0081] In a fifth step S5, the electronic computing device 44 generates the first control signal 54 for the first motor vehicle 12 in order to move the first motor vehicle 12, depending on the fit, to a position in the environment 38 that corresponds to the virtual target rectangle 34.

[0082] In a sixth step S6, the electronic computing device 44 can generate a control signal 60 to stop, in order to complete at least one stop at the at least one interaction point 56, 58.

[0083] In a seventh step S7, the electronic computing device 44 can check whether a stored loop termination criterion is met. If the electronic computing device 44 determines that the stored loop termination criterion is not met, it can initiate a new iteration of the procedure. Otherwise, the procedure can be terminated in this example.

[0084] In this example, the seventh step S7 can be at the end, but in another example, the electronic computing device 44 can also perform the check at any other point in the procedure. Furthermore, in another example, the electronic computing device 44 can check multiple times throughout the entire procedure whether the stored loop termination criterion is satisfied.

[0085] Taken together, the examples show how a process for the iterative evaluation of virtual spots can be carried out to support path planning in drive-through.

[0086] In this document, the word "exemplary" is used to mean "serving as an example, instance, or illustration." Each embodiment or implementation of the subject matter described herein as "exemplary" is not necessarily to be understood as preferred or advantageous over other embodiments.

[0087] The terms "includes," "contains," or other variations thereof are intended to cover non-exclusive inclusion, so that a setup, device, or process that includes a list of components or steps may contain not only those components or steps but may also contain other components or steps not expressly listed or belonging to such setup, device, or process. In other words, one or more elements in a system or device preceded by "includes" or "include" do not, without further limitations, preclude the existence of other elements or additional elements in the system or process. List of reference symbols 10 topographic map 12 (first) motor vehicle 14 driveable space 16 contour lines 18 contour lines 20 contour lines 22 contour lines 24 contour lines 26 contour lines 28 non-drivable space 30 second motor vehicle 32 stationary function 34 virtual destination rectangle 36 Fast food restaurants 38 Surroundings 40 optical sensor 42 data points for object recognition 44 electronic calculating device 46 map information servers 48 Altitude criterion 50 curb edges 52 Loss of fit function 54 first control signal 56 first interaction point 58 second interaction point 60 Control signal to stop 62 Geofence S1-S7 Steps of the procedure QUOTES INCLUDED IN THE DESCRIPTION

[0000] This list of documents cited by the applicant was automatically generated and is included solely for the reader's convenience. The list is not part of the German patent or utility model application. The DPMA accepts no liability for any errors or omissions. Cited patent literature

[0000] US 2023 / 0 041 498 A1

[0002]

Claims

[1] Method for navigating a motor vehicle (12) with at least partially automated driving functionality by means of an electronic computing device (44) of the motor vehicle (12), comprising the steps: - Obtaining (S1) object detection data (42) relating to an environment (38) of the motor vehicle (12) by the electronic computing device (44); - Generating (S2A) a topographic map (10) of the surroundings (38) by the electronic computing device (44), wherein a topographic content of the topographic map (10) is derived from the object acquisition data (42); - Determining (S2B) a navigable space (14) of the topographic map (10) by the electronic computing device (44) according to at least one height criterion (48); - Fitting (S4) a virtual destination rectangle (34) within the navigable space (14) by the electronic computing device (44) according to a fit loss function (52) of the electronic computing device (44); and - Generating (S5) a control signal (54) by the electronic computing device (44) for the motor vehicle (12) to move the motor vehicle (12) depending on the adaptation to a position in the environment (38) corresponding to the virtual destination rectangle (34). [2] Method according to claim 1, wherein the step of fitting (S4) the virtual destination rectangle (34) includes a discretization of at least a part of the mobile space (14) into at least one candidate rectangle, the virtual extent of which corresponds to a physical extent of the motor vehicle (12). [3] Method according to any of the preceding claims, wherein the step of generating the topographic map (10) and / or the step of fitting the virtual destination rectangle (34) is triggered when the electronic computing device (44) detects that the motor vehicle (12) has crossed at least one geofence boundary (62). [4] Method according to any one of the preceding claims, characterized by , that the steps of the procedure are carried out in an endless loop until the loop is terminated by the electronic computing device (44) upon detection (S7) of the fulfillment of a stored loop termination criterion. [5] Method according to one of the preceding claims, wherein at least some of the object recognition data (42) are received by the electronic computing device (44) from a map information server (46) (S3). [6] Method according to one of the preceding claims, wherein at least part of the object recognition data (42) is received by the electronic computing device (44) from at least one other motor vehicle (30) in the vicinity (38). [7] Method according to any of the preceding claims, comprising the additional step of generating (S6) a stop control signal (60) by the electronic computing device (44) to perform at least one stop at at least one interaction point (56, 58), i.e. at a place where a human occupant of the motor vehicle (12) interacts with at least one unit located outside the motor vehicle (12) and located at the interaction point (56, 58). [8] Computer program product containing computer-readable instructions for carrying out a method according to any one of claims 1 to 7. [9] Non-volatile, computer-readable storage medium containing the computer program product according to claim 8. [10] Electronic computing device (44) of a motor vehicle (12), wherein the electronic computing device (44) is configured to perform a method according to any one of claims 1 to 7.

Images