Steering control method, device and equipment for rear wheels of a vehicle and storage medium

Abstract

The application discloses a kind of vehicle rear wheel's steering control method, device, equipment and storage medium, by gathering comprehensive information package covering vehicle state information, road environment information and driver state information, realize the perception to vehicle operation panorama.Based on this information, current driving condition is identified simultaneously and driver style is judged, so as to lay the foundation for man-machine collaborative control.In addition, two-layer decision structure including upper layer and lower layer fuzzy decision is constructed, so that the final target rear wheel steering angle is obtained.The application decouples the macroscopic adaptation of working condition and driver style with the microscopic accurate tracking of vehicle dynamics, and realizes the steering control that considers both the individualized needs of drivers and accurately tracks the ideal state of the vehicle in complex and variable scenarios by modifying the basic strategy parameters.The technical scheme of the application can be widely applied in the field of vehicle technology.

Description

Technical Field

[0001] This application relates to the field of vehicle technology, and in particular to a method, device, equipment and storage medium for steering control of the rear wheels of a vehicle. Background Technology

[0002] With the rapid development of automotive intelligence and chassis electronic control technology, active rear-wheel steering systems, due to their ability to dynamically adjust the rear wheel angle at different vehicle speeds, significantly improve vehicle handling agility and driving stability, and have become one of the key technologies for enhancing vehicle dynamic performance. Among them, fuzzy logic control methods have been widely used in this field due to their good adaptability to complex nonlinear systems.

[0003] However, existing rear-wheel steering control schemes based on fuzzy logic still suffer from incomplete decision-making basis and insufficient scenario adaptability when facing complex and ever-changing actual driving conditions. They are unable to fully consider the personalized control needs and driving comfort of different drivers while ensuring driving safety, thus limiting their further application and performance in all scenarios and human-vehicle collaborative control. Summary of the Invention

[0004] This application provides a method, device, equipment, and storage medium for steering control of the rear wheels of a vehicle, which can take into account the driver's personalized needs and accurately track the ideal state of the vehicle's steering control.

[0005] One aspect of this application provides a method for steering control of the rear wheels of a vehicle, the method comprising: Collect a comprehensive information package of the target vehicle; wherein, the comprehensive information package includes vehicle status information, road environment information, and driver status information; Based on the comprehensive information package, the current driving condition of the target vehicle is identified, and the driving style of the driver of the target vehicle is determined. A two-layer structure including upper-layer fuzzy decision and lower-layer fuzzy decision is constructed. Based on the driving conditions and driving style, the upper-layer fuzzy decision outputs basic strategy parameters for defining the steering control strategy. Based on the real-time vehicle dynamic deviation parameters of the target vehicle, the basic strategy parameters are corrected through the lower-level fuzzy decision to obtain the target rear wheel steering angle; Based on the target rear wheel steering angle, control the rear wheel steering mechanism of the target vehicle to perform steering.

[0006] For example, in some embodiments, the comprehensive information package of the target vehicle includes: The vehicle status information of the target vehicle is collected by onboard sensors; wherein the vehicle status information includes at least one of the following: vehicle speed, front wheel steering angle, front wheel steering angular velocity, lateral acceleration, body roll angle, yaw rate and wheel speed. The road environment information of the target vehicle's location is collected by an onboard environmental perception device and a vehicle-road cooperative communication device; wherein, the onboard environmental perception device includes at least a lidar and a camera; The driver status information of the target vehicle is collected by a driver status monitoring device, wherein the driver status monitoring device includes at least an operation sensor for sensing the driver's operating actions and an image acquisition device for acquiring the driver's facial information.

[0007] For example, in some embodiments, identifying the current driving condition of the target vehicle based on the integrated information package includes: Vehicle speed, lateral acceleration, curve radius, and road surface adhesion coefficient are extracted from the comprehensive information package as key feature parameters; The key feature parameters are input into a pre-trained deep learning driving condition recognition model to obtain the current driving condition of the target vehicle; wherein the recognition result of the driving condition includes at least one of the following categories: low-speed straight driving, low-speed cornering driving, high-speed straight driving, high-speed cornering driving, low-adhesion road surface driving, and slope driving.

[0008] For example, in some embodiments, determining the driving style of the driver of the target vehicle includes: Acquire the driver's current control actions and historical driving data to construct driving style evaluation indicators including steering angular velocity, pedal operation frequency and amplitude, and following distance; Based on the driving style evaluation index, a fuzzy clustering algorithm is used to classify the driver's driving style to obtain the corresponding classification results; wherein, the driving style types include aggressive, stable, and cautious.

[0009] For example, in some embodiments, the step of using the upper-level fuzzy decision output to define the basic strategy parameters for steering control strategy based on the driving conditions and driving style includes: The driving conditions, driving style, and road surface adhesion coefficient level are divided into multiple fuzzy sets, and fuzzification is performed using a preset membership function. The fuzzified fuzzy set is input into a pre-defined working condition-adaptive fuzzy rule base for inference; The fuzzy output obtained from the inference is clarified to obtain the basic strategy parameters; wherein, the basic strategy parameters include at least one of steering mode, basic steering gain and steering response speed threshold.

[0010] For example, in some embodiments, the step of correcting the basic strategy parameters based on the real-time vehicle dynamic deviation parameters of the target vehicle through the lower-level fuzzy decision includes: Based on the basic strategy parameters, the ideal target state value corresponding to the target vehicle is calculated, and the difference between the actual measured value and the ideal target state value is used as the real-time vehicle dynamic deviation parameter. The real-time vehicle dynamic deviation parameters are input into the precise tracking fuzzy rule base for inference, and the fuzzy value of the steering angle correction is output; wherein, the weight of the precise tracking fuzzy rule base is dynamically adjusted according to the credibility of the driver's control intention. The fuzzy value of the steering angle correction is clarified to obtain the steering angle correction amount, and the basic strategy parameters are corrected based on the steering angle correction amount.

[0011] Exemplarily, in some embodiments, the method further includes: The system displays the rear wheel steering status information to the driver in real time and issues a warning message to the driver when the system intervention intensity exceeds a preset level.

[0012] On the other hand, embodiments of this application provide a steering control device for the rear wheels of a vehicle, the device comprising: The data acquisition unit is used to acquire a comprehensive information package of the target vehicle; wherein, the comprehensive information package includes vehicle status information, road environment information, and driver status information; The identification unit is used to identify the current driving condition of the target vehicle based on the comprehensive information package, and to determine the driving style of the driver of the target vehicle. The construction unit is used to construct a two-layer structure including upper-layer fuzzy decision and lower-layer fuzzy decision. Based on the driving conditions and the driving style, the upper-layer fuzzy decision outputs basic strategy parameters for defining the steering control strategy. The correction unit is used to correct the basic strategy parameters based on the real-time vehicle dynamic deviation parameters of the target vehicle through the lower-level fuzzy decision to obtain the target rear wheel steering angle. An execution unit is used to control the rear wheel steering mechanism of the target vehicle to perform steering based on the target rear wheel steering angle.

[0013] On the other hand, embodiments of this application provide an electronic device, including a processor and a memory; The memory is used to store computer programs; The processor executes the computer program to implement the aforementioned method for steering control of the vehicle's rear wheels.

[0014] On the other hand, embodiments of this application provide a computer-readable storage medium storing a computer program that is executed by a processor to implement the aforementioned method for steering control of the rear wheels of a vehicle.

[0015] On the other hand, embodiments of this application also provide a computer program product, which includes a computer program stored in a computer-readable storage medium. The processor of a computer device reads the computer program from the computer-readable storage medium and executes the computer program, causing the computer device to perform the aforementioned method for controlling the steering of the rear wheels of a vehicle.

[0016] The embodiments of this application include at least the following beneficial effects: This application provides a method, device, equipment, and storage medium for steering control of the rear wheels of a vehicle. This application achieves a comprehensive perception of the vehicle's overall operation by collecting a comprehensive information package covering vehicle status information, road environment information, and driver status information. Based on this information, the current driving condition is simultaneously identified and the driver's style is determined, thus laying the foundation for human-vehicle cooperative control. Furthermore, a two-layer decision structure is constructed, including upper and lower fuzzy decision-making. The upper-layer decision, based on driving conditions and driving style, outputs basic strategy parameters to define the steering control strategy, achieving preliminary adaptation of the control strategy to the macroscopic scenario and driver characteristics. The lower-layer decision, based on real-time vehicle dynamic deviation parameters, corrects the basic strategy parameters output by the upper layer, thereby obtaining the final target rear wheel steering angle. This application decouples the macroscopic adaptation of driving conditions and driver style from the microscopic precise tracking of vehicle dynamics. By correcting the basic strategy parameters, it achieves steering control that considers both the driver's personalized needs and accurately tracks the vehicle's ideal state in complex and ever-changing scenarios. Controlling the rear wheel steering mechanism based on the target rear wheel steering angle can improve vehicle stability and handling while enhancing the comfort and safety of human-vehicle coordination. Attached Figure Description

[0017] The accompanying drawings are used to provide a further understanding of the technical solutions of this application and constitute a part of the specification. They are used together with the embodiments of this application to explain the technical solutions of this application and do not constitute a limitation on the technical solutions of this application.

[0018] Figure 1 This is a system architecture diagram of a vehicle rear wheel steering control method provided in the embodiments of this application; Figure 2 This is a flowchart illustrating a method for controlling the steering of the rear wheels of a vehicle, as provided in an embodiment of this application. Figure 3 This is a structural block diagram of a vehicle rear wheel steering control device provided in an embodiment of this application; Figure 4 This is a structural block diagram of an electronic device provided in an embodiment of this application. Detailed Implementation

[0019] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0020] It is understood that the terms “first,” “second,” etc., used in this application may be used to describe various concepts herein, but unless otherwise stated, these concepts are not limited by these terms. These terms are used only to distinguish one concept from another.

[0021] As used in this application, the terms "at least one", "multiple", "each", "any", etc., "at least one" includes one, two or more, "multiple" includes two or more, "each" refers to each of the corresponding multiples, and "any" refers to any one of the multiples.

[0022] With the rapid development of automotive intelligence and chassis electronic control technology, active rear-wheel steering systems, due to their ability to dynamically adjust the rear wheel angle at different vehicle speeds, significantly improve vehicle handling agility and driving stability, and have become one of the key technologies for enhancing vehicle dynamic performance. Among them, fuzzy logic control methods have been widely used in this field due to their good adaptability to complex nonlinear systems.

[0023] However, existing rear-wheel steering control schemes based on fuzzy logic still suffer from incomplete decision-making basis and insufficient scenario adaptability when facing complex and ever-changing actual driving conditions. They are unable to fully consider the personalized control needs and driving comfort of different drivers while ensuring driving safety, thus limiting their further application and performance in all scenarios and human-vehicle collaborative control.

[0024] In view of this, this application provides a method, device, equipment, and storage medium for steering control of the rear wheels of a vehicle. This application achieves a comprehensive perception of the vehicle's overall operation by collecting a comprehensive information package covering vehicle status information, road environment information, and driver status information. Based on this information, the current driving condition is simultaneously identified and the driver's style is determined, thus laying the foundation for human-vehicle cooperative control. Furthermore, a two-layer decision structure is constructed, including upper and lower fuzzy decision-making. The upper-layer decision, based on driving conditions and driving style, outputs basic strategy parameters to define the steering control strategy, achieving preliminary adaptation of the control strategy to the macroscopic scenario and driver characteristics. The lower-layer decision, based on real-time vehicle dynamic deviation parameters, corrects the basic strategy parameters output by the upper layer, thereby obtaining the final target rear wheel steering angle. This application decouples the macroscopic adaptation of driving conditions and driver style from the microscopic precise tracking of vehicle dynamics. By correcting the basic strategy parameters, it achieves steering control that considers both the driver's personalized needs and accurately tracks the vehicle's ideal state in complex and ever-changing scenarios. Controlling the rear wheel steering mechanism based on the target rear wheel steering angle can improve vehicle stability and handling while enhancing the comfort and safety of human-vehicle coordination.

[0025] System architecture and scenario description used in the embodiments of this application Please refer to Figure 1 , Figure 1 The diagram shows a system architecture diagram of a vehicle rear wheel steering control method provided in an embodiment of this application, which includes a terminal device 140, an Internet 130, a gateway 120, a back-end server 110, etc.

[0026] In this embodiment, the terminal device 140 may be an on-board control unit installed on the target vehicle, which integrates a multi-source perception fusion module, a working condition self-identification module, a hierarchical fuzzy decision-making module, a rear-wheel steering execution module, and a collaborative monitoring and optimization module. The terminal device 140 can be connected to the vehicle's own sensors (such as inertial measurement units, wheel speed sensors, and steering wheel angle sensors), environmental perception devices (such as cameras and radar), and a driver monitoring system via an on-board network to collect and process vehicle status information, road environment information, and driver status information in real time. Simultaneously, the terminal device 140 can communicate with roadside units (RSUs) or cloud servers via the Internet 130 through an on-board communication unit (such as a T-Box) to obtain beyond-line-of-sight road information (such as ahead curves, slopes, and weather warnings), which is not limited in this application.

[0027] Backend server 110 refers to a computer system that can provide certain services to terminal device 140. Compared with ordinary terminal device 140, backend server 110 has higher requirements in terms of stability, security, and performance. Backend server 110 can be a single high-performance computer in a network platform, a cluster of multiple high-performance computers, a portion of a single high-performance computer (e.g., a virtual machine), or a combination of portions of multiple high-performance computers (e.g., virtual machines).

[0028] Gateway 120, also known as an internetwork connector or protocol converter, is a computer system or device that acts as a translator, enabling network interconnection at the transport layer. It bridges the gap between two systems using different communication protocols, data formats, languages, or even completely different architectures. Gateways can also provide filtering and security functions. Messages sent from terminal device 140 to backend server 110 are forwarded to the corresponding backend server 110 via gateway 120. Messages sent from backend server 110 to terminal device 140 are also forwarded to the corresponding terminal device 140 via gateway 120.

[0029] The backend server 110 can be an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms.

[0030] The vehicle rear wheel steering control method provided in this application embodiment can be executed independently on the terminal device 140 side, or based on data interaction between the terminal device 140 and the backend server 110.

[0031] Of course, it is understood that the implementation environment corresponding to the method in the embodiments of this application is not limited to that of the implementation environment. Figure 1 As shown, those skilled in the art can flexibly select the specific implementation environment according to actual needs, and this application does not impose any restrictions on this.

[0032] General Description of Embodiments in this Application Please refer to Figure 2 , Figure 2 A flowchart illustrating a vehicle rear wheel steering control method provided in an embodiment of this application is shown. Figure 2 As shown, a vehicle rear wheel steering control method according to an embodiment of this application includes, but is not limited to, the following steps: Step 210: Collect a comprehensive information package of the target vehicle; wherein the comprehensive information package includes vehicle status information, road environment information, and driver status information; Step 220: Based on the comprehensive information package, identify the current driving condition of the target vehicle and determine the driving style of the driver of the target vehicle; Step 230: Construct a two-layer structure including upper-layer fuzzy decision and lower-layer fuzzy decision. Based on the driving conditions and driving style, output basic strategy parameters for defining the steering control strategy through the upper-layer fuzzy decision. Step 240: Based on the real-time vehicle dynamic deviation parameters of the target vehicle, the basic strategy parameters are corrected through the lower-level fuzzy decision to obtain the target rear wheel steering angle; Step 250: Based on the target rear wheel steering angle, control the rear wheel steering mechanism of the target vehicle to perform steering.

[0033] In this application embodiment, a method for steering control of the rear wheels of a vehicle is provided. This method aims to improve the problem in related technologies where active rear wheel steering control has a single decision basis in complex scenarios and is difficult to take into account both vehicle stability control and the driver's personalized needs. By constructing an integrated control architecture of multi-source perception and hierarchical decision-making, the method can achieve precise, coordinated and adaptive adjustment of the rear wheel steering angle.

[0034] Specifically, this method first collects multi-dimensional information encompassing the vehicle's own state, external road environment, and driver's behavioral intentions to form a comprehensive information package, providing panoramic perception input for control decisions. Based on this, the system simultaneously identifies the vehicle's current driving conditions and determines the driver's driving style, thus providing a basis for human-vehicle cooperative control. Building upon this, the method employs a two-layer decision structure including upper and lower fuzzy decision-making. The upper-layer decision-making outputs basic strategy parameters to define the macro-level steering control strategy based on the identified driving conditions and driving style, achieving initial adaptation of the control mode to the scenario and driver. The lower-layer decision-making then refines the upper-layer output based on real-time vehicle dynamic deviation parameters, ultimately obtaining the target rear wheel steering angle, which is then executed by the rear wheel steering mechanism. This method combines adaptive decision-making oriented towards macro-level scenarios with precise tracking oriented towards micro-level dynamics. By correcting the basic strategy parameters, it effectively improves the control system's adaptability, control accuracy, and human-machine cooperation level in complex and changing driving environments, thereby ensuring vehicle stability while also considering handling flexibility and driving comfort.

[0035] Below, in conjunction with Figure 2 This paper introduces and explains the various process steps of the vehicle rear wheel steering control method in the embodiments of this application.

[0036] In step 210, a comprehensive information package of the target vehicle is collected.

[0037] In this application embodiment, the target vehicle refers to the vehicle to which the provided rear-wheel steering control method is specifically implemented and operates. Within the technical context of intelligent connected vehicles and drive-by-wire chassis, it can be an intelligent connected vehicle equipped with necessary multi-source sensors, a high-performance domain controller, a drive-by-wire rear-wheel steering actuator, and corresponding control software. This vehicle possesses vehicle-to-infrastructure (V2I) communication capabilities and high-performance edge computing capabilities, enabling it to autonomously or collaboratively process multi-dimensional information such as the vehicle itself, the surrounding environment, and the driver's state in collaboration with the cloud, and generate precise rear-wheel steering control commands. This application does not limit its specific power form (fuel, pure electric, hybrid, etc.).

[0038] In step 210, a panoramic, multi-source, high-quality data foundation is constructed through data acquisition. Specifically, the comprehensive information package may include, but is not limited to, vehicle status information, road environment information, and driver status information. For vehicle status information, parameters reflecting the vehicle's own dynamic state can be collected in real time by onboard sensors, including but not limited to: vehicle speed, front wheel steering angle, front wheel steering angular velocity, lateral acceleration, body roll angle, yaw rate, and wheel speed. These parameters provide a precise quantitative description of the vehicle's current motion state.

[0039] For collecting road environment information, vehicle-mounted sensing and vehicle-to-infrastructure (V2I) technologies can be employed, using a combination of vehicle-mounted environmental sensing devices and V2I communication devices. For example, active / passive sensors such as vehicle-mounted LiDAR and high-definition cameras can be used to collect close-range, high-precision road information, such as road surface adhesion coefficient, curve radius, and road surface smoothness. Simultaneously, wireless communication technologies such as 5G-V2X can be used to acquire long-range road information transmitted from roadside units (RSUs) or the cloud, such as curves, slopes, and areas with water / snow accumulation within 1.5 kilometers ahead, enabling beyond-line-of-sight condition prediction. Furthermore, environmental sensors can also collect macroscopic environmental conditions such as temperature, precipitation, and illumination; this application does not impose any limitations on this.

[0040] For collecting driver status information, operational sensors such as steering wheel torque sensors and accelerator / brake pedal travel sensors can be used to directly collect the driver's real-time control inputs and quantify their steering, acceleration, and deceleration intentions. Driver-oriented image acquisition devices can be used to non-contactly assess their level of attention and fatigue.

[0041] In particular, in some embodiments, after the raw data is acquired, an improved federated Kalman filter algorithm can be used to fuse the three sources of information to eliminate sensor noise and data redundancy; and a feature fusion network based on an attention mechanism is used to screen key feature parameters that are highly correlated with rear wheel steering control and output the fused comprehensive information package.

[0042] In step 220, after obtaining the comprehensive information package, the current driving conditions of the target vehicle can be identified based on the comprehensive information package, and the driver's driving style can be determined.

[0043] For example, in this embodiment of the application, deep learning technology can be used to build a relevant driving condition recognition model (such as a CNN-LSTM network). The model can learn and recognize complex spatiotemporal patterns, thereby accurately outputting the core driving condition category of the current vehicle. For the driver's driving style, a multi-dimensional evaluation index system can be constructed. Algorithms such as fuzzy clustering are used to analyze this index system and dynamically classify the driver's style, for example, into typical categories such as aggressive, stable, and cautious.

[0044] In step 230, the innovative architecture provided in this application embodiment is used to process the steering control of the vehicle's rear wheels through hierarchical fuzzy decision-making. Specifically, step 230 mainly uses upper-level fuzzy decision-making, which is responsible for formulating macro-level strategies.

[0045] In this embodiment, the input to the upper-level fuzzy decision is the output of step 220, namely the type of driving condition and driving style. Simultaneously, key environmental information such as the road surface adhesion coefficient level can be incorporated. These input quantities are first fuzzified, that is, they are converted from precise values ​​into fuzzy linguistic variables describing the degree to which a certain state is belonged through a membership function (such as a Gaussian function). For example, the degree to which the driving condition belongs to a high-speed curve, the degree to which the driving style is aggressive, and the degree to which the adhesion coefficient is high.

[0046] Next, these fuzzified inputs are used in a pre-defined fuzzy rule base for driving condition adaptation, based on extensive real-vehicle data and expert experience. This rule base includes fuzzy inference rules such as "IF driving condition is high-speed cornering AND driving style is smooth AND road surface adhesion is high, THEN steering mode is in phase, basic steering gain is medium, and response speed threshold is a certain value." Through fuzzy inference and declarative processes (such as weighted averaging), a set of basic strategy parameters can be output.

[0047] In step 240, lower-level fuzzy decision-making is used to accurately track and correct micro-dynamics within the macro-strategy framework.

[0048] Specifically, in this embodiment, the input to the lower-level fuzzy decision-making mainly consists of real-time vehicle dynamic deviation parameters, such as yaw rate deviation, lateral acceleration deviation, and vehicle roll angle deviation. These deviations are the differences between the actual vehicle state measurement values ​​and the ideal target state values ​​determined based on the current operating conditions, driving style, and the basic strategy parameters output by the upper layer, reflecting the subtle deviation between the actual vehicle response and the expected response.

[0049] Similarly, these deviation parameters can also be fuzzified and input into a precise tracking fuzzy rule base. A key feature of this rule base is that its rule weights can be dynamically adjusted based on the driver's intent credibility. When the system determines that the driver's intent is clear and highly credible (e.g., the driver is actively and smoothly cornering), it reduces the weight of vehicle state deviations in the decision-making process, prioritizing the driver's control; conversely, when the driver's intent is ambiguous or lacks credibility (e.g., the driver may not have reacted effectively to a sudden situation), it increases the deviation weights, strengthening the system's intervention to maintain stability. Through fuzzy reasoning and demarcation (e.g., the center of gravity method), the lower-level fuzzy decision outputs a precise rear wheel steering angle correction. This correction is a fine-tuning of the basic strategy parameters output by the upper layer (specifically, a basic steering angle), and the target rear wheel steering angle can be calculated by combining the basic steering angle and this correction.

[0050] Step 250: Based on the target rear wheel steering angle, control the rear wheel steering mechanism of the target vehicle to perform steering.

[0051] In this embodiment, the calculated target rear wheel steering angle can be converted into precise drive commands for a high-precision steer-by-wire rear wheel steering execution module (typically driven by a permanent magnet synchronous motor). This execution module needs to have high response speed (e.g., ≤20ms) and high positioning accuracy (e.g., ±0.01°) to ensure that the upper-level decision can be quickly and accurately converted into actual rear wheel steering angle changes.

[0052] It is understood that the rear-wheel steering control method provided in this application embodiment achieves a comprehensive perception of the vehicle's overall operation by collecting a comprehensive information package covering vehicle status information, road environment information, and driver status information. Based on this information, the current driving condition is simultaneously identified and the driver's style is determined, thus laying the foundation for human-vehicle cooperative control. Furthermore, a two-layer decision structure is constructed, including upper and lower fuzzy decision-making. The upper-layer decision, based on driving conditions and driving style, outputs basic strategy parameters to define the steering control strategy, achieving initial adaptation of the control strategy to the macroscopic scenario and driver characteristics. The lower-layer decision, based on real-time vehicle dynamic deviation parameters, corrects the basic strategy parameters output by the upper layer, thereby obtaining the final target rear-wheel steering angle. This application decouples the macroscopic adaptation of driving conditions and driver style from the microscopic precise tracking of vehicle dynamics. By correcting the basic strategy parameters, it achieves steering control that considers both the driver's personalized needs and accurately tracks the vehicle's ideal state in complex and ever-changing scenarios. Controlling the rear-wheel steering mechanism according to this target rear-wheel steering angle can improve vehicle stability and handling while enhancing the comfort and safety of human-vehicle cooperation.

[0053] Specifically, in some embodiments, identifying the current driving condition of the target vehicle based on the integrated information package includes: Vehicle speed, lateral acceleration, curve radius, and road surface adhesion coefficient are extracted from the comprehensive information package as key feature parameters; The key feature parameters are input into a pre-trained deep learning driving condition recognition model to obtain the current driving condition of the target vehicle; wherein the recognition result of the driving condition includes at least one of the following categories: low-speed straight driving, low-speed cornering driving, high-speed straight driving, high-speed cornering driving, low-adhesion road surface driving, and slope driving.

[0054] This application provides a method for accurately and efficiently identifying the current driving conditions of a vehicle, utilizing the powerful pattern recognition capabilities of deep learning models to achieve automated and highly accurate classification of complex driving conditions.

[0055] Specifically, in this embodiment, multiple key feature parameters are extracted from the comprehensive information package to encompass the largest amount of operating condition information with the smallest feature dimension. These key feature parameters may include vehicle speed, lateral acceleration, cornering radius, and road surface adhesion coefficient. Vehicle speed is the fundamental variable distinguishing vehicle dynamic behavior, directly determining vehicle inertia and control response requirements. Lateral acceleration directly reflects the vehicle's lateral dynamic state and is an indicator distinguishing between straight lines, curves, and extreme handling conditions. The cornering radius is a key quantification of road geometry, clarifying the road morphological constraints the vehicle is in. The road surface adhesion coefficient reflects the physical limits of tire-ground contact and is the basis for determining the vehicle's controllable boundary and stability margin. These four features together constitute a feature subspace describing the interaction between the vehicle and its environment, effectively distinguishing various typical operating conditions with significantly different rear-wheel steering control requirements.

[0056] Based on key feature parameters, this application embodiment employs a pre-trained deep learning driving condition recognition model for classification and prediction. This deep learning model is trained offline using a large amount of multi-dimensional real-vehicle historical data. The model can learn the complex, non-linear patterns formed by the aforementioned key feature parameters over time and establish a high-dimensional mapping relationship between them and the final driving condition category. For example, in some embodiments, a CNN-LSTM model combining convolutional neural networks and long short-term memory networks can be used. The CNN part of this model can be used to extract deep local features and spatial relationships from single or multiple frames of feature input, while the LSTM part excels at capturing the evolution and dependencies of vehicle states over time. The combination of the two allows the model to fully utilize the spatiotemporal correlation of features, thereby achieving dynamic and continuous recognition of driving conditions with a high accuracy rate. In this application embodiment, the driving condition recognition result includes at least one of the following categories: low-speed straight driving, low-speed cornering driving, high-speed straight driving, high-speed cornering driving, low-adhesion road surface driving, and slope driving. Of course, other categories can be set according to requirements, and this application does not impose any restrictions on this.

[0057] Specifically, in some embodiments, determining the driving style of the driver of the target vehicle includes: Acquire the driver's current control actions and historical driving data to construct driving style evaluation indicators including steering angular velocity, pedal operation frequency and amplitude, and following distance; Based on the driving style evaluation index, a fuzzy clustering algorithm is used to classify the driver's driving style to obtain the corresponding classification results; wherein, the driving style types include aggressive, stable, and cautious.

[0058] In this application embodiment, a method for quantifying and identifying a driver's personalized driving style is provided. This method constructs a multi-dimensional, quantifiable evaluation index system and uses fuzzy mathematics tools to handle the inherent boundary fuzziness problem in style classification, thereby transforming the abstract driving style into a clear category label that can be used by the control system.

[0059] Specifically, in this embodiment, the driving style evaluation indicators include steering angular velocity, pedal operation frequency and amplitude, and following distance. Its construction comprehensively considers the real-time nature of the operation and the statistical regularity of the behavior. Steering angular velocity is a direct indicator of the driver's decisiveness and intensity in steering operations; rapid steering input usually corresponds to a stronger intention to change paths. The frequency and amplitude of accelerator / brake pedal operation jointly describe the driver's finesse and tendency in longitudinal power control; frequent or deep pressing operation patterns reflect a high demand for power or a defensive driving habit. Following distance (usually measured by millimeter-wave radar or cameras, and a typical value derived from historical data statistics) quantifies the driver's risk tolerance and safety margin preference from the perspective of interactive behavior. These three types of indicators, from the three dimensions of lateral control, longitudinal control, and human-vehicle interaction, respectively, comprehensively depict the driver's behavioral characteristics when operating the vehicle.

[0060] In this embodiment, a fuzzy clustering algorithm (e.g., fuzzy C-means clustering) is used for style classification. Unlike traditional hard classification (either / or), fuzzy clustering acknowledges that a driver's behavior may simultaneously belong to multiple styles to varying degrees. The algorithm automatically calculates several cluster centers (e.g., "aggressive," "stable," and "cautious") based on the distribution of all driver samples (which can be historical big data or data from the current driver over a period of time) in a multivariate feature space composed of these evaluation metrics. It then provides the degree to which the current driver's feature vector belongs to each cluster center, i.e., the membership degree. Finally, the category with the highest membership degree is selected as the current driver's style classification result. For example, a driver's feature vector might be classified as having a membership degree of 0.7 for "aggressive," 0.25 for "stable," and 0.05 for "cautious," thus classifying the driver as "aggressive." This method can capture the intermediate states and gradual changes in driver style more delicately and accurately.

[0061] It should be noted that in some embodiments, while using fuzzy clustering algorithms to obtain classification results, a driver's real-time control intention credibility can also be calculated. This credibility is used to quantify the degree to which the driver's control input is clear, stable, and consistent with their historical style at the current moment. The calculation of the driver's real-time control intention credibility can comprehensively consider multiple instantaneous signals. For example, the variance or rate of change of the steering wheel angle signal and / or pedal travel signal over a short period of time can be calculated. If the variance is small and the change is stable, it indicates that the driver's input intention is clear and the operation is stable, with high credibility; conversely, if the input is jittery and frequently corrected, the credibility is low. At the same time, the current instantaneous operation characteristics (such as the current steering angle velocity and pedal depth) can be compared with the typical operation patterns under its historical style classification. If the consistency is high, the credibility is high. In addition, signals from driver state monitoring (such as eyes leaving the road ahead and frequent blinking indicating fatigue) can also be used as negative adjustment factors, which are not limited in this application.

[0062] In this embodiment, based on the working condition identification result and the classification of driving style, the rule weights and output constraint range of the hierarchical fuzzy decision can be initialized. For example, in low-speed cornering conditions and aggressive driving style, the rear wheel steering angle adjustment range is increased; in high-speed straight conditions and cautious driving style, the rear wheel steering response sensitivity is reduced.

[0063] Specifically, in some embodiments, the basic strategy parameters for defining the steering control strategy based on the driving conditions and driving style, output by the upper-level fuzzy decision, include: The driving conditions, driving style, and road surface adhesion coefficient level are divided into multiple fuzzy sets, and fuzzification is performed using a preset membership function. The fuzzified fuzzy set is input into a pre-defined working condition-adaptive fuzzy rule base for inference; The fuzzy output obtained from the inference is clarified to obtain the basic strategy parameters; wherein, the basic strategy parameters include at least one of steering mode, basic steering gain and steering response speed threshold.

[0064] In this embodiment, the input to the upper-level fuzzy decision-making is semantically processed qualitative or semi-qualitative information. Driving conditions (e.g., high-speed curves), driving style (e.g., aggressive driving), and road surface adhesion coefficient level (e.g., medium adhesion) can be conceptual descriptions with degrees. The system first fuzzifies these inputs using preset membership functions (e.g., Gaussian or trigonometric functions). For example, for the variable of vehicle speed, when determining whether it belongs to the fuzzy set of "high speed," it does not simply use 100 km / h as the boundary, but describes it through the membership function as "80 km / h belongs to 'high speed' with a degree of 0.2, 100 km / h with 0.8, and 120 km / h with 1.0." In this way, even if the input is near the category boundary (e.g., vehicle speed of 95 km / h), a reasonable soft classification of either 0 or 1 can be obtained, thus preserving the continuity and gradual characteristics of the input information and avoiding abrupt changes in control strategy caused by hard threshold division.

[0065] In this embodiment, the pre-defined fuzzy rule base for adapting to operating conditions serves as the knowledge carrier for upper-level fuzzy decision-making. This rule base consists of a large number of "IF-THEN" rules based on vehicle dynamics principles, real-vehicle test data, and expert experience. During inference, the activation intensity of each rule for all currently fuzzified input conditions is calculated (usually the minimum or product of the membership degrees of each antecedent). This activation intensity is then used to trim or scale the output fuzzy set of the "THEN" part of that rule. The output fuzzy sets of all activated rules are then combined through a union operation to form a total fuzzy set for each output parameter (such as "basic steering gain"). Then, for the combined output fuzzy set, a declarative method, such as the weighted average method or the centroid method, is used to calculate a single, precise value that best represents the fuzzy set. For example, by calculating the centroid position of the fuzzy set, a basic steering gain value such as "0.35" is obtained. In this embodiment, the basic strategy parameter may include at least one of the following: steering mode, basic steering gain, and steering response speed threshold.

[0066] Specifically, in some embodiments, the step of correcting the basic strategy parameters based on the real-time vehicle dynamic deviation parameters of the target vehicle through the lower-level fuzzy decision includes: Based on the basic strategy parameters, the ideal target state value corresponding to the target vehicle is calculated, and the difference between the actual measured value and the ideal target state value is used as the real-time vehicle dynamic deviation parameter. The real-time vehicle dynamic deviation parameters are input into the precise tracking fuzzy rule base for inference, and the fuzzy value of the steering angle correction is output; wherein, the weight of the precise tracking fuzzy rule base is dynamically adjusted according to the credibility of the driver's control intention. The fuzzy value of the steering angle correction is clarified to obtain the steering angle correction amount, and the basic strategy parameters are corrected based on the steering angle correction amount.

[0067] In this embodiment, the relatively abstract basic strategy parameters (such as steering mode and basic steering gain) output from the upper layer are transformed into specific and quantifiable ideal target state values ​​for the target vehicle. For example, based on the strategy of "high-speed curve + in-phase steering + gain 0.3", combined with the current vehicle speed, front wheel angle, etc., the desired ideal yaw rate and ideal lateral acceleration at the current moment can be calculated through a preset reference model or mapping relationship. The real-time vehicle dynamic deviation parameters are the differences between the actual sensor measurements and these ideal target values.

[0068] Real-time vehicle dynamic deviation parameters are input into a precise tracking fuzzy rule base. In this embodiment, the precise tracking fuzzy rule base is the core for performing correction calculations. This rule base contains fine-grained rules such as "IF yaw rate deviation is positive large AND lateral acceleration deviation is positive small, THEN steering angle correction is negative medium." Unlike the upper-level rule base, each rule or input variable in the lower-level rule base is assigned a weight coefficient, and this weight coefficient is not fixed but dynamically adjusted based on the real-time calculated confidence level of the driver's control intention. When the system determines that the driver's intention is clear and highly reliable (e.g., the driver is performing a smooth and confident steering operation), the weight of the deviation parameter is reduced (e.g., reduced to 0.3). This means that even if there is a certain vehicle state deviation, the system considers this to be the vehicle response characteristics expected by the driver, thereby reducing deviation-based corrective interventions and prioritizing the driver's control intention. Conversely, when the driver's intentions are ambiguous or lack credibility (for example, the driver may not react to the sideslip), the weight of the deviation parameter is increased (for example, increased to 0.8) to enhance the system's autonomous correction aimed at stability. In this case, the system will more actively eliminate the deviation and pull the vehicle back to an ideal safe state.

[0069] In this embodiment, the fuzzy value of the steering angle correction can be clarified, for example, by using a clarification method such as the center of gravity method, to calculate a precise steering angle correction. Based on this, the target rear wheel steering angle can be calculated. The final rear wheel steering angle is converted into a drive command for the drive-by-wire motor, and the rear wheel steering mechanism is driven by a permanent magnet synchronous motor to achieve steering angle adjustment. The execution module response time is ≤20ms, and the steering angle control accuracy is ±0.01°. It is equipped with a dual-path drive redundancy unit, which seamlessly switches within 1ms in case of failure, ensuring execution reliability.

[0070] Furthermore, in some embodiments, when an extreme operating condition is determined (such as high-speed sharp turning or risk of sideslip on low-traction surfaces), the chassis domain controller synchronously outputs coordinated commands to the ESP (Electronic Stability Program) and active suspension system; the ESP system implements precise braking intervention, and the active suspension system adjusts the vehicle's posture, forming an integrated and coordinated control with the rear-wheel steering system to improve vehicle stability. Moreover, in this embodiment, the rear-wheel steering status (steering angle, steering mode) can be displayed in real time on the instrument panel display. When the system intervention intensity is high, voice prompts are provided to the driver to enhance driving safety.

[0071] In this embodiment of the application, a full-process monitoring and iterative optimization mechanism can also be constructed to ensure the adaptability of the hierarchical fuzzy control rules and the stability of the control effect, specifically including: (1) Control effect monitoring: Real-time acquisition of vehicle dynamic parameters (yaw rate, lateral acceleration, body roll angle) after rear wheel steering is executed, and calculation of control error (deviation between actual value and ideal target value), steering response time, overshoot and other evaluation indicators; (2) Rule Iteration Optimization: When the control error is ≥0.05g (lateral acceleration deviation) or ≥0.02rad / s (yaw rate deviation) within 10 consecutive sampling periods, fuzzy rule optimization is initiated; based on the current operating conditions, driving style and control effect data, reinforcement learning algorithm (DQN) is used to update the rule weights and membership function parameters of the hierarchical fuzzy rule base to improve control accuracy; (3) Abnormal protection: When a fault is detected in the rear wheel steering execution module, sensor signal loss or control error exceeding the safety threshold (such as lateral acceleration deviation ≥0.2g), the active rear wheel steering control is immediately stopped, and the passive safety mode is switched (rear wheel lock is in the neutral position). At the same time, an alarm signal is triggered and a fault prompt is pushed to the driver to ensure driving safety.

[0072] It is understood that the technical solution of this application has at least the following advantages: 1. Multi-source fusion perception with strong scene adaptability: The innovative construction of a multi-source perception fusion system integrates roadside long-distance road conditions with driver style and intentions into rear wheel steering control, enabling advance prediction of working conditions within a 1.5km range. The full-scene recognition accuracy is high, improving the problem of single scene adaptability of existing technologies. 2. Layered fuzzy decision-making significantly improves control accuracy: A two-layer fuzzy architecture is adopted to realize working condition adaptation and dynamic tracking respectively. Combined with dynamic adjustment of rule weights, the control accuracy of the rear wheel steering angle reaches ±0.01°, which is a great improvement over the traditional single fuzzy control. The low-speed turning radius is greatly reduced, and the high-speed yaw rate fluctuation is effectively reduced, balancing low-speed flexibility and high-speed stability. 3. Personalized human-vehicle collaborative control for a more humanized driving experience: The control priority can be adjusted according to driving style and real-time control intentions, reducing system intervention and conflicts with driver operation, achieving personalized steering control, and improving comfort and handling. 4. Strong multi-system coordination and robustness: It realizes coordinated control of multiple systems such as rear-wheel steering, ESP, and active suspension to improve stability under extreme conditions; through rule iteration and anomaly protection mechanisms, it improves the system's working stability under complex environments and interference conditions. 5. High versatility and industrialization potential: It can be adapted to various vehicle models and power systems, and can be integrated into existing drive-by-wire chassis systems through software algorithms with minimal hardware modifications, making it a promising candidate for widespread application.

[0073] Reference Figure 3 In this embodiment of the application, a steering control device for the rear wheels of a vehicle is also provided, the steering control device for the rear wheels of the vehicle comprising: The acquisition unit 310 is used to acquire a comprehensive information package of the target vehicle; wherein, the comprehensive information package includes vehicle status information, road environment information, and driver status information; The identification unit 320 is used to identify the current driving condition of the target vehicle based on the comprehensive information package, and to determine the driving style of the driver of the target vehicle. The construction unit 330 is used to construct a two-layer structure including upper-layer fuzzy decision and lower-layer fuzzy decision. Based on the driving conditions and the driving style, the upper-layer fuzzy decision outputs basic strategy parameters for defining the steering control strategy. The correction unit 340 is used to correct the basic strategy parameters based on the real-time vehicle dynamic deviation parameters of the target vehicle through the lower-level fuzzy decision to obtain the target rear wheel steering angle. The execution unit 350 is used to control the rear wheel steering mechanism of the target vehicle to perform steering according to the target rear wheel steering angle.

[0074] It is understandable that, such as Figure 2 The content of the vehicle rear wheel steering control method embodiment shown is applicable to the vehicle rear wheel steering control device embodiment. The specific functions implemented by the vehicle rear wheel steering control device embodiment are the same as those shown. Figure 2 The method for controlling the steering of the rear wheels of the vehicle shown is the same as the embodiment described above, and the beneficial effects achieved are the same as those described above. Figure 2 The beneficial effects achieved by the embodiment of the vehicle rear wheel steering control method shown are also the same.

[0075] Reference Figure 4 This application also discloses an electronic device, including: At least one processor 410; At least one memory 420 is used to store at least one program; When at least one program is executed by at least one processor 410, such that at least one processor 410 performs as follows: Figure 2 An example of a vehicle rear wheel steering control method is shown.

[0076] The electronic device in the embodiments of this application may be a terminal device, a computer device, or a server device.

[0077] Understandable, Figure 2 The content of the vehicle rear wheel steering control method embodiment shown is applicable to the embodiment of this electronic device, and the specific functions implemented by the embodiment of this electronic device are the same as those shown in the previous embodiment. Figure 2 The embodiment of the vehicle's rear wheel steering control method shown is the same, and the beneficial effects achieved are the same. Figure 2 The beneficial effects achieved by the embodiment of the vehicle rear wheel steering control method shown are also the same.

[0078] This application also discloses a computer-readable storage medium storing a processor-executable program, which, when executed by a processor, is used to implement, for example... Figure 2 An example of a vehicle rear wheel steering control method is shown.

[0079] Understandable, Figure 2 The content of the vehicle rear wheel steering control method embodiment shown is applicable to the embodiment of this computer-readable storage medium, and the specific functions implemented by the embodiment of this computer-readable storage medium are the same as those in the embodiment of this computer-readable storage medium. Figure 2 The embodiment of the vehicle's rear wheel steering control method shown is the same, and the beneficial effects achieved are the same. Figure 2 The beneficial effects achieved by the embodiment of the vehicle rear wheel steering control method shown are also the same.

[0080] This application also discloses a computer program product or computer program, which includes computer instructions stored in the aforementioned computer-readable storage medium. Figure 4 The processor of the illustrated electronic device can read the computer instructions from the aforementioned computer-readable storage medium, and the processor executes the computer instructions, causing the computer device to perform... Figure 2 An example of a vehicle rear wheel steering control method is shown.

[0081] Understandable, Figure 2 The content of the vehicle rear wheel steering control method embodiments shown is applicable to this computer program product or computer program embodiment, and the specific functions implemented by this computer program product or computer program embodiment are the same as those described above. Figure 2The embodiment of the vehicle's rear wheel steering control method shown is the same, and the beneficial effects achieved are the same. Figure 2 The beneficial effects achieved by the embodiment of the vehicle rear wheel steering control method shown are also the same.

[0082] In some alternative embodiments, the functions / operations mentioned in the block diagrams may not occur in the order shown in the operation diagrams. For example, depending on the functions / operations involved, two consecutively shown blocks may actually be executed substantially simultaneously, or the blocks may sometimes be executed in reverse order. Furthermore, the embodiments presented and described in the flowcharts of this application are provided by way of example to provide a more comprehensive understanding of the technology. The disclosed methods are not limited to the operations and logic flows presented herein. Alternative embodiments are contemplated in which the order of various operations is changed and sub-operations described as part of a larger operation are executed independently.

[0083] Furthermore, although this application is described in the context of functional modules, it should be understood that, unless otherwise stated to the contrary, one or more of the functions and / or features may be integrated into a single physical device and / or software module, or one or more functions and / or features may be implemented in a separate physical device or software module. It is also understood that a detailed discussion of the actual implementation of each module is unnecessary for understanding this application. Rather, given the properties, functions, and internal relationships of the various functional modules in the apparatus disclosed herein, the actual implementation of the module will be understood within the scope of conventional technology for an engineer. Therefore, those skilled in the art can implement the application set forth in the claims using ordinary techniques without excessive experimentation. It is also understood that the specific concepts disclosed are merely illustrative and not intended to limit the scope of this application, which is determined by the full scope of the appended claims and their equivalents.

[0084] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0085] In the embodiments of this application, the terms "module" or "unit" refer to a computer program or part of a computer program that has a predetermined function and works with other related parts to achieve a predetermined goal, and can be implemented wholly or partially using software, hardware (such as processing circuitry or memory), or a combination thereof. Similarly, a processor (or multiple processors or memory) can be used to implement one or more modules or units. Furthermore, each module or unit can be part of an overall module or unit that includes the functionality of that module or unit.

[0086] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable storage medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable storage medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0087] It should be understood that various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0088] In the foregoing description of this specification, the references to terms such as "one embodiment," "another embodiment," or "some embodiments," etc., indicate that a specific feature, structure, material, or characteristic described in connection with an embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0089] Although embodiments of this application have been shown and described, those skilled in the art will understand that various changes, modifications, substitutions and variations can be made to these embodiments without departing from the principles and spirit of this application, the scope of which is defined by the claims and their equivalents.

[0090] The above is a detailed description of the preferred embodiments of this application, but this application is not limited to the embodiments. Those skilled in the art can make various equivalent modifications or substitutions without departing from the spirit of this application, and these equivalent modifications or substitutions are all included within the scope defined by the claims of this application.

Claims

1. A method for steering control of the rear wheels of a vehicle, characterized in that, The method includes: Collect a comprehensive information package of the target vehicle; wherein, the comprehensive information package includes vehicle status information, road environment information, and driver status information; Based on the comprehensive information package, the current driving condition of the target vehicle is identified, and the driving style of the driver of the target vehicle is determined. A two-layer structure including upper-layer fuzzy decision and lower-layer fuzzy decision is constructed. Based on the driving conditions and driving style, the upper-layer fuzzy decision outputs basic strategy parameters for defining the steering control strategy. Based on the real-time vehicle dynamic deviation parameters of the target vehicle, the basic strategy parameters are corrected through the lower-level fuzzy decision to obtain the target rear wheel steering angle; Based on the target rear wheel steering angle, control the rear wheel steering mechanism of the target vehicle to perform steering.

2. The vehicle rear wheel steering control method according to claim 1, characterized in that, The comprehensive information package of the target vehicle includes: The vehicle status information of the target vehicle is collected by onboard sensors; wherein the vehicle status information includes at least one of the following: vehicle speed, front wheel steering angle, front wheel steering angular velocity, lateral acceleration, body roll angle, yaw rate and wheel speed. The road environment information of the target vehicle's location is collected by an onboard environmental perception device and a vehicle-road cooperative communication device; wherein, the onboard environmental perception device includes at least a lidar and a camera; The driver status information of the target vehicle is collected by a driver status monitoring device, wherein the driver status monitoring device includes at least an operation sensor for sensing the driver's operating actions and an image acquisition device for acquiring the driver's facial information.

3. The vehicle rear wheel steering control method according to claim 1, characterized in that, The step of identifying the current driving condition of the target vehicle based on the comprehensive information package includes: Vehicle speed, lateral acceleration, curve radius, and road surface adhesion coefficient are extracted from the comprehensive information package as key feature parameters; The key feature parameters are input into a pre-trained deep learning driving condition recognition model to obtain the current driving condition of the target vehicle; wherein the recognition result of the driving condition includes at least one of the following categories: low-speed straight driving, low-speed cornering driving, high-speed straight driving, high-speed cornering driving, low-adhesion road surface driving, and slope driving.

4. The vehicle rear wheel steering control method according to claim 1, characterized in that, The determination of the driver's driving style of the target vehicle includes: Acquire the driver’s current control actions and historical driving data to construct driving style evaluation indicators including steering angular velocity, pedal operation frequency and amplitude, and following distance; Based on the driving style evaluation index, a fuzzy clustering algorithm is used to classify the driver's driving style to obtain the corresponding classification results; wherein, the driving style types include aggressive, stable, and cautious.

5. The vehicle rear wheel steering control method according to claim 1, characterized in that, The basic strategy parameters used to define the steering control strategy based on the driving conditions and driving style, through the upper-level fuzzy decision output, include: The driving conditions, driving style, and road surface adhesion coefficient level are divided into multiple fuzzy sets, and fuzzification is performed using a preset membership function. The fuzzified fuzzy set is input into a pre-defined working condition-adaptive fuzzy rule base for inference; The fuzzy output obtained from the inference is clarified to obtain the basic strategy parameters; wherein, the basic strategy parameters include at least one of steering mode, basic steering gain and steering response speed threshold.

6. The vehicle rear wheel steering control method according to claim 5, characterized in that, The process of correcting the basic strategy parameters based on the real-time vehicle dynamic deviation parameters of the target vehicle through the lower-level fuzzy decision-making includes: Based on the basic strategy parameters, the ideal target state value corresponding to the target vehicle is calculated, and the difference between the actual measured value and the ideal target state value is used as the real-time vehicle dynamic deviation parameter. The real-time vehicle dynamic deviation parameters are input into the precise tracking fuzzy rule base for inference, and the fuzzy value of the steering angle correction is output; wherein, the weight of the precise tracking fuzzy rule base is dynamically adjusted according to the credibility of the driver's control intention. The fuzzy value of the steering angle correction is clarified to obtain the steering angle correction amount, and the basic strategy parameters are corrected based on the steering angle correction amount.

7. The method for controlling the steering of the rear wheels of a vehicle according to any one of claims 1-6, characterized in that, The method further includes: The system displays the rear wheel steering status information to the driver in real time and issues a warning message to the driver when the system intervention intensity exceeds a preset level.

8. A steering control device for the rear wheels of a vehicle, characterized in that, The device includes: The data acquisition unit is used to acquire a comprehensive information package of the target vehicle; wherein, the comprehensive information package includes vehicle status information, road environment information, and driver status information; The identification unit is used to identify the current driving condition of the target vehicle based on the comprehensive information package, and to determine the driving style of the driver of the target vehicle. The construction unit is used to construct a two-layer structure including upper-layer fuzzy decision and lower-layer fuzzy decision. Based on the driving conditions and the driving style, the upper-layer fuzzy decision outputs basic strategy parameters for defining the steering control strategy. The correction unit is used to correct the basic strategy parameters based on the real-time vehicle dynamic deviation parameters of the target vehicle through the lower-level fuzzy decision to obtain the target rear wheel steering angle. An execution unit is used to control the rear wheel steering mechanism of the target vehicle to perform steering based on the target rear wheel steering angle.

9. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the vehicle rear wheel steering control method according to any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the vehicle rear wheel steering control method according to any one of claims 1 to 7.

Images