Steering condition synthesis method and device, electronic equipment, storage medium and vehicle

Abstract

The invention discloses a steering working condition synthesis method and device, electronic equipment, a storage medium and a vehicle, and relates to the technical field of vehicle steering systems.The method comprises the steps that vehicle steering data of a user in a real driving environment is collected, the vehicle steering data is preprocessed, and a steering data set is obtained; vehicle steering motion features are extracted from the steering data set; clustering the vehicle steering motion features to obtain a plurality of steering condition clusters; and determining a discrete working condition state of each steering working condition cluster, and synthesizing a steering working condition according to the discrete working condition states and the steering working condition clusters. The joint representation and analysis of multi-dimensional live broadcast are realized, and the steering process of the user in a real driving scene can be comprehensively defined.

Description

Technical Field

[0001] This application relates to the field of vehicle steering system technology, and in particular to steering condition synthesis methods, steering condition synthesis devices, electronic devices, storage media, and vehicles. Background Technology

[0002] As the automotive industry deepens its development towards intelligence and connectivity, the demands on vehicle handling, comfort, and active safety have reached unprecedented levels. As a core component for driver-vehicle interaction, the performance of the steering system directly determines the driving experience and safety baseline. During the design, optimization, matching, and verification of the steering system, engineers use theoretical knowledge and limited experience to set fixed-mode steering conditions as inputs to test the vehicle's steering. However, a significant drawback of fixed-mode steering condition design is its severe lack of representativeness. The pre-set, rule-based inputs cannot cover the randomness, complexity, and diversity of steering behavior in real-world driving, leading to a disconnect between test results and actual performance.

[0003] With the continuous development of the automotive industry, the scale of real user data for vehicles is becoming increasingly massive, and the steering data of users in real-world usage scenarios is increasing exponentially. Therefore, it has become possible to combine large-scale user data with steering condition analysis.

[0004] However, simply stitching together data in the time series dimension cannot truly reflect the driver's steering process. Furthermore, focusing too much on the steering wheel angle time series itself lacks a joint representation and analysis of steering dynamic characteristics, such as steering wheel speed, steering torque, and multi-dimensional indicators such as yaw rate, and cannot fully define the user's steering process in real driving scenarios. Summary of the Invention

[0005] The purpose of this invention is to provide a steering condition synthesis method, a steering condition synthesis device, an electronic device, a storage medium, and a vehicle, at least to solve the technical problem of how to realistically reflect the driver's steering process and how to comprehensively define the user's steering process in real driving scenarios.

[0006] This invention provides the following solution:

[0007] According to one aspect of the present invention, a method for synthesizing steering conditions is provided, comprising:

[0008] Collect vehicle steering data from users in real driving environments, and preprocess the vehicle steering data to obtain a steering dataset;

[0009] Extract vehicle steering motion features from the steering dataset;

[0010] Clustering the vehicle steering motion characteristics yields multiple steering condition clusters;

[0011] Determine the discrete operating condition state for each of the steering condition clusters, and synthesize a steering condition based on the discrete operating condition state and the steering condition cluster.

[0012] Furthermore, the extraction of vehicle steering motion features from the steering dataset includes:

[0013] Obtain the positive and negative intersection time series points of the steering wheel angle data in the steering dataset, and divide the steering dataset based on the positive and negative intersection time series points to obtain multiple steering data subsets;

[0014] Obtain preset valid segment setting conditions, and select the first steering data subset that satisfies the valid segment setting conditions from multiple steering data subsets;

[0015] Vehicle steering motion features are extracted from the first steering data subset.

[0016] Furthermore, the vehicle steering motion characteristics are clustered to obtain multiple steering condition clusters, including:

[0017] Among the vehicle steering motion features, one vehicle steering motion feature is arbitrarily selected as the initial centroid, and the first distance from the remaining vehicle steering motion features to the initial centroid is calculated.

[0018] The next vehicle steering motion feature with the centroid is determined based on the first distance, until all the first vehicle steering motion features with the centroid are determined.

[0019] Calculate the second distance from all vehicle steering motion features other than the first vehicle steering motion feature to each of the first vehicle steering motion features;

[0020] The vehicle steering motion features are clustered based on the second distance to obtain the same number of steering condition clusters as the first vehicle steering motion features.

[0021] Furthermore, the step of synthesizing a steering condition based on the discrete operating conditions and the steering condition cluster includes:

[0022] Based on the vehicle steering data, a continuous steering condition state sequence is determined;

[0023] Based on the discrete operating conditions, the continuous steering operating condition state sequence is divided into steering operating condition state transition sequence samples.

[0024] For each steering condition state transition sequence sample corresponding to each steering condition cluster, the condition state of each vehicle steering motion feature is statistically analyzed, and the transition frequency from one condition state to the next condition state is determined to construct a transition frequency matrix.

[0025] The transition frequency matrix is ​​normalized to obtain the transition probability matrix. Based on the transition probability matrix, the vehicle steering motion features in the steering condition cluster are spliced ​​together using a polynomial to synthesize the steering condition.

[0026] Furthermore, the preprocessing of the vehicle steering data to obtain a steering dataset includes:

[0027] The vehicle steering data includes steering wheel angle data, the mechanical limits of the vehicle steering system, and the physiological limits of the driver.

[0028] Based on the steering wheel angle data, the vehicle's steering wheel speed is calculated, and based on the mechanical limits, the physiological limits, and the steering wheel speed, the steering wheel angle threshold and the steering wheel speed threshold are determined.

[0029] The vehicle steering data that exceeds the steering wheel angle threshold or the steering wheel speed threshold is discarded to obtain the first vehicle steering data.

[0030] The median filter is used to remove glitch outliers from the first vehicle steering data to obtain the second vehicle steering data.

[0031] The steering data of the second vehicle is reconstructed using a multiple spline interpolation algorithm to obtain a steering dataset.

[0032] Furthermore, after synthesizing the steering condition based on the discrete operating conditions and the steering condition cluster, the method further includes:

[0033] Determine the statistical feature vector of the steering condition and obtain the original feature vector of the vehicle steering data;

[0034] If the error between the statistical feature vector and the original feature vector is less than a set error threshold, the synthesized steering condition is determined to be qualified.

[0035] According to a second aspect of the present invention, a steering condition synthesis device is provided, comprising:

[0036] The data acquisition module is used to collect vehicle steering data from users in real driving environments and preprocess the vehicle steering data to obtain a steering dataset.

[0037] The feature extraction module is used to extract vehicle steering motion features from the steering dataset;

[0038] The feature clustering module is used to cluster the vehicle steering motion features to obtain multiple steering condition clusters;

[0039] The working condition synthesis module is used to determine the discrete working condition state of each steering working condition cluster, and synthesize steering working conditions based on the discrete working condition state and the steering working condition cluster.

[0040] According to three aspects of the present invention, an electronic device is provided, comprising: a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus;

[0041] The memory stores a computer program, which, when executed by the processor, causes the processor to perform the steps of the working condition synthesis method.

[0042] According to four aspects of the present invention, a computer-readable storage medium is provided, comprising: storing a computer program executable by an electronic device, wherein when the computer program is run on the electronic device, the electronic device performs the steps of a steering condition synthesis method.

[0043] According to five aspects of the present invention, a vehicle is provided, comprising:

[0044] Electronic equipment used to implement the steps of the steering condition synthesis method;

[0045] The processor runs a program, and when the program runs, it executes the steps of the process synthesis method based on the data output from the electronic device.

[0046] A storage medium for storing a program that, when running, executes steps of a transition to a working condition synthesis method based on data output from an electronic device.

[0047] The above solution achieves the following beneficial technical effects:

[0048] This application processes the collected vehicle steering data to extract vehicle steering motion features. Based on the representation of a multi-dimensional steering feature system, it can cover the randomness, complexity, and diversity of steering behavior in real driving.

[0049] This application achieves decoupling of different driving scenarios by clustering vehicle steering motion features, which can realistically reflect the driver's steering process. The clustered steering condition clusters naturally correspond to different driving scenarios, are stable, and have low computational overhead.

[0050] This application determines the discrete working condition state of each steering working condition cluster, and then synthesizes the steering working condition based on the discrete working condition state and the steering working condition cluster, thereby realizing the joint representation and analysis of multi-dimensional live broadcast, and can comprehensively define the steering process of the user in real driving scenarios. Attached Figure Description

[0051] Figure 1 This is a flowchart of a steering condition synthesis method provided by one or more embodiments of the present invention.

[0052] Figure 2 This is a schematic diagram of the steering condition synthesis principle framework provided in a specific embodiment of the present invention.

[0053] Figure 3 This is a schematic diagram of vehicle steering data preprocessing provided in a specific embodiment of the present invention.

[0054] Figure 4 This is a schematic diagram illustrating the extraction of vehicle steering motion features according to a specific embodiment of the present invention.

[0055] Figure 5 This is a schematic diagram of vehicle steering motion feature clustering and synthesis provided in a specific embodiment of the present invention.

[0056] Figure 6 This is a structural diagram of a steering condition synthesis device provided in one or more embodiments of the present invention.

[0057] Figure 7 This is a block diagram of an electronic device structure for a steering condition synthesis method provided in one or more embodiments of the present invention. Detailed Implementation

[0058] The technical solution of the present invention will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0059] Figure 1 This is a flowchart of a steering condition synthesis method provided by one or more embodiments of the present invention.

[0060] like Figure 1 The steering condition synthesis method shown includes:

[0061] Step S1: Collect vehicle steering data from the user in a real driving environment, and preprocess the vehicle steering data to obtain a steering dataset.

[0062] In this embodiment, vehicle steering data may include driving timestamps, vehicle speed, steering wheel angle, steering wheel torque, yaw rate, lateral acceleration, and other data.

[0063] The collection and preprocessing of vehicle steering data mainly utilizes a remote vehicle communication module (Telematics BOX, TBOX) to transmit the vehicle's real driving data to a big data processing platform. The collected vehicle steering data needs to cover different types of drivers and driving scenarios.

[0064] Based on a big data processing platform, vehicle steering data is cleaned, including removing outliers such as jumps and spikes, and performing data preprocessing operations such as filtering the original vehicle steering data to obtain a steering dataset.

[0065] Step S2: Extract vehicle steering motion features from the steering dataset.

[0066] Among them, vehicle steering motion characteristics include macroscopic and microscopic characteristics, such as the duration of vehicle steering data segments, the average, maximum, minimum and standard deviation of vehicle speed, the maximum and standard deviation of steering wheel torque, the minimum, maximum, average and standard deviation of steering wheel angle, the angle range, the average and maximum of steering wheel rotation speed, the standard deviation, average and maximum of yaw rate, and the standard deviation, average and maximum of lateral acceleration.

[0067] In this embodiment, the vehicle steering motion features can be divided by the integrity of the steering action to obtain multiple steering data subsets, thereby extracting the corresponding vehicle steering motion features from each steering data subset.

[0068] Step S3: Cluster the vehicle steering motion features to obtain multiple steering condition clusters.

[0069] This embodiment can use an unsupervised machine learning algorithm to cluster the obtained vehicle steering motion features, thereby obtaining multiple steering condition clusters.

[0070] Step S4: Determine the discrete working condition state of each steering working condition cluster, and synthesize the steering working condition based on the discrete working condition state and the steering working condition cluster.

[0071] In this embodiment, each discrete state corresponds to a typical steering condition mode, which includes low-speed large-angle steering condition (e.g., U-turn in a parking lot), medium-speed lane change steering condition (e.g., lane change on urban roads), high-speed fine-tuning steering condition (e.g., maintaining direction on a highway), emergency obstacle avoidance steering condition (e.g., handling emergencies), and other steering condition modes.

[0072] Furthermore, based on the determined discrete operating conditions and the vehicle steering motion characteristics in the steering condition cluster, corresponding steering conditions are synthesized. These synthesized steering conditions are then used in the design, optimization, matching, and verification processes of the steering system, enabling the testing of the vehicle's steering.

[0073] Figure 2 This is a schematic diagram of the steering condition synthesis principle framework provided in a specific embodiment of the present invention, as shown below. Figure 2 As shown, real vehicle steering data is collected and preprocessed, and then the preprocessed vehicle steering data is divided into steering motion segments. Further, vehicle steering motion features are extracted from these segments. Through cluster analysis of the vehicle steering motion features, steering conditions are synthesized, and the synthesized steering conditions can also be detected.

[0074] Furthermore, the statistical feature vector of the steering condition is determined, and the original feature vector of the vehicle steering data is obtained. If the error between the statistical feature vector and the original feature vector is less than a set error threshold, the synthesized steering condition is deemed qualified, and the qualified steering condition is used to generate a test condition for the vehicle. Otherwise, iterative optimization processing needs to be performed again to determine the synthesized steering condition until the steering condition is qualified.

[0075] This embodiment characterizes steering conditions based on multi-dimensional steering motion features, breaking through the traditional approach of using only steering wheel angle time series and constructing a multi-dimensional feature system that integrates kinematics, dynamics, and vehicle response. Through automatic clustering, massive amounts of mixed steering segments are automatically classified into categories with clear physical meaning, achieving decoupling between different driving scenarios. This can cover the randomness, complexity, and diversity of steering behavior in real driving, and realistically reflect the driver's steering process.

[0076] In this embodiment, vehicle steering data can be collected from the driving data of a specified number of vehicles over a specified number of days, with the time-series data collection frequency not less than 100Hz. The specified number can be 100, and the specified number of days can be 5 days. The drivers of the specified number of vehicles include drivers of different ages, genders, and driving modes, and the vehicles include various vehicle models and vehicles driving in different scenarios. Examples include frequent low-speed turns and U-turns on urban roads, medium-speed lane changes and cornering on suburban roads, and minor steering adjustments on highways.

[0077] Figure 3 This is a schematic diagram of vehicle steering data preprocessing provided in a specific embodiment of the present invention, as shown below. Figure 3As shown, after collecting vehicle steering data, the corresponding steering wheel angle data, the mechanical limits of the vehicle steering system, and the driver's physiological limits can be obtained from the vehicle steering data. Based on the steering wheel angle data, the vehicle's steering wheel speed is calculated, and the steering wheel angle threshold θmax and steering wheel speed threshold Vmax are determined based on the mechanical limits, the physiological limits, and the steering wheel speed. Vehicle steering data exceeding the steering wheel angle threshold or steering wheel speed threshold is discarded to obtain the first vehicle steering data. A median filter is used to remove glitch outliers from the first vehicle steering data, resulting in smoother second vehicle steering data. Gap values ​​in the second vehicle steering data are identified, and the second vehicle steering data is reconstructed based on a multi-spline interpolation algorithm to fill in the missing vehicle steering data, resulting in a steering dataset. The multi-spline interpolation algorithm can be of degree 3 or higher. By constructing a piecewise cubic polynomial and ensuring that the interpolation curve has continuous first and second derivatives at the connection points, a smooth and physically meaningful steering condition curve is efficiently generated, maximizing the reproduction of the driver's true steering intention and avoiding the distortion that may be caused by linear interpolation.

[0078] Figure 4 This is a schematic diagram illustrating the extraction of vehicle steering motion features according to a specific embodiment of the present invention, as shown below. Figure 4 As shown, the positive and negative intersection time series points of the steering wheel angle data in the steering dataset are obtained, and the steering dataset is divided based on the positive and negative intersection time series points to obtain multiple steering data subsets. After dividing into multiple steering data subsets, the steering data subsets can be filtered to select the effective steering data subsets.

[0079] Furthermore, the preset valid segment setting conditions are obtained, and among multiple steering data subsets, the first steering data subset that meets the valid segment setting conditions is selected, and all vehicle steering motion features are extracted from the first steering data subset.

[0080] The effective segment setting conditions include that the shortest duration of a segment in the steering data subset is not less than 3 seconds, and the maximum absolute value of the steering wheel angle within the segment is not less than 5°.

[0081] Figure 5 This is a schematic diagram of vehicle steering motion feature clustering and synthesis provided in a specific embodiment of the present invention, as shown below. Figure 5 As shown, the KMeans++ clustering method is used. Among the vehicle steering motion features, one vehicle steering motion feature (e.g., speed or steering intensity) is arbitrarily selected as the initial centroid. The first distance (D(xi)) from the initial centroid to all remaining vehicle steering motion features is calculated. The square of the first distance is calculated, and the probability distribution of each vehicle steering motion feature being selected as the next centroid is calculated.

[0082] Based on the principle that the greater the initial distance, the higher the probability of it being identified as the next centroid, the next vehicle steering motion feature to be used as the centroid is determined according to the probability distribution. This process continues until all the first vehicle steering motion features that serve as centroids are determined, thus avoiding local solutions caused by completely random selection of the centroid for the steering condition. For example, the number of centroids is K.

[0083] Calculate the second distance from all vehicle steering motion features other than the first vehicle steering motion feature to each of the first vehicle steering motion features, where the second distance can be Euclidean distance. Cluster the vehicle steering motion features based on the second distance to obtain the same number of steering condition clusters as the first vehicle steering motion features. Further, calculate the Euclidean distance from all vehicle steering motion features to K cluster centers, assigning each vehicle steering motion feature to the nearest cluster center to form K temporary cluster partitions. For each cluster, recalculate the mean value of all vehicle steering motion features within that cluster, using this mean as the new cluster center. Compare the positional changes of the old and new cluster centers. If the movement distance of the cluster center is less than a preset threshold N, stop the iteration, resulting in a set of different steering condition clusters.

[0084] This clustering method significantly reduces the algorithm's dependence on initial values, typically yielding more stable and better clustering results with minimal increase in computational overhead. For example, with a K value of 4, the algorithm automatically clusters similar turning segments into 4 categories. These categories may naturally correspond to different driving scenarios, such as low-speed large-angle segments corresponding to parking and U-turn scenarios, medium-low speed medium-angle segments corresponding to urban driving turning scenarios, medium-high speed small-angle segments corresponding to highway lane change fine-tuning scenarios, and high-speed medium-angle segments corresponding to highway ramp scenarios.

[0085] To ensure the objectivity of the synthesized driving conditions, the scene categories are first divided according to experience. The proportion of each driving condition cluster in the scene library is determined based on the ratio of points in each cluster to the total number of points, and a corresponding number of turning segments are then randomly extracted. Based on this, the scene library is stitched together using a Markov transition probability-based sequence. Smoothing filtering is applied to the stitched points to synthesize the turning condition curves.

[0086] Furthermore, based on vehicle steering data, a continuous steering condition state sequence is determined, and based on discrete condition states, the continuous steering condition state sequence is divided into steering condition state transition sequence samples.

[0087] For each steering condition cluster, the state transition sequence samples corresponding to the steering condition are analyzed to determine the state of each vehicle steering motion feature and the frequency of transition from one state to the next, thus constructing a transition frequency matrix. The transition frequency matrix is ​​then normalized to obtain a transition probability matrix. Based on this matrix, a polynomial is used to concatenate the vehicle steering motion features within the steering condition cluster to synthesize the steering condition.

[0088] The synthesis process is repeated until the target time length is met, synthesizing the steering conditions corresponding to all steering condition clusters. By clustering the vehicle steering motion features and then stitching the clustered vehicle steering motion features together, a two-stage stitching strategy is adopted to ensure that the synthesized conditions not only conform to the driver's macroscopic behavioral habits but are also smooth and natural at the microscopic level, and can be directly used for high-fidelity simulation.

[0089] This embodiment synthesizes highly representative steering conditions based on vehicle steering data from a large number of real vehicle operations through intelligent decoupling, feature analysis, and clustering. This achieves a paradigm shift from manual experience-based design to data-driven intelligent generation. The synthesized steering conditions are statistically representative, physically reasonable, and scenario-covering, providing an efficient, reliable, and low-cost input benchmark for bench testing, HIL simulation, and performance evaluation of steering systems. This significantly shortens the development cycle, reduces testing costs, and substantially improves the verification quality of the product.

[0090] Figure 6 This is a structural diagram of a steering condition synthesis device provided in one or more embodiments of the present invention.

[0091] like Figure 6 The steering condition synthesis device shown includes: a data acquisition module, a feature extraction module, a feature clustering module, and a condition synthesis module;

[0092] The data acquisition module is used to collect vehicle steering data from users in real driving environments and preprocess the vehicle steering data to obtain a steering dataset.

[0093] The feature extraction module is used to extract vehicle steering motion features from the steering dataset;

[0094] The feature clustering module is used to cluster the vehicle steering motion features to obtain multiple steering condition clusters;

[0095] The working condition synthesis module is used to determine the discrete working condition state of each steering working condition cluster, and synthesize the steering working condition based on the discrete working condition state and the steering working condition cluster.

[0096] The feature extraction module is used to obtain the positive and negative intersection time series points of the steering wheel angle data in the steering dataset, and divide the steering dataset based on the positive and negative intersection time series points to obtain multiple steering data subsets; obtain preset effective segment setting conditions, select the first steering data subset that meets the effective segment setting conditions from the multiple steering data subsets; and extract vehicle steering motion features from the first steering data subset.

[0097] The feature clustering module is used to arbitrarily select one of the vehicle steering motion features as the initial centroid, calculate the first distance from all the remaining vehicle steering motion features to the initial centroid, determine the next vehicle steering motion feature as the centroid based on the first distance, and so on until all the first vehicle steering motion features as centroids are determined; calculate the second distance from all vehicle steering motion features other than the first vehicle steering motion features to each first vehicle steering motion feature; and cluster the vehicle steering motion features based on the second distance to obtain the same number of steering condition clusters as the first vehicle steering motion features.

[0098] The working condition synthesis module is used to determine a continuous steering working condition state sequence based on vehicle steering data; to segment the continuous steering working condition state sequence into steering working condition state transition sequence samples based on discrete working condition states; to statistically analyze the working condition state of each vehicle steering motion feature for each steering working condition cluster corresponding to the steering working condition state transition sequence sample, and to determine the transition frequency from one working condition state to the next working condition state, constructing a transition frequency matrix; to normalize the transition frequency matrix to obtain a transition probability matrix, and based on the transition probability matrix, to use a polynomial to splice the vehicle steering motion features in the steering working condition cluster to synthesize the steering working condition.

[0099] The data acquisition module is used to acquire steering wheel angle data, mechanical limits of the vehicle steering system, and physiological limits of the driver from vehicle steering data; calculate the vehicle's steering wheel speed based on the steering wheel angle data, and determine steering wheel angle thresholds and steering wheel speed thresholds based on mechanical limits, physiological limits, and steering wheel speed; remove vehicle steering data exceeding the steering wheel angle threshold or steering wheel speed threshold to obtain the first vehicle steering data; use a median filter to remove glitch outliers from the first vehicle steering data to obtain the second vehicle steering data; and reconstruct the second vehicle steering data based on a multi-spline interpolation algorithm to obtain the steering dataset.

[0100] The working condition synthesis module is also used to determine the statistical feature vector of the steering working condition and obtain the original feature vector of the vehicle steering data; in response to the error between the statistical feature vector and the original feature vector being less than the set error threshold, the synthesized steering working condition is determined to be qualified.

[0101] Figure 7This is a block diagram of an electronic device structure for a steering condition synthesis method provided in one or more embodiments of the present invention.

[0102] like Figure 7 As shown, this application provides an electronic device, including: a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus;

[0103] The memory stores a computer program that, when executed by the processor, causes the processor to perform steps of a steering condition synthesis method.

[0104] This application also provides a computer-readable storage medium storing a computer program executable by an electronic device, which, when run on the electronic device, causes the electronic device to perform the steps of a steering condition synthesis method.

[0105] This application also provides a vehicle, including:

[0106] Electronic equipment for implementing the steps based on the steering condition synthesis method;

[0107] The processor runs a program, and when the program runs, it executes the steps of the process synthesis method based on the data output from the electronic device.

[0108] A storage medium for storing a program that, when running, executes steps of a transition to a working condition synthesis method based on data output from an electronic device.

[0109] The communication bus mentioned in the above electronic devices can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This communication bus can be divided into address bus, data bus, control bus, etc. For ease of illustration, only one thick line is used to represent it in the diagram, but this does not mean that there is only one bus or one type of bus.

[0110] The electronic device comprises a hardware layer, an operating system layer running on top of the hardware layer, and an application layer running on the operating system. The hardware layer includes hardware such as a central processing unit (CPU), a memory management unit (MMU), and memory. The operating system can be any one or more computer operating systems that control the electronic device through processes, such as Linux, Unix, Android, iOS, or Windows. Furthermore, in this embodiment of the invention, the electronic device can be a smartphone, tablet computer, or other handheld device, or a desktop computer, portable computer, or other electronic device; there is no particular limitation in this embodiment.

[0111] In this embodiment of the invention, the executing entity for electronic device control can be an electronic device itself, or a functional module within an electronic device capable of calling and executing a program. The electronic device can obtain the firmware corresponding to the storage medium. This firmware is provided by the supplier, and different storage media may have the same or different firmware; no limitation is made here. After obtaining the firmware corresponding to the storage medium, the electronic device can write this firmware into the storage medium; specifically, it burns the firmware corresponding to the storage medium into the storage medium. The process of burning the firmware into the storage medium can be implemented using existing technology, and will not be elaborated upon in this embodiment of the invention.

[0112] Electronic devices can also obtain reset commands corresponding to the storage media. The reset commands corresponding to the storage media are provided by the supplier. The reset commands corresponding to different storage media can be the same or different, and no restrictions are imposed here.

[0113] At this time, the storage medium of the electronic device is a storage medium on which the corresponding firmware has been written. The electronic device can respond to the reset command corresponding to the storage medium on which the corresponding firmware has been written, thereby resetting the storage medium on which the corresponding firmware has been written according to the reset command. The process of resetting the storage medium according to the reset command can be implemented by existing technology and will not be described in detail in this embodiment of the invention.

[0114] For ease of description, the above devices are described separately by function as various units and modules. Of course, in implementing this application, the functions of each unit and module can be implemented in one or more software and / or hardware.

[0115] It will be understood by those skilled in the art that, unless otherwise defined, all terms used herein (including technical and scientific terms) have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. It should also be understood that terms such as those defined in general dictionaries should be understood to have the meaning consistent with their meaning in the context of the prior art, and should not be interpreted in an idealized or overly formal sense unless specifically defined.

[0116] For the sake of simplicity, the method embodiments are described as a series of actions. However, those skilled in the art should understand that the embodiments of the present invention are not limited to the described order of actions, because according to the embodiments of the present invention, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions involved are not necessarily essential to the embodiments of the present invention.

[0117] As can be seen from the above description of the embodiments, those skilled in the art can clearly understand that this application can be implemented by means of software plus necessary general-purpose hardware platforms. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in various embodiments or some parts of the embodiments of this application.

[0118] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for synthesizing steering conditions, characterized in that, The steering condition synthesis method includes: Collect vehicle steering data from users in real driving environments, and preprocess the vehicle steering data to obtain a steering dataset; Extract vehicle steering motion features from the steering dataset; Clustering the vehicle steering motion characteristics yields multiple steering condition clusters; Determine the discrete operating condition state for each of the steering condition clusters, and synthesize a steering condition based on the discrete operating condition state and the steering condition cluster.

2. The steering condition synthesis method according to claim 1, characterized in that, The extraction of vehicle steering motion features from the steering dataset includes: Obtain the positive and negative intersection time series points of the steering wheel angle data in the steering dataset, and divide the steering dataset based on the positive and negative intersection time series points to obtain multiple steering data subsets; Obtain preset valid segment setting conditions, and select the first steering data subset that satisfies the valid segment setting conditions from multiple steering data subsets; Vehicle steering motion features are extracted from the first steering data subset.

3. The steering condition synthesis method according to claim 1, characterized in that, The vehicle steering motion characteristics are clustered to obtain multiple steering condition clusters, including: Among the vehicle steering motion features, one vehicle steering motion feature is arbitrarily selected as the initial centroid, and the first distance from the remaining vehicle steering motion features to the initial centroid is calculated. The next vehicle steering motion feature with the centroid is determined based on the first distance, until all the first vehicle steering motion features with the centroid are determined. Calculate the second distance from all vehicle steering motion features other than the first vehicle steering motion feature to each of the first vehicle steering motion features; The vehicle steering motion features are clustered based on the second distance to obtain the same number of steering condition clusters as the first vehicle steering motion features.

4. The steering condition synthesis method according to claim 1, characterized in that, The process of synthesizing a steering condition based on the discrete operating conditions and the steering condition cluster includes: Based on the vehicle steering data, a continuous steering condition state sequence is determined; Based on the discrete operating conditions, the continuous steering operating condition state sequence is divided into steering operating condition state transition sequence samples. For each steering condition state transition sequence sample corresponding to each steering condition cluster, the condition state of each vehicle steering motion feature is statistically analyzed, and the transition frequency from one condition state to the next condition state is determined to construct a transition frequency matrix. The transition frequency matrix is ​​normalized to obtain the transition probability matrix. Based on the transition probability matrix, the vehicle steering motion features in the steering condition cluster are spliced ​​together using a polynomial to synthesize the steering condition.

5. The steering condition synthesis method according to claim 1, characterized in that, The preprocessing of the vehicle steering data to obtain a steering dataset includes: The vehicle steering data includes steering wheel angle data, the mechanical limits of the vehicle steering system, and the physiological limits of the driver. Based on the steering wheel angle data, the vehicle's steering wheel speed is calculated, and based on the mechanical limits, the physiological limits, and the steering wheel speed, the steering wheel angle threshold and the steering wheel speed threshold are determined. The vehicle steering data that exceeds the steering wheel angle threshold or the steering wheel speed threshold is discarded to obtain the first vehicle steering data. The median filter is used to remove glitch outliers from the first vehicle steering data to obtain the second vehicle steering data. The steering data of the second vehicle is reconstructed using a multiple spline interpolation algorithm to obtain a steering dataset.

6. The steering condition synthesis method according to claim 1, characterized in that, After synthesizing the steering condition based on the discrete operating conditions and the steering condition cluster, the method further includes: Determine the statistical feature vector of the steering condition and obtain the original feature vector of the vehicle steering data; If the error between the statistical feature vector and the original feature vector is less than a set error threshold, the synthesized steering condition is determined to be qualified.

7. A steering condition synthesis device, characterized in that, The steering condition synthesis device includes: The data acquisition module is used to collect vehicle steering data from users in real driving environments and preprocess the vehicle steering data to obtain a steering dataset. The feature extraction module is used to extract vehicle steering motion features from the steering dataset; The feature clustering module is used to cluster the vehicle steering motion features to obtain multiple steering condition clusters; The working condition synthesis module is used to determine the discrete working condition state of each steering working condition cluster, and synthesize steering working conditions based on the discrete working condition state and the steering working condition cluster.

8. An electronic device, characterized in that, include: The processor, communication interface, memory, and communication bus are connected, with the processor, communication interface, and memory communicating with each other via the communication bus. The memory stores a computer program that, when executed by a processor, causes the processor to perform the steps of the steering condition synthesis method as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The device stores a computer program executable by an electronic device, which, when run on the electronic device, causes the electronic device to perform the steps of the steering condition synthesis method as described in any one of claims 1 to 6.

10. A vehicle, characterized in that, include: An electronic device for implementing the steps of the steering condition synthesis method as described in any one of claims 1 to 6; A processor that runs a program that, when the program is running, executes the steps of the steering condition synthesis method as described in any one of claims 1 to 6 from data output by the electronic device. A storage medium for storing a program that, when running, performs the steps of the steering condition synthesis method as described in any one of claims 1 to 6 on data output from an electronic device.

Images