Method, system and computer program product for detecting a change in the steering angle of a motor vehicle

Abstract

Method for detecting a change in the steering angle of at least one wheel of a motor vehicle (10) by a second motor vehicle (20) using a data analysis device (40), wherein the data analysis device (40) is designed as a cloud-based solution in a cloud computing platform and is connected to the second motor vehicle (20) via a mobile communication connection, comprising: - Recording (S10) image and sensor data (32) by means of a camera and sensor device (30) of the second motor vehicle (20), wherein the image and sensor data (32) represent the environment of the second motor vehicle (20) with at least the first motor vehicle (10), and wherein the camera and sensor device (30) comprises an action camera; - Transferring (S20) the image and sensor data (32) to the data analysis device (40), wherein the data analysis device (40) comprises a detection system (400) for detecting a change in the steering angle of at least one wheel of the first motor vehicle (10), which uses algorithms from the field of artificial intelligence (AI) and machine image analysis, wherein the detection system (400) comprises an analysis module (410) and a classification module (430), wherein the detection system (400) uses deep learning with a neural network, wherein the neural network is configured as a convolutional neural network, and wherein the classification module (430) features (M1, M2, ..., M n ) of the wheel movements and wheel steering angle of a vehicle, which were determined or predefined in a training phase of the classification module (430); - Processing (S30) the image and sensor data (32) in the data analysis unit (40) using the recognition system (400) to classify possible changes in the wheel steering angle of the wheel.; - Assigning (S40) the classified change in wheel steering angle to at least one state (S j ) from a set of defined states (S1, S2, ..., S n ); - Generating (S50) output data (450) from the determined state (Sj) for further use in an automated driving function; - wherein the processing of the image and sensor data (32) and the generation of output data (450) takes place in real time; - wherein the image and sensor data (32) are transmitted via the mobile communication connection to the data analysis facility (40) in the cloud computing platform, in particular using 5G radio modules, - where the analysis and calculation are performed in the cloud computing platform, and - wherein the analysis and calculation results are sent back to the second motor vehicle (20) in real time for integration into automated driving functions.

Description

[0001] The invention relates to a method, a system and a computer program product for detecting a change in a wheel steering angle of at least one wheel in a motor vehicle.

[0002] When a motor vehicle is driven by a person, the driver observes very carefully and intuitively whether any potential hazards are in the path. In particular, vehicles ahead are closely observed to obtain various information, such as the speed of the vehicle ahead or whether an overtaking maneuver is planned. A trained human driver performs these observations intuitively while driving and is often even aware of how they process the information and assign it to a potentially dangerous situation.

[0003] Semi-autonomous and autonomous vehicles use camera systems and sensors to obtain information about the vehicle's surroundings. The development of highly automated driving (HAD) is therefore accompanied by increased demands on vehicle sensor systems to capture suitable sensor data, particularly image data. Furthermore, the recorded sensor data must be carefully interpreted to draw the correct conclusions regarding a potentially hazardous situation.

[0004] A particularly dangerous situation arises when a moving vehicle is driving past a parked vehicle in a parking space. It is often difficult for a driver to determine whether a parked vehicle intends to leave the parking space. Although brake lights often serve as indicators for whether a vehicle intends to change from parked to drive mode, these lights can be defective or, due to the large number of information signals, are overlooked by the driver of a first vehicle driving past the second parked vehicle. A sure sign of a vehicle leaving a parking space, however, is a change in the steering angle of the vehicle's wheels once the driver of the second parked vehicle has begun to maneuver to leave the parking space. This similarly applies to an overtaking maneuver, where a change in the steering angle of the wheels also indicates a change in driving behavior.

[0005] US 2018 / 0 134 284 A1 relates to a control system with a sensor in a motor vehicle. The sensor records data from a front wheel of a neighboring vehicle. A wheel angle parameter of the front wheel of the neighboring vehicle is determined based on the data, and a control command is generated to change a direction or acceleration of the motor vehicle based on the determined wheel angle parameter.

[0006] DE 10 2017 204 347 A1 discloses a method and a system for determining a kinematic property of an object. For this purpose, image data comprising a sequence of individual images of the object is acquired. The image data is forwarded to a convolutional neural network, which processes the image data and provides corresponding output data.

[0007] EP 3 561 733 A1 discloses a communication device for evaluating sensor data using two artificial neural networks. It contains a sensor that records physical parameters and provides the sensor data. A processor executes a first neural network locally in the device, which reduces the amount of sensor data. The reduced data is transmitted via a communication interface to a server, which uses a second neural network for further processing. The processed sensor data is then sent from the server back to the communication device and is available to the processor for further evaluation.

[0008] An object of the present invention is therefore to provide a method, a system and a computer program product for detecting a change in a wheel steering angle in at least one wheel of a motor vehicle, which is characterized by high reliability and efficient use of computing capacity.

[0009] This object is achieved according to the invention with regard to a method by the features of patent claim 1, with regard to a system by the features of patent claim 2, and with regard to a computer program product by the features of patent claim 3.

[0010] According to a first aspect, the invention relates to a method for detecting a change in the steering angle of at least one wheel in a motor vehicle by a second motor vehicle using a data analysis device. The data analysis device is designed as a cloud-based solution in a cloud computing platform and is connected to the second motor vehicle via a mobile radio connection. The method comprises the following method steps: - Recording image and sensor data by means of a camera and sensor device of the second motor vehicle, wherein the image and sensor data represent the surroundings of the second motor vehicle with at least the first motor vehicle, and wherein the image and sensor device comprises an action camera; - forwarding the image and sensor data to the data analysis device, wherein the data analysis device comprises a recognition system for detecting a change in a wheel steering angle of at least one wheel of the first motor vehicle, which uses algorithms from the field of artificial intelligence (AI) and machine image analysis, wherein the recognition system comprises an analysis module and a classification module, wherein the recognition system uses deep learning with a neural network, wherein the neural network is designed as a convolutional neural network, and wherein the classification module features M1, M2, ..., M n the wheel movements and wheel steering angle of a vehicle, which were determined in a training phase of the classification module or defined in advance; - Processing the image and sensor data in the data analysis device using the detection system to classify possible changes in the wheel steering angle; - Assigning the classified change in the wheel steering angle to at least one state S j from a set of defined states S1, S2, ..., S n ; - Generating output data from the determined state S j for further use in an automated driving function;., - where the processing of image and sensor data and the generation of output data takes place in real time, - wherein the image and sensor data are transmitted to the data analysis device in the cloud computing platform via the mobile radio connection, in particular using 5G radio modules, - where the analysis and calculation is carried out in the cloud computing platform, and - whereby the analysis and calculation results are sent back to the second motor vehicle in real time for integration into automated driving functions.

[0011] According to a second aspect, the invention relates to a system for detecting a change in a wheel steering angle of at least one wheel of a motor vehicle by a second motor vehicle. The system comprises an image and sensor device of the second motor vehicle for recording image and sensor data and a data analysis device, wherein the image and sensor device comprises an action camera. The data analysis device is designed as a cloud-based solution in a cloud computing platform and is connected to the second motor vehicle via a mobile radio connection. The image and sensor data represent the surroundings of the second motor vehicle with at least the first motor vehicle. The data analysis device comprises a detection system for detecting a change in a wheel steering angle of at least one wheel in the first motor vehicle. The detection system uses algorithms from the field of artificial intelligence (AI) and machine image analysis.The recognition system comprises an analysis module and a classification module and uses deep learning with a neural network, which is specifically designed as a convolutional neural network. The classification module contains features M1, M2, ..., M. n the wheel movements and the wheel steering angle of a vehicle, which were determined in a training phase of the classification module or defined in advance. The data analysis device is designed to process the image and sensor data by means of the recognition system, to classify possible changes in the wheel steering angle of the wheel, to assign at least one state S to the classified change in the wheel steering angle j from a set of defined states S1, S2, ..., S n and output data from the determined state S jfor further use in an automated driving function. The processing of the image and sensor data and the generation of output data takes place in real time. The image and sensor data are transmitted via the mobile network connection to the data analysis device in the cloud computing platform, using in particular 5G radio modules. The analysis and calculation are performed in the cloud computing platform, with the analysis and calculation results being sent back to the second motor vehicle in real time for integration into automated driving functions.

[0012] According to a third aspect, the invention relates to a computer program product comprising an executable program code which is configured to carry out the method according to the first aspect when executed.

[0013] The invention is explained in more detail below using an embodiment shown in the drawing.

[0014] It shows: Fig. 1 a schematic representation of a system according to the invention for detecting a change in a wheel steering angle of at least one wheel in a motor vehicle; Fig. 2 shows an embodiment of a recognition system according to the invention; Fig. 3 a flow chart to explain the individual method steps of a method according to the invention; Fig. 4 a computer program product according to an embodiment of the third aspect of the invention.

[0015] Additional features, aspects and advantages of the invention or its embodiments will become apparent from the detailed description taken in conjunction with the claims.

[0016] In Fig. Figure 1 shows the system 100 according to the invention for detecting a change in a wheel steering angle of at least one wheel of a motor vehicle 10. In particular, the motor vehicle 10 is a parked motor vehicle. A camera and sensor device 30 of a second motor vehicle 20 records the surroundings of the motor vehicle 20 and thus also the parked motor vehicle 10 when the second motor vehicle 20, for example, passes the first motor vehicle 10. The camera and sensor device 30 transmits the recorded image data and measured values ​​to a data analysis device 40 for further processing.

[0017] The camera and sensor device 30 captures image and sensor data 32 in a recording area. The camera and sensor device 30 comprises, in particular, an RGB camera 35 in the visible range with the primary colors blue, green, and red. However, a UV camera 37 in the ultraviolet range and / or an IR camera 39 in the infrared range can also be provided. The cameras 35, 37, 39, which differ in their recording spectrum, can thus image different lighting conditions in the recording area.

[0018] The recording frequency of the camera of the camera and sensor device 30 is designed for high wheel movement speeds and can record image data 32 at a high frame rate. Furthermore, the camera and sensor device 30 can be equipped with a microphone for detecting acoustic signals. This allows tire rolling noise or engine noise to be recorded.

[0019] Furthermore, it can be provided that the camera and sensor device 30 automatically starts the image acquisition process when a significant change in area occurs in the recording area of ​​the camera and sensor device 30, for example, when a vehicle 10 appears in the recording area of ​​the camera and sensor device 30. This enables a selective data acquisition process, and only relevant image and sensor data 32 are processed by the data analysis device 40. This allows computing capacity to be used more efficiently.

[0020] In addition, a GPS connection is advantageously provided to determine the geographical location and to assign it to the recorded image and sensor data 32.

[0021] In particular, it is intended to use a weatherproof action camera as the camera, which can be arranged particularly outside the vehicle 20. Action cameras have wide-angle fisheye lenses, making it possible to achieve a visible radius of approximately 180°. Action cameras can usually record videos in Full HD (1,920 x 1,080 pixels), but action cameras can also be used in Ultra HD or 4K (at least 3,840 x 2,160 pixels), resulting in a significant improvement in image quality. The image recording frequency is typically 60 frames per second in 4K and up to 240 frames per second in Full HD. An integrated image stabilizer can also be provided. Furthermore, action cameras are often equipped with an integrated microphone. Differential signal processing methods can also be used to specifically suppress background noise.

[0022] The image and sensor data 32 recorded by the camera and sensor device 30 are preferably transmitted to the data analysis device 40 via a wireless mobile radio connection.

[0023] The data analysis device 40 preferably has a processor 41 that processes the image and sensor data 32 using a recognition system 400. The processor 41 or another processor is also configured to control the camera and image recording device 30. However, it is also conceivable for the image and sensor data 32 to be initially stored in a storage unit 50 or a software module 55 and only processed at a later time by the data analysis device 40. The data analysis device 40 and the processor 41 can be integrated into the vehicle 20 or configured as a cloud-based solution connected to the vehicle 20 via a mobile radio connection.

[0024] In addition, the data analysis device 40 can access one or more additional databases 60. For example, classification parameters for analyzing the recorded image and sensor data 32 or additional images and / or parameters can be stored in the database 60. Furthermore, target variables and target values ​​that define a safety standard can be stored in the database 60. Furthermore, a user interface 70 can be provided for entering additional data and for displaying the calculation results generated by the data analysis device 40. In particular, the user interface 70 is designed as a display with a touchscreen.

[0025] In the context of the invention, a "processor" can be understood, for example, as a machine, an electronic circuit, or a powerful computer. A processor can be, in particular, a central processing unit (CPU), a microprocessor, or a microcontroller, for example, an application-specific integrated circuit or a digital signal processor, possibly in combination with a memory unit for storing program instructions, etc. A processor can also be understood as a virtualized processor, a virtual machine, or a soft CPU.For example, it may also be a programmable processor that is equipped with configuration steps for executing the aforementioned method according to the invention or is configured with configuration steps such that the programmable processor implements the inventive features of the method, the component, the modules, or other aspects and / or sub-aspects of the invention. Highly parallel computing units and powerful graphics modules can also be provided.

[0026] In the context of the invention, a "storage unit" or "storage module" and the like can be understood to mean, for example, a volatile memory in the form of random-access memory (RAM), a permanent memory such as a hard drive or a data storage device, or, for example, a removable storage module. However, the storage module can also be a cloud-based storage solution.

[0027] In the context of the invention, a "module" can be understood, for example, as a processor and / or a memory unit for storing program instructions. For example, the processor is specifically configured to execute the program instructions in such a way that the processor performs functions to implement or realize the method according to the invention or a step of the method according to the invention.

[0028] In the context of the invention, recorded image and sensor data 32 are understood to mean both the raw data and already processed data from the recording results of the image and sensor device 30.

[0029] In particular, the imaging and sensor device 30 can be equipped with 5G standard mobile communications modules. 5G is the fifth-generation mobile communications standard and, compared to the 4G mobile communications standard, is characterized by higher data rates of up to 10 Gbit / sec, the use of higher frequency ranges such as 2100, 2600, or 3600 megahertz, increased frequency capacity and thus increased data throughput, and real-time data transmission, as up to one million devices per square kilometer can be addressed simultaneously. Latency times range from a few milliseconds to less than 1 ms, enabling real-time transmission of data and calculation results. The image and sensor data 32 acquired by the imaging and sensor device 30 are sent in real time to a cloud platform, where the corresponding analysis and calculation are performed.The analysis and calculation results are sent back to the vehicle 20 in real time and can therefore be quickly integrated into driver instructions or automated driving functions. This speed of data transmission is necessary if cloud-based solutions are to be used for processing the image and sensor data 32. Cloud-based solutions offer the advantage of high and therefore fast computing power.

[0030] If the data analysis device 40 is integrated into the vehicle, AI hardware acceleration such as the Coral Dev Board is advantageously used for the processor 41 to enable real-time processing. This is a microcomputer with a tensor processing unit (TPU), allowing a pre-trained software application to evaluate up to 70 images per second.

[0031] Fig.2 shows the recognition system 400 according to the invention, which is embodied as a software application for analyzing and processing the acquired and / or stored image and sensor data 32 in order to detect a change in the wheel steering angle on the vehicle 10. In particular, the recognition system 400 processes the acquired image and sensor data 32 using artificial intelligence and machine image analysis algorithms in order to select and classify them. Advantageously, the recognition system 400 uses algorithms from the field of machine learning, preferably deep learning with, for example, convolutional neural networks, to analyze the acquired image and sensor data 32.

[0032] A neural network consists of neurons arranged in multiple layers and connected to one another in various ways. A neuron is capable of receiving information at its input from outside or from another neuron, evaluating the information in a specific way, and forwarding it in a modified form to another neuron at the neuron output or outputting it as the final result. Hidden neurons are arranged between the input neurons and output neurons. Depending on the network type, there may be multiple layers of hidden neurons. They ensure the forwarding and processing of information. Output neurons ultimately deliver a result and transmit it to the outside world. The arrangement and connection of the neurons gives rise to different types of neural networks, such as feedforward networks, recurrent networks, or convolutional neural networks.The networks can be trained through unsupervised or supervised learning.

[0033] In particular, the recognition system 400 has an analysis module 410 configured as a convolutional neural network (CNN). The image and sensor data 32 from the camera and sensor device 30 are used as input data for the analysis module 410. Data from the database 60 can also be used. The data formats of the input data are preferably configured as tensors. Furthermore, different image formats can advantageously be used.

[0034] The convolutional neural network is a special type of artificial neural network. It has multiple convolutional layers and is highly suitable for machine learning and artificial intelligence (AI) applications in the field of image and speech recognition. The functionality of a convolutional neural network is modeled to some extent on biological processes, and its structure is comparable to the brain's visual cortex. Training of a convolutional neural network is usually supervised. Conventional neural networks consist of fully or partially meshed neurons in multiple layers. However, these structures reach their limits when processing images, as a number of inputs corresponding to the number of pixels would be required. The convolutional neural network is composed of various layers and, in principle, is a partially locally meshed feedforward neural network.The individual layers of the CNN are the convolutional layer, the pooling layer, and the fully meshed layer. The pooling layer follows the convolutional layer and can be present multiple times in this combination. Because the pooling layer and the convolutional layer are locally meshed subnetworks, the number of connections in these layers remains limited and manageable, even with large input volumes. The final layer is a fully meshed layer. The convolutional layer is the actual convolutional layer and is capable of detecting and extracting individual features from the input data. In image processing, these can be features such as lines, edges, or specific shapes. The input data is processed in the form of tensors, such as a matrix or vectors.The pooling layer, also called the subsampling layer, condenses and reduces the resolution of the detected features using appropriate filter functions. In particular, a maxpool function is used for this purpose, which calculates the maximum value for a (usually) non-overlapping subset of the data. In addition to maximum pooling, mean pooling can also be used. This pooling discards superfluous information and reduces the data volume. This does not reduce the performance of machine learning. The reduced data volume increases the calculation speed.

[0035] The final layer of the convolutional neural network is the fully connected layer. It is the result of the repeated sequence of convolutional and pooling layers. All features and elements of the upstream layers are linked to each output feature. The fully connected neurons can be arranged in multiple layers.

[0036] The number of neurons depends on the input data that the convolutional neural network is to process.

[0037] The convolutional neural network (CNN) therefore offers numerous advantages over conventional non-convolutional neural networks. It is suitable for machine learning and artificial intelligence applications with large amounts of input data, such as image recognition. The network operates reliably and is insensitive to distortions or other optical changes. The CNN can process images taken under different lighting conditions and from different perspectives. It still recognizes the typical features of an image. Because the CNN is divided into several local, partially meshed layers, it requires significantly less memory than fully meshed neural networks. The convolutional layers drastically reduce memory requirements. The training time of the convolutional neural network is also significantly reduced. With the use of modern graphics processors, CNNs can be trained very efficiently.The CNN detects and extracts features from the input images using filters. Initially, the CNN detects simple structures such as lines, color features, or edges in the first few layers. In subsequent layers, the convolutional neural network learns combinations of these structures, such as simple shapes or curves. With each layer, more complex structures can be identified. The data is repeatedly resampled and filtered in each layer.

[0038] In the analysis module 410, the image and sensor data 32 are thus preferably processed using a convolutional neural network. A classification module 430 is also provided, which classifies features M1, M2, ..., M n of the wheel movements and the wheel steering angle of a vehicle. In addition, these features M1, M2, ..., M n certain states S1, S2, ..., S nof the vehicle. Thus, certain values ​​of the wheel steering angles of the wheels of vehicle 10 can indicate that vehicle 10 has begun to leave the parking space and will soon leave it. The speed of the wheel movements can also be used to determine how quickly vehicle 10 is likely to leave the parking space. The states S1, S2, ..., S n can in turn be assigned security levels. These characteristics M1, M2, ..., M n and / or states S1, S2, ..., S n of the vehicle were preferably determined by the CNN in a training phase or they were defined in advance and transmitted to the classification module.

[0039] The image and sensor data 32 processed in this way are integrated into an automated driving function as output data 450 and / or transmitted to the user interface 70. They can be output there as recommended actions or warnings to the driver of the vehicle 20. For example, a warning tone or a visual signal can be output via the user interface 70. With an automated driving function, the driving speed can also be reduced automatically.

[0040] A method for detecting a change in a wheel steering angle of at least one wheel in a motor vehicle according to the present invention therefore comprises the following steps:

[0041] In a step S10, image and sensor data 32 are recorded by a camera and sensor device 30 of a second motor vehicle 20, wherein the image and sensor data 32 represent the surroundings of the vehicle 20 with at least the first motor vehicle 10.

[0042] In a step S20, the image and sensor data 32 are forwarded to a data analysis device 40, wherein the data analysis device 40 comprises a detection system 400 for detecting a change in a wheel steering angle of at least one wheel in the first motor vehicle, which system uses algorithms from the field of artificial intelligence (AI) and machine image analysis.

[0043] In a step S30, the image and sensor data 32 are processed in the data analysis device 30 by means of the recognition system 200 in order to classify possible changes in the wheel steering angle of the wheel.

[0044] In a step S40, the classified change in the wheel steering angle is assigned a state S j from a set of defined states S1, S2, ..., S n assigned.

[0045] In a step S50, the determined state S jOutput data 280 is generated for further use in an automated driving function and / or for a user interface 70.

[0046] Using a recognition system 400 that uses algorithms from the field of artificial intelligence (AI) and machine image analysis, images from the surroundings of a second vehicle 20 can be analyzed in real time with regard to changes in the wheel steering angle of another first vehicle 10. The present invention enables the automatic detection of changes in the wheel steering angle of at least one wheel of the vehicle 10, in particular of a parked vehicle 10. The driving behavior of the vehicle 10 can be derived from the classified changes in the wheel steering angle. The result of the analysis is output, for example, as a warning signal on a user interface 70 of the second vehicle 20 if the change in the wheel steering angle indicates a critical driving situation for the second vehicle 20. The present invention can thus further increase driving safety. Reference symbol 10 first motor vehicle 20 second motor vehicle 30 Camera and sensor setup 32 image and sensor data 35 RGB camera 37 UV camera 39 IR camera 40 Data analysis facility 41 processor 50 storage units 55 Software module 60 database 70 User interface 100 systems 400 detection system 410 Analysis module 430 Classification module 450 output data 500 computer program product 550 program code

Claims

[1] Method for detecting a change in a wheel steering angle of at least one wheel in a motor vehicle (10) by a second motor vehicle (20) by means of a data analysis device (40), wherein the data analysis device (40) is designed as a cloud-based solution in a cloud computing platform and is connected to the second motor vehicle (20) via a mobile radio connection, comprising: - Recording (S10) image and sensor data (32) by means of a camera and sensor device (30) of the second motor vehicle (20), wherein the image and sensor data (32) represent the surroundings of the second motor vehicle (20) with at least the first motor vehicle (10), and wherein the camera and sensor device (30) comprises an action camera; - forwarding (S20) the image and sensor data (32) to the data analysis device (40), wherein the data analysis device (40) comprises a recognition system (400) for detecting a change in a wheel steering angle of at least one wheel in the first motor vehicle (10), which uses algorithms from the field of artificial intelligence (AI) and machine image analysis, wherein the recognition system (400) comprises an analysis module (410) and a classification module (430), wherein the recognition system (400) uses deep learning with a neural network, wherein the neural network is designed as a convolutional neural network, and wherein the classification module (430) features (M1, M2, ..., M n ) of the wheel movements and the wheel steering angle of a vehicle, which were determined or predefined in a training phase of the classification module (430); - processing (S30) the image and sensor data (32) in the data analysis device (40) by means of the recognition system (400) in order to classify possible changes in the wheel steering angle of the wheel; - Assigning (S40) the classified change in the wheel steering angle to at least one state (S j ) from a set of defined states (S1, S2, ..., S n ); - generating (S50) output data (450) from the determined state (Sj) for further use in an automated driving function; - wherein the processing of the image and sensor data (32) and the generation of output data (450) takes place in real time; - wherein the image and sensor data (32) are transmitted to the data analysis device (40) in the cloud computing platform by means of the mobile radio connection, in particular using 5G radio modules, - where the analysis and calculation is carried out in the cloud computing platform, and - wherein the analysis and calculation results are sent back to the second motor vehicle (20) in real time for integration into automated driving functions. [2] System (100) for detecting a change in a wheel steering angle of at least one wheel in a motor vehicle (10) by a second motor vehicle (20), comprising an image and sensor device (30) of the second motor vehicle (20), wherein the image and sensor data (32) represent the surroundings of the second motor vehicle (20) with at least the first motor vehicle (10), and wherein the image and sensor device (30) comprises an action camera;and a data analysis device (40) which is designed as a cloud-based solution in a cloud computing platform and is connected to the second motor vehicle (20) via a mobile radio connection, wherein the data analysis device (20) comprises a detection system (400) for detecting a change in a wheel steering angle of at least one wheel in the first motor vehicle (10), which uses algorithms from the field of artificial intelligence (AI) and machine image analysis, and wherein the data analysis device (40) is designed to process the image and sensor data (32) by means of the detection system (400), to classify possible changes in the wheel steering angle of the wheel, to assign at least one state (S; j ) from a set of defined states (S1, S2, ..., S n) and to generate output data (450) from the determined state (Sj) for further use in an automated driving function; wherein the recognition system (400) comprises an analysis module (410) and a classification module (430), wherein the recognition system (400) uses deep learning with a neural network which is designed as a convolutional neural network, wherein the classification module (430) comprises features (M1, M2, ..., M n) of the wheel movements and the wheel steering angle of a vehicle, which were determined in a training phase of the classification module (430) or defined in advance; and wherein the processing of the image and sensor data (32) and the generation of output data (450) takes place in real time, wherein the image and sensor data (32) are transmitted by means of the mobile radio connection to the data analysis device (40) in the cloud computing platform, wherein in particular 5G radio modules are used, wherein the analysis and calculation are carried out in the cloud computing platform, and wherein the analysis and calculation results are sent back to the second motor vehicle (20) in real time for integration into automated driving functions. [3] A computer program product (500) comprising executable program code (550) configured to perform the method of claim 1 when executed.

Images