New energy automobile ice and snow covered pavement intelligent cooperative anti-skid control method and system

Abstract

The invention relates to the technical field of vehicle intelligent control, and provides a new energy vehicle ice and snow pavement intelligent cooperative anti-skid control method and system. The method comprises the steps of predicting a risk level of a vehicle about to slip based on vehicle state information and road surface information; according to the risk levels, control instruction combinations used for controlling a steering system, a driving system and a braking system to cooperatively act are generated, and different risk levels correspond to different control instruction combinations; and based on the control instruction combination, cooperative intervention is conducted on the vehicle through the steering system, the driving system and the braking system. According to the method, through predictive risk judgment and multi-system cooperative execution, the transformation from remedy after slipping to prevention before slipping is realized, and the safety, smoothness and energy efficiency of driving on the ice and snow covered pavement are effectively improved.

Description

Technical Field

[0001] This invention relates to the field of vehicle intelligent control technology, and more specifically, to a method and system for intelligent collaborative anti-skid control of new energy vehicles on icy and snowy roads. Background Technology

[0002] New energy vehicles, especially pure electric vehicles, face unique challenges compared to traditional gasoline-powered vehicles when driving on low-traction conditions such as icy and snowy roads. Due to the rapid torque response and high initial torque of their drive motors, the drive wheels are prone to momentary slippage during start-up or acceleration, leading to dynamic instability. Ensuring vehicle safety and stability under such complex road conditions has become a critical issue that the industry urgently needs to address.

[0003] Currently, the industry generally relies on braking-based vehicle stability systems (such as Traction Control System (TCS) and Electronic Stability Program (ESP)) as the primary means of anti-skid control. This type of technology is essentially a passive control strategy of "remediation after slippage," meaning that braking intervention only occurs after the wheel slip ratio exceeds a safe threshold. This lag leads to an unavoidable delay in system response, and its forceful braking intervention can cause vehicle jerking and interrupt power output, severely impacting driving smoothness and ride comfort, and also negatively affecting the driving range of new energy vehicles. Furthermore, existing solutions primarily rely solely on the braking system, failing to effectively integrate other controllable actuators such as steering and drive to form a forward-looking, synergistic control strategy, leaving significant room for improvement in anti-skid control effectiveness, energy efficiency, and driving experience.

[0004] In summary, existing anti-skid control technologies suffer from drawbacks such as delayed response, abrupt intervention, single control method, and high energy consumption. Therefore, there is an urgent need in this field for an anti-skid control method for icy and snowy roads that can achieve early prediction, multi-system coordination, smooth intervention, and energy efficiency, in order to overcome the shortcomings of existing technologies and improve the overall performance of new energy vehicles under adverse road conditions. Summary of the Invention

[0005] This invention addresses the technical problems existing in the prior art by providing a method and system for intelligent collaborative anti-skid control of new energy vehicles on icy and snowy roads. It overcomes the shortcomings of traditional vehicle anti-skid systems, such as reliance on braking, delayed response, and abrupt intervention, and achieves intelligent anti-skid control that can predict risks in advance and coordinate steering, drive, and braking systems for smooth and efficient collaborative intervention.

[0006] According to a first aspect of the present invention, a method for intelligent collaborative anti-skid control of new energy vehicles on icy and snowy roads is provided, comprising: Based on vehicle status information and road surface information, predict the risk level of the vehicle skidding. Based on the risk level, a combination of control commands is generated to control the coordinated operation of the steering system, drive system and braking system, wherein different risk levels correspond to different combinations of control commands. Based on the combination of control commands, the vehicle is coordinated and intervened through the steering system, drive system and braking system.

[0007] Based on the above technical solution, the present invention can also be improved as follows.

[0008] Optionally, the prediction of the risk level of impending vehicle skidding based on vehicle state information and road surface information includes: Based on the road surface information and vehicle status information, the wheel motion state in future time periods is predicted through a vehicle dynamics model; wherein, the road surface information includes the road surface adhesion coefficient; The risk threshold is dynamically calculated based on the road surface adhesion coefficient. The risk level of impending vehicle skidding is determined by comparing the predicted wheel motion state with the risk threshold.

[0009] Optionally, the step of predicting the wheel motion state in future time periods based on the road surface information and vehicle state information using a vehicle dynamics model includes: When driving on icy and snowy roads, the real-time road adhesion coefficient, current vehicle speed, steering wheel angle and driver-requested torque are used as inputs into the vehicle dynamics model. Using the current vehicle state as the initial value, a forward simulation calculation is performed on the vehicle dynamics model to predict the slip ratio and sideslip angle of each wheel within a set future time period.

[0010] Optionally, the dynamic calculation of the risk threshold based on the road surface adhesion coefficient includes: Based on the real-time acquired road adhesion coefficient, the tire force utilization rate threshold and the slip rate threshold are dynamically calculated according to a preset relationship function. The tire force utilization rate threshold includes a high-risk tire force utilization rate threshold and a low-risk tire force utilization rate threshold, and the slip rate threshold includes a high-risk slip rate threshold and a low-risk slip rate threshold. The relationship function is configured such that the lower the road surface adhesion coefficient, the lower the calculated risk threshold.

[0011] Optionally, determining the risk level of impending vehicle skidding by comparing the predicted wheel motion state with the risk threshold includes: Extract the maximum tire force utilization rate and maximum slip rate of each wheel during the prediction period; The maximum tire force utilization rate is compared with the tire force utilization rate threshold, and the maximum slip ratio is compared with the slip ratio threshold: If the maximum value of the tire force utilization rate is lower than the low-risk threshold of the tire force utilization rate, and the maximum value of the slip ratio is lower than the low-risk threshold of the slip ratio, then it is determined to be low-risk. If the maximum value of the tire force utilization rate is higher than the high-risk threshold of the tire force utilization rate, or if the maximum value of the slip ratio is higher than the high-risk threshold of the slip ratio, then it is determined to be high-risk. If the risk level falls between low and high, it is classified as medium risk.

[0012] Optionally, generating a combination of control commands for coordinating the steering system, drive system, and braking system based on the risk level includes: When the risk level is determined to be low, the first combination of control commands for the corresponding prevention mode is triggered. When the risk level is determined to be medium, the second combination of control instructions corresponding to the intervention mode is triggered. When the risk level is determined to be high, the third combination of control commands corresponding to the strong stability mode is triggered; The first control command combination, the second control command combination, and the third control command combination all control the coordinated operation of the steering system, the drive system, and the braking system.

[0013] Optionally, in prevention mode, the first combination of control commands includes: For the drive system, the maximum rise gradient of the drive torque is set based on the real-time road adhesion coefficient to gently limit the rate of increase of the drive torque; for the steering system, the electric power steering system is adjusted to the high road feel mode to reduce steering assistance and improve system response readiness without active angle correction; for the braking system, the pre-charge function of the electronic stability program is triggered to keep the brake lines in a low-pressure standby state. In intervention mode, the second combination of control commands includes: For the drive system, the upper limit of torque is calculated based on the real-time road surface adhesion coefficient and the torque requested by the driver is smoothed and filtered; for the steering system, stability assist compensation is activated based on the yaw rate deviation; for the braking system, low-amplitude pulse braking is triggered on the low-load side wheels. In strong stability mode, the third control command combination includes: For the drive system, the output torque is directly limited to the upper limit calculated based on the coefficient of adhesion or the slip ratio closed-loop control; for the steering system, a compensating angle or torque opposite to the driver's steering input is applied to correct the vehicle's attitude; for the braking system, independent high-pressure braking is applied to the slipping wheels and differential braking is applied to the wheels with good adhesion to generate a corrective yaw torque.

[0014] Optionally, the coordinated intervention of the vehicle through the steering system, drive system, and braking system based on the control command combination includes: Based on the aforementioned control command combination, steering sub-commands, drive sub-commands, and braking sub-commands with a unified timestamp are generated and synchronously sent to the corresponding actuators; wherein: The steering system performs yaw stability auxiliary compensation or vehicle attitude correction according to the steering sub-command; The drive system performs torque smoothing or slip ratio closed-loop tracking according to the drive sub-instruction; The braking system performs precise pressure control from pre-charge, low-amplitude pulses to independent high-pressure braking according to the braking sub-command.

[0015] According to a second aspect of the present invention, a smart collaborative anti-skid control system for new energy vehicles on icy and snowy roads is provided, comprising: The risk assessment module is configured to predict the risk level of an impending vehicle skidding based on vehicle status information and road surface information. The collaborative decision-making module is configured to generate a combination of control commands for controlling the coordinated action of the steering system, drive system and braking system based on the risk level, wherein different risk levels correspond to different combinations of control commands. The collaborative execution module is configured to coordinately intervene in the vehicle through the steering system, drive system, and braking system based on the combination of control commands.

[0016] According to a third aspect of the present invention, an electronic device is provided, including a memory and a processor, wherein the processor is used to execute a computer management program stored in the memory to implement the steps of the above-described intelligent collaborative anti-skid control method for new energy vehicles on icy and snowy roads.

[0017] According to a fourth aspect of the present invention, a computer-readable storage medium is provided, on which a computer management program is stored, wherein when the computer management program is executed by a processor, the steps of the above-described intelligent collaborative anti-skid control method for new energy vehicles on icy and snowy roads are implemented.

[0018] This invention provides a method, system, electronic device, and storage medium for intelligent collaborative anti-skid control of new energy vehicles on icy and snowy roads. It predicts wheel slippage trends in the short term by acquiring real-time vehicle status (e.g., vehicle speed, wheel speed) and road surface information (e.g., road adhesion coefficient), and determines the current risk level (low, medium, high) based on dynamically calculated risk thresholds. Subsequently, the system generates differentiated combinations of collaborative control commands according to different risk levels. For example, in low-risk situations, preventative adjustments are prioritized (e.g., limiting torque gradient, steering system pre-preparation); in medium-risk situations, active smoothing interventions are initiated (e.g., torque filtering, yaw compensation, pulse braking); and in high-risk situations, strong stability control is adopted (e.g., torque hard limiting, active steering correction, differential braking). Finally, these commands are synchronously sent to the steering, drive, and braking systems, enabling them to coordinate intervention based on a unified control objective. This invention transforms anti-skid control from traditional post-slip braking remedies to pre-slip prediction and collaborative prevention, effectively improving vehicle response speed and smoothness. By coordinating the steering, drive, and braking systems, the power interruption and jerking caused by relying solely on braking are avoided. The control potential of each actuator is fully utilized, which effectively suppresses wheel slippage, ensures vehicle stability, improves driving comfort, and reduces unnecessary braking energy loss, thus helping to extend the driving range of new energy vehicles. Attached Figure Description

[0019] Figure 1 A flowchart of an intelligent collaborative anti-skid control method for new energy vehicles on icy and snowy roads provided by the present invention; Figure 2 A schematic diagram of a method for intelligent collaborative anti-skid control of new energy vehicles on icy and snowy roads, provided for one embodiment; Figure 3 A block diagram of a smart collaborative anti-skid control system for new energy vehicles on icy and snowy roads provided by the present invention; Figure 4 A schematic diagram of a possible hardware structure of an electronic device provided by the present invention; Figure 5 This is a schematic diagram of the hardware structure of a possible computer-readable storage medium provided by the present invention. Detailed Implementation

[0020] The specific embodiments of the present invention will be described in further detail below with reference to the accompanying drawings and examples. The following examples are for illustrative purposes only and are not intended to limit the scope of the invention.

[0021] In this embodiment of the invention, when collecting, processing, and storing user personal information (such as images, behavioral characteristics, etc.), the implementation of the technical solution strictly adheres to the principles of legality, legitimacy, and necessity, as well as the core rule of "notification-consent." Specifically, before information collection, the system clearly informs the user of the purpose, method, scope, and usage rules of information collection through an interactive interface, and requires the user's active authorization and consent. The entire information processing process employs data encryption, access control, and other technical measures to ensure information security, and establishes mechanisms to facilitate users' exercise of their rights (such as querying, correcting, withdrawing consent, and deleting information). For exceptions stipulated by law (such as those necessary for fulfilling statutory duties or responding to public health emergencies), their application is strictly limited to the scope and limits authorized by law, ensuring that the technical solution does not contain any content that violates the law, social morality, or harms the public interest.

[0022] Figure 1 This invention provides a flowchart of an intelligent collaborative anti-skid control method for new energy vehicles on icy and snowy roads. Figure 2 This is a schematic diagram of a method for intelligent collaborative anti-skid control of new energy vehicles on icy and snowy roads in a specific implementation scenario, combined with... Figure 1 and Figure 2 As shown, the method includes steps S1 to S3: S1 predicts the risk level of an impending vehicle skidding based on vehicle status information and road surface information.

[0023] In this step, road surface images and point cloud data are first acquired using sensors such as cameras and radar. Feature extraction and classification models are then used to identify low-adhesion road surface types, such as ice and snow, and to estimate the prior adhesion coefficient. Simultaneously, tire force is inferred in real-time based on vehicle dynamics signals such as wheel speed and acceleration, allowing for online identification of the current road adhesion coefficient. Subsequently, the prior information perceived visually is weighted and fused with the real-time dynamic estimates to obtain a more reliable fused adhesion coefficient. Finally, using this coefficient and the current vehicle state as input, a simplified vehicle dynamics model is used for forward simulation to predict the slip rate and sideslip angle of each wheel in the near future. By comparing this prediction with dynamic thresholds, low, medium, and high risk levels are quantified. By predicting slippage risk in advance, anti-skid control shifts from passive remediation to proactive prevention, solving the problem of lag in traditional systems.

[0024] S2, based on the risk level, generate a combination of control commands for controlling the coordinated operation of the steering system, drive system and braking system, wherein different risk levels correspond to different combinations of control commands.

[0025] This step selects one of three preset control modes based on the risk level obtained in step S1. For example, if the risk is low, the system enters the prevention mode, with instructions including: limiting the rate of increase of drive torque, adjusting the power steering to a low gear to increase road feel, and pre-emptively establishing low-pressure standby in the braking system. If the risk is medium, the system enters the intervention mode, with instructions including: calculating a safe torque limit and smoothing the driver's request, activating the steering system with a small steering angle to assist in stabilizing the vehicle, and applying slight pulse braking to the low-loaded wheels. If the risk is high, the system enters the strong stability mode, with instructions including: strictly limiting drive torque or directly controlling the slip ratio, applying a reverse compensation angle to the steering system to correct the vehicle's attitude, and applying independent high-pressure braking to the slipping wheels and using differential braking to generate stabilizing torque. This step generates control instructions specifically based on the risk level, ensuring that the system's response measures accurately match the risk level, avoiding simplistic and harsh interventions, and improving control smoothness.

[0026] S3, based on the combination of control commands, the vehicle is coordinated and intervened through the steering system, drive system and braking system.

[0027] This step combines the control commands generated in step S2 and decomposes them into specific operational commands for three subsystems: steering, drive, and braking. These commands are ensured to have a unified timestamp for synchronized execution. For example, the steering system performs stability assistance compensation or attitude correction based on the commands; the drive system smoothly limits torque or quickly tracks the target slip ratio; and the braking system precisely controls pressure, from pre-charge and low-amplitude pulses to high-pressure intervention. The vehicle system continuously monitors the vehicle's actual response (such as slip ratio and yaw rate). If the condition improves, the intervention is smoothly discontinued; if it deteriorates, a higher-level mode is immediately switched, forming a closed-loop process that dynamically adjusts based on the effect. This step, through the synchronized and coordinated actions of the steering, drive, and braking systems, comprehensively utilizes the advantages of each actuator to effectively stabilize the vehicle while reducing power interruption, improving energy efficiency and driving experience.

[0028] Understandably, given the deficiencies in the background technology, this invention proposes an intelligent collaborative anti-skid control method for new energy vehicles on icy and snowy roads. This method first predicts the risk level of wheel slippage in the near future using sensor data and the vehicle's real-time status. Then, it automatically selects different combinations of control commands based on different risk levels, issuing specific operational instructions to the steering, drive, and braking systems respectively. Finally, these three systems coordinate and act synchronously based on a unified command, achieving early or initial collaborative intervention. This method transforms anti-skid control from post-slip braking remediation to proactive prevention before slippage. By collaboratively utilizing steering adjustment, fine torque control, and braking assistance, it effectively reduces the abruptness of system intervention, improving driving smoothness and reducing energy consumption while ensuring vehicle stability.

[0029] Based on the above technical solution, this embodiment can be further improved as follows.

[0030] In one possible implementation, step S1 includes sub-steps S101 to S103.

[0031] S101, based on the road surface information and vehicle state information, predict the wheel motion state in the future time period through a vehicle dynamics model; wherein, the road surface information includes the road surface adhesion coefficient.

[0032] More specifically, including: (1) Under the driving conditions on icy and snowy roads, the real-time road adhesion coefficient is calculated based on multi-source environmental perception and information fusion, combined with real-time vehicle status information. The real-time road adhesion coefficient, current vehicle speed, steering wheel angle and driver-requested torque are used as inputs and input into the vehicle dynamics model. (2) Using the current vehicle state as the initial value, perform forward simulation calculations on the vehicle dynamics model to predict the slip ratio and sideslip angle of each wheel within a set future time period.

[0033] For example, in this embodiment, the system simultaneously acquires timestamp-aligned image frames (I_frame) and radar point clouds (P_cloud) using a front-facing visual camera and a forward-facing millimeter-wave radar. First, distortion correction, noise reduction, and extraction of the region of interest (ROI) are performed on the image frames (I_frame), while ground segmentation is performed on the radar point clouds (P_cloud) to obtain the ground point cloud (P_ground).

[0034] Subsequently, multimodal feature extraction is performed: statistical features of saturation (S) and brightness (L) in the HSL color space are extracted from the ROI image, and texture features (such as entropy) based on the gray-level co-occurrence matrix (GLCM) are calculated; the average radar cross section (RCS) value and vertical height variance are calculated from the ground point cloud.

[0035] Next, these visual and radar features are combined into a feature vector and input into a pre-trained Support Vector Machine (SVM) classification model. This model outputs structured road prior information (Info_prior), including: 1) Road surface type label (R_type), for example, DRY, WET, SNOW, ICE. In this embodiment, the road surface type label is identified as "SNOW". 2) The prior road surface adhesion coefficient estimate (μ_prior) is obtained through a preset mapping table based on the road surface type label R_type (e.g., μ_prior = 0.3 when identified as snow). 3) The confidence level (C_vis) of this visual recognition, for example, C_vis=0.8.

[0036] After obtaining prior information about the road surface, the system performs adaptive fusion calculation of the real-time road surface adhesion coefficient.

[0037] On the one hand, dynamic estimation is performed based on real-time vehicle signals (such as wheel speed ω_w, longitudinal acceleration a_x, and motor torque T_m): the vehicle reference speed (v_ref) is estimated by the non-driving wheel speeds and the slip ratio (λ) of the driving wheels is calculated; then, based on the wheel rotation dynamics equation, the longitudinal force F_x of each wheel is inversely derived. The wheel rotation dynamics equation is expressed as: I_w dω_w / dt = T_m - T_brk - F_x R, Where I_w is the moment of inertia, T_brk is the braking torque, F_x is the longitudinal force, and R is the radius.

[0038] By utilizing the characteristics of the "magic formula" in the low slip ratio region, the dynamic adhesion coefficient estimate μ_dyn and its confidence level C_dyn of the current road surface are identified in real time by fitting the relationship between the slip ratio λ of the drive wheel and the longitudinal force F_x of each wheel online.

[0039] On the other hand, a core adaptive weighted fusion algorithm is employed to fuse visual prior information with dynamic estimates. Specifically, the formula is: μ_fused = (C_vis μ_prior + C_dyn μ_dyn) / (C_vis + C_dyn) The final fused road adhesion coefficient (μ_fused) is calculated. This road adhesion coefficient algorithm is adaptive in weighting. For example, when the visual recognition confidence is high (e.g., C_vis=0.8), the result relies more on prior road information (μ_prior=0.3), enabling the system to quickly respond to abrupt changes in the road surface from dry to snowy. When the vehicle is in a condition with indistinct dynamic characteristics, such as constant speed (where the confidence C_dyn is lower), it relies more on reliable real-time dynamic adhesion coefficient estimates (μ_dyn), thereby improving the overall robustness of the system when sensors are limited or the operating conditions are complex. Finally, the road adhesion coefficient μ_fused is output as a unified and reliable indicator characterizing the current and near-term road adhesion capability, used for subsequent risk prediction.

[0040] In a real-world scenario where a vehicle is driving on a snow-covered curve, the system uses real-time calculated parameters such as the fused road adhesion coefficient μ_fused, current vehicle speed v, steering wheel angle δ, driver-requested torque T_req, and estimated vertical loads (F_z) on each wheel as input parameters. These parameters are then fed into a pre-established simplified vehicle dynamics model that couples the longitudinal, lateral, and yaw dynamics of the entire vehicle. Subsequently, using the vehicle's current yaw rate, wheel speed, and other real-time states as initial values, and assuming that the driver's control inputs (such as steering wheel angle and accelerator pedal opening) remain constant during a future prediction period (e.g., T_h = 150 milliseconds), the Euler method is used to perform forward numerical integration on the model. Through this simulation process, the model can predict the dynamic state of each wheel at every moment within this future timeframe. Specifically, the output is the curves showing the slip ratio λ(t) and sideslip angle α(t) of each wheel as a function of time, thus providing a direct and forward-looking quantitative basis for subsequent risk level assessment.

[0041] S102, dynamically calculate the risk threshold based on the road surface adhesion coefficient. More specifically, based on the real-time acquired road surface adhesion coefficient, dynamically calculate the tire force utilization rate threshold and the slip ratio threshold according to a preset relationship function, wherein the tire force utilization rate threshold includes a high-risk tire force utilization rate threshold and a low-risk tire force utilization rate threshold, and the slip ratio threshold includes a high-risk slip ratio threshold and a low-risk slip ratio threshold; The relationship function is configured such that the lower the road surface adhesion coefficient, the lower the calculated risk threshold.

[0042] In this embodiment, the system dynamically calculates the risk assessment threshold based on the real-time acquired road adhesion coefficient (μ_fused). For example, the calibration benchmark value η_base_high for the tire force utilization rate threshold is set to 1.0, and the calibration benchmark value λ_base for the slip ratio threshold is set to 0.2 (i.e., 20%). When the system detects that a vehicle has entered an icy or snowy road surface and calculates the road adhesion coefficient μ_fused = 0.3, it will calculate the dynamic threshold in real time according to a preset relational function: the high-risk threshold for tire force utilization η_thresh_high = η_base_high (0.5 + 0.5 μ_fused) = 1.0 (0.5 + 0.5 0.3) = 0.65; High-risk slip ratio threshold λ_thresh = λ_base (0.7 + 0.3 μ_fused) = 0.2 (0.7 + 0.3 0.3) = 0.158.

[0043] This calculation process clearly demonstrates the core configuration of the relationship function: due to the low road adhesion coefficient (μ_fused=0.3), the system automatically calculates a lower risk threshold (0.65 and 0.158 are significantly lower than the threshold under dry road surface), which makes the system more sensitive to the risk of skidding on low adhesion road surface, and can trigger intervention earlier, thereby improving the predictability and safety of control.

[0044] S103, based on a comparison between the predicted wheel motion state and the risk threshold, determine the risk level of impending vehicle skidding. More specifically, this includes: Extract the maximum tire force utilization rate and maximum slip rate of each wheel during the prediction period; The maximum tire force utilization rate is compared with the tire force utilization rate threshold, and the maximum slip ratio is compared with the slip ratio threshold: If the maximum value of the tire force utilization rate is lower than the low-risk threshold of the tire force utilization rate, and the maximum value of the slip ratio is lower than the low-risk threshold of the slip ratio, then it is determined to be low-risk. If the maximum value of the tire force utilization rate is higher than the high-risk threshold of the tire force utilization rate, or if the maximum value of the slip ratio is higher than the high-risk threshold of the slip ratio, then it is determined to be high-risk. If the risk level falls between low and high, it is classified as medium risk.

[0045] For example, in a real-world scenario where a vehicle is driving on an icy, winding road, the system first predicts the dynamic state of each wheel within a 150-millisecond forecast period and extracts the maximum tire force utilization rate η_max of all wheels as 0.73 and the maximum slip ratio λ_max as 0.15. Simultaneously, based on the real-time road adhesion coefficient μ_fused = 0.32, the system dynamically calculates the following thresholds: a low-risk threshold η_thresh_low for tire force utilization of 0.50, a high-risk threshold η_thresh_high for tire force utilization of 0.72, a low-risk threshold λ_thresh_low for slip ratio of 0.10, and a high-risk threshold λ_thresh_high for slip ratio of 0.16.

[0046] Subsequently, the system compares the maximum tire force utilization rate η_max and the maximum slip ratio λ_max with these four thresholds: Since η_max = 0.73 is higher than η_thresh_high = 0.72, the condition of "maximum tire force utilization rate is higher than the high-risk threshold" is met. Therefore, the system directly determines the current risk level as high risk. This risk level determination result will serve as a direct basis in subsequent steps, triggering the system to enter the corresponding strong stability control mode.

[0047] In one possible implementation, step S2 includes: (1) When the risk level is determined to be low, the first control command combination of the corresponding prevention mode is triggered; specifically, the first control command combination includes: For the drive system, the maximum rise gradient of the drive torque is set based on the real-time road adhesion coefficient to gently limit the rate of increase of the drive torque; for the steering system, the electric power steering system is adjusted to the high road feel mode to reduce steering assistance and improve system response readiness without active angle correction; for the braking system, the pre-charge function of the electronic stability program is triggered to keep the brake lines in a low-pressure standby state.

[0048] For example, when the system determines that the vehicle is traveling at a constant speed on a compacted snow-covered road surface and the risk level is low, the prevention mode is triggered. In this prevention mode, the first combination of control commands generated by the system is specifically executed as follows: For the drive system, based on the real-time estimated road adhesion coefficient μ_fused=0.25, the maximum gradient of the drive torque dT / dt_max is set to 50 Nm / s (e.g., by the formula dT / dt_max = k1). μ_fused = 200 Calculated at 0.25 (where k1 is the calibration coefficient), this makes the rate of increase of the driving torque smoother, avoiding sudden acceleration that could lead to slippage. On icy or snowy surfaces (where μ_fused is small), the maximum gradient of the driving torque, dT / dt_max, automatically decreases.

[0049] For the steering system, the electric power steering (EPS) system is adjusted to "high road feel" mode, which reduces the steering assist current by 20%, allowing the driver to perceive the road conditions more clearly through the steering wheel. The system itself does not apply active steering angle correction, but the internal controller prioritizes the response to the highest level, ensuring instantaneous intervention when needed.

[0050] For the braking system, a command is sent to the Electronic Stability Program (ESP) to trigger its pre-charge function, which establishes and maintains a stable pressure of about 3 bar in the lines from the master cylinder to the wheel cylinders. This causes the brake caliper friction pads to be slightly close to the brake disc, thereby reducing the braking system's response delay to the millisecond level and preparing for possible emergency intervention.

[0051] (2) When the risk level is determined to be medium, the second control instruction combination of the corresponding intervention mode is triggered; specifically, the second control instruction combination includes: For the drive system, the upper limit of torque is calculated based on the real-time road surface adhesion coefficient and the torque requested by the driver is smoothed and filtered; for the steering system, stability assist compensation is initiated based on the yaw rate deviation calculation; for the braking system, low-amplitude pulse braking is triggered on the low-load side wheels.

[0052] For example, when a vehicle accelerates slightly by pressing the accelerator in a snow-covered bend, and the system determines the risk level to be medium, the intervention mode is triggered. In this intervention mode, the second set of control commands generated by the system is executed as follows: For the drive system, based on the real-time road adhesion coefficient (μ_fused=0.30), drive axle dynamic load (F_z=4000N), and wheel radius (R=0.35m), and taking a safety factor k2=0.85, the upper limit of torque T_max = k2 is calculated. μ_fused F_z R=0.85 0.30 4000 0.35 ≈ 357 Nm, k2 is the safety factor, and in this embodiment, k2 = 0.85. Subsequently, the driver's requested torque T_req (e.g., T_req = 350 Nm) is processed by a first-order low-pass filter: T_cmd(s) = T_req(s) / (τ The filtering time constant τ is adjusted online based on the risk level and the real-time road adhesion coefficient μ_fused. The higher the risk and the slipperier the road surface, the larger the value of τ, and the smoother the output. In this embodiment, the time constant τ is set to 200ms to output a smoothly increasing torque command and avoid sudden torque changes.

[0053] For the steering system, yaw stability assist is activated. Based on the current steering wheel angle and vehicle speed, the desired yaw rate γ_des is calculated. The PD controller then calculates the compensation angle in real time based on the deviation between the desired yaw rate γ_des and the actual yaw rate γ: δ_comp = Kp (γ_des - γ) + Kd d(γ_des - γ) / dt, where Kp and Kd are the PD control coefficients, and δ_comp is the compensation angle, which is usually limited to a small range (e.g., absolute value less than 0.5°). Based on the calculated compensation angle δ_comp, the vehicle is assisted in stable steering.

[0054] For the braking system, low-frequency (2-5Hz) and low-amplitude (5-15bar) pulse braking is applied to the inner front wheel, which is under reduced load during acceleration, to generate a small corrective yaw moment to assist in stabilization and to synergistically suppress the vehicle's oversteer tendency.

[0055] (3) When the risk level is determined to be high, the third control command combination corresponding to the strong stability mode is triggered; specifically, the third control command combination includes: For the drive system, the output torque is directly limited to the upper limit calculated based on the coefficient of adhesion or the slip ratio closed-loop control; for the steering system, a compensating angle or torque opposite to the driver's steering input is applied to correct the vehicle's attitude; for the braking system, independent high-pressure braking is applied to the slipping wheels and differential braking is applied to the wheels with good adhesion to generate a corrective yaw torque.

[0056] For example, when the system detects that the maximum actual slip ratio λ_max of the outer drive wheel instantaneously reaches 25% (exceeding the 20% threshold) during vehicle acceleration out of a corner, it determines that the vehicle has entered a high-risk state and triggers a strong stability mode. At this time, the third set of control commands generated by the system is immediately executed: For the drive system, ignoring the driver's requested torque T_req of up to 400Nm, the output torque is directly limited to the upper limit T_max=280Nm calculated based on the current road surface adhesion coefficient (μ_fused=0.25), and simultaneously engages a fast closed-loop control with a target slip ratio of 10%, actively adjusting the torque to pull the slipping wheel back to the stable area.

[0057] For the steering system, direct yaw moment control is implemented in conjunction. If an oversteer tendency is detected, the electric power steering (EPS) system immediately applies a compensation angle δ_comp that is opposite to the driver's steering input. The compensation angle δ_comp can reach 1-2°, generating a stable counter-yaw moment to help correct the vehicle's attitude.

[0058] For the braking system, strong limited-slip intervention is applied to the slipping wheels with independent pressure control; simultaneously, selective differential braking is applied to the wheels with good traction, generating a significant corrective yaw moment. For example, independent high-pressure braking intervention is applied to the severely slipping outer drive wheel, with the braking pressure rapidly rising to 120 bar at a frequency of 15 Hz; at the same time, 80 bar of braking force is applied to the inner wheel with good traction. This differential braking generates a strong corrective yaw moment, which works in conjunction with the steering system to suppress vehicle fishtailing.

[0059] Through the powerful and coordinated intervention of the steering, drive, and braking systems, the tendency for the vehicle to lose control was quickly contained.

[0060] In one possible implementation, step S3 includes: Based on the aforementioned control command combination, steering sub-commands, drive sub-commands, and braking sub-commands with a unified timestamp are generated and synchronously sent to the corresponding actuators; wherein: The steering system performs yaw stability auxiliary compensation or vehicle attitude correction according to the steering sub-command; The drive system performs torque smoothing or slip ratio closed-loop tracking according to the drive sub-instruction; The braking system performs precise pressure control from pre-charge, low-amplitude pulses to independent high-pressure braking according to the braking sub-command.

[0061] For example, when the system determines that the vehicle is at a medium-risk level and decides to enter intervention mode, the central controller immediately generates a set of coordinated control instructions. This instruction set includes three sub-instructions: a yaw stability auxiliary compensation angle instruction for the steering system (δ_comp = +0.3°), a smoothed and filtered torque instruction for the drive system (T_cmd = 320Nm), and an instruction for the braking system to apply 5Hz / 10bar pulse braking to the left rear wheel.

[0062] The key is that these three sub-instructions are assigned the same precise timestamp. At the start of the next control cycle, the controllers of the steering system (EPS), drive system (MCU), and braking system (ESP) synchronously begin execution based on this unified timestamp. The EPS (Electrical Steering) system receives compensation angle δ_comp or compensation torque commands. For example, the EPS system applies a compensation angle of 0.3° based on the command. The system applies multiple protections (such as absolute value limits, rate of change limits, and torque limits superimposed on the driver's hand torque) to ensure smooth intervention and easy driver control.

[0063] The drive system (MCU) receives the smoothed torque command T_cmd or the target slip ratio. For example, the drive system (MCU) precisely controls the motor torque to 320 Nm. In intervention mode, the drive system (MCU) can use a model predictive control (MPC) framework to achieve "extreme smoothness," that is, solving an optimization problem in each control cycle to minimize the cost function J = w1 while satisfying the constraints that the torque does not exceed the maximum torque T_max and the rate of change. (T - T_req) 2 + w2 (dT / dt) 2 + w3 (Vehicle stability index), weights w1, w2, w3 are dynamically adjusted according to the risk level.

[0064] The ESP braking system performs precise pressure control, ranging from pre-charge and low-amplitude pulses to high-pressure differential braking, depending on the mode requirements. For example, it accurately builds up a 10-bar pulse pressure on the left rear wheel.

[0065] The steering system (EPS), drive system (MCU), and braking system (ESP) start from a unified time base. The control strength parameters of each subsystem (such as torque filter constant τ, compensation angle δ_comp, and braking pulse amplitude) are dynamically fine-tuned according to the real-time feedback of vehicle status (such as slip ratio and yaw rate error) to ensure that the overall control effect is smooth, coordinated, and stable.

[0066] In this embodiment, the synchronized actions based on a unified time reference ensure that the steering assist, torque adjustment, and braking force are precisely coordinated in the time domain, thereby generating a coordinated yaw moment that smoothly and effectively corrects the initial unstable trend of the vehicle, rather than the control conflicts or effect cancellation that might occur if the three systems act independently and sequentially.

[0067] In one possible implementation, such as Figure 2 As shown, after step S3, the following steps are also included: S4, dynamic evaluation and closed-loop adjustment.

[0068] Specifically, the vehicle system continuously monitors the actual vehicle state after collaborative intervention (such as actual slip ratio λ_actual and yaw rate error e_γ). Based on predefined evaluation functions (such as whether the actual slip ratio λ_actual converges to a safe range and whether the yaw rate error e_γ decreases), the control effect is evaluated, and closed-loop adjustments are made.

[0069] The closed-loop adjustment specifically includes: (1) If the assessment results show that the control effect is good and the risk indicators continue to improve, the current strategy shall be maintained; (2) If the risk is eliminated, the braking compensation will be gradually and smoothly released within a preset time (e.g., hundreds of milliseconds), the normal drive torque response will be restored, and the torque distribution intervention will be withdrawn. (3) If the risk is detected to be increasing (e.g., the actual slip ratio λ_actual continues to rise), then immediately and seamlessly switch to a higher-order control mode (e.g., switch from intervention mode to strong stability mode).

[0070] (4) Key closed-loop feedback: The actual vehicle dynamic response is used as new observation data and fed back to the risk level assessment step based on the vehicle dynamics model in step S1. This is used to update the dynamic adhesion coefficient estimate (μ_dyn) and its confidence level (C_dyn), so that the road adhesion coefficient μ_fused is recalculated in the next control cycle, the fusion weight is dynamically adjusted, and an adaptive complete closed loop is formed.

[0071] The present invention will now be illustrated with an example of a specific implementation scenario.

[0072] Implementation scenario: A vehicle enters a snow-covered curve (μ_prior=0.3) with a radius of 50m at a speed of 40km / h.

[0073] Workflow: 1. Step S1 (Prediction): (1) The camera identifies the curve as “snow” (R_type=SNOW, μ_prior=0.3, C_vis=0.8).

[0074] (2) The kinetic estimation yields μ_dyn = 0.35 and C_dyn = 0.7. After fusion calculation: μ_fused = (0.8) 0.3 +0.7 0.35) / (0.8+0.7) ≈ 0.32.

[0075] (3) The forward simulation model is based on μ_fused=0.32, and combined with the cornering speed, steering wheel angle and requested torque, predicts that the outer drive wheel will have η_max=0.73 in the future time domain. Since μ_fused=0.32, η_thresh_high(0.32)=0.72 is dynamically calculated. Because η_max=0.73>0.72, it is judged as high risk.

[0076] 2. Step S2 (Decision): Based on the high-risk level, the decision was made to enter a "strong stability mode".

[0077] 3. Step S3 (Collaborative Execution): Steering: EPS applies a 0.2° unidirectional compensation steering angle based on the yaw tracking algorithm to help stabilize the steering posture.

[0078] Drive: The MCU calculates the upper limit of torque T_max based on μ_fused=0.32, and smoothly limits the torque requested by the driver to accelerate out of the corner (e.g., 300Nm) to about T_max (e.g., 220Nm).

[0079] Braking: ESP applies a 5Hz, 8bar pulse braking to the inner rear wheel, generating a yaw moment to assist steering.

[0080] 4. Step S4 (Evaluation and Adjustment): The vehicle navigated the curve smoothly and controllably, without noticeable slippage or jerking. Once the system detected a decrease in the slip ratio, it gradually and smoothly disengaged the braking intervention, feeding back the vehicle's response data during this process to update the state estimate for the next moment.

[0081] Figure 3 A structural diagram of an intelligent collaborative anti-skid control system for new energy vehicles on icy and snowy roads is provided as an embodiment of the present invention, as follows: Figure 3As shown, a new energy vehicle intelligent collaborative anti-skid control system for icy and snowy roads includes a risk assessment module, a collaborative decision-making module, and a collaborative execution module, wherein: The risk assessment module is configured to predict the risk level of an impending vehicle skidding based on vehicle status information and road surface information. The collaborative decision-making module is configured to generate a combination of control commands for controlling the coordinated action of the steering system, drive system and braking system based on the risk level, wherein different risk levels correspond to different combinations of control commands. The collaborative execution module is configured to coordinately intervene in the vehicle through the steering system, drive system, and braking system based on the combination of control commands.

[0082] It is understood that the intelligent collaborative anti-skid control system for new energy vehicles on icy and snowy roads provided by the present invention corresponds to the intelligent collaborative anti-skid control method for new energy vehicles on icy and snowy roads provided in the foregoing embodiments. The relevant technical features of the intelligent collaborative anti-skid control system for new energy vehicles on icy and snowy roads can be referred to the relevant technical features of the intelligent collaborative anti-skid control method for new energy vehicles on icy and snowy roads, and will not be repeated here.

[0083] Please see Figure 4 , Figure 4 A schematic diagram illustrating an embodiment of the electronic device provided in this invention. For example... Figure 4 As shown, this embodiment of the invention provides an electronic device 400, including a memory 410, a processor 420, and a computer program 411 stored in the memory 410 and executable on the processor 420. When the processor 420 executes the computer program 411, it performs the following steps: Based on vehicle status information and road surface information, predict the risk level of the vehicle skidding. Based on the risk level, a combination of control commands is generated to control the coordinated operation of the steering system, drive system and braking system, wherein different risk levels correspond to different combinations of control commands. Based on the combination of control commands, the vehicle is coordinated and intervened through the steering system, drive system and braking system.

[0084] Please see Figure 5 , Figure 5 This is a schematic diagram illustrating an embodiment of a computer-readable storage medium provided by the present invention. (See diagram below.) Figure 5 As shown, this embodiment provides a computer-readable storage medium 500 on which a computer program 411 is stored. When the computer program 411 is executed by a processor, it performs the following steps: Based on vehicle status information and road surface information, predict the risk level of the vehicle skidding. Based on the risk level, a combination of control commands is generated to control the coordinated operation of the steering system, drive system and braking system, wherein different risk levels correspond to different combinations of control commands. Based on the combination of control commands, the vehicle is coordinated and intervened through the steering system, drive system and braking system.

[0085] This invention provides a method, system, electronic device, and storage medium for intelligent collaborative anti-skid control of new energy vehicles on icy and snowy roads. Through forward simulation prediction and dynamic risk thresholds based on real-time road adhesion coefficients, it achieves a fundamental shift from post-skid braking remediation to pre-skid prediction and prevention, significantly improving vehicle system response speed and solving the core problem of lag in traditional systems. Secondly, by employing collaborative control modes for different risk levels (such as a prevention mode limiting torque gradients and an intervention mode performing torque smoothing filtering and pulse braking), it transforms the previously simple and crude braking intervention into a refined collaborative intervention involving the steering, drive, and braking systems. This effectively avoids power interruption and vehicle jerking, greatly improving driving smoothness. Furthermore, by reducing excessive reliance on the braking system and relying more on precise control of drive torque and minor steering compensation to maintain stability, it reduces the waste of converting kinetic energy into heat energy, which is beneficial to the energy-saving requirements of new energy vehicles. Finally, synchronous issuance of instructions based on a unified timestamp ensures the time consistency of the actions of the three subsystems, avoiding control friction caused by execution delays, resulting in a more coordinated and stable overall control effect.

[0086] It should be noted that the descriptions of each embodiment in the above embodiments have different focuses. For parts that are not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0087] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0088] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0089] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0090] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0091] Although preferred embodiments of the invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including both the preferred embodiments and all changes and modifications falling within the scope of the invention.

[0092] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. A method for intelligent collaborative anti-skid control of new energy vehicles on icy and snowy roads, characterized in that, include: Based on vehicle status information and road surface information, predict the risk level of the vehicle skidding. Based on the risk level, a combination of control commands is generated to control the coordinated operation of the steering system, drive system and braking system, wherein different risk levels correspond to different combinations of control commands. Based on the combination of control commands, the vehicle is coordinated and intervened through the steering system, drive system and braking system.

2. The intelligent collaborative anti-skid control method for new energy vehicles on icy and snowy roads according to claim 1, characterized in that, The method of predicting the risk level of an impending vehicle skidding based on vehicle status information and road surface information includes: Based on the road surface information and vehicle status information, the wheel motion state in future time periods is predicted through a vehicle dynamics model; wherein, the road surface information includes the road surface adhesion coefficient; The risk threshold is dynamically calculated based on the road surface adhesion coefficient. The risk level of impending vehicle skidding is determined by comparing the predicted wheel motion state with the risk threshold.

3. The intelligent collaborative anti-skid control method for new energy vehicles on icy and snowy roads according to claim 2, characterized in that, The method of predicting wheel motion state in future time periods based on the road surface information and vehicle state information using a vehicle dynamics model includes: When driving on icy and snowy roads, the real-time road adhesion coefficient, current vehicle speed, steering wheel angle and driver-requested torque are used as inputs into the vehicle dynamics model. Using the current vehicle state as the initial value, a forward simulation calculation is performed on the vehicle dynamics model to predict the slip ratio and sideslip angle of each wheel within a set future time period.

4. A method for intelligent collaborative anti-skid control of new energy vehicles on icy and snowy roads according to claim 2 or 3, characterized in that, The dynamic calculation of the risk threshold based on the road surface adhesion coefficient includes: Based on the real-time acquired road adhesion coefficient, the tire force utilization rate threshold and the slip rate threshold are dynamically calculated according to a preset relationship function. The tire force utilization rate threshold includes a high-risk tire force utilization rate threshold and a low-risk tire force utilization rate threshold, and the slip rate threshold includes a high-risk slip rate threshold and a low-risk slip rate threshold. The relationship function is configured such that the lower the road surface adhesion coefficient, the lower the calculated risk threshold.

5. The intelligent collaborative anti-skid control method for new energy vehicles on icy and snowy roads according to claim 4, characterized in that, The step of determining the risk level of impending vehicle skidding by comparing the predicted wheel motion state with the risk threshold includes: Extract the maximum tire force utilization rate and maximum slip rate of each wheel during the prediction period; The maximum tire force utilization rate is compared with the tire force utilization rate threshold, and the maximum slip ratio is compared with the slip ratio threshold: If the maximum value of the tire force utilization rate is lower than the low-risk threshold of the tire force utilization rate, and the maximum value of the slip ratio is lower than the low-risk threshold of the slip ratio, then it is determined to be low-risk. If the maximum value of the tire force utilization rate is higher than the high-risk threshold of the tire force utilization rate, or if the maximum value of the slip ratio is higher than the high-risk threshold of the slip ratio, then it is determined to be high-risk. If the risk level falls between low and high, it is classified as medium risk.

6. The intelligent collaborative anti-skid control method for new energy vehicles on icy and snowy roads according to claim 1, characterized in that, The step of generating a combination of control commands for coordinating the steering system, drive system, and braking system based on the risk level includes: When the risk level is determined to be low, the first combination of control commands for the corresponding prevention mode is triggered. When the risk level is determined to be medium, the second combination of control instructions corresponding to the intervention mode is triggered. When the risk level is determined to be high, the third combination of control commands corresponding to the strong stability mode is triggered; The first control command combination, the second control command combination, and the third control command combination all control the coordinated operation of the steering system, the drive system, and the braking system.

7. The intelligent collaborative anti-skid control method for new energy vehicles on icy and snowy roads according to claim 6, characterized in that, In prevention mode, the first combination of control commands includes: For the drive system, the maximum rise gradient of the drive torque is set based on the real-time road adhesion coefficient to gently limit the rate of increase of the drive torque; for the steering system, the electric power steering system is adjusted to the high road feel mode to reduce steering assistance and improve system response readiness without active angle correction; for the braking system, the pre-charge function of the electronic stability program is triggered to keep the brake lines in a low-pressure standby state. In intervention mode, the second combination of control commands includes: For the drive system, the upper limit of torque is calculated based on the real-time road surface adhesion coefficient and the torque requested by the driver is smoothed and filtered; for the steering system, stability assist compensation is activated based on the yaw rate deviation; for the braking system, low-amplitude pulse braking is triggered on the low-load side wheels. In strong stability mode, the third control command combination includes: For the drive system, the output torque is directly limited to the upper limit calculated based on the coefficient of adhesion or the slip ratio closed-loop control; for the steering system, a compensating angle or torque opposite to the driver's steering input is applied to correct the vehicle's attitude; for the braking system, independent high-pressure braking is applied to the slipping wheels and differential braking is applied to the wheels with good adhesion to generate a corrective yaw torque.

8. A method for intelligent collaborative anti-skid control of new energy vehicles on icy and snowy roads according to claim 6 or 7, characterized in that, The coordinated intervention of the vehicle through the steering system, drive system, and braking system based on the control command combination includes: Based on the aforementioned control command combination, steering sub-commands, drive sub-commands, and braking sub-commands with a unified timestamp are generated and synchronously sent to the corresponding actuators; wherein: The steering system performs yaw stability auxiliary compensation or vehicle attitude correction according to the steering sub-command; The drive system performs torque smoothing or slip ratio closed-loop tracking according to the drive sub-instruction; The braking system performs precise pressure control from pre-charge, low-amplitude pulses to independent high-pressure braking according to the braking sub-command.

9. A smart collaborative anti-skid control system for new energy vehicles on icy and snowy roads, characterized in that, include: The risk assessment module is configured to predict the risk level of an impending vehicle skidding based on vehicle status information and road surface information. The collaborative decision-making module is configured to generate a combination of control commands for controlling the coordinated action of the steering system, drive system and braking system based on the risk level, wherein different risk levels correspond to different combinations of control commands. The collaborative execution module is configured to coordinately intervene in the vehicle through the steering system, drive system, and braking system based on the combination of control commands.

10. An electronic device, characterized in that, The system includes a memory and a processor, wherein the processor is used to execute computer management programs stored in the memory to implement the steps of the intelligent collaborative anti-skid control method for new energy vehicles on icy and snowy roads as described in any one of claims 1-8.

Images