Dynamically determining deviations of a relative arrangement of radar sensors

Abstract

The invention relates to a computer-implemented method for dynamically determining deviations (140) of a relative arrangement (160) of at least a first radar sensor (162) and a second radar sensor (164) with respect to one another. The method comprises receiving first reflection data (130) of a first reflection signal determined using the first radar sensor (162), second reflection data (132) of a second reflection signal determined using the second radar sensor (164), crosstalk data (134) of a crosstalk signal determined using the first radar sensor (162), first noise data (136) of a first noise signal of ambient noise of the first radar sensor (162), said first noise signal being determined using said first sensor, and second noise data (138) of a second noise signal of ambient noise of the second radar sensor (164), said second noise signal being determined using said second sensor. A deviation (140) of the relative arrangement (160) of the first and second radar sensors (162, 164) is determined using the first reflection data (130), the second reflection data (132), the crosstalk data (134), the first noise data (136) and the second noise data (138).

Description

DYNAMICAL DETERMINATION OF DEVIATIONS OF A RELATIVE ARRANGEMENT OF RADAR SENSORS FIELD OF TECHNOLOGY

[0001] The invention relates to a computer-implemented method, a computer program and a computer unit for dynamically determining deviations of a relative arrangement of at least a first radar sensor and a second radar sensor to one another. STATE OF THE ART

[0002] The demands on modern radar systems are constantly increasing, for example as a result of the advancing automation of vehicles. In order to meet these increased requirements and improve the performance of radar systems, the complexity of the hardware and software is being increased, for example. Increasing software complexity, such as using super-resolution approaches, can, however, have the disadvantage that this is accompanied by a significant increase in the computing power required to run the software, and even then the resulting improvements are often limited. Another approach is to increase the complexity of the hardware, for example by increasing the number of transmit and / or receive channels. However, such hardware expansions require more complex hardware, which is generally more cost-intensive.

[0003] Therefore, there is a need for an alternative approach to improve the performance of radar systems, especially radar systems for vehicles such as automobiles.

[0004] It is an object of the invention to provide an improved method for dynamically determining deviations in the relative arrangement of at least a first radar sensor and a second radar sensor. The objects underlying the invention are achieved by the features of the independent claims. SUMMARY

[0005] In one aspect, a computer-implemented method for dynamically determining deviations of a relative arrangement of at least a first radar sensor and a second radar sensor is disclosed, which comprises receiving first reflection data of a first reflection signal determined using the first radar sensor. The first reflection signal results from reflections of a first radar signal emitted by the first radar sensor by one or more surrounding objects and comprises distance information about one or more distances of the first radar sensor to the one or more surrounding objects. Second reflection data of a second reflection signal determined using the second radar sensor is received.The second reflection signal results from reflections of a second radar signal emitted by the second radar sensor by one or more surrounding objects and comprises distance information about one or more distances between the second radar sensor and the one or more surrounding objects. At least crosstalk data of a crosstalk signal determined using the first radar sensor is received. The crosstalk signal results from crosstalk of the second radar signal of the second radar sensor to the first radar sensor. First noise data of a first noise signal of ambient noise of the first sensor, determined using the first radar sensor, is received. Furthermore, second noise data of a second noise signal of ambient noise of the second sensor, determined using the second radar sensor, is received.A deviation of the relative arrangement of the first and second radar sensors is determined using the first reflection data, the second reflection data, the crosstalk data, the first noise data and the second noise data.

[0006] This allows the use of a combination of a plurality of radar sensors, for example two radar sensors, to improve the performance of a radar system. This approach makes it unnecessary to extensively adapt the radar system's software or hardware. The at least two radar sensors are two radar sensors arranged at a distance from each other, which are independent of each other, i.e. they are not synchronized or only roughly synchronized with each other. In the following, such a combination of at least two independent radar sensors, whose detection ranges at least partially overlap, is referred to as a stereo radar system. For example, in the case of N radar sensors with N > 2 N reflection data from N under Using the N radar sensors, reflection signals determined, N noise data from N noise signals determined using the N radar sensors, and one to N crosstalk data from one to N using one to N crosstalk signals determined from the N radar sensors are received. Using the aforementioned data, for example, deviations in the relative arrangement of the N radar sensors to one another are determined.

[0007] The stereo radar system is, for example, a stereo radar system of a vehicle, in particular a motor vehicle. The radar sensors of the stereo radar system are, for example, installed in a vehicle, in particular a motor vehicle, and configured to detect the surroundings of the vehicle or objects in the surroundings of the vehicle. The stereo radar system comprises, for example, a radar sensor of a front radar, corner radar, side radar, and / or rear radar of a vehicle, in particular a motor vehicle. For example, the stereo radar system comprises a combination of a radar sensor of a front radar and a radar sensor, which is installed in a corner of the vehicle or motor vehicle.

[0008] Such a stereo radar system can be used in a motor vehicle, for example, to implement functions for assisted, automated, and / or autonomous driving. For example, such a stereo radar system can be used in a motor vehicle for adaptive cruise control (ACC). Adaptive cruise control is a speed control system in motor vehicles that incorporates the distance to a vehicle ahead as an additional feedback and control variable during control. Adaptive cruise control can, for example, be part of a radar-based emergency braking assistant. Furthermore, such a stereo radar system can be used, for example, for a cross-traffic alert system to detect cross traffic behind the vehicle when reversing.

[0009] A stereo radar system, similar to a stereo camera system in the field of optical image processing, enables the performance of the radar system to be improved by combining the radar data from at least two radar sensors at different levels. However, for optimal combined evaluation of the data from the radar signals acquired by at least two radar sensors, the relative arrangement of the radar sensors, i.e., the relative positions and / or orientations of the radar sensors to one another, must be precisely known. Even a deviation of the order of magnitude of the wavelength of the radar signals, for example, approximately 4 mm, is sufficient. For example, for a frequency of 77 GHz, this can drastically reduce the performance of a stereo setup with two or more radar sensors. Typically used radar frequencies, for example, are in the range of 76 to 77 GHz.

[0010] The radar sensors can, for example, be radar sensors of a frequency-modulated continuous wave radar (FMCW radar). With an FMCW radar, the transmitted radar signal is frequency modulated. This frequency modulation enables distance measurement using an indirect time-of-flight measurement by comparing the frequency of the received radar signal to a reference, such as the transmitted radar signal. Radial velocities of detected objects can be measured, for example, using the Doppler shift. Thus, radar signals received by the radar sensors include information about, for example, the distance from detected objects, the radial velocity of the detected objects, and the distance of the objects.If, for example, MIMO (Multiple Input Multiple Output) radar sensors are used, the position of objects can be determined not only in terms of their distance, but also, for example, in terms of an azimuth angle and an elevation angle. The radar signal can be analyzed using appropriate signal processing, such as fast Fourier transforms (FFT), and the positions of detected objects can be determined, for example, in terms of distance, azimuth angle and / or elevation angle, as well as radial velocity. The presence of an object in the detection range of the radar sensors is indicated, for example, by an intensity peak in the received radar signal.

[0011] For example, determining the deviation of the relative arrangement of the first and second radar sensors makes it possible to carry out online calibration, i.e. calibration during operation of the radar sensors and / or a vehicle comprising the radar sensors. Such online calibration, for example of the relative positioning and / or relative alignment of the at least two radar sensors to one another, can ensure that optimal performance is achieved in all situations from the stereo approach, i.e. from the combined use of the at least two radar sensors or the combined evaluation of radar signals received using the at least two radar sensors. During online calibration, for example, the absolute position of the at least two radar sensors to one another is not determined, but rather deviations in the relative arrangement are determined, i.e. deviations from the original calibration.Determining such deviations makes it possible to. To dynamically compensate for deviations that may occur during operation of the radar sensors, for example in a vehicle.

[0012] To calibrate or determine the deviation, various effects are combined. For example, a machine learning module, such as one with at least one neural network, can be used.

[0013] First, for example, reflection data from reflection signals determined using the radar sensors are used to determine the deviation. This reflection data describes reflection signals that result from reflections of radar signals from the radar sensors off one or more surrounding objects. This reflection data includes, for example, distance information determined using the reflection signals about one or more distances from the individual radar sensor to the one or more reflective surrounding objects. In contrast to visual sensors, such as cameras, which do not natively provide distance information, radar sensors make it possible to directly determine distances to the corresponding one or more reflective objects based on the reflection signals. For example, distance information to one or more significant objects is determined, e.g.to objects whose reflection signals each have an intensity that exceeds a predefined threshold. The radar sensors can, for example, be arranged at a comparatively short distance of approximately 0.5 m to 2 m relative to each other. In this case, it can be assumed, for example, that the reflecting objects should be largely identical, especially the significant objects.

[0014] From this distance information, deviations in the relative arrangement of the radar sensors can be determined, for example using triangulation. For example, furthermore or alternatively, distances with corresponding significant objects can be selected and the intensity spectra or power spectra of the reflection signals for these selected distances can be determined. The corresponding intensity spectra or power spectra each describe, for example, an intensity or power distribution of the reflection signal for a specific distance or distance range as a function of an azimuth angle and a polar or elevation angle. Based on position differences of intensity peaks or maxima within the area spanned by the azimuth and elevation angles, deviations in the relative arrangement of the radar sensors can also be determined.Intensity I and power P are proportional to each other with an area A as the proportionality constant, ie I = P / A.

[0015] For example, a distance-Doppler profile can be created which describes a distribution of intensity or power as a function of distance and radial velocity. To do this, the parameter space for distance and radial velocity can be discretized by dividing it into intervals or bins. Based on intensity peaks, bins can be identified within which one or more objects are present or have been detected. For these bins, for example, an intensity or power spectrum can then be determined as a function of azimuth angle and elevation angle. This spectrum corresponds to a two-dimensional image, based on which the position of the corresponding object(s) within the area spanned by the azimuth and elevation angles can be determined.

[0016] For example, a machine learning module with, for example, one or more neural networks is used to determine the deviation. For example, the reflection data represents an initial input for the machine learning module.

[0017] Second, for example, crosstalk data from a crosstalk signal from the second radar sensor to the first radar sensor is used to determine the deviation. The corresponding crosstalk signal results from a crosstalk of the radar signal emitted by the second radar sensor to the first radar sensor and includes crosstalk information about the corresponding crosstalk. When using a machine learning module, the crosstalk data represents a second input for the module, for example.

[0018] Thus, the crosstalk from one radar sensor to the other can be taken into account when determining the deviation. If the radar sensors are arranged accordingly, there can be a direct signal path between the at least two radar sensors. This crosstalk signal, i.e. a radar signal emitted by one of the two radar sensors and received by the other radar sensor, can be used in the form of crosstalk data as a further basis for determining the deviation. The crosstalk signal transmitted between the at least two radar sensors is, in particular, a radar signal transmitted via a direct transmission path between the at least two radar sensors.

[0019] For example, further crosstalk data of a crosstalk signal determined using the second radar sensor can be received, which consists of a Crosstalk of the first radar signal from the first radar sensor to the second radar sensor results.

[0020] Thirdly, for example, noise data from noise signals of ambient noise of the two sensors determined using the at least two radar sensors is used to determine the deviation. This is, for example, ambient noise in the vicinity of the corresponding radar sensor. The detected ambient noise depends, for example, on the installation angle of the corresponding radar sensor. Thus, noise data from the at least two radar sensors can be used in particular to determine a deviation of a relative alignment of the at least two radar sensors to one another. When using a machine learning module, the noise data from the at least two radar sensors represents, for example, a third input for the module.

[0021] In order to create the most accurate calibration possible of the relative arrangement of the at least two radar sensors of the stereo radar, the temporal relationship of several measurements is used, ie a temporal progression of reflection data, crosstalk data and noise data is used.

[0022] The determined deviation is provided, for example, for dynamically adapting a combined evaluation of radar signals received using the at least two radar sensors for dynamic compensation of the determined deviation of the relative arrangement.

[0023] Examples enable calibration, in particular auto-calibration, for a stereo radar system comprising at least two radar sensors. Vibration, thermal changes, and even mechanical changes can significantly alter the original orientation and / or original position of the radar sensors relative to one another. Such vibration, thermal changes, and even mechanical changes can occur, in particular, in the case of a stereo radar system integrated into a motor vehicle. Due to such dynamic changes in the relative arrangement of the radar sensors of the stereo radar system, an initial static calibration, for example, at the end of production of the stereo radar system and / or a device, such as a motor vehicle, into which the stereo radar system is installed, may not be sufficient to ensure precise and / or error-free function of the stereo radar system in the long term.

[0024] Effective dynamic auto-calibration enables reliable use of a stereo radar system. In contrast to a single radar sensor, a stereo approach with multiple radar sensors provides significantly more data that can be used for calibration. To effectively combine this multitude of data, which is acquired using the multiple radar sensors of the stereo radar system, a machine learning module, for example, can be used. The machine learning module comprises one or more neural networks, in particular a recurrent neural network, which is well suited for combining data in this way. This allows, for example, a high level of calibration accuracy to be achieved and, moreover, sufficient robustness to be ensured.For example, such dynamic auto-calibration can provide a basis for a series-production version of stereo radar systems, which are particularly suitable for use in motor vehicles.

[0025] For example, the deviation in the relative arrangement includes a deviation in the relative positioning of the at least two radar sensors to one another. For example, the deviation in the relative arrangement includes a deviation in the relative orientation of the at least two radar sensors to one another. Thus, both translations and rotations can be determined as resulting deviations.

[0026] For example, the method further comprises dynamically adapting a combined evaluation of third radar signals received using the at least two radar sensors. Dynamically adapting the combined evaluation comprises dynamically adapting one or more parameter values ​​used for the combined evaluation, which describe the relative arrangement of the at least two radar sensors.

[0027] Through appropriate dynamic adjustment, the effects of deviations can be compensated for in the combined evaluation of radar signals, which combines radar signals from at least two radar sensors. For example, parameter values ​​used in the calculation of the evaluation, which are based on the relative arrangement of the at least two radar sensors to each other, are adjusted in such a way that the deviations are taken into account and errors or inaccuracies due to non-considered deviations can be avoided. For example, the radar signals received individually by the radar sensors are used to determine the deviation and subsequently used for a combined evaluation, whereby the combined evaluation is based on the results of the determination of deviations.

[0028] For example, the one or more parameter values ​​of the relative arrangement of the at least two radar sensors include a distance between the at least two radar sensors. For example, the one or more parameter values ​​of the relative arrangement of the at least two radar sensors include a relative inclination of the at least two radar sensors relative to each other. Thus, both deviations in the form of translations and rotations can be taken into account during compensation.

[0029] For example, determining the relative arrangement deviation is performed using a machine learning module trained to receive the first reflection data, the second reflection data, the crosstalk data, the first noise data, and the second noise data as inputs and to output the relative arrangement deviation of the first and second radar sensors as output.

[0030] For example, the method may further comprise training a machine learning module to provide or train a trained machine learning module to determine the relative arrangement deviation. For example, the trained machine learning module may be trained to receive the first reflection data, the second reflection data, the crosstalk data, the first noise data, and the second noise data as inputs and provide the relative arrangement deviation of the first and second radar sensors as output.

[0031] For example, a set of training datasets may be provided to train the machine learning module to be trained. For example, each training dataset may include first training reflection data, second training reflection data, training crosstalk data, first training noise data, and second training noise data, as well as a training bias. The machine learning module to be trained may be trained to receive the combination of first training reflection data, second training reflection data, training crosstalk data, first training noise data, and second training noise data of the training datasets as input and, in response, to provide the training bias of the respective training dataset as output.

[0032] For example, the machine learning module includes at least one neural network. For example, the machine learning module includes at least one recurrent neural network.

[0033] To effectively combine the multitude of data acquired using the plurality of radar sensors of the stereo radar system, a recurrent neural network, for example, can be used, which is well suited for such data combination. This can, for example, achieve high calibration accuracy and also ensure sufficient robustness.

[0034] For example, each of the radar sensors provides different data that can be recorded using one or more individual measurements. For example, the first radar sensor receives reflection data from objects with high reflectivity, crosstalk data from a direct radar signal that the first radar sensor receives from the second radar sensor, and noise data from a noise signal in the vicinity of the first radar sensor. For example, the second radar sensor receives reflection data from objects with high reflectivity and noise data from a noise signal in the vicinity of the second radar sensor. If the radar sensors are arranged at a short distance relative to one another, for example at a distance of approximately 0.5 m to 2 m, and at the same time the distance to the detected objects is sufficiently large, for example 50 m or more, it can be assumed that the objects are largely identical.

[0035] For example, a machine learning module with a multi-stage configuration can be used to jointly evaluate the received data. In a first stage, the various received data are preprocessed. This stage can use classic signal processing algorithms, for example, but can also include one or more neural networks. The goal of preprocessing is to convert all data into a similar form that can be interpreted by the network. One possibility is, for example, to transform all data into a 2D representation or to specifically extract properties from the received data.

[0036] The preprocessed data is then used, for example, at the next level as input for a neural network, such as a recurrent neural network. This neural network performs, for example, a regression to determine a deviation in the relative arrangement of the radar sensors, such as the position and / or orientation of the radar sensors relative to each other, and outputs it in response to receiving the input. At a further level, the output of the neural network is used, for example, in post-processing, to compensate for the determined deviation. For example, One or more parameter values ​​used for a combined evaluation of radar signals received using the at least two radar sensors are adjusted using the determined deviation in order to compensate for this determined deviation. The adjusted parameter values ​​describe, for example, the relative arrangement of the at least two radar sensors to one another. For example, the parameter values ​​of the relative arrangement of the at least two radar sensors include a distance between the at least two radar sensors. For example, the parameter values ​​of the relative arrangement of the at least two radar sensors include a relative inclination of the at least two radar sensors to one another.

[0037] A recurrent neural network can advantageously be used for evaluating a temporal relationship between the measurements, ie a temporal progression of reflection data, crosstalk data and noise data.

[0038] Using a recurrent neural network, the temporal relationship between individual measurements can be taken into account and, for example, weighted accordingly. This allows calibration to be performed over a longer period of time. For example, if the radar sensors are those of a motor vehicle, calibration over a longer period of time can efficiently suppress effects that occur during a journey, such as potholes. Furthermore, by considering the temporal progression, for example, using a recurrent neural network, effects that arise from periodic vibrations of vehicle parts can be estimated, determined, and compensated for.

[0039] A recurrent neural network is a feedback neural network which, in contrast to a feedforward network, comprises connections from model neurons in one layer to neurons in the same or a previous layer. Such recurrent interconnection of model neurons can be used to determine temporally encoded information in data. A recurrent neural network has memory because it uses information from previous inputs to influence the current input and output. Another characteristic of recurrent networks is that they share parameters across all layers of the network. While feedforward networks have different weights across each node, recurrent neural networks, for example, share the same weighting parameter within each layer.However, these weights are still adjusted through the processes of backpropagation and gradient descent to facilitate reinforcement learning.

[0040] Examples of such a recurrent neural network are an Elman network, a Jordan network, a Hopfield network or a fully interconnected neural network.

[0041] For example, training a recurrent neural network involves the following process: A training dataset is input to the recurrent neural network. The recurrent neural network receives this training dataset and performs several complex calculations with randomly initialized variables. A predicted result is output in response to the recurrent neural network receiving the training dataset. This result is compared with an expected training result from the training dataset, which generally yields an error. If the corresponding error propagates back through the same path, the variables are adjusted. The above steps are repeated until the variables are well-defined and the result matches the expected training result.The difference from a feedforward network arises from the fact that the previous inputs are also known before the result is evaluated. Recurrent neural networks can therefore be viewed as multiple feedforward neural networks, with information being passed from one network to the other.

[0042] For example, the machine learning module includes one or more convolutional neural networks (CNNs). For example, the evaluation of the temporal relationship between measurements—that is, the temporal progression of reflection data, crosstalk data, and noise data—can also be processed non-recursively, but rather using one or more convolutional neural networks.

[0043] A convolutional neural network comprises three main layer types: convolutional layers, pooling layers, and fully-connected layers. For example, a convolutional neural network comprises a structure with one or more convolutional layers followed by a pooling layer. This structure can be repeated one or more times. Convolutional layers are configured to perform discrete convolutions and to detect and extract features from the input data. Pooling layers, also known as downsampling layers, reduce the dimensions and thus the number of input parameters. A fully-connected layer completes a convolutional neural network. In such a fully-connected layer, each node of the output layer is directly connected to a node of the previous layer.Such a fully connected layer enables classification based on the features extracted by the previous layers and the various associated filters.

[0044] For example, Fast-ABC can be used as a neural network, as described in Xiaoru Xie et al., "Fast-ABC: A Fast Architecture for Bottleneck-Like Based Convolutional Neural Networks", 2019 IEEE Computer Society Annual Symposium on VLSI (ISVLSI), pages 1 to 6. Fast-ABC provides an accelerator for BLO (Bottleneck-Like Operations)-based convolutional neural networks.

[0045] For example, a UNet can be used as a neural network, as described in Olaf Ronneberger, "U-Net: Convolutional Networks for Biomedical Image Segmentation" (https: / / arxiv.org / abs / 1505.04597). The architecture of the U-Net is based on a so-called fully convolutional network. The basic idea is to supplement a conventional contracting network with successive layers in which pooling operations are replaced by upsampling operators. These layers thus increase the resolution of the output. A subsequent convolutional layer can then learn to compile a precise output based on this information. The upsampling part of the U-Net contains a large number of feature channels, allowing the network to pass context information to layers with higher resolution.As a result, the expansive path is more or less symmetric to the contracting part and leads to an egg-shaped architecture of the network.

[0046] For example, a ResNet (residual neural network) can be used as a neural network, as described, for example, in Kaiming He et al., "Deep Residual Learning for Image Recognition" (https: / / arxiv.org / abs / 1512.03385). A RestNet is a deep learning model in which weight layers learn residual functions with respect to the inputs of the layers. The corresponding network includes skip connections, also called residual connections, which perform identity mappings and are merged with the outputs of the layers by addition.

[0047] For example, a temporal course of the deviation of the relative arrangement of the first and second radar sensors is determined.

[0048] For this purpose, a temporal relationship between several measurements—i.e., a temporal progression of reflection data, crosstalk data, and noise data—is used. For example, the temporal progression of crosstalk behavior can be taken into account. In particular, periodic deviations over time can also be determined in this way.

[0049] For example, a periodically repeating pattern of the time course of the deviation is determined. The determined deviation is recorded as part of the periodically repeating A repeating pattern is used for a periodically repeating dynamic adjustment of the combined evaluation of the third radar signals received using the at least two radar sensors. Thus, for example, periodically occurring vibrations, for example due to properties of a motor vehicle comprising the radar sensors or a roadway on which the corresponding motor vehicle is traveling, can be effectively determined and compensated.

[0050] In a further aspect, a computer program for dynamically determining deviations of a relative arrangement of at least a first radar sensor and a second radar sensor is disclosed. The computer program comprises machine-readable program instructions. Execution of the machine-readable program instructions by a processor unit of a computer unit causes the processor unit to control the computer unit to receive a first reflection signal determined using the first radar sensor. The first reflection signal results from reflections of a first radar signal emitted by the first radar sensor by one or more surrounding objects and comprises distance information about one or more distances of the first radar sensor to the one or more surrounding objects. Second reflection data of a second reflection signal determined using the second radar sensor is received.The second reflection signal results from reflections of a second radar signal emitted by the second radar sensor by one or more surrounding objects and comprises distance information about one or more distances between the second radar sensor and the one or more surrounding objects. At least crosstalk data of a crosstalk signal determined using the first radar sensor is received. The crosstalk signal results from crosstalk of the second radar signal of the second radar sensor to the first radar sensor. First noise data of a first noise signal of ambient noise of the first sensor, determined using the first radar sensor, is received. Furthermore, second noise data of a second noise signal of ambient noise of the second sensor, determined using the second radar sensor, is received.A deviation of the relative arrangement of the first and second radar sensors is determined using the first reflection data, the second reflection data, the crosstalk data, the first noise data and the second noise data.

[0051] For example, a computer program product for dynamically determining deviations of a relative arrangement of at least one first radar sensor and one second radar sensor to each other, a computer-readable storage medium with machine-readable program instructions embodied therein. Execution of the machine-readable program instructions by a processor unit of a computer unit causes the processor unit to control the computer unit to receive a first reflection signal determined using the first radar sensor. The first reflection signal results from reflections of a first radar signal emitted by the first radar sensor by one or more surrounding objects and includes distance information about one or more distances of the first radar sensor to the one or more surrounding objects. Second reflection data of a second reflection signal determined using the second radar sensor is received.The second reflection signal results from reflections of a second radar signal emitted by the second radar sensor by one or more surrounding objects and comprises distance information about one or more distances between the second radar sensor and the one or more surrounding objects. At least crosstalk data of a crosstalk signal determined using the first radar sensor is received. The crosstalk signal results from crosstalk of the second radar signal of the second radar sensor to the first radar sensor. First noise data of a first noise signal of ambient noise of the first sensor, determined using the first radar sensor, is received. Furthermore, second noise data of a second noise signal of ambient noise of the second sensor, determined using the second radar sensor, is received.A deviation of the relative arrangement of the first and second radar sensors is determined using the first reflection data, the second reflection data, the crosstalk data, the first noise data and the second noise data.

[0052] In a further aspect, a computer unit for dynamically determining deviations of a relative arrangement of at least a first radar sensor and a second radar sensor to one another is disclosed. The computer unit comprises a processor unit and a memory unit with machine-readable program instructions. Execution of the machine-readable program instructions by the processor unit causes the processor unit to control the computer unit to receive a first reflection signal determined using the first radar sensor. The first reflection signal results from reflections of a first radar signal emitted by the first radar sensor by one or more surrounding objects and comprises distance information about one or more distances of the first radar sensor to the one or more surrounding objects. Second reflection data of a first radar signal emitted using the second radar sensor is received. The second reflection signal results from reflections of a second radar signal emitted by the second radar sensor by one or more surrounding objects and comprises distance information about one or more distances between the second radar sensor and the one or more surrounding objects. At least crosstalk data of a crosstalk signal determined using the first radar sensor is received. The crosstalk signal results from crosstalk of the second radar signal of the second radar sensor to the first radar sensor. First noise data of a first noise signal of ambient noise of the first sensor, determined using the first radar sensor, is received. Furthermore, second noise data of a second noise signal of ambient noise of the second sensor, determined using the second radar sensor, is received.A deviation of the relative arrangement of the first and second radar sensors is determined using the first reflection data, the second reflection data, the crosstalk data, the first noise data and the second noise data.

[0053] It is understood that one or more of the aforementioned embodiments may be combined with one another, as long as the embodiments do not exclude one another. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] The following examples are explained in more detail using the drawings. They show:

[0055] Fig. 1 is a flowchart of an exemplary method for dynamically determining deviations of a relative arrangement of radar sensors,

[0056] Fig. 2 is a block diagram of an exemplary computer unit for dynamically determining deviations of a relative arrangement of radar sensors,

[0057] Fig. 3 is a block diagram of an exemplary arrangement of radar sensors, and

[0058] Fig. 4 is a flowchart of an exemplary method for dynamically determining deviations of a relative arrangement of radar sensors. DETAILED DESCRIPTION

[0059] In the following, similar elements are identified by the same reference numerals.

[0060] Figure 1 shows an exemplary computer-implemented method for dynamically determining deviations of a relative arrangement of at least a first radar sensor and a second radar sensor. In block 200, first reflection data of a first reflection signal determined using the first radar sensor is received. The first reflection signal results from reflections of a first radar signal emitted by the first radar sensor from one or more surrounding objects and includes distance information about one or more distances of the first radar sensor to the one or more surrounding objects.

[0061] In block 202, second reflection data of a second reflection signal determined using the second radar sensor is received. The second reflection signal results from reflections of a second radar signal emitted by the second radar sensor from one or more surrounding objects and includes distance information about one or more distances of the second radar sensor to the one or more surrounding objects.

[0062] In block 204, at least crosstalk data of a crosstalk signal determined using the first radar sensor is received. The crosstalk signal results from a crosstalk of the second radar signal from the second radar sensor to the first radar sensor.

[0063] In block 206, first noise data of a first noise signal of an ambient noise of the first sensor determined using the first radar sensor is received.

[0064] In block 208, second noise data of a second noise signal of ambient noise of the second sensor determined using the second radar sensor is received.

[0065] In block 210, a deviation of the relative arrangement of the first and second radar sensors is determined using the first reflection data, the second reflection data, the crosstalk data, the first noise data, and the second noise data. The determined deviation of the relative arrangement comprises, for example, a deviation of a relative positioning of the at least two radar sensors to one another. For example, the deviation of the relative arrangement comprises a deviation of a relative orientation of the at least two radar sensors to one another. To determine the deviation of the relative arrangement of the two radar sensors, a machine learning module is used, for example, which comprises, for example, one or more neural networks. The neural networks comprise, for example, one or more recurrent neural networks.

[0066] The determined deviation is provided, for example, for dynamically adapting a combined evaluation of radar signals received using the at least two radar sensors for dynamic compensation of the determined deviation of the relative arrangement.

[0067] In block 212, for example, a combined evaluation of radar signals received using the at least two radar sensors is dynamically adjusted. Dynamically adjusting the combined evaluation includes dynamically adjusting one or more parameter values ​​used for the combined evaluation, which describe the relative arrangement of the at least two radar sensors.

[0068] Figure 2 shows an exemplary computer unit or computer device 102 for dynamically determining deviations of a relative arrangement of at least a first radar sensor and a second radar sensor. The computer unit 102 can be integrated into various types of systems. For example, the computer unit 102 is a computer unit 102 integrated into a motor vehicle. This computer unit 102 integrated into the motor vehicle can, for example, also be implemented as a distributed system. The illustrated computer unit 102 comprises a processor unit or computing unit 104. The processor unit 104 can, for example, be an integrated circuit in the form of a microprocessor or a microcontroller in an embedded system. The illustrated processor unit 104 represents one or more processor units.The illustrated computer unit 102 further includes an optional hardware interface 106. The hardware interface can enable the processor unit 104 to control other components, for example, radar sensors. The illustrated processor unit 104 can further be connected to an optional user interface 108. The user interface 108 can, for example, be a user interface 108 of an on-board computer of a motor vehicle. The user interface 108 can, for example, also include a display device. This could, for example, include a two-dimensional computer display, a touchscreen, a virtual reality system, and / or an augmented reality system.

[0069] The illustrated processor unit 104 is further connected to a storage unit 110. The storage unit 110 represents various types of memory that the processor unit 104 can access. In one example, the storage unit 110 is a non-transferable storage medium.

[0070] The memory unit 110 is illustrated as including machine-readable or machine-executable program instructions 120. The machine-readable program instructions 120 can enable the processor unit 104 to perform various numerical, image processing, and computational tasks. The machine-readable program instructions 120 can also enable the processor unit 104 to control and operate other components via the hardware interface 106, for example, two or more radar sensors. Execution of the machine-readable program instructions 120 by the processor unit 104 can cause the processor unit 104 to control the computer unit 102 to carry out the method for dynamically determining deviations of a relative arrangement of at least a first radar sensor and a second radar sensor.

[0071] The illustrated storage unit 110 further includes, for example, first reflection data 130 of a first reflection signal determined using the first radar sensor. The first reflection signal results from reflections of a first radar signal emitted by the first radar sensor from one or more surrounding objects and includes distance information about one or more distances between the first radar sensor and the one or more surrounding objects. The first reflection data 130 is received by the computer unit 110 from the first radar sensor, for example, via the hardware interface 106.

[0072] The illustrated storage unit 110 further includes, for example, second reflection data 132 of a second reflection signal determined using the second radar sensor. The second reflection signal results from reflections of a second radar signal emitted by the second radar sensor from one or more surrounding objects and includes distance information about one or more distances between the second radar sensor and the one or more surrounding objects. The second reflection data 132 is received by the computer unit 110 from the second radar sensor, for example, via the hardware interface 106.

[0073] The illustrated storage unit 110 further includes, for example, at least crosstalk data 134 of a crosstalk signal determined using the first radar sensor. The crosstalk signal results from crosstalk of the second radar signal from the second radar sensor to the first radar sensor. The crosstalk data 134 is received by the computer unit 110 from the first radar sensor, for example, via the hardware interface 106.

[0074] The illustrated storage unit 110 further includes, for example, first noise data 136 of a first noise signal of ambient noise from the first sensor, determined using the first radar sensor. The first noise data 136 is received by the computer unit 110 from the first radar sensor, for example, via the hardware interface 106.

[0075] The illustrated storage unit 110 further includes, for example, second noise data 138 of a second noise signal of ambient noise from the second sensor, determined using the second radar sensor. The second noise data 138 is received by the computer unit 110 from the second radar sensor, for example, via the hardware interface 106.

[0076] The first reflection data 130, the second reflection data 132, the crosstalk data 134, the first noise data 136, and the second noise data 138 are used by the processor unit 104 to determine a deviation 140 in the relative arrangement of the first and second radar sensors. For example, the determined deviation 140 in the relative arrangement of the radar sensors includes a deviation in a relative positioning of the at least two radar sensors to one another and / or a relative alignment of the at least two radar sensors to one another.

[0077] Furthermore, the computer unit 102 can be configured to compensate for the determined deviation 140. For example, one or more parameter values ​​142 used for a combined evaluation of radar signals received using the at least two radar sensors are adjusted using the determined deviation 140 in order to compensate for this specific deviation 140. The adjusted parameter values ​​142 describe, for example, the relative arrangement of the at least two radar sensors to one another. For example, the parameter values ​​142 of the relative arrangement of the at least two radar sensors include a distance between the at least two radar sensors. For example, the parameter values ​​142 of the relative arrangement of the at least two radar sensors include a relative inclination of the at least two radar sensors to one another.

[0078] For example, the relative arrangement deviation 140 is determined using a machine learning module 122 that is trained to receive the first reflection data 130, the second reflection data 132, the crosstalk data 134, the first noise data 136, and the second noise data 138 as inputs and to Deviation 140 of the relative arrangement of the first and second radar sensors as an output. For example, the machine learning module 122 comprises at least one neural network 124, which is, for example, a recurrent neural network. Furthermore, the machine learning module 122 can, for example, comprise a submodule 126 configured to preprocess the received data 130, 132, 134, 136, 138. For example, the preprocessed data is used as input for the neural network 124. Furthermore, the machine learning module 122 can, for example, comprise a submodule 128 configured to compensate for the deviation 140 by adjusting the parameter values ​​142. For example, the output of the neural network 124, for example in the form of the determined deviation 140, is used for post-processing.

[0079] Figure 3 shows an exemplary arrangement 160 of two radar sensors 162, 164 of a stereo radar system. The arrangement 160 comprises a first radar sensor 162 and a second radar sensor 164, which are arranged at a distance 166 from each other. The two radar sensors can, for example, be aligned with their detection fields parallel to each other. For example, the radar sensors 162, 164 can be tilted or inclined relative to each other, as in the example shown. In the example shown, the second radar sensor 164 is inclined by the inclination 168 relative to the first radar sensor 162, for example, inclined relative to each other. Deviations in the relative positioning, in particular the distance between the radar sensors 162, 164, and / or the relative alignment of the radar sensors 162, 164 can occur, for example, as a result of vibrations, thermal changes, or even mechanical changes.As a result, the original orientation and / or original position of the radar sensors 162, 164 relative to one another can be significantly changed. Such vibration, thermal changes, and even mechanical changes can occur, in particular, in the case of a stereo radar system integrated into a motor vehicle. Precisely determined deviations can be used to compensate for the corresponding deviations by parameter values ​​that are used for a combined evaluation of radar signals received using the two radar sensors 162, 164. The adjusted parameter values ​​describe, for example, the distance 166 between the two radar sensors 162, 164 that has changed as a result of the deviation and / or the inclination 168 of the two radar sensors 162, 164 relative to one another that has changed as a result of the deviation.

[0080] Figure 4 shows an exemplary computer-implemented method for dynamically determining deviations of a relative arrangement of at least a first radar sensor and a second radar sensor using a machine learning module.

[0081] Each of the at least two radar sensors provides different data that was acquired using one or more individual measurements. For example, the first radar sensor receives first reflection data 130 from objects with high reflectivity, crosstalk data 134 from a direct radar signal that the first radar sensor receives from the second radar sensor, and first noise data 136 from a noise signal in the vicinity of the first radar sensor. The first reflection signal 130 results from reflections of a first radar signal emitted by the first radar sensor from one or more surrounding objects and includes distance information about one or more distances between the first radar sensor and the one or more surrounding objects. The crosstalk data includes crosstalk information about crosstalk of the second radar signal from the second radar sensor to the first radar sensor.

[0082] For example, the second radar sensor receives second reflection data 132 from objects with high reflectivity and second noise data 138 from a noise signal in the vicinity of the second radar sensor. The second reflection signal 132 results from reflections of a second radar signal emitted by the second radar sensor from one or more surrounding objects and includes distance information about one or more distances between the second radar sensor and the one or more surrounding objects.

[0083] If the at least two radar sensors are arranged at a short distance of approximately 0.5 m to 2 m relative to each other, it can be assumed that the objects are largely identical.

[0084] For the joint evaluation of the data 130, 132, 134, 136, 138 received by at least two radar sensors, a machine learning module 122 can be used, for example, which has a multi-stage configuration. In a first stage, for example, preprocessing of the various received data 130, 132, 134, 136, 138 takes place by a submodule or preprocessing module 126 configured for this purpose. At this stage, for example, classic algorithms from signal processing can be used, but can also already include one or more neural networks. The goal of the preprocessing is to convert all data 130, 132, 134, 136, 138 into a similar form that can be interpreted by the network. One possibility is For example, to transform all data 130, 132, 134, 136, 138 into a 2D representation or to specifically extract properties from the received data. Furthermore, preprocessing can include, for example, outlier detection, averaging, and / or filtering.

[0085] The preprocessed data is then used, for example, at the next level as input for a neural network, such as a recurrent neural network 124. This recurrent neural network 124 performs, for example, a regression to determine a deviation in the relative arrangement of the radar sensors, such as the position and / or orientation of the radar sensors relative to each other, and outputs it in response to receiving the input.

[0086] At a further stage, the output of the recurrent neural network 124 is used, for example, during post-processing by a submodule or post-processing module 128 configured for this purpose, to compensate for the deviation determined by the recurrent neural network 124. For example, one or more parameter values ​​used for a combined evaluation of radar signals received using the at least two radar sensors are adjusted using the determined deviation in order to compensate for this determined deviation. The adjusted parameter values ​​describe, for example, the relative arrangement of the at least two radar sensors to one another. For example, the parameter values ​​of the relative arrangement of the at least two radar sensors include a distance between the at least two radar sensors.For example, the parameter values ​​of the relative arrangement of the at least two radar sensors include a relative inclination of the at least two radar sensors to each other. Furthermore, the post-processing may include, for example, averaging and / or filtering.

[0087] Although the invention has been fully illustrated and described in the drawings and the foregoing description, this illustration and description is to be considered as exemplary and not restrictive; the invention is not limited to the disclosed examples.

[0088] Other variations of the disclosed examples may be understood and practiced by those skilled in the art in practicing the claimed invention, based on the drawings, the description, and the appended claims. In the claims, the word "comprising" does not exclude other elements or steps, and the indefinite article "a" does not exclude a plurality. The mere fact that certain features are recited in conflicting dependent claims does not mean that a combination of those features cannot be advantageous. Any reference signs in the claims should not be interpreted as limiting the scope of protection.

[0089] A single processor or other unit may perform the functions of several elements recited in the claims. A computer program may be stored / distributed on any suitable medium, such as an optical storage medium or a solid-state medium supplied with or as part of other hardware, but it may also be distributed in other forms, such as via the Internet or other wired or wireless telecommunications systems.

[0090] As will be understood by those skilled in the art, aspects of the present invention may be embodied in the form of an apparatus, a method, or a computer program product. Accordingly, aspects of the present invention may take the form of a pure hardware variant, a pure software variant (including firmware, resident software, microcode, etc.), or a variant combining software and hardware aspects, which may be referred to generally herein as a "circuit," "module," or "system." Furthermore, aspects of the present invention may take the form of a computer program product embodied in one or more computer-readable media having computer-executable code embodied thereon.

[0091] Any combination of one or more computer-readable media may be used. The computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. As used herein, a "computer-readable storage medium" includes any tangible storage medium capable of storing instructions executable by a processor or computing system of a computing device. The computer-readable storage medium may be referred to as a computer-readable non-transitory storage medium. The computer-readable storage medium may also be referred to as a tangible computer-readable medium. In some embodiments, a computer-readable storage medium may also be capable of storing data accessible by the processor or computing system of the computing device.Examples of computer-readable storage media include: a floppy disk, a magnetic hard disk drive, a solid-state hard disk, a flash memory, a USB flash drive, random access memory (RAM), read-only memory (ROM), an optical disk, a magneto-optical disk, and the computer's register file. Processor or computing system. Examples of optical discs are compact discs (CDs) and digital versatile discs (DVDs), such as CD-ROM, CD-RW, CD-R, DVD-ROM, DVD-RW, or DVD-R discs. The term "computer-readable storage medium" also refers to various types of recording media that the computer unit can access via a network or communications connection. For example, data may be retrieved via a modem, over the Internet, or over a local area network. Computer-readable or computer-executable code embodied on a computer-readable medium may be transmitted via any suitable medium, including, but not limited to, wireless transmission, wired transmission, fiber optic cable, radio frequency transmission, etc., or via any suitable combination of the foregoing media.

[0092] A computer-readable signal medium may contain a propagated data signal with computer-executable code embodied therein, for example, in baseband or as part of a carrier wave. Such a transmitted signal may take any form, including, but not limited to, electromagnetic or optical signals, or any suitable combination thereof. A computer-readable signal medium may be any computer-readable medium, other than a computer-readable storage medium, that can convey, propagate, or transport a program for use by or in connection with an instruction-executing system, apparatus, or device.

[0093] A "computer memory," "storage unit," or "memory" is an example of a computer-readable storage medium. Computer memory is any memory that can be directly accessed by a processor or computing system.

[0094] A "processor system," "processor unit," "computing system," or "computing unit," as used herein, includes an electronic component capable of executing a program or machine-executable instruction or computer-executable code. References to the processor system or computing system, including an example "a processor system" or "a computing system," should be understood to mean that the example may include more than one processor system, processor unit, computing system, computing unit, or processor core. The processor system or computing system may, for example, be a multi-core processor. A processor system, processor unit, computing system, or computing unit may also refer to a collection of processor units or computing units within a single computer system or distributed across multiple computer systems.The term "processor system", "processor unit", "computing system" or "computing unit" should also be interpreted in such a way. that it may refer to a collection or network of computing devices, each comprising a processor or computing system. The machine-executable code or instructions may be executed by multiple computing systems or processors residing within the same computing device or even distributed across multiple computing devices.

[0095] Machine-readable or machine-executable instructions, or computer-readable or computer-executable code, may comprise instructions or a program that causes a processor or other computing system to carry out an aspect of the present invention. Computer-executable code for performing operations for aspects of the present invention may be written and compiled into machine-executable instructions in any combination of one or more programming languages, including an object-oriented programming language such as Java, Smalltalk, C++, or the like, and conventional procedural programming languages ​​such as the "C" programming language or similar programming languages. In some cases, the computer-executable code may be in high-level or precompiled form and used in conjunction with an interpreter that generates the machine-executable instructions on the fly.In other cases, the machine-executable instructions or computer-executable code may be in the form of programming for programmable logic gate arrays.

[0096] The executable computer code may be executed entirely on the user's computer unit, partially on the user's computer unit, as a standalone software package, partially on the user's computer unit and partially on a remote computer unit, or entirely on the remote computer unit or server. In the latter case, the remote computer unit may be connected to the user's computer unit via any network, including a local area network (LAN) or a wide area network (WAN), or the connection may be established with an external computer unit (for example, via the Internet with the assistance of an Internet service provider).

[0097] Aspects of the present invention are described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It is understood that each block or a portion of the blocks of the flowchart, illustrations, and / or block diagrams may be implemented by computer program instructions in the form of computer-readable or computer-executable code, if TI is applicable. It is further understood that combinations of blocks in different flowcharts, illustrations, and / or block diagrams may be combined if they are not mutually exclusive. These computer program instructions may be provided to a computing system of a general-purpose computer, a special-purpose computer, or other programmable data processing device to produce a machine such that the instructions, executing via the computing system of the computer or other programmable data processing device, provide means for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0098] These machine-executable instructions or computer program instructions may also be stored in a computer-readable medium that can instruct a computer, other programmable data processing apparatus, or other devices to function in a particular manner such that the instructions stored in the computer-readable medium produce an article of manufacture that includes instructions that perform the function / action specified in the flowchart and / or block diagram block or blocks.

[0099] The machine-readable or machine-executable instructions or computer program instructions may also be loaded onto a computer, other programmable data processing device, or other devices to cause a series of method steps to be performed on the computer, other programmable device, or other devices to produce a computer-implemented process, such that the instructions executing on the computer or other programmable device provide processes for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0100] A "user interface," as used herein, is an interface that enables a user or operator to interact with a computer or computer system. A "user interface" may also be referred to as a "human interface device." A user interface may provide information or data to the user and / or receive information or data from the user. A user interface may enable the computer to receive input from the user and provide output from the computer to the user. In other words, the user interface may enable a user to control or manipulate, and the interface can allow the computer to indicate the effects of the user's control or manipulation. Displaying data or information on a display or graphical user interface is an example of delivering information to a user. Receiving data via a keyboard, mouse, trackball, touchpad, pointing stick, graphics tablet, joystick, gamepad, webcam, headset, pedals, wired glove, remote control, and accelerometer are all examples of user interface components that enable the receipt of information or data from a user.

[0101] A "hardware interface," as used herein, includes an interface that enables the processor system or computing system of a computing unit or system to interact with and / or control an external computing device and / or apparatus. A hardware interface may enable a computing unit to send control signals or commands to an external computing device and / or apparatus. A hardware interface may also enable a computing unit to exchange data with an external data processing system and / or apparatus.Examples of a hardware interface include: a universal serial bus, an IEEE 1394 port, a parallel port, an IEEE 1284 port, a serial port, an RS-232 port, an IEEE 488 port, a Bluetooth connection, a wireless local area network connection, a TCP / IP connection, an Ethernet connection, a control voltage interface, a MIDI interface, an analog input interface, and a digital input interface.

[0102] A "display," a "display," or a "display device," as used herein, includes an output device or user interface capable of displaying images or data. A display may output visual, audible, and / or tactile data. Examples of a display include, but are not limited to: a computer monitor, a television screen, a touchscreen, a tactile electronic display, a Braille screen,

[0103] Cathode ray tube (CRT), storage tube, bi-stable display, electronic paper, vector display, flat panel display, vacuum fluorescent display (VF display), light emitting diode display (LED), electroluminescent display (ELD), plasma display panel (PDP), liquid crystal display (LCD), organic Light-emitting diode display (English: Organic Light-Emitting Diode Displays / OLED), projector and head-mounted display.

[0104] The term "machine learning" (ML) refers to a computer algorithm used to extract useful information from training datasets by automatically building probabilistic models called machine learning modules or models. A machine learning module can also be called a predictive model. Machine learning algorithms build a mathematical model based on sample data called "training data" to make predictions or decisions without being explicitly programmed to perform the task. The machine learning module can be performed using a learning algorithm, such as supervised or unsupervised learning. The machine learning module can use various techniques, such as clustering, classification, linear regression, reinforcement learning, and more.reinforcing learning), self-learning, support vector machines, neural networks, etc. A machine learning module can be, for example, a data structure or a program such as a neural network, in particular a convolutional neural network (CNN), a support vector machine, a decision tree, a Bayesian network, etc. The machine learning module can be adapted, i.e. trained, to predict an unmeasured value. The trained machine learning module can thus be enabled to predict the unmeasured value as output from other known values ​​as input.

[0105] For example, a machine learning module to be trained can be an untrained machine learning module, a pre-trained machine learning module, or a partially trained machine learning module. The machine learning module to be trained can be an untrained machine learning module that is trained from scratch. Alternatively, the machine learning module to be trained can be a pre-trained or partially trained machine learning module. In general, it is not necessary to start with an untrained machine learning module, for example, in deep learning. One can start with a pre-trained or partially trained machine learning module, for example. The pre-trained or partially trained machine learning module can be pre-trained or partially trained on the same or a similar task.The use of a pre-trained or. For example, a partially trained machine learning module can enable faster training of the machine learning module being trained, meaning the training can converge more quickly. For example, transfer learning can be used to train a pre-trained or partially trained machine learning module. Transfer learning refers to a machine learning module in which the learning process does not start from scratch, but rather starts from patterns already learned while solving another problem. In this way, for example, previous learning experiences can be used without having to start from scratch. A pre-trained machine learning module is a machine learning module that has been previously trained, for example on a large benchmark dataset, to solve a problem similar to the one the additional learning is intended to solve.In the case of a pre-trained machine learning module, a previous learning process has been successfully completed. A partially trained machine learning module is a machine learning module that has been partially trained, meaning the learning process may not yet be complete. A pre-trained or partially trained machine learning module can, for example, be imported and trained to be used for the purposes disclosed herein. LIST OF REFERENCE SYMBOLS 102 Computer unit 104 Processor unit 106 Hardware interface 108 User interface 110 storage unit 120 machine-readable program instructions 122 Machine Learning Module 124 recurrent neural network 126 Pre-processing module 128 Post-processing module 130 first reflection data 132 second reflection data 134 crosstalk data 136 first noise data 138 second noise data 140 Deviation 142 parameter values 160 Arrangement of radar sensors 162 radar sensor 164 radar sensor 166 distance 168 inclination

Claims

CLAIMS 1. A computer-implemented method for dynamically determining deviations (140) of a relative arrangement (160) of at least a first radar sensor (162) and a second radar sensor (164) to each other, the method comprising: • Receiving first reflection data (130) of a first reflection signal determined using the first radar sensor (162), which results from reflections of a first radar signal emitted by the first radar sensor (162) at one or more surrounding objects and comprises distance information about one or more distances of the first radar sensor (162) to the one or more surrounding objects, • Receiving second reflection data (132) of a second reflection signal determined using the second radar sensor (164), which results from reflections of a second radar signal emitted by the second radar sensor (164) at one or more surrounding objects and includes distance information about one or more distances of the second radar sensor (164) to the one or more surrounding objects, • Receiving at least crosstalk data (134) of a crosstalk signal determined using the first radar sensor (162), which results from a crosstalk of the second radar signal of the second radar sensor (164) to the first radar sensor (162), • receiving first noise data (136) of a first noise signal of an ambient noise of the first sensor determined using the first radar sensor (162), • receiving second noise data (138) of a second noise signal of an ambient noise of the second sensor (164) determined using the second radar sensor (164), • Determining a deviation (140) of the relative arrangement (160) of the first and second radar sensors (162, 164) using the first reflection data (130), the second reflection data (132), the crosstalk data (134), the first noise data (136) and the second noise data (138).

2. The method according to claim 1, wherein the deviation (140) of the relative arrangement (160) comprises a deviation (140) of a relative positioning and / or a relative orientation of the at least two radar sensors (162, 164) to one another.

3. The method according to any one of the preceding claims, wherein the method further comprises dynamically adapting a combined evaluation of third radar signals received using the at least two radar sensors (162, 164), which comprises dynamically adapting one or more parameter values ​​(142) used for the combined evaluation, which describe the relative arrangement (160) of the at least two radar sensors (162, 164).

4. The method according to claim 3, wherein the one or more parameter values ​​(142) of the relative arrangement of the at least two radar sensors (162, 164) comprise a distance (166) between the at least two radar sensors (162, 164) and / or a relative inclination (168) of the at least two radar sensors (162, 164) to one another.

5. The method according to any one of the preceding claims, wherein determining the deviation (140) of the relative arrangement (160) is performed using a machine learning module trained to receive the first reflection data (130), the second reflection data (132), the crosstalk data (134), the first noise data (136) and the second noise data (138) as inputs and to output the deviation (140) of the relative arrangement (160) of the first and second radar sensors (162, 164) as output.

6. The method according to claim 5, wherein the machine learning module (122) comprises at least one neural network, in particular at least one recurrent neural network (124).

7. Method according to one of the preceding claims, wherein a time course of the deviation (140) of the relative arrangement (160) of the first and second radar sensors (162, 164) is determined.

8. The method according to claim 7, wherein a periodically repeating pattern of the temporal course of the deviation (140) is determined, wherein the determined deviation (140) is used as part of the periodically repeating pattern for a periodically repeating dynamic adaptation of the combined evaluation of the third radar signals received using the at least two radar sensors (162, 164).

9. A computer program for dynamically determining deviations (140) of a relative arrangement (160) of at least a first radar sensor (162) and a second radar sensor (164) to one another, which comprises machine-readable program instructions (122), wherein execution of the machine-readable program instructions (122) by a processor unit (104) of a computer unit (102) causes the processor unit (104) to control the computer unit (102) to: • Receiving first reflection data (130) of a first reflection signal determined using the first radar sensor (162), which results from reflections of a first radar signal emitted by the first radar sensor (162) at one or more surrounding objects and includes distance information about the one or more distances of the first radar sensor (162) to one or more surrounding objects, • Receiving second reflection data (132) of a second reflection signal determined using the second radar sensor (164), which results from reflections of a second radar signal emitted by the second radar sensor (164) at one or more surrounding objects and includes distance information about one or more distances of the second radar sensor (164) to the one or more surrounding objects, • Receiving at least crosstalk data (134) of a crosstalk signal determined using the first radar sensor (162), which results from a crosstalk of the second radar signal of the second radar sensor (164) to the first radar sensor (162), • receiving first noise data (136) of a first noise signal of an ambient noise of the first sensor determined using the first radar sensor (162), • receiving second noise data (138) of a second noise signal of an ambient noise of the second sensor determined using the second radar sensor (164), • Determining a deviation (140) of the relative arrangement (160) of the first and second radar sensors (162, 164) using the first reflection signal, the second reflection signal, the crosstalk signal, the first noise signal and the second noise signal.

10. Computer unit (102) for dynamically determining deviations (140) of a relative arrangement (160) of at least a first radar sensor (162) and a second radar sensor (164) to one another, wherein the computer unit (102) comprises a processor unit (104) and a memory unit (110) with machine-readable program instructions (122), wherein execution of the machine-readable program instructions (122) by the processor unit (104) causes the processor unit (104) to control the computer unit (102) to: • Receiving first reflection data (130) of a first reflection signal determined using the first radar sensor (162), which results from reflections of a first radar signal emitted by the first radar sensor (162) at one or more surrounding objects and includes distance information about the one or more distances of the first radar sensor (162) to one or more surrounding objects, • Receiving second reflection data (132) of a second reflection signal determined using the second radar sensor (164), which results from reflections of a second radar signal emitted by the second radar sensor (164) at one or more surrounding objects and includes distance information about one or more distances of the second radar sensor (164) to the one or more surrounding objects, • Receiving at least crosstalk data (134) of a crosstalk signal determined using the first radar sensor (162), which results from a crosstalk of the second radar signal of the second radar sensor (164) to the first radar sensor (162), • receiving first noise data (136) of a first noise signal of an ambient noise of the first sensor determined using the first radar sensor (162), • receiving second noise data (138) of a second noise signal of an ambient noise of the second sensor determined using the second radar sensor (164), • Determining a deviation (140) of the relative arrangement (160) of the first and second radar sensors (162, 164) using the first reflection data (130), the second reflection data (132), the crosstalk data (134), the first noise data (136) and the second noise data (138).

Images