Method of operating detection device with interference handling using artificial neural network

Abstract

The invention relates to a method (44) for operating a detection device, in particular a detection device (14) for a vehicle (10), a detection device, a driver assistance system and a vehicle. In the method (44), at least one electromagnetic beam (26) is emitted by a detection device into a monitoring region of the detection device. The detection device receives at least one electromagnetic beam from the monitoring region and converts it into at least one detection variable (40) which can be processed with at least one evaluation device. Based on the at least one detected variable (40), at least one interference process is performed using at least one artificial neural network (CNN). In at least one interference process, at least one interference analysis (46) is performed, in which at least one detection variable (40) is examined for a known interference pattern (52) of the interference variable using at least one artificial neural network (CNN). If at least one known interference pattern (52) is identified, the at least one detection variable (40) is corrected by an interference variable belonging to the at least one identified interference pattern (52).

Description

Technical Field

[0001] The invention relates to a method for operating a testing device, in particular a testing device for a vehicle, wherein:

[0002] using a detection device to emit at least one electromagnetic beam into a monitoring area of ​​the detection device,

[0003] receiving at least one electromagnetic beam from the monitoring area using a detection device and converting it into at least one captured variable that can be processed using at least one evaluation device,

[0004] At least one disturbance handling process is performed based on at least one captured variable using at least one artificial neural network.

[0005] The invention also relates to a detection device, in particular a detection device for a vehicle,

[0006] having at least one transmitting device for transmitting an electromagnetic beam into a monitoring area of ​​the detection device,

[0007] having at least one means for receiving an electromagnetic beam from a surveillance area and for determining a capture variable from the received electromagnetic beam,

[0008] There is at least one device for performing a disturbance handling process based on captured variables, wherein the at least one device has at least one artificial neural network.

[0009] Furthermore, the invention relates to a driver assistance system, in particular for a vehicle, having at least one detection device, wherein the at least one detection device has:

[0010] at least one transmitting device for transmitting an electromagnetic beam into a monitoring area of ​​at least one detection device,

[0011] at least one means for receiving an electromagnetic beam from the monitoring area and determining a capture variable from the received electromagnetic beam,

[0012] At least one device for performing a disturbance handling process based on captured variables, wherein at least one device has at least one artificial neural network.

[0013] Furthermore, the invention relates to a vehicle having at least one detection device, wherein the at least one detection device has:

[0014] at least one transmitting device for transmitting an electromagnetic beam into a monitoring area of ​​at least one detection device,

[0015] at least one means for receiving an electromagnetic beam from the monitoring area and determining a capture variable from the received electromagnetic beam,

[0016] At least one device for performing a disturbance handling process based on captured variables, wherein at least one device has at least one artificial neural network. Background Art

[0017] A method for operating a radar system having at least two radar sensors is known from DE 10 2020 107 372 A1. In this case, in particular, the following steps are provided to be performed, preferably successively in the sequence described or in any sequence, wherein individual and / or all steps may also be performed repeatedly:

[0018] - a signal transmission is performed in the radar sensor in order to transmit in each case at least one radar signal (by the radar sensor), preferably by means of at least one transmitting antenna of the respective radar sensor, in particular in the form of an electromagnetic signal, into an environment outside the radar sensor,

[0019] - performing signal processing in the radar sensors so that each radar sensor determines a capture variable that is specific to the respectively transmitted radar signal, in particular specific to the transmitted radar signal that is reflected at a target object and has a delayed signal propagation time and can be received, for example, by at least one receiving antenna of the radar sensor,

[0020] - performing a disturbance evaluation in order to detect in each case at least one disturbance in the radar sensor based on the respective captured variables, wherein the disturbance evaluation can preferably be performed centrally for all captured variables or individually for the respective captured variables in the respective radar sensor,

[0021] - providing at least one or at least two or at least four or at least six adaptation options for avoiding at least one detected interference by adapting the signal transmission,

[0022] - evaluating at least one adaptation option for each radar sensor, in particular by each radar sensor,

[0023] - Based on the evaluation, an adaptation option is performed between the individual radar sensors,

[0024] - Based on the adjustment, an adaptation of the signal transmission is performed according to at least one adaptation option, in particular only when the adaptation option leads to a reduced interference for a majority of radar sensors and / or by selecting this adaptation option which leads to a reduced interference for a majority of radar sensors.

[0025] The object of the invention is to design a method, a detection device, a driver assistance system and a vehicle of the type mentioned at the outset which allow an improved determination of a captured variable. In particular, the object is to improve the signal-to-noise ratio of the captured variable. In particular, the object is to alternatively or additionally improve the determination of the captured variable with respect to costs, in particular with respect to material costs, component costs and / or installation costs, and / or with respect to the effectiveness of the captured variable. Summary of the invention

[0026] According to the invention, in the case of the method, this object is achieved by the fact that during at least one interference handling process at least one interference analysis is performed, in which analysis at least one captured variable is checked for known interference patterns of interference variables using at least one artificial neural network and, if at least one known interference pattern is identified, interference variables belonging to at least one identified interference pattern are purified from the at least one captured variable.

[0027] According to the present invention, at least one electromagnetic beam is emitted into the monitoring area. A detection device is used to receive the at least one electromagnetic beam from the monitoring area and convert it into at least one captured variable.

[0028] Using a detection device, in particular using at least one receiving device which may have at least one antenna, the electromagnetic beam from the monitoring area can advantageously be converted into a captured variable in the form of an electrical reception signal. The electrical reception signal can be processed using electrical means, in particular electrical control and / or evaluation means.

[0029] The electromagnetic beam that can be received by the detection device may have or consist of an electromagnetic echo beam. The electromagnetic echo beam may come from an electromagnetic beam emitted using the detection device and reflected at at least one object. The capture variable determined from the echo beam is specific to the reflecting object. For better distinction, the capture variable only from the echo beam may also be referred to as an "echo reception variable".

[0030] Alternatively or in addition, the received electromagnetic beam may have or consist of an interference beam from an interference source. The interference beam received using the detection device is converted into a corresponding received variable in a similar manner to the echo beam. For better distinction, the received variable only from the interference variable may also be referred to as a "interference variable".

[0031] The captured variable can be the superposition of any echo received variable and any disturbance variable. If no disturbance beam is captured, the captured variable consists only of the echo variable (if any). If no echo beam is captured, the captured variable consists only of the disturbance variable (if any).

[0032] According to the present invention, at least one artificial neural network is used to perform at least one interference handling process based on at least one captured variable so as to reduce the influence of any interference source and corresponding interference variable on determining information related to the monitoring area, especially object information related to objects in the monitoring area.

[0033] The object information may be a distance variable, a direction variable and / or a speed variable, which characterizes the distance, direction and / or speed of the object relative to the detection device or a corresponding reference point or reference system.

[0034] At least one interference analysis is performed during at least one interference handling process. During the at least one interference analysis, at least one captured variable is checked for a known interference pattern. The known interference pattern is derived from interference variables that were known prior to performing the interference analysis. If a known interference pattern is identified, the corresponding interference variable is purged from the captured variable.

[0035] In particular, the known interference sources may be external interference sources. External interference sources may be other radiation sources, in particular radar sources, which emit electromagnetic beams in the same wavelength range or in an overlapping wavelength range as the detection device according to the invention.

[0036] Interference beams from known interference sources can cause characteristic interference patterns in corresponding interference variables determined using the detection device. In particular, corresponding noise patterns from known interference sources can be identified in the determined captured variables. Therefore, if a known interference pattern is identified, the corresponding interference variables can be purified from the captured variables. Therefore, the signal-to-noise ratio of the captured variables, in particular the signal-to-noise ratio of the echo reception variables contained therein, can be improved overall.

[0037] According to the present invention, machine learning is used to analyze the capture variables. The shape of the received electromagnetic beam is different depending on the object type, material, shape, XYZ coordinates, environmental conditions (such as rain), external noise, dynamics of the environment or object, and other factors, and also depends on the emitted electromagnetic beam.

[0038] The interference analysis uses at least one artificial neural network. For this purpose, a suitable multi-layer neural network (deep neural network) with an input layer, a number of intermediate layers (hidden layers) and an output layer can be specified. For training, a number of different scenarios can be pre-recorded using the detection device and can be used to train the neural network. Depending on the type of application and the degree of automation, e.g. SAE Level 0 to SAE Level 4, different levels can be used.

[0039] Purging the at least one captured variable by means of at least one interference analysis also makes it possible to use a detection device with less accurate components to determine sufficiently good data. It is also possible to use components that may themselves be filled with greater noise. Thus, simpler and cheaper components can be used overall for the detection device, which can still be used to determine a sufficiently good captured variable for the application and possibly a corresponding degree of automation. Thus, by correcting the measurement by means of at least one interference analysis, the performance of the detection device can be improved.

[0040] The validity of the data thus determined can be increased by improving the signal-to-noise ratio of the captured variables. Thus, a higher safety level can be achieved using the detection device according to the invention. The detection device according to the invention can be used to determine data in accordance with the automation levels SAE 0 to 4 required for autonomous or semi-autonomous driving.

[0041] The invention can advantageously be used in detection equipment for vehicles, in particular motor vehicles. Advantageously, the invention can be used in detection equipment for land vehicles, in particular cars, trucks, buses, motorcycles, etc., aircraft, in particular drones, and / or ships. The invention can also be used in detection equipment for vehicles that can operate autonomously or at least semi-autonomously. However, the invention is not limited to detection equipment for vehicles. It can also be used in detection equipment in steady-state operation, detection equipment in robots and / or machines, in particular construction or transport machines, such as cranes, excavators, etc.

[0042] The detection device can advantageously be connected to or can be part of at least one electronic control device of the vehicle or machine, in particular a driver assistance system and / or a chassis control system and / or a driver information device and / or a parking assistance system and / or a gesture recognition system etc. In this way, at least some functions of the vehicle or machine can be performed autonomously or semi-autonomously using the information obtained by the detection device.

[0043] The detection device can be used to capture stationary or moving objects, in particular vehicles, people, animals, plants, obstacles, uneven road surfaces, in particular potholes or rocks, road boundaries, traffic signs, open spaces, in particular parking spaces, precipitation, etc., and / or movements and / or gestures.

[0044] In an advantageous configuration of the method, at least one interference analysis can be performed repeatedly and the purified captured variables determined from the respective interference analyses can be combined to form at least one combined captured variable. This makes it possible to further improve the signal-to-noise ratio of the captured variable.

[0045] The at least one interference analysis can advantageously be performed between two and ten times, in particular four times. The signal-to-noise ratio is further improved with each pass of the at least one interference analysis. If the analysis is performed four times, the signal-to-noise ratio is especially improved by a factor of two.

[0046] In another advantageous configuration of the method, a plurality of different electromagnetic beams can be emitted into the same scene of the monitoring area and the corresponding captured variables can be determined,

[0047] At least one interference analysis can be performed on at least a portion of the plurality of capture variables determined in this way, respectively, and a corresponding purified capture variable can be determined for at least a portion of the emitted different electromagnetic beams,

[0048] And at least a portion of the plurality of purified capture variables determined in this manner may be combined to form at least one combined capture variable.

[0049] This makes it possible to further improve the signal-to-noise ratio of the captured variables.

[0050] To capture the same scene, different electromagnetic beams can be emitted within corresponding small time windows.

[0051] A plurality of different electromagnetic beams can advantageously be emitted successively into the same scene of the monitoring area. This makes it possible to avoid mutual interference of the emitted electromagnetic beams.

[0052] Advantageously, four different electromagnetic beams can be emitted into the same scene, corresponding capture variables can be determined, and corresponding interference analysis can be performed. This makes it possible to achieve correspondingly small time windows, so that changes in the capture scene are as small as possible.

[0053] The different electromagnetic beams can differ in shape, wavelength, pulse duration, emission duration, emission power, encoding, etc. By varying the emitted electromagnetic beam, the corresponding echo reception variables can be better distinguished from any interfering variables. Thus, interfering variables can be better identified and removed.

[0054] In another advantageous configuration of the method, an artificial convolutional neural network can be used as at least one artificial neural network. Artificial convolutional neural networks (CNNs) are a biologically inspired machine learning concept with the aim of extracting features. Since the noise has a pattern (especially an interference pattern) that is different from the pattern (especially an object pattern) of a conventional signal (especially an echo beam), the captured capture variables can be reduced accordingly after identifying the interference pattern. In this case, even the detection device used for scanning can be used to change the electromagnetic beam emitted into the monitoring area. In this way, at least one interference analysis can be used to determine which electromagnetic beams originate from the beam emitted by the detection device. The interfering noise can be identified based on this knowledge and removed accordingly by calculation.

[0055] In another advantageous configuration of the method,

[0056] During at least one interference analysis, at least one capture variable may be initially checked against a known object pattern caused by an electromagnetic echo beam reflected at the known object,

[0057] and if at least one known object pattern is identified, the echo acquisition variable corresponding to the at least one known object pattern may be removed from the at least one acquisition variable,

[0058] Then, at least one captured variable of the at least one echo captured variable that has not been identified can be checked for known interference patterns of interference variables using at least one artificial neural network, and if at least one known interference pattern is identified, interference variables belonging to the at least one identified interference pattern can be cleaned from the original at least one captured variable containing the at least one echo captured variable. This makes it possible to further improve the signal-to-noise ratio.

[0059] Due to the fact that at least one captured variable is initially free of echo captured variables by means of a known object pattern, the corresponding interference pattern can be identified in an even better manner. Thus, the release of the original captured variables from the interference variables can be improved.

[0060] To some extent, an object pattern caused by an object whose object pattern is known can be initially removed from at least one raw captured variable. The captured variables without the object pattern can then be subjected to at least one further interference analysis, during which interference variables with the known interference pattern can be identified. The identified interference variables can then be removed from at least one raw captured variable, so that the purified captured variable ideally only contains the echo variables of the object, provided that all interference variables have been identified.

[0061] In another advantageous configuration of the method,

[0062] Predefined interference patterns and / or possible object patterns may be used for at least one interference analysis,

[0063] and / or

[0064] Interference patterns and / or object patterns learned during operation of the detection device can be used for at least one interference analysis. In this way, the method can more flexibly access a greater number of known interference patterns and / or known object patterns.

[0065] Predefined interference patterns and / or object patterns can be used in at least one interference analysis. These patterns can be learned in advance, in particular under laboratory conditions, and can be stored in a corresponding storage medium, in particular a storage medium of the detection device. In this way, when the method is carried out, the corresponding interference patterns and / or object patterns can be accessed more quickly.

[0066] Alternatively or additionally, interference patterns and / or object patterns learned during operation can be used. This makes it possible to continuously increase the number of known interference patterns and / or object patterns. This also makes it possible to continuously improve the method.

[0067] In another advantageous configuration of the method,

[0068] A received signal, in particular an electrical received signal, converted from the electromagnetic beam using a receiving device of the detection device can be used as a captured variable,

[0069] and / or

[0070] Object information related to the object captured during measurement with the detection device, which object information is determined from a received signal, in particular an electrical received signal, converted from an electromagnetic beam using a receiving device of the detection device, can be used as a captured variable. In this way, at least one interference analysis can be performed on a suitable processing level.

[0071] The received signal can advantageously be used as a captured variable. Thus, interference analysis can be performed directly with the received signal at a lower processing level. In this way, interference variables can be removed very early.

[0072] An electrical reception signal, in particular a voltage variable or the like, can advantageously be used as a captured variable. The electrical reception signal is generated during the conversion of the electromagnetic beam using a device of the detection apparatus, in particular a receiving device. The electrical reception signal can be processed using electrical means, in particular an electrical evaluation device or the like.

[0073] The received signal may be an echo received signal from the echo beam, an interference signal from the interference beam, or a superposition of the echo received signal and the interference signal.

[0074] Alternatively or additionally, object information can be used as a capture variable. In this way, interference analysis can be performed at a higher processing level. The effectiveness of images with object information, especially range images, can therefore be increased.

[0075] In a further advantageous configuration of the method, the method can be used to operate a detection device in the form of a radar sensor for emitting an electromagnetic beam in the form of a radar beam.

[0076] The radar sensor varies greatly with respect to the emitted radar beam. This also makes it possible to change the acquisition variable in order to improve the distinction between object patterns and interference patterns. Thus, the same scene can be scanned with different radar beams, in particular in succession. As a result, the signal-to-noise ratio can be improved overall in the cleaned acquisition variable.

[0077] The at least one receiving device of the detection device, in particular a radar sensor, can advantageously be configured to receive an electromagnetic beam, in particular a radar beam, of the same type as the electromagnetic beam emitted using the detection device.

[0078] The wavelength range in which the at least one receiving device can receive the electromagnetic beam can advantageously include the wavelength range in which the electromagnetic beam, in particular the radar beam, is transmitted using the detection device. This ensures that at least the echo of the transmitted electromagnetic beam, in particular the radar beam, can be received.

[0079] In a further advantageous configuration of the method, at least one purified captured variable, in particular possibly at least one purified combined captured variable, can be further processed, in particular can be subjected to image processing,

[0080] and / or

[0081] At least one transmitting device and / or at least one receiving device of the detection device can be adjusted based on at least one purified captured variable, in particular, possibly at least one purified combined captured variable.

[0082] The at least one purified captured variable, in particular possibly the at least one purified combined captured variable, can advantageously be further processed. This makes it possible to obtain further information related to the monitored area.

[0083] At least one object information item, in particular at least one distance variable, at least one direction variable and / or at least one speed variable, can advantageously be determined from at least one purified captured variable, in particular possibly from at least one purified combined captured variable. This allows a more accurate characterization of the captured scene.

[0084] At least one purified captured variable, in particular possibly at least one purified combined captured variable, can advantageously be subjected to image processing. This makes it possible to further remove interfering effects.

[0085] Alternatively or additionally, at least one transmitting device and / or at least one receiving device of the detection device can be adjusted based on at least one purified capture variable, in particular at least one purified combined capture variable. This makes it possible to adapt the performance of the detection device to the prevailing situation.

[0086] Furthermore, according to the invention, in the case of a detection device, this object is achieved due to the fact that the detection device has at least a part of the means for carrying out the method according to the invention.

[0087] According to the invention, the detection device has at least one interference analysis device, which can be used to carry out the interference analysis according to the invention.

[0088] The detection device can advantageously have at least one artificial neural network, in particular an artificial convolutional neural network. During the interference analysis, the captured variables can be checked for known interference patterns of the interference variables using the artificial neural network, and if a known interference pattern is identified, the captured variables can be purified from the interference variables belonging to the identified interference pattern.

[0089] Using artificial convolutional neural networks, interference patterns can be even better identified.

[0090] In an advantageous embodiment, the detection device can be a radar sensor. The radar sensor can be used to monitor the monitoring area for objects without contact. The radar sensor can be variably adjusted based on the emitted radar beam. In particular, the shape, pulse duration, length and / or coding of the radar beam can thus be changed. In this way, using the radar sensor, a larger number of capture variables can be determined for the same capture scene by emitting different radar beams into the same scene. The recognition of interference patterns can thus be further improved.

[0091] Furthermore, according to the invention, in the case of a driver assistance system, the object is achieved by the fact that the driver assistance system has at least a part of a device for carrying out the method according to the invention.

[0092] According to the invention, a driver assistance system has at least one detection device and at least part of a device for carrying out a method according to the invention for operating the at least one detection device.

[0093] The vehicle can be operated autonomously or semi-autonomously using driver assistance systems.

[0094] The detection device may be used to monitor at least one monitoring area in the vehicle environment and / or inside the vehicle for an object. Using the at least one detection device, a distance variable, a direction variable, and / or a speed variable characterizing the distance, direction, and / or speed of the captured object may be determined. The information obtained using the at least one detection device may be used with a driver assistance system for autonomously or semi-autonomously operating the vehicle.

[0095] According to the invention, a driver assistance system has at least a part of a device for carrying out the method according to the invention. At least one detection device of a driver assistance system can advantageously have at least a part of a device for carrying out the method according to the invention. If at least one detection device is part of a driver assistance system, then the part of the device of at least one detection device for carrying out the method according to the invention is therefore also part of the driver assistance system, that is to say also part of the device of the driver assistance system for carrying out the method according to the invention. This applies accordingly to the device of a vehicle having at least one driver assistance system and / or at least one detection device.

[0096] Furthermore, according to the invention, in the case of a vehicle, the object is achieved by the fact that the vehicle has at least a part of a device for carrying out the method according to the invention.

[0097] The vehicle can advantageously have at least one driver assistance system, in particular at least one driver assistance system according to the invention, with which the vehicle can be operated autonomously or semi-autonomously.

[0098] Alternatively or additionally, the vehicle can have at least one detection device, in particular at least one detection device according to the invention.The detection device can be used to monitor at least one monitoring area in the vehicle environment and / or in the vehicle interior for objects.

[0099] At least one detection device, in particular at least one detection device according to the present invention, can advantageously be connected to a driver assistance system, in particular at least one driver assistance system according to the present invention, or be part of it. In this way, information obtained using the at least one detection device can be used by the driver assistance system to operate the vehicle autonomously or semi-autonomously.

[0100] Furthermore, the features and advantages indicated in connection with the method according to the invention, the detection device according to the invention, the driver assistance system according to the invention and the vehicle according to the invention and their respective advantageous configurations apply in a mutually corresponding manner and vice versa. The individual features and advantages can of course be combined with one another, in which case further advantageous effects can result which exceed the sum of the individual effects. BRIEF DESCRIPTION OF THE DRAWINGS

[0101] Other advantages, features and details of the present invention will become apparent from the following description, in which exemplary embodiments of the present invention are explained in more detail with reference to the accompanying drawings. A person skilled in the art will also readily consider the features disclosed in the drawings, the description and the claims to be combined individually and to form further useful combinations. Schematically in the accompanying drawings,

[0102] Figure 1 shows a front view of a vehicle having a driver assistance system including a radar sensor;

[0103] Figure 2 Shows that there is Figure 1 Functional diagram of the driver assistance system with radar sensors;

[0104] Figure 3 Shows the use of Figure 1 and Figure 2a time curve of an original electrical reception signal determined by a receiving device of the radar sensor from the radar echo signal and the electromagnetic interference beam, and a time curve of the corresponding electrical echo reception signal and the electrical interference signal;

[0105] Figure 4 Shown from Figure 3 The time curve of the original received signal;

[0106] Figure 5 Shown from Figure 3 The time curve of the echo receiving signal;

[0107] Figure 6 Shows the operation Figure 1 and Figure 2 Flowchart of a method for a radar sensor.

[0108] In the drawings, identical components have identical reference numerals. DETAILED DESCRIPTION

[0109] Figure 1 A front view of a vehicle 10 in the form of an automobile is shown. The vehicle 10 has a driver assistance system 12. The vehicle 10 can operate autonomously or semi-autonomously using the driver assistance system 12. Figure 2 Driver assistance system 12 is shown in the functional diagram.

[0110] The driver assistance system 12 comprises a detection device in the form of a radar sensor 14 . Furthermore, the driver assistance system 12 has a central processing unit 16 .

[0111] The radar sensor 14 is arranged, for example, in the front fender of the vehicle 10 and is directed into the monitoring area 18 in the direction of travel in front of the vehicle 10. The radar sensor 14 can also be arranged at different locations on the vehicle 10 and be oriented differently. The driver assistance system 12 can also have a plurality of radar sensors 14, which can be arranged at different locations on the vehicle 10 with different orientations. The driver assistance system 12 can also additionally have different detection devices.

[0112] By using Figure 1 and Figure 2 The invention is explained by way of example using a radar sensor 14. However, the invention can also be used accordingly for other radar sensors or other detection devices which use an electromagnetic beam to monitor a corresponding monitoring area.

[0113] Radar sensor 14 comprises a transmitting device 20 with, for example, a transmitting antenna Tx, a receiving device 22 with, for example, a receiving antenna Rx, and a control and evaluation device 24 , for example, an electronic control and evaluation device.

[0114] The transmitting device 20 and the receiving device 22 are each functionally connected to a control and evaluation device 24. This makes it possible to exchange information between the transmitting device 20, the receiving device 22 and the control and evaluation device 24.

[0115] The control and evaluation device 24 is connected to the central processor unit 16 of the driver assistance system 12 . This enables an exchange of information between the radar sensor 14 or the control and evaluation device 24 and the central processor unit 16 .

[0116] The radar sensor 14 may also be equipped with multiple transmit antennas Tx and multiple receive antennas Rx. The radar sensor 14 may be in the form of a multiple-input multiple-output (MIMO) radar sensor.

[0117] The transmitting device 20 can be used, for example, to generate an electronic scanning signal, which can be transmitted into the monitoring area 18 as an electromagnetic scanning beam in the form of a radar signal 26 using the transmitting antenna Tx. The radar signal 26 can be transmitted, for example, as a radar pulse in the form of a chirp. The transmitting device 20 can be used to change the transmitted radar signal 26. For example, the shape, pulse duration, signal duration and / or coding of the radar signal 26 can be changed.

[0118] Radar signal 26 may be reflected from an object 28 located in monitoring area 18 .

[0119] The radar sensor 14 may be used, for example, to capture stationary or moving objects 28 , such as vehicles, persons, animals, plants, obstacles, uneven road surfaces such as potholes or rocks, road boundaries, traffic signs, open spaces such as parking spaces, precipitation, etc., and / or movements and / or gestures.

[0120] Using receiving antenna Rx of receiving device 22 , radar signal 26 reflected at object 28 in the direction of radar sensor 14 may be received as an electromagnetic beam in the form of radar echo signal 30 .

[0121] Using the receiving device 22 , the received radar return signal 30 may be converted into a captured variable in the form of an electrical return receive signal 38 . Figure 3 and Figure 5 A time profile of an exemplary electrical echo reception signal 38 generated from a radar echo signal 30 of an exemplary radar signal 26 is shown.

[0122] Based on the propagation time from the transmitted radar signal 26 until the corresponding radar echo signal 30 is received, object information related to the captured object 28 can be determined. For example, a distance variable 32, a direction variable and a speed variable can be determined, which characterize the distance, direction and speed of the captured object 28 within a reference system, for example relative to the radar sensor 14. Indirect or direct propagation time methods can be used. When a MIMO radar sensor 14 is used, the distance variable 32 can be determined from the phase difference between the electronic scanning signal used to generate the radar signal 26 and the electronic echo reception signal 38 of the captured radar echo signal 30.

[0123] The object information is determined in the control and evaluation device 24 .

[0124] In addition to the radar echo signal 30 from the captured object 28, the receiving antenna Rx of the receiving device 22 is also used to receive an electromagnetic interference beam 34, for example from an external interference source 42. The electromagnetic interference beam 34 is converted into an electrical interference signal 36 using the receiving device 22.

[0125] Interference source 42 may be, for example, another radar sensor that transmits interference beam 34 in the form of a radar beam. Figure 2 Three interference sources 42 are shown, and for better differentiation, the reference numerals of the interference sources have the reference numerals 1, 2 and 3. The reference numerals of the corresponding electrical interference signals 36 (whose time curve is Figure 3 ) are indicated by the reference numerals 1, 2 and 3 respectively.

[0126] The electrical echo received signal 38 and the electrical interference signal 36 derived from the echo signal 30 are superimposed to form a captured variable in the form of an electrical original received signal 40. As an example, Figure 3 and Figure 4 Shows Figure 2 Time curve of the original received signal 40 of the scenario shown, in which there are three interference sources 42 1 , 42 1 and 42 3 .

[0127] The raw received signal 40 depends on the type, material, shape and spatial position, e.g. the position in a defined reference system, of the reflecting object 28. Furthermore, the raw received signal 40 depends on environmental conditions, e.g. prevailing precipitation etc., external noise, the environment or the dynamics of the captured object 28. Furthermore, the raw received signal 40 depends on the radar signal 26 used.

[0128] For comparison, Figure 3 An exemplary electrical original received signal 40, a corresponding echo received signal 38 and three electrical interference signals 36 are shown. 1 , 36 2 and 36 3time curve.

[0129] Electrical interference signal 36 1 , 36 2 and 36 3 From three interference sources42 1 , 42 2 and 42 3 , each of which emits an electromagnetic interference beam 34 1 , 34 2 and 34 3 .

[0130] Figure 4 Only the Figure 3 The time curve of the original received signal 40. Figure 5 shows the interference processing from Figure 3 The time curve of the electric echo reception signal 38, wherein the interference signal 36 is removed according to the method explained in more detail below 1 , 36 2 and 36 3 .

[0131] Interference signal 36 impairs the signal-to-noise ratio of echo reception signal 38. As a result, the accuracy of the determined object information associated with object 28 captured by radar sensor 14 is impaired.

[0132] In order to be able to determine the most accurate possible object information about object 28 , for example an accurate distance variable 32 , an accurate direction variable and / or an accurate speed variable of object 28 , it is necessary to improve the signal-to-noise ratio.

[0133] For this purpose, an interference handling process is performed in a method 44 for operating the radar sensor 14. The method 44 is as follows: Figure 6 As shown in the flowchart.

[0134] During the interference handling process, an interference analysis 46 is performed with the aid of an artificial neural network. For example, the neural network is implemented as a convolutional neural network CNN.

[0135] By way of example, four interference analyses 46 are performed in the method 44. It is also possible to perform more or fewer interference analyses 46. The signal-to-noise ratio improves with the number of interference analyses 46.

[0136] For each interference analysis 46, a radar signal 26 is emitted and the corresponding echo signal 30 is captured and converted into an original received signal 40. Four interference analyses 46 are performed at short time intervals on the same scene in the monitoring area 18. A different variation of the radar signal 26 is used for each interference analysis 46, resulting in four different variations of the radar signal 26 for the four interference analyses 46. For simple differentiation, the reference numerals of the four different variations of the radar signal 26 are provided below with the reference numerals 1, 2, 3 and 4.

[0137] For greater clarity, Figure 6 In the flowchart of FIG. 4 , the four interference analyses 46 are indicated at the same level. The interference analyses 46 and the corresponding radar measurements occur consecutively in time. The order and principle of the four interference analyses 46 are the same. Therefore, the same reference numerals are used in the illustration. In order to represent all four interference analyses 46, the following uses Figure 2 The example of the scenario shown is explained in more detail Figure 6 Radar signal 26 on the left 1 Interference analysis46.

[0138] In a measuring step 48, the radar signal 26 is used 1 The receiving device 22 uses the receiving antenna Rx to receive the radar signal from Figure 2 The corresponding echo signal 30 and the interference beam 34 of the interference source 42 shown by way of example in FIG. 4 are detected and converted into the electrical original received signal 40 . Figure 3 and Figure 4 The time curve of the original received signal 40 is shown.

[0139] The original received signal 40 is transmitted to the neural network CNN.

[0140] Furthermore, known interference patterns 52 of known electrical interference signals and known object patterns 54 of known objects 28 are transmitted from pattern memory 50 to neural network CNN. Pattern memory 50 is part of control and evaluation device 24, for example.

[0141] Interference pattern 52 is characterized by the time profile of electrical interference signal 36. Known interference pattern 52 may be a pattern of interference signal 36 that typically occurs when operating vehicle 10. For example, known interference signal 36 may originate from interference beam 34 emitted by a radar sensor of another vehicle.

[0142] The object pattern 54 is characterized by the time curve of the electric echo reception signal 38. The known object pattern 54 may be, for example, a pattern of the echo reception signal 38 of an object 28 that is typically present during operation of the vehicle 10. The known object 28 may be, for example, a vehicle, a person, an animal, a plant, an obstacle, an uneven road surface (e.g., a pothole or a rock), a road boundary, a traffic sign, an empty space (e.g., a parking space), etc.

[0143] The known interference patterns 52 and the known object patterns 54 are for example determined in advance, for example at the end of a production line, by means of reference measurements using known interference sources 42 or known objects 28, and stored in the pattern memory 50. For example, the reference measurements can be carried out under laboratory conditions. Alternatively or in addition, the known interference patterns 52 and / or the known object patterns 54 can also be recorded, for example "learned", under normal operating conditions of the vehicle 10.

[0144] In the exemplary embodiment described, it is assumed that the corresponding known interference pattern 52 is stored in the pattern memory 50 for use from Figure 2 It is also assumed that corresponding known object patterns 54 are stored in pattern memory 50 for echo received signals 38 of object 28 shown there, for example a road sign.

[0145] In an object cleaning step 56, the raw received signal 40 is compared with a known object pattern 54 in the neural network. For example, a pattern recognition method can be implemented for this purpose. If a match with a known object pattern 54 (in the present case, the object pattern 54 of a road sign) is identified, the raw received signal 40 is reduced by the recognized echo received signal 38 of the known object pattern 54 (i.e., the object pattern of the road sign) and is supplied as a reduced received signal 58 to an interference analysis step 60.

[0146] In an interference analysis step 60, the reduced received signal 58 is compared with the known interference pattern 52. For example, a pattern recognition method can be performed for this purpose. If a match with the known interference pattern 52 is identified, then in a cleaning step 62, the original raw received signal 40 is reduced by the interference signal 36 of the corresponding known interference pattern 52. In the exemplary embodiment shown, the reduced received signal 58 is compared with the known interference pattern 52. For example, a pattern recognition method can be performed for this purpose. If a match with the known interference pattern 52 is identified, then in a cleaning step 62, the original raw received signal 40 is reduced by the interference signal 36 of the corresponding known interference pattern 52. Figure 2 Three interference sources shown in the scenario 42 1 , 42 1 and 42 3 Interference beam 34 1 , 34 1 and 34 3 The pattern of the interference signal 36 caused matches the corresponding known interference pattern 52 stored in the pattern memory 50, for example. 1 , 361 and 36 3 The original raw received signal 40 is reduced.

[0147] After removing the identified interference signal 36 1 , 36 1 and 36 3 After the influence of 1 , 36 1 and 36 3 , only the echo reception signal 38 which has been cleaned of interference and originates from the reflecting object 28 (ie, the road sign) is retained.

[0148] In a superposition step 64 , the cleaned echo reception signals 38 determined in each of the four exemplary interference analyses 46 are combined to form a combined echo reception signal 66 .

[0149] In the information determination step 68 , object information of the captured object 28 , such as the distance variable 32 , the direction variable and / or the speed, is determined from the combined echo reception signal 66 .

[0150] Optionally, the object information may be subjected to further processing, such as image processing.

[0151] Object information, such as distance variable 32 , is transmitted to central processor unit 16 of driver assistance system 12 .

[0152] Optionally, the settings of the transmitting device 20 and / or the receiving device 22 may be adapted to the current scenario based on the combined echo reception signal 66 .

[0153] Instead of being performed based on the raw received signal 40 as the captured variable, the interference analysis 46 can also be performed based on object information (eg, distance variable 32 , direction variable and / or speed variable) as the captured variable. In this case, the object information is predetermined based on the corresponding raw received signal 40 .

Claims

1. A method (44) for operating a test device (14), in particular a test device (14) for a vehicle (10), in, Using the detection device (14), emitting at least one electromagnetic beam (26) into a monitoring area (18) of the detection device (14), Using the detection device (14) to receive at least one electromagnetic beam (30, 34) from the monitoring area (18) 1 , 34 2 ,34 3 ) and directing the at least one electromagnetic beam (30, 34 1 , 34 2 , 34 3 ) into at least one captured variable (40) that can be processed using at least one evaluation device (24), performing at least one disturbance handling process based on at least one captured variable (40) using at least one artificial neural network (CNN), The invention is characterized in that during at least one interference handling process at least one interference analysis (46) is performed, in which at least one captured variable (40) is checked for known interference patterns (52) of interference variables (36) using at least one artificial neural network (CNN), and if at least one known interference pattern (52) is identified, interference variables (36) belonging to at least one identified interference pattern (52) are cleaned from the at least one captured variable (40).

2. The method according to claim 1, It is characterized in that The at least one interference analysis (46) is repeatedly performed and the cleansed captured variables (38) determined from the respective interference analyses (46) are combined to form at least one combined captured variable (66).

3. The method according to claim 1 or 2, It is characterized in that Multiple different electromagnetic beams (26 1 , 26 2 , 26 3 , 26 4 ) is transmitted to the same scene of the monitoring area (18) and the corresponding captured variables (40) are determined, At least one interference analysis (46) is respectively performed for at least a portion of the plurality of captured variables (40) determined in this way and for different emitted electromagnetic beams (26 1 , 26 2 , 26 3 , 26 4 ) determines at least a portion of a corresponding purified capture variable (38), And at least a portion of the plurality of purified capture variables (38) determined in this manner are combined to form at least one combined capture variable (66).

4. A method as claimed in any one of the preceding claims, It is characterized in that An artificial convolutional neural network is used as at least one artificial neural network (CNN).

5. A method as claimed in any one of the preceding claims, It is characterized in that during the at least one interference analysis (46), initially checking the at least one captured variable (40) against a known object pattern (54) caused by an electromagnetic echo beam (30) reflected at a known object (28), and, if at least one known object pattern (54) is identified, removing the echo acquisition variable (38) corresponding to the at least one known object pattern (54) from the at least one acquisition variable (40), Then, at least one captured variable (58) without the identified at least one echo captured variable (38) is checked for known interference patterns (52) of the interference variables (36) using at least one artificial neural network (CNN), and if at least one known interference pattern (52) is identified, the interference variables (36) belonging to the at least one identified interference pattern (52) are purified from the original at least one captured variable (40) that can contain the at least one echo captured variable (38).

6. A method as claimed in any one of the preceding claims, It is characterized in that Predefined interference patterns (52) and / or possible object patterns (54) are used for the at least one interference analysis (46) and / or The interference patterns (52) and / or object patterns (54) learned during operation of the detection device (14) are used for at least one interference analysis (46).

7. A method as claimed in any one of the preceding claims, It is characterized in that The receiving device (22) of the detection device (14) receives the electromagnetic beam (30, 34 1 , 34 2 , 34 3 ) converted received signal, in particular electrical received signal, is used as captured variable (40), and / or Object information (32) relating to the object (28) captured during measurement with the detection device (14) is used as a captured variable (40), wherein the object information is determined from a received signal (38), in particular an electrical received signal, converted from an electromagnetic beam (30) using a receiving device (22) of the detection device (14).

8. A method as claimed in any one of the preceding claims, It is characterized in that The method (44) is used to operate a detection device (14) in the form of a radar sensor, the detection device (14) being used to emit an electromagnetic beam (26) in the form of a radar beam.

9. A method as claimed in any one of the preceding claims, It is characterized in that further processing of at least one cleaned captured variable (40), in particular at least one cleaned combined captured variable (66), in particular image processing, and / or Based on at least one purified captured variable (38), in particular at least one purified combined captured variable (66), at least one transmitting device (20) and / or at least one receiving device (22) of the detection device (14) is adjusted.

10. A detection device (14), in particular a detection device (14) for a vehicle (10), having at least one emitting device (20) for emitting an electromagnetic beam (26) into a monitoring area (18) of the detection device (14), having a device for receiving an electromagnetic beam (30, 34) from a monitoring area (18) 1 , 34 2 , 34 3 ) and for the received electromagnetic beam (30, 34 1 , 34 2 , 34 3 ) determining at least one device (22) for capturing a variable (40), having at least one means (24) for performing a disturbance handling process based on a captured variable (40), in, The at least one device (24) has at least one artificial neural network (CNN), It is characterized in that The detection device (14) has at least a part of a device for carrying out the method according to any one of claims 1 to 9.

11. The detection device (14) according to claim 10, It is characterized in that The detection device (14) is a radar sensor.

12. A driver assistance system (12), in particular a driver assistance system (12) for a vehicle (10), comprising at least one detection device (14), in, The at least one detection device (14) has: at least one emitting device (20) for emitting an electromagnetic beam (26) into a monitoring area (18) of the at least one detection device (14), for receiving an electromagnetic beam (30, 34) from a monitoring area (18) 1 , 34 2 , 34 3 ) and for the received electromagnetic beam (30, 34 1 , 34 2 , 34 3 ) determining at least one device (22) for capturing a variable (40), At least one device (24) for performing a disturbance handling process based on captured variables (40), wherein the at least one device (24) has at least one artificial neural network (CNN), It is characterized in that A driver assistance system (12) comprises at least a part of a device for carrying out a method according to any one of claims 1 to 9.

13. A vehicle (10) having at least one detection device (14), in, The at least one detection device (14) has: at least one transmitting device (20) for transmitting an electromagnetic beam (26) into a monitoring area (18) of at least one detection device (14), for receiving an electromagnetic beam (30, 34) from a monitoring area (18) 1 , 34 2 , 34 3 ) and for the received electromagnetic beam (30, 34 1 , 34 2 , 34 3 ) determining at least one device (22) for capturing a variable (40), At least one device (24) for performing a disturbance handling process based on captured variables (40), wherein the at least one device (24) has at least one artificial neural network (CNN), It is characterized in that The vehicle (10) has at least a part of a device for carrying out the method as claimed in any one of claims 1 to 9.

Images