Method for hand detection, computer program, and device

Abstract

Exemplary embodiments of the present invention provide a method (100) for improving hand detection on a steering wheel of a vehicle. The method (100) comprises determining (110) a parameter for evaluating the safety relevance of a situation and carrying out (120) the hand detection on the basis of at least one machine learning algorithm and a model-based algorithm on the basis of the parameter.

Description

[0001] Description

[0002] Method for hand detection, computer program, and device

[0003] Embodiments of the present invention relate to a method for hand detection, a computer program, and a device. In particular, but not exclusively, embodiments of the present invention relate to a method for improving the detection of hand detection on a steering wheel of a vehicle.

[0004] Driver assistance systems are designed to support and relieve the driver's workload in specific situations, making driving as comfortable and safe as possible. Despite a progressively increased level of automation, the driver, as an active part of the control strategy for longitudinal and lateral guidance, remains crucial for monitoring the systems and the respective situation. Part of this active role is placing their hands on the steering wheel to quickly ensure full control and the driver's ability to stabilize the system in critical situations.

[0005] DE 10 2016 005 013 A1 discloses a steer-by-wire steering system for motor vehicles with a steering actuator acting on the steered wheels and electronically controlled depending on the driver's steering input, with a feedback actuator transmitting road reactions to a steering wheel, and with a control unit that controls the feedback actuator and the steering actuator. The control unit includes an estimator comprising an observer and a model of the feedback actuator. The estimator is configured to estimate a driver steering torque based on measured values ​​from the feedback actuator and with the aid of the model and the observer, and to provide the resulting torque.

[0006] DE 10 2018 129 563 A1 discloses a method for determining the control mode of a steering wheel of a vehicle, wherein the control mode is a first control mode in which a driver controls the steering wheel, or wherein the control mode is a second control mode in which the driver does not control the steering wheel. The method comprises the steps of detecting at least one steering parameter and determining the control mode of the steering wheel using a machine learning technique. EP 2 371 649 B1 discloses a method for determining information related to the line of sight of a driver and the position of the driver's hands relative to the steering wheel in a motor vehicle.

[0007] Accordingly, the detection of hands on the steering wheel is necessary for the operation of various assistance functions in the area of ​​longitudinal and lateral guidance. The integration of a capacitive sensor in the steering wheel solves this problem robustly, but incurs considerable additional costs. One way to reduce these costs is to implement a virtual sensor that generates signals from available signal curves (e.g., measurable variables on the steering wheel such as steering torque,

[0008] Steering wheel angle, steering wheel angular speed or vehicle reaction) estimates the driver's grip on the steering wheel, i.e. carries out hand detection.

[0009] A neural network, for example, can be used for this purpose. However, due to the current lack of validation of machine learning methods, this method is unsuitable for subfunctions with automotive safety integrity level (ASIL) requirements. Another approach is the use of classic model-based or mathematical / rule-based approaches. However, due to the complex distinction between driver-induced excitation on the steering wheel, system-related excitation resulting, for example, from uneven road surfaces, and system-related friction, these can only determine the desired identification of the hands on the steering wheel with significantly less accuracy.

[0010] There is therefore a need to provide improved hand detection on a steering wheel, for example, in certain driving situations, such as starting off. The method, device, and computer program according to the independent claims address this need.

[0011] Embodiments are based on the core idea that hand detection on a steering wheel of a vehicle can be improved by using a hybrid approach that, depending on the situation, uses at least one algorithm from a machine learning (ML) algorithm or a model-based algorithm (e.g., a classical, mathematical approach) to detect hands on the steering wheel. This allows, for example, hand detection to be adapted to a situation using an algorithm. For example, in a safety-critical situation, hand detection can be determined using an algorithm that meets an ASIL requirement (e.g., a model-based algorithm). Embodiments relate to a method for improving hand detection on a steering wheel of a vehicle.The method comprises determining a parameter for assessing the safety relevance of a situation and performing hand detection based on at least one of a machine learning algorithm and a model-based algorithm based on the parameter. This allows an algorithm to be selected that is suitable for a particular situation. For example, for a non-safety-critical situation, an algorithm that does not meet ASIL requirements (e.g., an ML algorithm) can be selected. This can, for example, increase accuracy.

[0012] In one embodiment, if the parameter exceeds a threshold, hand detection can be performed based on the model-based algorithm. This allows for simplified assignment for different situations. For example, the threshold can be selected such that the parameter is above the threshold for a safety-critical situation that must meet ASIL requirements.

[0013] In one embodiment, if the parameter falls below a threshold, hand detection can be performed based on the machine learning algorithm. This allows for simplified assignment for different situations. For example, the threshold can be selected such that the parameter is below the threshold for a non-safety-critical situation that does not require ASIL.

[0014] In one embodiment, the method may further comprise obtaining information about the vehicle's surroundings and determining the parameter for assessing safety relevance based on the obtained environmental information. This can, in particular, improve the detection of safety relevance. For example, a safety-critical situation can be detected when a moving object (e.g., a person) falls below a minimum distance from the vehicle (e.g., in front of the vehicle).

[0015] In one embodiment, the method may further comprise obtaining status information about a state of the vehicle and determining the parameter for assessing safety relevance based on the obtained status information. This allows, for example, a vehicle's speed to be used to evaluate a situation.

[0016] In one embodiment, the method may further comprise obtaining interior information of the vehicle and using the interior information for hand detection. This may improve the reliability of hand detection by using a further input parameter for determination or verification.

[0017] Embodiments also provide a computer program for performing any of the methods described herein when the computer program runs on a computer, a processor, or a programmable hardware component.

[0018] Another embodiment is a device for improving the detection of a hand on a steering wheel of a vehicle. The device comprises one or more interfaces for communication (e.g., with the sensor for determining environmental information) and a data processing circuit configured to perform at least one of the methods described herein. Embodiments further provide a vehicle with a device as described herein.

[0019] Examples of embodiments are explained in more detail below with reference to the attached figures:

[0020] Fig. 1 shows a schematic representation of an example of a method for improving hand detection on a steering wheel of a vehicle;

[0021] Fig. 2 shows a block diagram of an embodiment of a device in a vehicle for improving hand detection on a steering wheel of a vehicle; and

[0022] Fig. 3 shows embodiments for the integration of a virtual sensor.

[0023] Various embodiments will now be described in more detail with reference to the accompanying drawings, in which some embodiments are illustrated. In the figures, the thickness dimensions of lines, layers and / or regions may be exaggerated for the sake of clarity. Fig. 1 shows a schematic representation of an example of a method 100 for improving hand detection on a steering wheel of a vehicle. The method 100 comprises determining 110 a parameter for assessing a safety relevance of a situation and performing 120 the hand detection based on at least one of a machine learning algorithm and a model-based algorithm based on the parameter. As a result, a selection of an algorithm to be used can be made using the parameter.In particular, using this parameter can be used to select a suitable algorithm, for example, to meet an ASIL requirement. By combining different algorithms, hand detection can be improved, eliminating the need for a capacitive sensor and thus reducing costs. Furthermore, error-prone hand detection can be replaced / avoided or made more robust by observing the vehicle's interior.

[0024] By using multiple algorithms, an algorithm can be adapted to a specific situation. For example, a first algorithm, e.g., the ML algorithm, may have an advantage in determining hand detection accuracy. The ML algorithm can be sensitive to external disturbances, such as road surface excitation, small torques from the driver, or friction in the system. This allows for more robust performance in the presence of disturbances. Furthermore, improved / more robust performance can be achieved across a wide range of different situations, especially without an approach that requires manual, situation-dependent parameterization.

[0025] For example, a second algorithm, e.g., the model-based algorithm, may have an advantage in determining ASIL requirements because it is ASIL compliant.

[0026] By selecting one or combining several algorithms, consisting of ML algorithms and classical mathematical / model-based algorithms, hand detection can be improved, for example, hands-off detection (HOD). For example, in non-safety-critical situations, the advantages of nonlinear pattern recognition from ML algorithms can be utilized. In safety-critical situations and / or when operating critical subfunctions that have an ASIL classification, mathematical / model-based methods can be used that can be secured according to ASIL requirements. By restricting the state space to a subset of the operating range (for example, by having the ML algorithm cover the other subset, depending on the parameter for assessing safety relevance), these functions can be further optimized depending on the operating point, thereby achieving a performance gain.

[0027] The assessment of whether a situation is safety-critical or not can be made in advance for each situation. In particular, an assessment for a plurality of situations can be stored in a database, for example, a look-up table, a file system, or in a data structure. The database can be stored, for example, on a storage unit of a device (see Fig. 2) for implementing a method according to the invention. For example, a situation can be assigned a value within a range of values, with a higher value representing a higher criticality of the situation. This allows different situations to be assessed for criticality using different parameters. By combining this with a limit value, a selection can then be made, in particular, as to which situation is classified as safety-critical or as non-safety-critical. In particular, this selection can be changed by varying the limit values.

[0028] By selecting / combining an algorithm, a high-performance, secure, virtual sensor can be realized that reduces the disadvantages of individual approaches and offers significant cost savings compared to a real sensor (e.g., a capacitive sensor). The selection based on the parameter for assessing safety relevance can, in particular, make it possible to adapt the individual algorithms to the respective situations, e.g., by defining thresholds.

[0029] Furthermore, it can provide a purely software-based solution for hand detection that can be implemented in a vehicle independently of additional hardware. This can, for example, result in cost reduction, increased security, increased robustness, and / or a performance gain through operating point-dependent implementation.

[0030] In one embodiment, if the parameter exceeds a threshold value, hand detection can be performed based on the model-based algorithm. This allows the model-based algorithm to be provided with an associated threshold value, for example, for specific situations, particularly safety-critical situations. In particular, a plurality of model-based algorithms can be used that meet different ASIL requirements. A selection of a model-based algorithm from the plurality of model-based algorithms can then be made based on the parameter, for example. The threshold value can be specific to one situation or a plurality of situations.

[0031] In one embodiment, if the parameter falls below a threshold, hand detection can be performed based on the machine learning algorithm. This allows the ML algorithm to be used only for situations that are not safety-critical, i.e., in particular, situations that do not have to meet ASIL requirements. This allows the increased accuracy of the ML algorithm to be exploited, particularly for non-safety-critical situations. In particular, a plurality of ML algorithms trained for different situations can also be used. A selection of an ML algorithm from the plurality of ML algorithms can then be made, for example, based on the parameter.

[0032] Alternatively or optionally, a combination of an ML algorithm and a model-based algorithm can be used. For example, one algorithm, e.g., the ML algorithm, can be used to verify the result of another algorithm, e.g., the model-based algorithm.

[0033] In one embodiment, the method may further comprise obtaining information about the vehicle's surroundings and determining the parameter for assessing safety relevance based on the obtained information about the surroundings. This can improve the assessment of a safety-critical situation.

[0034] For example, the environmental information may be obtained by determining information about the environment using one or more sensors of the vehicle and / or by receiving information about the environment (e.g., through a cooperative awareness message). The environmental information may be received from a vehicle, infrastructure, a smartphone, a base station, etc. The one or more sensors may, for example, belong to a variety of vehicle sensors, e.g., a radar sensor, a lidar sensor, an ultrasonic sensor, or an imaging sensor such as a camera or infrared sensors.

[0035] Environmental information can, in particular, improve the determination of safety relevance. For example, in an environment with few obstacles, moving objects, etc., the safety relevance may be lower than in an environment with more obstacles, moving objects, etc. This allows, in particular, an adaptive adjustment of the determination of the parameter for assessing safety relevance.

[0036] In one embodiment, the method may further comprise obtaining status information about a state of the vehicle and determining the parameter for assessing safety relevance based on the obtained status information. This allows, for example, a vehicle speed to be taken into account when determining the parameter. For example, a situation may be more critical for a stationary vehicle that is starting to move than for a vehicle traveling on a highway at a speed typical for the highway.

[0037] In one embodiment, the method may further comprise obtaining status information about a state of the vehicle and determining the parameter for assessing safety relevance based on the obtained status information. This allows, for example, a vehicle's speed to be used to evaluate a situation.

[0038] In one embodiment, the method may further comprise determining interior information of the vehicle and using the interior information for hand detection. A determination may be made, for example, using a camera, an infrared camera, etc. The interior information may then be used, for example, to verify a result determined using the algorithm.

[0039] For example, a driver observation camera can be used to detect and / or estimate the driver's attention and / or hand position. In addition to the robust development of appropriate image processing algorithms, it is important to ensure that the information from the camera provides robust information despite potential overlap or visual interference.

[0040] Further details and aspects are mentioned in connection with the embodiments described below. The embodiment shown in Fig. 1 may comprise one or more optional additional features corresponding to one or more aspects mentioned in connection with the proposed concept or one or more embodiments described below (e.g., Figs. 2-3). Fig. 2 shows a block diagram of an embodiment of a device in a vehicle 200 for improving hand detection on a steering wheel of a vehicle. The device 30 comprises one or more interfaces 32 for communication. The device 30 further comprises a data processing circuit 34 configured to carry out at least one of the methods described herein, for example, the method described with reference to Fig. 1. Further embodiments include a vehicle with a device 30.

[0041] The one or more interfaces 32 may, for example, correspond to one or more inputs and / or one or more outputs for receiving and / or transmitting information, for example in digital bit values, based on a code, within a module, between modules, or between modules of different entities. The at least one or more interfaces 32 may, for example, be configured to communicate with other network components via a (radio) network or a local area network.

[0042] As shown in Fig. 2, the one or more interfaces 32 are coupled to the respective data processing circuitry 34 of the device 30. In examples, the device 30 may be implemented by one or more processing units, one or more processing devices, any means of processing, such as a processor, a computer, or a programmable hardware component operable with appropriately adapted software. Likewise, the described functions of the data processing circuitry 34 may also be implemented in software, which is then executed on one or more programmable hardware components. Such hardware components may be a general-purpose processor, a digital signal processor (DSP), a microcontroller, etc.The data processing circuit 34 may be capable of controlling the one or more interfaces 32 such that any data transmission that occurs over the one or more interfaces 32 and / or any interaction that may involve the one or more interfaces 32 may be controlled by the data processing circuit 34.

[0043] In exemplary embodiments, the data processing circuit 34 can correspond to any controller or processor or a programmable hardware component. For example, the data processing circuit 34 can also be implemented as software programmed for a corresponding hardware component. In this respect, the data processing circuit 34 can be implemented as programmable hardware with appropriately adapted software. Any processors, such as digital signal processors (DSPs), can be used. Exemplary embodiments are not limited to a specific type of processor. Any processor or even multiple processors are conceivable for implementing the data processing circuit 34.

[0044] In one embodiment, the device 30 may include a memory and at least one data processing circuit 34 operatively coupled to the memory and configured to perform the method described below.

[0045] In examples, the one or more interfaces 32 may correspond to any means for obtaining, receiving, transmitting, or providing analog or digital signals or information, e.g., any terminal, contact, pin, register, input terminal, output terminal, conductor, trace, etc., that enables the provision or receipt of a signal or information. The one or more interfaces 32 may be wireless or wired and may be configured to communicate with other internal or external components, e.g., to send or receive signals or information.

[0046] In at least some embodiments, the vehicle may, for example, correspond to a land vehicle, a watercraft, an aircraft, a rail vehicle, a road vehicle, a car, a bus, a motorcycle, an off-road vehicle, a motor vehicle, or a truck. The data processing circuit may, for example, be part of a control unit of the vehicle.

[0047] Further details and aspects are mentioned in connection with the embodiments described below and / or above. The embodiment shown in Fig. 2 may include one or more optional additional features corresponding to one or more aspects mentioned in connection with the proposed concept or one or more embodiments described above (e.g., Fig. 1) and / or below (e.g., Fig. 3).

[0048] Fig. 3 shows various examples of hands-off detection. Fig. 3a shows various HOD concepts known from the state of the art. For example, a virtual sensor, which is inexpensive, can be used, or an additional sensor, which is associated with higher costs. The use of virtual sensors can be divided into model-based algorithms (ASIL compatible) and ML algorithms (increased performance through better consideration of environmental influences such as friction, road re-excitation, etc.). Additional sensors can be used, for example, capacitive sensors (ASIL compatible) or driver observation cameras (usable for a variety of purposes).

[0049] Fig. 3b shows an example of a hybrid approach that uses situation-dependent machine learning methods or classical, mathematical model-based approaches for HOD. Combining both algorithms / approaches based on a situation-dependent parameter can enable the exploitation of improved performance of the ML algorithm, as well as situation-dependent validation, for example, according to ASIL, of the model-based algorithm.

[0050] Fig. 3c shows an embodiment of a model creation for a virtual sensor. Vehicle reactions or movement information (e.g., speed, yaw rate, lateral acceleration), an output from an assistance system (e.g., desired curvature, assistance torque, desired steering angle), and steering wheel information (e.g., steering angle, steering angular velocity, steering torque) can be used as training data for the ML algorithm. Data from vehicles with integrated, capacitive hardware sensors can serve as evaluation data (ground truth) for a result of the ML algorithm. In particular, these integrated hardware sensors can be replaced by the use of a virtual sensor consisting of a combination of ML and a model-based algorithm. In a first step, a model can be created for the virtual sensor. Hardware sensors (e.g., from other vehicles) can be used for this purpose.These hardware sensors can provide training data, especially ground truth data, on the basis of which a software-based solution can be developed and optionally tested.

[0051] A system for training the ML algorithm can be configured to provide information (training input data) about vehicle reactions or motion information (e.g., speed, yaw rate, lateral acceleration), an output from an assistance system (e.g., desired curvature, assistance torque, desired steering angle), and steering wheel information (e.g., steering angle, steering angular velocity, steering torque) as input to a machine learning model. Machine learning refers to algorithms and statistical models that computer systems can use to perform a specific task without explicit instructions, relying instead on models and inferences. For example, instead of a rule-based transformation of data, machine learning can use a transformation of data derived from an analysis of historical and / or training data.

[0052] Machine learning models are trained using training data. Many different approaches can be used to train a machine learning model. For example, supervised learning, semi-supervised learning, or unsupervised learning can be used. In supervised learning, the machine learning model is trained using a variety of training samples, where each sample may include a variety of input data values ​​and a variety of desired output values, e.g., each training sample is associated with a desired output value. By specifying both training samples and desired output values, the machine learning model "learns" what output value to produce based on an input sample that is similar to the samples provided during training. In addition to supervised learning, semi-supervised learning can also be used.In semi-supervised learning, some of the training samples lack a corresponding desired output value. Supervised learning can be based on a supervised learning algorithm, such as a classification algorithm, a regression algorithm, or a similarity learning algorithm. In unsupervised learning, (only) input data can be provided, and an unsupervised learning algorithm can be used to find structure in the input data, for example, by grouping or clustering the input data to find commonalities in the data.

[0053] The machine learning model can, for example, be an artificial neural network (ANN). ANNs are systems modeled on biological neural networks, such as those found in the brain. ANNs consist of a large number of interconnected nodes and a large number of connections, called edges, between the nodes. Typically, there are three types of nodes: input nodes that receive input values, hidden nodes that are connected to other nodes, and output nodes that provide output values. Each node can represent an artificial neuron. Each edge can transfer information from one node to another. The output of a node can be defined as a (non-linear) function of the sum of its inputs. The inputs of a node can be used in the function based on a "weight" of the edge or node that provides the input.The weights of nodes and / or edges may be adjusted during the learning process. In other words, training an artificial neural network may include adjusting the weights of the nodes and / or edges of the artificial neural network, e.g., to achieve a desired output for a given input. In at least some examples, the machine learning model may be a deep neural network, e.g., a neural network with one or more layers of hidden nodes (e.g., hidden layers), preferably a plurality of hidden node layers.

[0054] Training machine learning models requires significant effort, so reusing a machine learning model for different problem sizes can reduce the overall training time. In various examples of the present disclosure, the machine learning model can be applied to a different number of devices or vehicles.

[0055] The training input data can be obtained, for example, via an interface, e.g., an interface of the system. The training input data can be obtained from a database, a file system, or a data structure stored in a computer memory. The training input data can include training information about vehicle reactions or movement information (e.g., speed, yaw rate, lateral acceleration), an output from an assistance system (e.g., desired curvature, assistance torque, desired steering angle), steering wheel information (e.g., steering angle, steering angular velocity, steering torque). The term "training information" can merely indicate that the respective data is suitable, e.g., designed, for training the machine learning model. For example, the training information can include information about vehicle reactions or movement information (e.g.,speed, yaw rate, lateral acceleration), an output from an assistance system (e.g. desired curvature, assistance torque, desired steering angle), steering wheel information (e.g. steering angle, steering angular speed, steering torque) that is representative of the respective data to be processed by the machine learning model, e.g. in order to obtain a machine learning model that is suitable for the task at hand, e.g. suitable for hand detection on a steering wheel. For example, the machine learning model can provide information about hand detection that is based on the training information as described above, which can be provided at the input of the machine learning model. In other words, the machine learning model can be provided with the training input data, which represents a plurality of parameters for assessing hand detection, and with the task of improving hand detection.

[0056] For example, the machine learning model can be trained by repeatedly performing a group of training tasks (or procedural steps) (e.g., at least twice, at least five times, at least ten times, at least 20 times, at least 50 times, at least 100 times, at least 1000 times). For example, the machine learning model can be trained by repeatedly feeding the training input data into the machine learning model, performing a hand detection, evaluating the hand detection based on ground truth from a hardware sensor, and adapting the machine learning model based on the evaluation result.

[0057] A repetition of the above tasks can be referred to as an "epoch" in reinforcement learning. An epoch means that the entire set of training input data is passed forward and backward through the machine learning model once. Within an epoch, multiple batches of training data can be input to the machine learning model to determine hand detection. To keep the problem size small, the training data can, for example, be divided into multiple batches that can be provided separately to the machine learning model. Each batch from the multiple batches can be input separately to the machine learning model.

[0058] As can be seen in Fig. 3c, information (a scenario, a driving situation, a driving task, a criticality, etc.) for determining a situation can be provided in 310. This information can be used, for example, to determine the parameter for assessing the safety relevance of a situation. An assistance system 320 can include a subfunction 330 for HOD. To train the ML algorithm, a hardware sensor can be present, which provides evaluation data for the ML algorithm. This allows modeling of the ML algorithm to be improved based on evaluation data. The assistance system 320 can then, for example, output information to a driver, for example a warning that they should put their hands on the steering wheel and / or perform a control of the vehicle, for example, braking, maneuver abort, etc.(for example, if no hands were detected on the steering wheel in a critical situation).

[0059] After training the ML algorithm, it can be used in synergy with a model-based algorithm. As shown in Figs. 3d and 3e, a respective algorithm can be used depending on the assessment of a situation 340d, 340e. In Fig. 3d, the provision 310 of the information leads to an assessment of the situation 340d as not being safety-critical. Accordingly, an ML approach, i.e., an ML algorithm for HOD, is used in subfunction 330. This algorithm can offer improved performance. As already explained above, the assessment of the criticality of a situation can be made in advance and then by comparison with a database, a file system, or from a data structure.

[0060] In Fig. 3e, the provision 310 of the information leads to an assessment of the situation 340e as a safety-critical situation. Accordingly, a mathematical approach, i.e., a model-based algorithm for HOD, is used in subfunction 330. This algorithm can, in particular, meet ASIL requirements.

[0061] By using the second path with the virtual sensor, the first path with the hardware sensor can be eliminated. This eliminates the need for an expensive hardware sensor, which in particular can save costs.

[0062] Further details and aspects are mentioned in connection with the embodiments described above. The embodiment shown in Fig. 3 may include one or more optional additional features corresponding to one or more aspects mentioned in connection with the proposed concept or one or more embodiments described above (e.g., Figs. 1-2).

[0063] Further embodiments are computer programs for carrying out one of the methods described herein when the computer program runs on a computer, a processor, or a programmable hardware component. Depending on specific implementation requirements, embodiments of the invention can be implemented in hardware or in software. The implementation can be carried out using a digital storage medium, for example a floppy disk, a DVD, a Blu-ray disc, a CD, a ROM, a PROM, an EPROM, an EEPROM or a FLASH memory, a hard disk, or another magnetic or optical storage device on which electronically readable control signals are stored that can interact or interact with a programmable hardware component in such a way that the respective method is carried out.

[0064] A programmable hardware component can be formed by a processor, a computer processor (CPU = Central Processing Unit), a graphics processor (GPU = Graphics Processing Unit), a computer, a computer system, an application-specific integrated circuit (ASIC = Application-Specific Integrated Circuit), an integrated circuit (IC = Integrated Circuit), a single-chip system (SOC = System on Chip), a programmable logic element or a field-programmable gate array with a microprocessor (FPGA = Field Programmable Gate Array).

[0065] The digital storage medium can therefore be machine- or computer-readable. Some embodiments thus comprise a data carrier having electronically readable control signals capable of interacting with a programmable computer system or a programmable hardware component such that one of the methods described herein is performed. One embodiment is thus a data carrier (or a digital storage medium or a computer-readable medium) on which the program for performing one of the methods described herein is recorded.

[0066] In general, embodiments of the present invention can be implemented as a program, firmware, computer program, or computer program product with program code or data, wherein the program code or data is effective to perform one of the methods when the program runs on a processor or a programmable hardware component. The program code or data can also be stored, for example, on a machine-readable medium or data carrier. The program code or data can be present, among other things, as source code, machine code, or bytecode, as well as other intermediate code.

[0067] The above-described embodiments are merely illustrative of the principles of the present invention. It is understood that modifications and variations of the arrangements and details described herein will be apparent to others skilled in the art. Therefore, it is intended that the invention be limited only by the scope of the following claims and not by the specific details presented in the description and explanation of the embodiments herein.

[0068] List of reference symbols Device Interface Data processing unit Method Improvement of a hand detection on a steering wheel Determination of a parameter for evaluating a safety relevance of a situation Carrying out the hand detection Vehicle Information for determining a situation Assistance system Subfunction for hand detection d, 340e Evaluation of the situation

Claims

Patent claims 1. A method (100) for improving hand detection on a steering wheel of a vehicle, comprising: Determining a parameter for assessing the safety relevance of a situation; and performing the hand detection based on at least one of a machine Learning algorithm and a model-based algorithm based on the parameter.

2. The method (100) of claim 1, wherein if the parameter exceeds a threshold value, the hand detection is performed based on the model-based algorithm.

3. The method (100) according to claim 1 or 2, wherein if the parameter falls below a threshold value, the hand detection is performed based on the machine learning algorithm.

4. The method (100) according to any one of the preceding claims, further comprising obtaining environmental information of the vehicle; and Determine the parameter for assessing safety relevance based on the obtained environmental information.

5. The method (100) according to any one of the preceding claims, further comprising obtaining status information about a state of the vehicle; and Determine the parameter for assessing safety relevance based on the received status information.

6. The method (100) according to any one of the preceding claims, further comprising determining interior information of the vehicle; and Using interior information for hand detection.

7. The method (100) according to claim 7, wherein if the parameter exceeds a threshold value, the hand detection is performed based on the interior information and the machine learning algorithm.

8. A computer program for carrying out one of the methods (100) according to one of the preceding claims, when the computer program runs on a computer, a processor, or a programmable hardware component.

9. A device for improving the detection of hand detection on a steering wheel of a vehicle, comprising: one or more interfaces (32) for communication; and a data processing circuit (34) configured to control the one or more interfaces (32) and to execute a method (100) according to any one of claims 1 to 7 using the one or more interfaces (32).

10. Vehicle (200) with a device (30) according to claim 9.

Images