Vehicle cruise control method and device, vehicle-mounted computing equipment and vehicle

Abstract

The invention relates to a vehicle cruise control method and device, vehicle-mounted computing equipment and a vehicle, relates to the technical field of intelligent driving, and can improve the driving safety and stability of the vehicle under ice and snow weather conditions. The method comprises the following steps: predicting a future road surface state of a driving road surface of a vehicle according to meteorological data and road surface state information; under the condition that the future road surface state is the ice and snow road surface state, actual friction information of the driving road surface is obtained; determining a target driving state of the vehicle according to the actual friction information and a vehicle cruise condition, controlling the driving of the vehicle according to the target driving state, and obtaining an actual driving state in the driving process; and according to the actual driving state and a braking compensation strategy corresponding to the ice and snow pavement state, braking control information is determined, and driving of the vehicle is adjusted according to the braking control information.

Description

Technical Field

[0001] The present application relates to the field of intelligent driving technology, and in particular to a vehicle cruise control method, apparatus, on-board computing device, vehicle, computer-readable storage medium, and computer program product. Background Art

[0002] With the development of intelligent driving technology, vehicles can perceive the driving environment through on-board sensors and improve braking stability on conventional roads.

[0003] However, for vehicle driving in icy and snowy weather, traditional solutions have difficulty in performing adaptive vehicle control in severe icy and snowy weather, and there is a risk of low stability and safety. Summary of the Invention

[0004] Based on this, it is necessary to provide a vehicle cruise control method, apparatus, on-board computing device, vehicle, computer-readable storage medium and computer program product to address the above technical issues.

[0005] In a first aspect, the present application provides a vehicle cruise control method, comprising:

[0006] Predict the future road conditions of the vehicle's driving surface based on meteorological data and road condition information;

[0007] When the future road surface state is an icy or snowy road surface state, obtaining actual friction information of the driving road surface;

[0008] determining a target driving state of the vehicle based on the actual friction information and a vehicle cruising condition, controlling the driving of the vehicle based on the target driving state, and obtaining an actual driving state during the driving process;

[0009] Braking control information is determined according to the actual driving state and the braking compensation strategy corresponding to the icy and snowy road state, and the driving of the vehicle is adjusted according to the braking control information.

[0010] In one embodiment, the vehicle cruising condition includes a desired following state;

[0011] Determining the target driving state of the vehicle according to the actual friction information and the vehicle cruising condition includes:

[0012] Determining the acceleration coefficient in the dynamic model based on the actual friction information to obtain a target dynamic model; the dynamic model represents the vehicle following state at the current moment and is obtained by adjusting the vehicle following state at the previous moment based on the acceleration at the previous moment;

[0013] According to the target dynamics model and the solution target, the target following state and target acceleration of the vehicle are determined to obtain a target driving state; the solution target is to make the target following state meet the expected following state.

[0014] In one embodiment, determining the target following state and target acceleration of the vehicle according to the target dynamics model and the solution target includes:

[0015] Obtaining an objective function for the solution target; the objective function comprising a first error term determined based on a following vehicle state error at each moment in a prediction time domain, a second error term determined based on an acceleration error at each of the moments, and a third error term determined based on a following vehicle state error at an end moment of the prediction time domain; in the objective function under the icy or snowy road condition, a weight of at least one of the first error term, the second error term, and the third error term is greater than a weight of a corresponding error term in the objective function under the normal road condition, and the prediction time domain in the objective function under the icy or snowy road condition is smaller than the prediction time domain in the objective function under the normal road condition;

[0016] A target following state and a target acceleration of the vehicle are determined according to the objective function and the target dynamics model.

[0017] In one embodiment, determining the braking control information according to the braking compensation strategy corresponding to the actual driving state and the icy and snowy road state includes:

[0018] Determining a first proportional coefficient, a first integral coefficient, and a first differential coefficient based on a compensation strategy corresponding to the icy and snowy road condition; the first proportional coefficient is smaller than the second proportional coefficient, and / or the first integral coefficient is smaller than the second integral coefficient, and / or the first differential coefficient is smaller than the second differential coefficient; the second proportional coefficient, the second integral coefficient, and the second differential coefficient are coefficients used under normal road conditions;

[0019] The error between the actual driving state and the target driving state is obtained, and braking control information is determined according to the error and the first proportional coefficient, the integral result of the error and the first integral coefficient, the differential result of the error and the first differential coefficient.

[0020] In one embodiment, the vehicle cruising condition is determined by the following steps:

[0021] adjusting a pre-acquired first collision time corresponding to a normal road surface state according to the actual friction information to obtain a second collision time;

[0022] determining a preview distance according to the second collision time;

[0023] determining a predicted travel distance of the vehicle when it stops based on the actual friction information;

[0024] The vehicle cruising condition is determined according to the second collision time, the preview distance and the predicted travel distance.

[0025] In one embodiment, obtaining actual friction information of the driving road surface includes:

[0026] Obtaining wheel speed information collected by a wheel speed sensor of the vehicle and a road surface image captured by an onboard camera;

[0027] Inputting the wheel speed information and the road surface image into a trained adhesion coefficient determination model to obtain an adhesion coefficient prediction result output by the adhesion coefficient determination model;

[0028] According to the adhesion coefficient prediction result, real-time friction information of the driving road surface is determined.

[0029] In one embodiment, predicting the future road condition of the road on which the vehicle is traveling based on meteorological data and road condition information includes:

[0030] Inputting meteorological data provided by the meteorological service end into a trained meteorological trend prediction model to obtain a weather forecast result within a preset time in the future outputted by the meteorological trend prediction model;

[0031] Determining icing possibility information of the road surface on which the vehicle is traveling based on first sensor data acquired by a road sensor for monitoring road conditions and second sensor data acquired by an on-board sensor;

[0032] A future road surface condition of the driving road surface is predicted based on the weather forecast result and the icing possibility information.

[0033] In a second aspect, the present application further provides a vehicle cruise control device, comprising:

[0034] A road surface condition recognition module is used to predict the future road surface condition of the vehicle based on meteorological data and road surface condition information;

[0035] a friction information acquisition module, configured to acquire actual friction information of the driving road surface when the future road surface state is an icy or snowy road surface state;

[0036] an information processing module, configured to determine a target driving state of the vehicle based on the actual friction information and a vehicle cruising condition, control the driving of the vehicle based on the target driving state, and obtain an actual driving state during the driving process;

[0037] The braking module is used to determine braking control information according to the actual driving state and the braking compensation strategy corresponding to the icy and snowy road state, and adjust the driving of the vehicle according to the braking control information.

[0038] In a third aspect, the present application further provides a vehicle-mounted computing device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the vehicle cruise control method as described above when executing the computer program.

[0039] In a fourth aspect, the present application also provides a vehicle, which includes the on-board computing device as described above.

[0040] In a fifth aspect, the present application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the vehicle cruise control method as described in any one of the above items.

[0041] In a sixth aspect, the present application also provides a computer program product, comprising a computer program, which, when executed by a processor, implements the steps of the vehicle cruise control method as described in any one of the above items.

[0042] The above-described vehicle cruise control method, apparatus, on-board computing device, vehicle, computer-readable storage medium, and computer program product can predict the future road surface condition of the vehicle based on meteorological data and road surface condition information. If the future road surface condition is icy or snowy, actual friction information of the road surface can be obtained. Based on the actual friction information and the vehicle's cruise conditions, a target driving state for the vehicle can be determined. The vehicle's driving can then be controlled based on the target driving state. The actual driving state during driving can be obtained, and braking control information can be determined based on a braking compensation strategy corresponding to the actual driving state and the icy or snowy road surface condition. The vehicle's driving can then be adjusted based on the braking control information. In this embodiment, on the one hand, the onset of icy or snowy weather can be predicted in advance using multi-source data and triggered to adjust the vehicle control strategy in advance, thereby timely obtaining actual friction information of the road surface. On the other hand, under the special operating condition of icy or snowy roads, a target driving state that matches the current vehicle and road conditions can be obtained based on the vehicle's significantly changing actual dynamic characteristics, enabling accurate control decisions under icy or snowy road conditions. Furthermore, by generating braking control information based on the braking compensation strategy corresponding to the icy or snowy road surface condition, the vehicle's stability and safety can be effectively improved during braking on icy or snowy roads, thereby enhancing the vehicle's driving stability and safety in icy or snowy weather. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following briefly introduces the drawings required for use in the embodiments of the present application or related technical descriptions. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying any creative work.

[0044] Figure 1 1 is a flow chart of a vehicle cruise control method according to an embodiment;

[0045] Figure 2 A schematic flow chart of a step of obtaining a future road surface state in one embodiment;

[0046] Figure 3 is a flow chart of a vehicle cruise control method according to another embodiment;

[0047] Figure 4 is a structural block diagram of a vehicle cruise control device in one embodiment;

[0048] Figure 5 The figure is a diagram of the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0049] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0050] It should be noted that the terms "first" and "second" used in this application can be used to describe various objects, but these objects are not limited by these terms. These terms are only used to distinguish the first object from the second object. The terms "including" and "having" used in this application and any variations thereof are intended to cover non-exclusive inclusions. The term "plurality" used in this application refers to two or more. The term "and / or" used in this application refers to one of the solutions or any combination of multiple solutions.

[0051] In one embodiment, Figure 1As shown, a vehicle cruise control method is provided. This embodiment uses the method as an example of an onboard computing device, where the onboard computing device is a device with computing capabilities installed on a vehicle. It is understood that the method can also be applied to a system including an onboard computing device and a server, and implemented through the interaction between the onboard computing device and the server. In some embodiments, while driving a vehicle, a user can enable intelligent driving mode. In intelligent driving mode, the vehicle cruise control method provided in this application can be used to control the vehicle, where the vehicle can be referred to as the host vehicle.

[0052] In this embodiment, the method includes the following steps:

[0053] Step S101 : predicting the future road condition of the vehicle's driving road based on meteorological data and road condition information.

[0054] The meteorological data may be quantitative or qualitative information related to weather phenomena obtained and / or analyzed using meteorological observation equipment. In some embodiments, the meteorological data may be obtained through one or more of meteorological satellites, ground observation stations, and high-altitude observations.

[0055] The road surface condition information may be information reflecting the physical properties and usage conditions of the road surface. In some exemplary embodiments, the road surface condition information may be obtained by roadside sensors and / or vehicle-mounted sensing equipment for monitoring the road surface condition.

[0056] In practice, different weather conditions can affect the state of the road surface on which the vehicle is traveling. For example, sunny weather creates dry roads, making the vehicle highly maneuverable. However, snowy weather can lead to slippery and icy roads, increasing driving risks. Therefore, in this step, the future state of the road surface on which the vehicle is traveling can be predicted based on pre-acquired meteorological data and actual road surface condition information.

[0057] Step S102 , when the future road surface state is an icy or snowy road surface state, actual friction information of the driving road surface is obtained.

[0058] The icy and snowy road surface state may be a state where there is snow or ice on the road surface, such as snow accumulation on the road caused by snowfall or ice on the road surface caused by low temperature.

[0059] In this embodiment, adaptive control algorithms can be designed in advance for normal road conditions and icy and snowy road conditions respectively. That is, different control algorithms can be used to control the vehicle driving mode under different road conditions to improve the performance and adaptability of the vehicle control system under different weather conditions.

[0060] Specifically, if the future road surface state is a normal road surface state, control can be performed based on the control algorithm corresponding to the normal road surface state; if the future road surface state is an icy or snowy road surface state, then compared with the relatively stable friction force of a normal road surface, the friction force of an icy or snowy road surface may change dynamically, increasing the uncertainty factor. In this regard, the actual friction information of the driving road surface can be obtained in this step, wherein the actual friction information is a parameter or information reflecting the actual friction conditions between the vehicle tires and the driving road surface. Subsequently, the vehicle control method can be adjusted in a timely manner according to the actual friction information, which helps to adapt to the complex road conditions in icy and snowy weather.

[0061] Step S103 , determining a target driving state of the vehicle based on actual friction information and vehicle cruising conditions, controlling the vehicle's driving based on the target driving state, and acquiring the actual driving state during the driving process.

[0062] In practical applications, after obtaining the actual friction information, the target driving state of the vehicle can be determined based on the predetermined vehicle cruising conditions. The target driving state can be understood as the vehicle state calculated based on the control algorithm corresponding to the icy and snowy road conditions. In some examples, the target driving state may include one or more of the following: the target driving speed of the vehicle, the target following distance between the vehicle and the vehicle in front, and the target acceleration of the vehicle.

[0063] After obtaining the target driving state, the vehicle can be controlled accordingly, and the actual driving condition of the vehicle can be monitored to obtain the actual driving state of the vehicle during driving. The actual driving state can be understood as the actual driving state of the vehicle.

[0064] Step S104 : determining braking control information according to the actual driving state and the braking compensation strategy corresponding to the icy and snowy road state, and adjusting the driving of the vehicle according to the braking control information.

[0065] In specific implementation, due to the influence of one or more factors, there may be a difference between the actual driving state of the vehicle and the calculated target driving state to be controlled to achieve. For example, the calculated target driving speed is A, but after adjusting the speed according to the target driving speed A, the actual driving speed of the vehicle is B, which is different from the target driving speed A. At this time, it is often necessary to apply corresponding braking compensation to the vehicle. Among them, braking compensation can be understood as dynamically adjusting the braking force distribution to compensate for the deviation between the actual driving state and the target driving state caused by road friction, load changes or system characteristics.

[0066] Related technologies typically use a single brake compensation strategy to address various road conditions. However, on icy and snowy roads, road friction decreases significantly, making wheels susceptible to slipping. This single brake compensation strategy often reduces vehicle stability and safety during braking on icy and snowy roads. To address this, this embodiment pre-designs different brake compensation strategies for both normal and icy road conditions, improving braking control stability and accuracy in both conditions.

[0067] Furthermore, when there is a difference between the actual driving state and the target driving state, the braking control information can be determined based on the braking compensation strategy corresponding to the actual driving state and the icy and snowy road condition, and then corresponding braking processing can be performed based on the braking control information to adjust the vehicle driving.

[0068] Among them, the braking control information can be a set of instructions generated based on the braking compensation strategy and used to adjust the working state of the braking system. The braking control information can directly act on the corresponding braking actuator (such as one or more of the brake master cylinder, wheel cylinder, hydraulic regulator, etc.) to achieve precise control of parameters such as braking torque, braking pressure, and braking force distribution of each wheel, ensuring the braking safety and stability of the vehicle under different working conditions.

[0069] In the above-mentioned vehicle cruise control method, the future road surface condition of the vehicle's driving surface can be predicted based on meteorological data and road surface condition information. If the future road surface condition is icy or snowy, actual friction information of the driving surface can be obtained. Based on the actual friction information and the vehicle's cruise conditions, a target driving state for the vehicle can be determined. The vehicle's driving can then be controlled based on the target driving state. The actual driving state during driving is obtained, and braking control information is determined based on a braking compensation strategy corresponding to the actual driving state and the icy or snowy road surface condition. The vehicle's driving can then be adjusted based on the braking control information. This embodiment, on the one hand, can utilize multi-source data to predict the onset of icy or snowy weather in advance and trigger vehicle control strategy adjustments in advance, thereby timely obtaining actual friction information of the driving surface. On the other hand, under the special operating conditions of icy or snowy roads, a target driving state that matches the current vehicle and road conditions can be determined based on the significantly changing actual vehicle dynamic characteristics (e.g., friction between the vehicle's tires and the driving surface), enabling precise control decisions under icy or snowy road conditions. Furthermore, by generating braking control information based on the braking compensation strategy corresponding to the icy or snowy road surface condition, the vehicle's stability and safety during braking on icy or snowy roads can be effectively improved, thereby enhancing the vehicle's driving stability and safety in icy or snowy conditions.

[0070] In an exemplary embodiment, the vehicle cruising condition may include a desired following state. For example, the desired following state may include a desired driving speed and a safe following distance.

[0071] In step S103, the target driving state of the vehicle is determined according to the actual friction information and the vehicle cruising condition, which may include the following steps:

[0072] Based on the actual friction information, the acceleration coefficient in the dynamic model is determined to obtain the target dynamic model; the dynamic model represents the following state at the current moment, and is obtained by adjusting the following state at the previous moment according to the acceleration at the previous moment; based on the target dynamic model and the solution target, the target following state and target acceleration of the vehicle are determined to obtain the target driving state; the solution target is to make the target following state meet the expected following state.

[0073] In a specific implementation, a dynamic model of the vehicle during driving can be constructed. The dynamic model can characterize the following state of the vehicle at the current moment. It is obtained by adjusting the following state at the previous moment based on the acceleration at the previous moment. The following state can include driving speed and following distance.

[0074] For example, for normal road conditions under normal weather conditions, a simplified linear time-invariant vehicle dynamics model can be used, and the state variables corresponding to the following vehicle state are , where v is the vehicle's speed, s is the distance between the vehicle and the preceding vehicle, and the control variable , a is the acceleration of the vehicle, then the vehicle dynamics model corresponding to the normal road condition can be expressed as a discrete time state space equation, as shown below:

[0075]

[0076] in, is the following vehicle status at the current moment, is the following vehicle status at the previous moment, is the acceleration at the previous moment, i.e. the control variable; and for and The corresponding coefficients can use preset values. In one example, , is the time interval between two adjacent moments, which can be .

[0077] For the icy and snowy road conditions in icy and snowy weather, the impact of the reduced road friction coefficient can be considered to construct a vehicle dynamics model. The dynamics model can be expressed as follows:

[0078]

[0079] in, ,in, is the actual friction information.

[0080] Then, after obtaining the actual friction information, the acceleration coefficient in the dynamic model can be updated according to the actual friction information, that is, the coefficient corresponding to the control variable can be determined. , thereby obtaining the target dynamic model of the vehicle corresponding to the current actual friction information. For example, if the actual friction information currently calculated is 0.2, the coefficient can be updated accordingly in .

[0081] Then, the target dynamic model currently determined and the solution target determined by the desired following state can be combined to perform state solution based on the Model Predictive Control (MPC) algorithm to determine the target following state and target acceleration of the vehicle, and then determine the target following state and target acceleration as the target driving state. The solution target is to make the target following state meet the desired following state. Specifically, the target following state can include a target driving speed and a target following distance. The solution target can be a safe following distance when the target following distance meets the desired following state. When the target driving speed is reduced, the target driving speed is reduced to the expected driving speed in the expected following state. The difference between the target speed and the expected speed is made as close as possible to the target speed. .

[0082] In this embodiment, the acceleration coefficient in the dynamic model is determined according to the actual friction information, and the target dynamic model is updated. The dynamic model can be adjusted accordingly based on the characteristics of the actual nonlinear change of friction, so that the model can better characterize the complex nonlinear dynamic characteristics of the vehicle under special working conditions such as icy and snowy roads, so that the decision-making and control of vehicle driving are more adaptable to changes in vehicle dynamic characteristics. Compared with traditional linear control algorithms that are difficult to cope with complex nonlinear vehicle dynamic characteristics, this embodiment designs different predictive control algorithm models for normal weather and icy and snowy weather, and configures different model parameters for them, which helps to achieve more accurate control decisions and improve the accuracy and safety of vehicle control on icy and snowy roads.

[0083] In one embodiment, determining a target following state and a target acceleration of a vehicle based on a target dynamics model and a solution target may include the following steps:

[0084] Obtain an objective function for solving the target; determine the target following state and target acceleration of the vehicle based on the objective function and the target dynamics model.

[0085] Among them, the objective function includes a first error term determined according to the following vehicle state error at each moment in the prediction time domain, a second error term determined according to the acceleration error at each moment, and a third error term determined according to the following vehicle state error at the end moment of the prediction time domain; in the objective function under icy and snowy road conditions, the weight of at least one error term among the first error term, the second error term and the third error term is greater than the weight of the corresponding error term in the objective function under normal road conditions, and the prediction time domain in the objective function under icy and snowy road conditions is smaller than the prediction time domain in the objective function under normal road conditions.

[0086] In an exemplary embodiment, the objective function may be as follows:

[0087]

[0088] in, It can reflect the difference between the following state calculated by the dynamic model and the expected following state, and is used to determine the first error term. The first error term can be used to penalize the errors in the solved formal speed and following distance. It can reflect the difference between the acceleration calculated by the dynamic model and the expected acceleration, and can be used to determine the second error term, which can be used to penalize the acceleration change amplitude; It can reflect the difference between the following state at the terminal of the prediction time domain (also called the end point of the prediction time domain) calculated by the dynamic model and the expected following state, and can be used to determine the third error term. The third error term can be used to impose an additional penalty on the error in the terminal state of the prediction time domain, thereby enhancing the safety of the final state of the prediction time domain.

[0089] In this embodiment, different weight matrices can be set for the objective function for normal road conditions and snowy weather conditions. 、 and Among them, Q is the state weight matrix, R is the control weight matrix, and P is the terminal weight matrix. For example, the objective function corresponding to the normal road state is , where the state weight matrix , control weight matrix , the terminal weight matrix ; Objective function corresponding to ice and snow road conditions , where the state weight matrix , control weight matrix , the terminal weight matrix .

[0090] That is, when configuring the weights of the first, second, and third error terms for the objective function, the weight of at least one of the first, second, and third error terms in the objective function for icy and snowy road conditions can be greater than the weight of the corresponding error term in the objective function for normal road conditions. Thus, by increasing the weight of the first error term for icy and snowy road conditions, the penalty for deviations from the desired following state can be increased in complex and changeable icy and snowy driving environments, thereby improving the accuracy of state control at each moment. By increasing the weights of the second and / or third error terms for icy and snowy road conditions, overly aggressive speed adjustment strategies can be avoided, while simultaneously improving the proximity between the following state at the predicted time-domain endpoint and the desired following state, thereby enhancing vehicle control safety.

[0091] In addition, the prediction time domain in the objective function under icy and snowy road conditions can be smaller than the prediction time domain in the objective function under normal road conditions. For example, the prediction time domain in the objective function under icy and snowy road conditions can be 8, and the prediction time domain in the objective function under normal road conditions can be 10, thereby improving the response speed of vehicle control when driving on icy and snowy roads.

[0092] Then, the target following state and target acceleration of the vehicle can be determined based on the objective function and the target dynamics model, and then the target driving state can be solved by combining the constraint information provided by the corresponding vehicle cruising conditions. In some embodiments, different vehicle cruising conditions can be set for normal road conditions and icy and snowy road conditions. For example, in normal road conditions, the following constraint information can be provided in the vehicle cruising conditions: speed constraint , acceleration constraint , safety distance constraint On icy and snowy roads, the vehicle cruising conditions can provide the following constraint information: , acceleration constraint , safety distance constraint .

[0093] In this embodiment, the weight of at least one of the first error term, the second error term, and the third error term in the objective function under icy and snowy road conditions is set to be greater than the weight of the corresponding error term in the objective function under normal road conditions, and the prediction time domain in the objective function under icy and snowy road conditions is made smaller than the prediction time domain in the objective function under normal road conditions. This allows algorithm models and parameters that match the actual driving environment to be provided for normal weather and icy and snowy weather, respectively, and dynamically optimizes the prediction time domain to achieve more accurate control decisions.

[0094] In one embodiment, in step S104, determining the braking control information according to the braking compensation strategy corresponding to the actual driving state and the icy and snowy road conditions may include the following steps:

[0095] According to the compensation strategy corresponding to the icy and snowy road conditions, the first proportional coefficient, the first integral coefficient and the first differential coefficient are determined; the error between the actual driving state and the target driving state is obtained, and the braking control information is determined based on the error and the first proportional coefficient, the integral result of the error and the first integral coefficient, and the differential result of the error and the first differential coefficient.

[0096] Among them, the first proportional coefficient is smaller than the second proportional coefficient, and / or the first integral coefficient is smaller than the second integral coefficient, and / or the first differential coefficient is smaller than the second differential coefficient. The second proportional coefficient, the second integral coefficient and the second differential coefficient are coefficients used under normal road conditions.

[0097] Exemplarily, the error between the actual driving state and the target driving state may include one or more of the following: an error between the target driving speed and the actual driving speed, an error between the target following distance and the actual following distance, and an error between the target acceleration and the actual acceleration.

[0098] In some exemplary embodiments, the actual driving state of the vehicle can be determined according to a preset sampling frequency, and the actual driving state can be compared with the calculated target driving state. When the error between the two reaches a threshold, braking compensation is performed according to the corresponding braking compensation strategy.

[0099] In practical applications, different Proportional-Integral-Derivative control (PID) models can be constructed in advance for normal road conditions and icy and snowy road conditions to obtain PID brake compensators under different scenarios.

[0100] In one example, the proportional integral derivative control model for icy and snowy road conditions It can be as follows:

[0101]

[0102] in, is the first proportional coefficient, is the first integral coefficient, is the first differential coefficient, and e(t) is the error between the actual driving state and the target driving state.

[0103] Proportional-integral-derivative control model for normal road conditions It can be as follows:

[0104]

[0105] in, is the second proportional coefficient, is the second integral coefficient, is the second differential coefficient, is the error between the actual driving state and the target driving state.

[0106] In this embodiment, the coefficients in the proportional-integral-differential control model of the icy and snowy road conditions may have one or more of the following situations: the first proportional coefficient is smaller than the second proportional coefficient, the first integral coefficient is smaller than the second integral coefficient, and the first differential coefficient is smaller than the second differential coefficient.

[0107] Then, the corresponding integral result and differential result can be calculated according to the error, and the braking control information can be determined according to the error and the first proportional coefficient, the integral result of the error and the first integral coefficient, and the differential result of the error and the first differential coefficient.

[0108] For example, in normal weather conditions, taking speed control as an example, the target driving speed and the actual speed can be input to determine the speed error between the two, and then the proportional integral differential control model corresponding to normal weather conditions can be used. The output control signal u (i.e., brake control information) is obtained, such as throttle opening or brake pressure; in icy and snowy weather, the speed error between the target driving speed and the actual speed can be input into the proportional integral differential control model , and obtain the corresponding control signal u.

[0109] In this embodiment, a PID-based brake pressure dynamic compensator can determine brake control information, while using different PID parameters for normal weather and icy and snowy conditions to improve brake control stability and accuracy. Specifically, when braking on icy and snowy roads, this embodiment reduces the first proportional coefficient to reduce the response intensity of the brake pressure, preventing excessive tire braking and locking due to low friction coefficients, maintaining tire adhesion, and avoiding wheel lock. By reducing the integral and differential coefficients, it can reduce drastic changes in control variables caused by road signal fluctuations, avoid frequent fluctuations in brake pressure that exacerbate vehicle instability, and improve driving stability on slippery roads. Furthermore, by adaptively switching parameters based on road conditions, the brake control logic is matched to the low friction characteristics of icy and snowy roads, ensuring braking effectiveness while improving vehicle stability and extending the brake system's adaptability to complex operating conditions.

[0110] In one embodiment, before step S102, the vehicle cruising condition may be determined by the following steps:

[0111] Based on the actual friction information, the first collision time corresponding to the normal road condition obtained in advance is adjusted to obtain a second collision time; the preview distance is determined based on the second collision time; the predicted driving distance when the vehicle stops is determined based on the actual friction information; and the vehicle cruising condition is determined based on the second collision time, the preview distance and the predicted driving distance.

[0112] In related technologies, a control model with a fixed safe vehicle distance is mainly used in intelligent driving. However, this method cannot adapt to the changes in the dynamic friction coefficient of icy and snowy roads, resulting in unreasonable safety distance when driving on icy and snowy roads, increasing the risk of accidents such as rear-end collisions.

[0113] In this regard, in this embodiment, the first collision time corresponding to the normal road surface state obtained in advance can be adjusted according to the actual friction information to obtain the second collision time. In one example, the first collision time under the normal road surface state calculated according to the preset method can be obtained first. , then, the second collision time can be calculated as follows :

[0114]

[0115] in, is the friction coefficient of dry road surface, which can be set to a preset value (such as 0.8). In actual applications, different correction coefficients (e.g., 0.8 to 1.5) can be set, and the first collision time can be adjusted based on the correction coefficient and the actual friction information.

[0116] Then, a preview distance can be determined based on the second collision time. The preview distance can be understood as the horizontal distance between the forward path point observed during driving and the current position. In this embodiment, when the collision time changes based on actual friction information, the preview distance can be adjusted accordingly. This adaptive adjustment strategy for the preview distance allows for pre-planning of the vehicle's driving path.

[0117] In one example, the preview distance under normal road conditions Preview distance on icy and snowy roads , can be calculated as follows:

[0118]

[0119]

[0120] In addition, the predicted distance when the vehicle stops can be determined based on the actual friction information. This distance is also called the stopping point relative to the current position. For example, the stopping point under normal road conditions is and braking points on icy and snowy roads , can be calculated as follows:

[0121]

[0122]

[0123] in, is the current speed of the vehicle, is the acceleration due to gravity, Delay in sensor detection distance, is the braking response time, in one example It can be 0.3~0.8 seconds, is the actual friction information.

[0124] Furthermore, the vehicle cruising condition can be determined based on the second collision time, preview distance and predicted driving distance. For example, one or more of the safe following distance, upper speed limit, etc. can be updated based on the second collision time, preview distance and predicted driving distance.

[0125] In this embodiment, by determining the second collision time, preview distance and predicted driving distance when the vehicle brakes to a stop based on actual friction information, the vehicle cruising conditions can be dynamically adjusted in parameters, which helps to achieve adaptive adjustment of the vehicle cruising conditions (safe distance and safe speed). The safe distance can be adjusted according to different weather and road conditions, providing a reliable reference for decision-making and control under complex road conditions in icy and snowy weather.

[0126] In one embodiment, in step S102, obtaining actual friction information of the driving road surface may include the following steps:

[0127] The wheel speed information collected by the vehicle's wheel speed sensor and the road surface image captured by the vehicle's on-board camera are obtained; the wheel speed information and road surface image are input into a trained adhesion coefficient determination model to obtain an adhesion coefficient prediction result output by the adhesion coefficient determination model; and based on the adhesion coefficient prediction result, real-time friction information of the driving road surface is determined.

[0128] The friction between a vehicle's tires and the road surface differs between driving in snowy and icy conditions and normal weather, affecting the tire's rotational speed differently. To address this, wheel speed information collected by the vehicle's wheel speed sensors can be obtained, along with road surface images captured by the vehicle's onboard cameras.

[0129] The wheel speed information and road image can then be input into a trained adhesion coefficient determination model. The adhesion coefficient determination model can be a model trained using deep learning. For example, a convolutional neural network can be trained using deep learning to obtain an adhesion coefficient determination model, also known as an adhesion coefficient estimation network. Furthermore, the adhesion coefficient determination model can estimate the adhesion coefficient based on the wheel speed information and road image inputs, obtaining a real-time estimate of the road's adhesion coefficient and outputting it as an adhesion coefficient prediction result.

[0130] In some embodiments, the adhesion coefficient determination model can perform road surface type identification. For example, the convolutional neural network module contained therein can classify the type of the road surface on which the vehicle is currently traveling as dry, wet, snowy, and icy based on the input road surface image. By accurately judging the road surface type, the reliability of the calculated adhesion coefficient prediction result can be effectively tested, and it can be determined whether the calculated adhesion coefficient matches the currently identified road surface type.

[0131] In some embodiments, the adhesion coefficient determination model can estimate the adhesion coefficient using a recursive least squares method based on the wheel speed information provided by the wheel speed sensor. For example, the wheel speed information can include one or more types of information, such as wheel speed (e.g., angular velocity), speed change rate (e.g., acceleration or deceleration), and wheel slip rate. After calculating the adhesion coefficient, the road icing severity level can also be determined based on the adhesion coefficient. For example, the icing severity level can be classified into levels 1 to 4, corresponding to adhesion coefficients of 0.1 to 0.4, respectively. Determining the icing severity based on the adhesion coefficient can verify the accuracy of the road type determination result and provide a reference for subsequent vehicle control.

[0132] In this embodiment, wheel speed information and road surface images are input into a trained adhesion coefficient determination model to obtain an adhesion coefficient prediction result output by the adhesion coefficient determination model. Based on the adhesion coefficient prediction result, real-time friction information of the driving road surface is determined. This allows for real-time adhesion coefficient calculation using multiple sources of information, such as wheel speed information and road surface images, to ensure efficient acquisition of the resulting real-time friction information and reliable results.

[0133] In one embodiment, Figure 2 As shown, in step S101, based on meteorological data and road surface condition information, predicting the future road surface condition of the vehicle may include the following steps:

[0134] Step S201: input the meteorological data provided by the meteorological service end into the trained meteorological trend prediction model to obtain the weather forecast result within a preset time in the future output by the meteorological trend prediction model.

[0135] In practical applications, communication with a weather service can be achieved. The weather service can provide monitoring data related to weather analysis and can also analyze the monitoring data to obtain weather analysis results. The weather service can then provide the monitoring data and / or weather analysis results as weather data to the onboard computing device. Furthermore, the weather data can be input into a pre-trained weather trend prediction model. The model will then determine weather trends based on the weather data and predict weather conditions within a preset timeframe, generating a weather forecast result.

[0136] In some exemplary embodiments, a weather trend prediction model can be constructed based on a long short-term memory network (LSTM), and the weather trend prediction model can be supervised and trained using meteorological data samples associated with weather forecast result labels to obtain a trained weather trend prediction model. When the model is subsequently applied, a meteorological satellite cloud image with a preset resolution (such as 1 km) can be obtained from the meteorological service end and input into the weather trend prediction model to predict the weather conditions in the vehicle driving area in a few minutes to obtain the weather forecast results.

[0137] Step S202 , determining icing possibility information of the road surface on which the vehicle is traveling based on first sensing data acquired by a road sensor for monitoring road surface conditions and second sensing data acquired by an onboard sensor.

[0138] In another implementation, the road surface can be pre-installed with road sensors for monitoring road conditions. In some examples, the road sensors can be sensing devices installed on both sides of the road or on roadside infrastructure, known as roadside sensors. These roadside sensors can obtain road temperature and humidity information through various technical means. In this embodiment, the road sensors can communicate with an onboard computing device, allowing the onboard computing device to obtain first sensor data collected by the road sensors. The first sensor data can include temperature and / or humidity information of the road surface on which the vehicle is traveling. Simultaneously, the vehicle's own onboard sensors can obtain relevant second sensor data, such as images captured by an onboard camera, wheel speed data obtained by a wheel speed sensor, or other information related to road conditions. Based on the first and second sensor data, the likelihood of road icing can be identified, thereby obtaining icing probability information. In some embodiments, a road icing probability calculation model can be constructed, which can be automatically triggered when the temperature falls below 0°C. The road icing probability calculation model can determine the likelihood of road icing based on the first and second sensor data.

[0139] In some embodiments, a vehicle may be equipped with an external information receiver for receiving meteorological data and primary sensor data from roadside sensors. This external information receiver may support 5G V2X communication, a fusion of fifth-generation mobile communication technology (5G) and vehicle-to-everything (V2X) communications. 5G V2X communication enables high-speed, low-latency data exchange between the vehicle and multiple entities, including roads, infrastructure, pedestrians, and the cloud. The vehicle may also be equipped with a multi-beam lidar (LIDAR) with a detection range that meets a preset threshold (e.g., 200 meters) or a sufficiently fine angular resolution (e.g., 0.1°), enabling accurate perception of the vehicle's surroundings and reliable secondary sensor data. This approach allows the vehicle to obtain timely multi-source data, including meteorological data, primary sensor data, and secondary sensor data, while driving, enabling the onboard computing device to accurately and quickly identify future road conditions by combining these multi-source data.

[0140] Step S203: predicting the future road condition of the driving road based on the weather forecast result and the icing possibility information.

[0141] After obtaining weather forecast results and icing probability information, the two can be combined to predict the future road conditions of the driving road. In some embodiments, before performing weather forecasts and icing probability predictions based on meteorological data, first sensor data, and second sensor data, data alignment can be performed to reduce time synchronization errors between multiple data sources (e.g., time synchronization errors can be less than 50ms), thereby increasing the accuracy of subsequent predictions based on the fusion of multi-source data.

[0142] In some embodiments, multi-source data consistency verification can be performed through Kalman filter fusion. For example, if the weather forecast indicates that snowy weather is imminent or has already occurred, and the icing probability information indicates that the likelihood of snow or ice (e.g., ice or snow) on the road surface is greater than or equal to a threshold, the future road surface state can be determined to be snowy. If the weather forecast indicates that there will be no snowy weather in the future, or the icing probability information indicates that the likelihood of snow or ice on the road surface is less than a threshold, the future road surface state can be temporarily determined to be snowy and ice, and monitoring can continue.

[0143] Compared with traditional technologies in which environmental perception systems based only on radar or cameras cannot predict the arrival of ice and snow in advance, this embodiment can predict changes in ice and snow weather based on multi-source data by obtaining meteorological data provided by the meteorological service end, first sensor data obtained by road sensors, and second sensor data obtained by on-board sensors. It can accurately adjust vehicle control strategies in advance before severe weather is about to arrive.

[0144] In order to enable those skilled in the art to better understand the above steps, the embodiment of the present application is exemplified below by an embodiment, but it should be understood that the embodiment of the present application is not limited thereto.

[0145] In this embodiment, the vehicle can be equipped with hardware modules such as a weather information receiver, a multi-line laser radar, a six-axis inertial measurement unit (IMU), an electric hydraulic brake (EHB) system, and a central computing unit. The weather information receiver receives meteorological satellite data and roadside sensor information, the multi-line laser radar accurately perceives the vehicle's surroundings, the six-axis IMU monitors the vehicle's posture and motion in real time, the EHB enables precise braking control, and the central computing unit provides strong computing power to process multi-source data and execute control algorithms.

[0146] The software architecture in vehicle computing devices can be divided into the perception layer, decision layer and execution layer.

[0147] The perception layer can include modules such as the weather forecast interface (Application Programming Interface, API) and convolutional neural networks (CNN) for identifying road conditions. The perception layer can be used to fuse multi-source data to perceive weather and road conditions.

[0148] The decision-making layer, comprising an MPC controller and a safety distance calculator, can adapt the MPC algorithm to different weather conditions. Based on a nonlinear tire model and dynamically updated actual friction information, the decision-making layer adjusts MPC algorithm parameters to better adapt to changes in vehicle dynamics.

[0149] The execution layer includes a PID brake controller and torque distribution module, which can implement braking and torque distribution control based on PID parameters in different weather conditions. Based on a four-wheel drive torque distribution optimization algorithm, the execution layer can adjust the front and rear axle torque ratio in real time to enhance the vehicle's driving performance on various road surfaces.

[0150] In this embodiment, if Figure 3 As shown, the following steps may be included:

[0151] Step S301: input the meteorological data provided by the meteorological service end into the trained meteorological trend prediction model to obtain the weather forecast result within a preset time in the future output by the meteorological trend prediction model; determine the icing possibility information of the road surface on which the vehicle is traveling based on the first sensor data obtained by the road sensor used to monitor the road surface condition and the second sensor data obtained by the on-board sensor.

[0152] Step S302: predicting the future road condition of the driving road based on the weather forecast result and the icing possibility information.

[0153] Step S303: When the future road surface state is an icy or snowy road surface state, actual friction information of the driving road surface is obtained.

[0154] Step S304: determining a second collision time, a preview distance, and a predicted travel distance based on the actual friction information, and determining a vehicle cruising condition based on the second collision time, the preview distance, and the predicted travel distance.

[0155] In step S305 , the acceleration coefficient in the dynamic model is determined based on the actual friction information to obtain the target dynamic model; the target following state and target acceleration of the vehicle are determined based on the target dynamic model, the vehicle cruising conditions and the solution target to obtain the target driving state.

[0156] Step S306 : determining a first proportional coefficient, a first integral coefficient, and a first differential coefficient according to a compensation strategy corresponding to the icy and snowy road condition.

[0157] Step S307, obtaining the error between the actual driving state and the target driving state, determining the braking control information based on the error and the first proportional coefficient, the integral result of the error and the first integral coefficient, the differential result of the error and the first differential coefficient, and adjusting the vehicle's driving according to the braking control information.

[0158] It should be understood that, although the various steps in the flowcharts involved in the various embodiments described above are displayed in sequence according to the instructions of the arrows, these steps are not necessarily performed in sequence in the order indicated by the arrows. Unless clearly stated herein, the execution of these steps is not strictly limited in order, and these steps can be performed in other orders. Moreover, at least a portion of the steps in the flowcharts involved in the various embodiments described above may include multiple steps or multiple stages, and these steps or stages are not necessarily performed at the same time, but can be performed at different times, and the execution order of these steps or stages is not necessarily performed in sequence, but can be performed in turn or alternately with at least a portion of the steps or stages in other steps or other steps. It is understandable that the various steps in different embodiments can be freely combined as needed, and the various non-contradictory schemes formed by the combination all fall within the scope of protection of this application.

[0159] Based on the same inventive concept, embodiments of the present application further provide a vehicle cruise control device for implementing the aforementioned vehicle cruise control method. The solution provided by this device is similar to the solution described in the aforementioned method. Therefore, the specific limitations in one or more vehicle cruise control device embodiments provided below can be found in the above-described limitations on the vehicle cruise control method and will not be further elaborated here.

[0160] In an exemplary embodiment, Figure 4 As shown, a vehicle cruise control device is provided, comprising:

[0161] A road surface state recognition module 401 is used to predict the future road surface state of the vehicle based on meteorological data and road surface state information;

[0162] The friction information acquisition module 402 is configured to acquire actual friction information of the driving road surface when the future road surface state is an icy or snowy road surface state;

[0163] An information processing module 403 is configured to determine a target driving state of the vehicle based on the actual friction information and the vehicle cruising condition, control the driving of the vehicle based on the target driving state, and obtain the actual driving state during the driving process;

[0164] The braking module 404 is configured to determine braking control information according to the actual driving state and the braking compensation strategy corresponding to the icy and snowy road state, and adjust the driving of the vehicle according to the braking control information.

[0165] In one embodiment, the vehicle cruising condition includes a desired following state;

[0166] The information processing module 403 is used to:

[0167] Determining the acceleration coefficient in the dynamic model based on the actual friction information to obtain a target dynamic model; the dynamic model represents the vehicle following state at the current moment and is obtained by adjusting the vehicle following state at the previous moment based on the acceleration at the previous moment;

[0168] According to the target dynamics model and the solution target, the target following state and target acceleration of the vehicle are determined to obtain a target driving state; the solution target is to make the target following state meet the expected following state.

[0169] In one embodiment, the information processing module 403 is configured to:

[0170] Obtaining an objective function for the solution target; the objective function comprising a first error term determined based on a following vehicle state error at each moment in a prediction time domain, a second error term determined based on an acceleration error at each of the moments, and a third error term determined based on a following vehicle state error at an end moment of the prediction time domain; in the objective function under the icy or snowy road condition, a weight of at least one of the first error term, the second error term, and the third error term is greater than a weight of a corresponding error term in the objective function under the normal road condition, and the prediction time domain in the objective function under the icy or snowy road condition is smaller than the prediction time domain in the objective function under the normal road condition;

[0171] A target following state and a target acceleration of the vehicle are determined according to the objective function and the target dynamics model.

[0172] In one embodiment, the braking module 404 is configured to:

[0173] Determining a first proportional coefficient, a first integral coefficient, and a first differential coefficient based on a compensation strategy corresponding to the icy and snowy road condition; the first proportional coefficient is smaller than the second proportional coefficient, and / or the first integral coefficient is smaller than the second integral coefficient, and / or the first differential coefficient is smaller than the second differential coefficient; the second proportional coefficient, the second integral coefficient, and the second differential coefficient are coefficients used under normal road conditions;

[0174] The error between the actual driving state and the target driving state is obtained, and braking control information is determined according to the error and the first proportional coefficient, the integral result of the error and the first integral coefficient, the differential result of the error and the first differential coefficient.

[0175] In one embodiment, the information processing module 403 is further configured to:

[0176] adjusting a pre-acquired first collision time corresponding to a normal road surface state according to the actual friction information to obtain a second collision time;

[0177] determining a preview distance according to the second collision time;

[0178] determining a predicted travel distance of the vehicle when it stops based on the actual friction information;

[0179] The vehicle cruising condition is determined according to the second collision time, the preview distance and the predicted travel distance.

[0180] In one embodiment, the friction information acquisition module 402 is used to:

[0181] Obtaining wheel speed information collected by a wheel speed sensor of the vehicle and a road surface image captured by an onboard camera;

[0182] Inputting the wheel speed information and the road surface image into a trained adhesion coefficient determination model to obtain an adhesion coefficient prediction result output by the adhesion coefficient determination model;

[0183] According to the adhesion coefficient prediction result, real-time friction information of the driving road surface is determined.

[0184] In one embodiment, the braking module 404 is configured to:

[0185] Inputting meteorological data provided by the meteorological service end into a trained meteorological trend prediction model to obtain a weather forecast result within a preset time in the future outputted by the meteorological trend prediction model;

[0186] Determining icing possibility information of the road surface on which the vehicle is traveling based on first sensor data acquired by a road sensor for monitoring road conditions and second sensor data acquired by an on-board sensor;

[0187] A future road surface condition of the driving road surface is predicted based on the weather forecast result and the icing possibility information.

[0188] Each module in the aforementioned vehicle cruise control device may be implemented in whole or in part through software, hardware, or a combination thereof. Each module may be embedded in or independent of a processor within a computer device in the form of hardware, or may be stored in a memory within the computer device in the form of software, so that the processor can call and execute the corresponding operations of each module.

[0189] In an exemplary embodiment, a computer device is provided. The computer device may be a vehicle-mounted computing device, and its internal structure diagram may be as shown in FIG. Figure 5As shown. The computer device includes a processor, memory, an input / output interface, a communication interface, a display unit, and an input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are connected to the system bus via the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with external terminals via wired or wireless means, and the wireless means can be implemented via Wi-Fi, a mobile cellular network, near field communication (NFC), or other technologies. When executed by the processor, the computer program implements a vehicle cruise control method. The display unit of the computer device is used to form a visually visible image, and can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device casing, or an external keyboard, touchpad or mouse.

[0190] Those skilled in the art will understand that Figure 5 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0191] In one embodiment, a vehicle-mounted computing device is provided, including a memory and a processor. The memory stores a computer program, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.

[0192] In one embodiment, a vehicle is further provided, comprising the in-vehicle computing device as described above.

[0193] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0194] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0195] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0196] Those skilled in the art will understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. In particular, any reference to memory, database, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The databases involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the various embodiments provided herein may be, but are not limited to, general-purpose processors, central processing units (CPUs), graphics processing units (GPUs), digital signal processors (DSPs), programmable logic devices (PLDs), quantum computing-based data processing logic devices, artificial intelligence (AI) processors, and the like.

[0197] The technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0198] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present application. It should be noted that a person of ordinary skill in the art may make various modifications and improvements without departing from the spirit of the present application, and these modifications and improvements fall within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be determined by the appended claims.

Claims

1. A vehicle cruise control method, characterized in that: The method comprises: Predict the future road conditions of the vehicle's driving surface based on meteorological data and road condition information; When the future road surface state is an icy or snowy road surface state, obtaining actual friction information of the driving road surface; determining a target driving state of the vehicle according to the actual friction information and a vehicle cruising condition, controlling the driving of the vehicle according to the target driving state, and obtaining an actual driving state during the driving process; Braking control information is determined according to the actual driving state and the braking compensation strategy corresponding to the icy and snowy road state, and the driving of the vehicle is adjusted according to the braking control information.

2. The method according to claim 1, characterized in that The vehicle cruising condition includes an expected vehicle-following state; Determining the target driving state of the vehicle according to the actual friction information and the vehicle cruising condition includes: Determining the acceleration coefficient in the dynamic model based on the actual friction information to obtain a target dynamic model; the dynamic model represents the vehicle following state at the current moment and is obtained by adjusting the vehicle following state at the previous moment based on the acceleration at the previous moment; According to the target dynamics model and the solution target, the target following state and target acceleration of the vehicle are determined to obtain a target driving state; the solution target is to make the target following state meet the expected following state.

3. The method according to claim 2, characterized in that Determining a target following state and a target acceleration of the vehicle according to the target dynamics model and the solution target includes: Obtaining an objective function for the solution target; the objective function comprising a first error term determined based on a following vehicle state error at each moment in a prediction time domain, a second error term determined based on an acceleration error at each of the moments, and a third error term determined based on a following vehicle state error at an end moment of the prediction time domain; in the objective function under the icy or snowy road condition, a weight of at least one of the first error term, the second error term, and the third error term is greater than a weight of a corresponding error term in the objective function under the normal road condition, and the prediction time domain in the objective function under the icy or snowy road condition is smaller than the prediction time domain in the objective function under the normal road condition; A target following state and a target acceleration of the vehicle are determined according to the objective function and the target dynamics model.

4. The method according to claim 1, wherein The determining of the braking control information according to the braking compensation strategy corresponding to the actual driving state and the icy and snowy road state includes: Determining a first proportional coefficient, a first integral coefficient, and a first differential coefficient based on a compensation strategy corresponding to the icy and snowy road condition; the first proportional coefficient is smaller than the second proportional coefficient, and / or the first integral coefficient is smaller than the second integral coefficient, and / or the first differential coefficient is smaller than the second differential coefficient; the second proportional coefficient, the second integral coefficient, and the second differential coefficient are coefficients used under normal road conditions; The error between the actual driving state and the target driving state is obtained, and braking control information is determined according to the error and the first proportional coefficient, the integral result of the error and the first integral coefficient, the differential result of the error and the first differential coefficient.

5. The method according to claim 1, wherein The vehicle cruising condition is determined by the following steps: adjusting a pre-acquired first collision time corresponding to a normal road surface state according to the actual friction information to obtain a second collision time; determining a preview distance according to the second collision time; determining a predicted travel distance of the vehicle when it stops based on the actual friction information; The vehicle cruising condition is determined based on the second collision time, the preview distance, and the predicted travel distance.

6. The method according to claim 1, characterized in that The obtaining of actual friction information of the driving road surface includes: Obtaining wheel speed information collected by a wheel speed sensor of the vehicle and a road surface image captured by an onboard camera; Inputting the wheel speed information and the road surface image into a trained adhesion coefficient determination model to obtain an adhesion coefficient prediction result output by the adhesion coefficient determination model; According to the adhesion coefficient prediction result, real-time friction information of the driving road surface is determined.

7. The method according to any one of claims 1 to 6, characterized in that The method of predicting the future road condition of the road on which the vehicle is traveling based on the meteorological data and the road condition information includes: Inputting meteorological data provided by the meteorological service end into a trained meteorological trend prediction model to obtain a weather forecast result within a preset time in the future outputted by the meteorological trend prediction model; Determining icing possibility information of the road surface on which the vehicle is traveling based on first sensor data acquired by a road sensor for monitoring road conditions and second sensor data acquired by an on-board sensor; A future road surface condition of the driving road surface is predicted based on the weather forecast result and the icing possibility information.

8. A vehicle cruise control device, characterized in that: The device comprises: A road surface condition recognition module is used to predict the future road surface condition of the vehicle based on meteorological data and road surface condition information; a friction information acquisition module, configured to acquire actual friction information of the driving road surface when the future road surface state is an icy or snowy road surface state; an information processing module, configured to determine a target driving state of the vehicle based on the actual friction information and a vehicle cruising condition, control the driving of the vehicle based on the target driving state, and obtain an actual driving state during the driving process; The braking module is used to determine braking control information according to the actual driving state and the braking compensation strategy corresponding to the icy and snowy road state, and adjust the driving of the vehicle according to the braking control information.

9. A vehicle-mounted computing device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A vehicle, characterized in that: The vehicle includes the on-board computing device of claim 9.

Images