Heavy-duty car cruise control method, system and equipment and storage medium

Abstract

The invention relates to the technical field of automobiles, and particularly provides a heavy-duty automobile cruise control method, system and device and a storage medium, and the method comprises the steps: obtaining real-time road condition information and vehicle operation data through the fusion of a vehicle-mounted sensor and a driving assistance map; predicting a future vehicle weight, and predicting a future road adhesion coefficient based on the vehicle operation data and the historical road adhesion coefficient data; constructing a state variable based on the real-time road condition information, the vehicle operation data and the road adhesion coefficient, and defining a control variable; establishing a cost function including a safety item, a fuel saving item and a stability item, and setting constraint conditions of a vehicle state variable and a control variable; based on a dynamic programming algorithm, solving a minimum value of a cost function under the condition of satisfying constraint conditions, and obtaining an optimal control variable sequence; and according to the optimal control variable sequence, the gear, the driving torque and the braking torque of the vehicle are adjusted. Through multi-source information fusion and layered dynamic planning, the cruise control performance of the heavy-duty car is remarkably improved.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of automobiles, and particularly relates to a heavy truck cruise control method, system, device and storage medium. BACKGROUND

[0002] With the intensification of global energy crisis, the fuel economy of heavy trucks has become a key bottleneck in the industry. At the same time, due to its large load and high center of mass, the lateral stability and driving safety on complex road conditions such as curves also face severe challenges. Existing cruise control technologies, such as the solution described in patent CN202311269761.2, although focus on fuel saving, have large computational load and do not fully consider lateral stability; while the solution of CN202111173731.2 is difficult to adapt to dynamic load and complex road conditions, and generally has the technical limitation that fuel saving, safety and stability are difficult to be optimized simultaneously. Therefore, there is an urgent need in the field for an intelligent cruise control method that can deeply integrate multi-source information, perform forward-looking global optimization, and at the same time consider fuel economy, driving safety and vehicle lateral stability. SUMMARY

[0003] In view of the above deficiencies of the prior art, the present application provides a heavy truck cruise control method, system, device and storage medium to solve the above technical problems.

[0004] In a first aspect, the present application provides a heavy truck cruise control method, comprising: fusing vehicle-mounted sensors with a driving assistance map to obtain real-time road condition information and vehicle operation data; predicting future vehicle weight based on historical and current load information, and predicting future road adhesion coefficient based on wheel slip rate, vehicle acceleration and historical road adhesion coefficient data in the vehicle operation data; constructing state variables based on real-time road condition information, vehicle operation data and road adhesion coefficient, defining control variables, establishing a cost function including safety items, fuel saving items and stability items, and setting constraint conditions for vehicle state variables and control variables; solving the minimum value of the cost function based on the dynamic programming algorithm under the constraint conditions to obtain an optimal control variable sequence; According to the optimal control variable sequence, the gear, driving torque and braking torque of the vehicle are dynamically adjusted through the driving assistance domain controller.

[0005] In an optional embodiment, fusing vehicle-mounted sensors with a driving assistance map to obtain real-time road condition information and vehicle operation data comprises: By utilizing millimeter-wave radar, cameras, GPS positioning devices, and vehicle-to-everything (V2X) communication modules, and integrating driving assistance maps, real-time road condition information within a predetermined range in front of the vehicle is collected. The real-time road condition information includes the speed of the vehicle in front, distance to the vehicle, lane position, road curvature, and slope information. Meanwhile, vehicle operation data is acquired through vehicle body sensors, including wheel slip ratio, vehicle longitudinal and lateral acceleration, longitudinal speed, engine speed and torque.

[0006] In one optional implementation, predicting future vehicle weight based on historical and current load information includes: A time series forecasting model is used, taking historical and current load data as input, to output the predicted vehicle weight at future times.

[0007] In one optional implementation, predicting the future road adhesion coefficient based on wheel slip ratio, vehicle acceleration, and historical road adhesion coefficient data from vehicle operation data includes: A support vector regression model is used, taking wheel slip ratio, vehicle acceleration and historical road adhesion coefficient data as input, and outputting the predicted road adhesion coefficient for future time.

[0008] In one optional implementation, state variables are constructed based on real-time traffic information, vehicle operation data, and road adhesion coefficient; control variables are defined; a cost function including safety, fuel-saving, and stability terms is established; and constraints on the vehicle state variables and control variables are set, including: Constructing state variables ,in For longitudinal velocity, The longitudinal distance to the vehicle in front, This is the lateral offset. For fuel consumption rate, For road slope, The road adhesion coefficient; Define control variables ,in To request a gear, To request positive torque, This is the negative braking torque; The cost function L(k) is the safety item L s (k) Fuel-saving items L e (k) and the stable term L st The weighted sum of (k), i.e. ,in , , These are the corresponding weight coefficients; in,

[0009] for vehicle safety distance; for vehicle minimum distance; for penalty coefficient, represents strong penalty;

[0010] represents the instantaneous fuel consumption rate determined by the vehicle longitudinal speed , the requested positive torque and the requested gear at the k moment; is a preset weight coefficient of torque change penalty, which is a preset weight coefficient; is the requested positive torque at the last moment;

[0011] is a preset weight coefficient for adjusting the importance of the mass center side slip angle deviation in the total cost; is the mass center side slip angle at the k moment; is a yaw rate weight coefficient; is the actual yaw rate; is the expected yaw rate; is a lateral offset weight coefficient; is the lateral offset square term; The constraint conditions include longitudinal vehicle speed constraints, mass center side slip angle constraints, yaw rate constraints, gear range constraints, and lateral offset constraints.

[0012] In an optional embodiment, the dynamic programming algorithm adopts a hierarchical optimization architecture combining a macro planning layer and a micro control layer: The macro planning layer generates a global reference speed trajectory in a long prediction time domain based on the slope and curvature information provided by the driving assistance map, using a simplified vehicle dynamics model and a dynamic programming algorithm; The micro control layer performs rolling optimization using the state variables and the control variables in a short prediction time domain based on the global reference speed trajectory output by the macro planning layer, using a model predictive control framework to solve the minimum value of the cost function; Wherein, the prediction time of the micro control layer can be adaptively adjusted according to the real-time road condition complexity.

[0013] In an optional embodiment, the rolling optimization of the micro control layer is specifically: ​The cost function thereof adds a tracking item of the global reference speed trajectory on the basis of the weighted sum of the original safety item, fuel saving item and stability item, and constitutes a comprehensive cost function in the following form for optimization:

[0014] Wherein, L(k) is a cost function, is a weight coefficient of the speed tracking item, is the corresponding reference speed given by the macro planning layer and the current longitudinal displacement .

[0015] In the second aspect, the application provides a heavy truck cruise control system, comprising: A data acquisition module is configured to acquire real-time road condition information and vehicle operation data by fusing vehicle-mounted sensors and a driving assistance map; A coefficient prediction module is configured to predict future vehicle weight based on historical and current load information, and predict future road adhesion coefficient based on wheel slip rate, vehicle acceleration and historical road adhesion coefficient data in the vehicle operation data; A function definition module is configured to construct state variables based on real-time road condition information, vehicle operation data and road adhesion coefficient, define control variables, establish a cost function comprising a safety item, a fuel saving item and a stability item, and set constraint conditions for vehicle state variables and control variables; A function solving module is configured to solve the minimum value of the cost function based on a dynamic programming algorithm under the constraint conditions, and obtain an optimal control variable sequence; An instruction execution module is configured to dynamically adjust the gear, driving torque and braking torque of the vehicle through a driving assistance domain controller according to the optimal control variable sequence.

[0016] In the third aspect, an equipment is provided, comprising: A memory is configured to store a heavy truck cruise control program; A processor is configured to implement the steps of the heavy truck cruise control method provided in the first aspect when executing the heavy truck cruise control program.

[0017] In the fourth aspect, a computer readable storage medium is provided, and the storage medium stores a heavy truck cruise control program.

[0018] The heavy truck cruise control method, system, device and storage medium provided by the application have the beneficial effects that the heavy truck cruise control performance is significantly improved through multi-source information fusion and hierarchical dynamic planning. The beneficial effects are as follows: global fuel saving, the road potential energy is maximally utilized through long-time domain prediction and speed trajectory optimization, and the fuel consumption is significantly reduced; safety and stability, the driving safety is effectively ensured and the rollover risk is reduced through active intervention in the scene such as a curve and a crosswind through a lateral stability model and real-time risk assessment; high efficiency and real-time, the macro-micro hierarchical optimization and the self-adaptive focusing mechanism are adopted, the calculation complexity is greatly reduced while the optimization quality is ensured, and the real-time control demand of the vehicle is met. Finally, the fuel economy, the driving safety and the vehicle stability are cooperatively optimized. BRIEF DESCRIPTION OF DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or the prior art description. Obviously, for those of ordinary skill in the art, other drawings can also be obtained based on these drawings without creative labor.

[0020] Figure 1 is a schematic flow chart of the method of one embodiment of the present application.

[0021] Figure 2 is a schematic principle diagram of the method of one embodiment of the present application.

[0022] Figure 3 is another schematic flow chart of the method of one embodiment of the present application.

[0023] Figure 4 is a schematic block diagram of the system of one embodiment of the present application.

[0024] Figure 5 is a structural schematic diagram of the device provided by the embodiment of the present application. DETAILED DESCRIPTION

[0025] In order to make the person skilled in the art better understand the technical solutions in the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below in combination with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative labor should belong to the protection scope of the present application.

[0026] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used in the description herein is for describing particular embodiments only and is not intended to be limiting of the application.

[0027] The heavy truck cruise control method provided by the embodiment of the application is executed by a computer device, and accordingly, the heavy truck cruise control system runs in the computer device.

[0028] Figure 1 is a schematic flowchart of the method of one embodiment of the application. In the flowchart, Figure 1 The execution subject can be a heavy truck cruise control system. According to different requirements, the order of steps in the flowchart can be changed, and some steps can be omitted.

[0029] As Figure 1 shown, the method comprises: S1. obtaining real-time road condition information and vehicle running data by fusing vehicle-mounted sensors and a driving assistance map; S2. predicting future vehicle weight based on historical and current load information, and predicting future road adhesion coefficient based on wheel slip rate, vehicle acceleration and historical road adhesion coefficient data in the vehicle running data; S3. constructing state variables based on real-time road condition information, vehicle running data and road adhesion coefficient, defining control variables, establishing a cost function comprising safety items, fuel saving items and stability items, and setting constraint conditions of vehicle state variables and control variables; S4. solving the minimum value of the cost function under the constraint conditions based on a dynamic programming algorithm to obtain an optimal control variable sequence; S5. dynamically adjusting the gear, driving torque and braking torque of the vehicle through a driving assistance domain controller according to the optimal control variable sequence.

[0030] Please refer to Figure 2 and Figure 3 , the specific content of each step of the application is as follows.

[0031] In one embodiment of the application, based on step S1, a possible embodiment will be given below to non-restrictively describe the specific implementation scheme.

[0032] S101. Multi-element road condition information perception and fusion To realize forward-looking cruise control, it is necessary to accurately perceive the vehicle's surrounding environment and road information in front. In this embodiment, the following hardware modules work together: Environment perception sensor suite: including millimeter-wave radar and camera. Millimeter-wave radar is mainly used to detect the relative speed and distance of the vehicle in front (including the same lane and adjacent lane); the camera captures the lane line position in real time through image recognition technology, and fuses with the radar data to improve the accuracy of target recognition and distance measurement.

[0033] Positioning and communication module: including GPS positioning device and vehicle networking communication module. GPS provides absolute position and speed information of the vehicle. Vehicle networking communication module (V2X) is used to receive real-time traffic flow density, accident warning and other dynamic information pushed from the traffic information platform.

[0034] Driving assistance map: integrating electronic map with high-precision road curvature and slope information. Based on the current position of the vehicle positioned by GPS, the map provides a prediction of the road geometric characteristics within a range of 5 kilometers in front.

[0035] All the above road condition information is sent to the driving assistance domain controller in real time. In the domain controller, the original data (especially radar scattering points and image data) are first filtered (such as Kalman filtering) to remove noise interference. Then, the preprocessed real-time perception information, V2X traffic information and static road attributes provided by the map are data fused, and finally the comprehensive road condition characteristic parameters such as road complexity coefficient and traffic flow density for subsequent decision-making are calculated.

[0036] S102. Vehicle operation data acquisition The real-time state of the vehicle itself is the basis for precise control. In this embodiment, it is directly measured and obtained by various sensors deployed on the vehicle body, mainly including: Wheel speed sensor: used to calculate the wheel slip rate.

[0037] Inertial measurement unit (IMU): used to measure the longitudinal and lateral acceleration of the vehicle.

[0038] Engine control unit (ECU) and transmission control unit (TCU): directly obtain key parameters such as engine speed, engine torque and longitudinal speed through CAN bus.

[0039] These vehicle operation data are also transmitted to the driving assistance domain controller in real time, together with the aforementioned real-time road condition information, to form a complete input set for algorithm decision-making.

[0040] In an embodiment of the present application, based on step S2, a possible embodiment will be given below to non-limitingly illustrate the specific implementation thereof.

[0041] S201. Adopting time series prediction model, using historical and current load data as input, and outputting predicted vehicle weight at future time.

[0042] The total mass of the vehicle is a key parameter in calculating various resistances in the vehicle dynamics equation, and its accurate prediction is essential for fuel consumption optimization.

[0043] Data source and preprocessing: The system obtains the current load information W(t) from the air suspension pressure sensor or the vehicle controller in real time through the vehicle CAN bus at a fixed frequency (such as 1 Hz), and stores it in the memory in a loop to form a historical load data sequence {W(t), W(t 1),...,W(t p+1)}.

[0044] Prediction model selection and deployment: The preferred embodiment selects the regression integral moving average model (ARIMA) as the time series prediction model. This model can effectively handle the time correlation and non-stationary characteristics of the load data.

[0045] Model training and online application: Model parameters θ1, θ2,..., θp can be determined by offline training of historical driving data. When applied online, the latest historical and current load data sequence is input into the trained ARIMA model, which can predict the future vehicle weight W(t+k) at k time points, providing a forward-looking vehicle mass parameter for subsequent dynamic programming.

[0046] S202. Adopt support vector regression model, take wheel slip rate, vehicle acceleration and historical road adhesion coefficient data as input, output predicted road adhesion coefficient at future time.

[0047] The road adhesion coefficient directly affects the longitudinal driving force, braking force limit and lateral stability of the vehicle, and its accurate prediction is the premise of improving safety and stability control.

[0048] Data source and feature construction: The system synchronously collects the wheel slip rate λ (calculated by the wheel speed sensor) and the vehicle longitudinal acceleration a x (measured by IMU), and combines the historically calculated road adhesion coefficient μ to form the input feature vector x=[λ, a x ,μ hist ].

[0049] Prediction model selection and deployment: The preferred embodiment adopts the support vector regression (SVR) model. This model has excellent generalization ability for small sample and nonlinear problems. Preferably, the Gaussian radial basis function (RBF) is used as the kernel function K(x i ,x j ) to capture the complex nonlinear relationship between the input features and the adhesion coefficient.

[0050] Model training and online application: The SVR model (i.e. determining the Lagrange multipliers αi and bias term b) need to be trained offline using a large amount of real vehicle data containing different road conditions (such as dry asphalt, wet asphalt, ice and snow). When applied online, the real-time constructed feature vector x(t+m) is input into the trained SVR model, and the predicted road adhesion coefficient μ(t+m) at time m in the future can be output, which is expressed as: . The predicted value will be used in the evaluation of the stability term in the subsequent cost function and the dynamic setting of the control constraint condition.

[0051] In an embodiment of the present application, based on step S3, a possible embodiment will be given below to specifically and non-limitingly illustrate the specific implementation thereof.

[0052] The longitudinal motion of the vehicle during driving is affected by driving force (F ), rolling resistance (F ), air resistance (F ), slope resistance (F ), and the longitudinal dynamics equation is:

[0053] wherein: m is the mass of the vehicle; v is the longitudinal speed of the vehicle; The engine fuel consumption is related to the engine speed and torque, and based on the engine universal characteristic curve, the fuel consumption (C ) can be obtained:

[0054] wherein: T is the engine torque; n is the engine speed; Based on the two-degree-of-freedom model of the vehicle, under the condition of considering the tire side slip characteristics, the vehicle's mass center side slip angle (φ ) and yaw rate (r ) can be obtained as:

[0055]

[0056] wherein: v is the lateral speed of the vehicle; v is the driving speed of the vehicle; M is the yaw moment of the vehicle; I is the moment of inertia of the vehicle around the mass center; The state variable x is constructed as: wherein v is the longitudinal speed, is the longitudinal distance from the front vehicle, is the lateral offset amount, is the fuel consumption rate, is the road slope, is the road adhesion coefficient; define the control variables wherein is the requested gear, is the requested positive torque, is the braking negative torque; The cost function L(k) is a weighted sum of a safety term L s (k), a fuel saving term L e (k) and a stability term L st (k), i.e. wherein , , are the respective weight coefficients; The safety term L is centered on the vehicle distance, with a piecewise penalty to ensure the safety of the vehicle:

[0057] is the vehicle safety distance; is the vehicle minimum distance; , are the penalty coefficients, representing a strong penalty; The fuel saving term L is directly related to the instantaneous fuel consumption rate, while taking into account the vehicle ride comfort, with the second term penalizing torque jumps to reduce the additional fuel consumption:

[0058] represents the instantaneous fuel consumption rate at time k, determined by the vehicle longitudinal speed , the requested positive torque and the requested gear ; is the torque variation penalty weight coefficient, which is a preset weight coefficient; is the requested positive torque at the previous time; The stability term L is based on the deviation penalty of the center of mass side slip angle and yaw rate, to suppress the lateral instability of the vehicle:

[0059] is a preset weight coefficient, used to adjust the importance of the center of mass side slip angle deviation in the total cost; is the center of mass side slip angle at time k; is the yaw rate weight coefficient; is the actual yaw rate; is the desired yaw rate; is the lateral offset weight coefficient; is the lateral offset square term.

[0060] The constraint conditions include a longitudinal vehicle speed constraint, a mass center side slip angle constraint, a yaw rate constraint, a gear range constraint, and a lateral offset constraint. The established constraint conditions are:

[0061] wherein: is the lowest vehicle speed; is the highest vehicle speed; is the mass center side slip angle safety threshold value; is the yaw rate safety threshold value; is the lowest gear; is the highest gear; is the lateral limit threshold value.

[0062] In an embodiment of the present application, based on step S4, a possible embodiment will be given below to specifically and non-restrictively illustrate the specific implementation thereof.

[0063] The solving process decomposes the complex global optimization problem into two levels of macroscopic strategy planning and microscopic real-time control, and introduces an adaptive focusing mechanism to significantly improve the calculation efficiency while ensuring the quality of optimization.

[0064] S401. Macroscopic planning layer: global speed trajectory generation based on coarse-grained model The macroscopic layer focuses on planning an optimal reference speed trajectory in a long prediction time domain (5 kilometers as described in the document). It uses a simplified vehicle model and cost function to reduce the calculation dimension.

[0065] State variable simplification: the state variable of the macroscopic layer is simplified as wherein is the longitudinal displacement of the vehicle. The details such as the microscopic following distance d(k), the lateral offset y(k), etc. are temporarily ignored.

[0066] Cost function simplification: the cost function of the macroscopic layer is Mainly considering fuel economy and global travel time, and integrating map information (slope, curvature).

[0067]

[0068] wherein, is the road slope at the displacement s(k) provided by the high-precision map, which is directly used to estimate the fuel consumption. is the desired average speed.

[0069] Optimization: On this simplified model, a standard dynamic programming algorithm is used for backward recursion. Due to the greatly reduced dimension of the state space, even with a long prediction horizon, a globally optimal reference speed profile V ref (s) is quickly obtained. This profile indicates where to decelerate early and where to accelerate early to achieve global fuel saving.

[0070] S402. Micro-control layer: Real-time decision based on adaptive horizon MPC The micro layer conducts fine optimization in a short horizon based on the reference speed provided by the macro layer, handling real-time traffic and vehicle stability issues. This method innovatively adopts a model predictive control (MPC) framework, but its prediction horizon N micro is adaptive.

[0071] Cost function enhancement: Micro layer cost function The comprehensive cost function L(k) defined in the document is directly used, but a tracking term for the macro reference speed is added:

[0072] Adaptive prediction horizon and focus mechanism: This is the core innovation of this method. The prediction step N micro of the micro layer is not fixed, but dynamically adjusted according to road complexity. The specific adjustment method is as follows: Normal working condition: When the traffic flow is smooth and the road is straight, set a longer prediction horizon (such as 15 seconds) for smooth optimization, giving priority to fuel saving.

[0073] Complex working condition: When radar / camera detects an incoming vehicle in front, or map indicates that an acute bend is approaching, the algorithm automatically shortens the prediction horizon (such as 5 seconds), and increases the weight coefficients of safety (ω s ) and stability (ω st ). This "focus" mechanism can concentrate limited computing resources on handling imminent challenges, making safer and more timely decisions.

[0074] S403. Collaborative optimization and real-time solving Initialization: The macro planning layer calculates the global speed reference line V ref (s) based on 5 km of map information offline or low-frequency online.

[0075] Rolling optimization: In each control period: (1) Situation awareness: The fusion module evaluates road curvature, distance to the vehicle in front, traffic density, etc. in real time to determine the current road complexity.

[0076] (2) Parameter adaptation: dynamically set the prediction horizon N of micro-MPC according to the complexity micro and the weight ω of each cost term s , ω e , ω st .

[0077] (3) Problem solving: solve the micro-level optimization problem in a shortened time domain with the current vehicle state as the initial value. Due to the small problem size, a faster numerical optimizer (such as quadratic programming QP) can be used for online solving, directly outputting the optimal control sequence (gear, torque).

[0078] Feedback correction: after the vehicle state changes, the micro-optimization is performed again in the next cycle to form a closed-loop feedback to offset the model error.

[0079] In an embodiment of the present application, based on step S5, a possible embodiment will be given below to non-restrictively illustrate the specific implementation thereof.

[0080] S501. Packaging and sending of control instructions After the driving assistance domain controller solves the optimal control variable sequence , the first control variable in the sequence (i.e., the control instruction that should be immediately executed at the current time) is output.

[0081] Instruction encapsulation: the controller packages the request value in digital form into a specific data frame according to the vehicle's established communication protocol (such as CAN bus protocol). The data frame explicitly contains: the value of the requested gear identifier and .

[0082] the value of the requested positive torque identifier and (usually a positive torque value).

[0083] the value of the requested negative torque identifier and (usually a brake pressure or negative torque value).

[0084] Instruction distribution: the encapsulated data frame is sent to different actuators through the corresponding CAN bus channel: the instruction frame containing is sent to the transmission control unit (TCU).

[0085] the instruction frame containing is sent to the engine control unit (ECU).

[0086] the instruction frame containing is sent to the electronic brake control system (EBS) or hydraulic retarder controller.

[0087] S502. Synergetic control of actuators Upon receiving the instructions from the domain controller, each actuator drives the mechanism to act, completing the dynamic adjustment of the vehicle.

[0088] Gear adjustment: The transmission control unit (TCU) adjusts the gear according to the received value, combined with the current vehicle speed and engine speed, to accurately perform the operation of upshift, downshift or maintain the current gear by controlling the shift solenoid valve and clutch.

[0089] Drive torque adjustment: The engine control unit (ECU) adjusts the drive torque according to the received value by adjusting the fuel injection amount, throttle opening, etc., so that the engine outputs the corresponding drive torque, thereby controlling the vehicle acceleration or maintaining the vehicle speed.

[0090] Braking torque adjustment: The electronic brake control system (EBS) or hydraulic retarder controller adjusts the brake chamber pressure or retarder vane opening according to the received value to accurately control the braking torque, achieving fine control of deceleration or vehicle speed.

[0091] S503. Closed-loop feedback and safety assurance The entire execution process forms a closed-loop control system. The vehicle body sensors (such as wheel speed sensors, acceleration sensors) continuously monitor the actual state of the vehicle (such as actual vehicle speed, actual acceleration), and feed these data back to the driving assistance domain controller. The domain controller compares the actual state with the expected state, and if a large deviation is detected in the next control cycle or the actuator fails, the control strategy will be re-optimized or the safety backup mode will be intervened, thereby ensuring the accuracy of the control and the safety of the driving.

[0092] In some embodiments, the heavy vehicle cruise control system can include a plurality of functional modules composed of computer program segments. The computer programs of each program segment in the heavy vehicle cruise control system can be stored in the memory of the computer device and executed by at least one processor to perform the functions of the heavy vehicle cruise control (see Figure 1 description).

[0093] In this embodiment, the heavy vehicle cruise control system can be divided into a plurality of functional modules according to the functions it performs, as shown in Figure 4 The module referred to in the present invention refers to a series of computer program segments that can be executed by at least one processor and can complete a fixed function, which are stored in the memory. In this embodiment, the functions of each module will be described in detail in subsequent embodiments.

[0094] The data acquisition module is configured to acquire real-time road condition information and vehicle operation data by fusing vehicle-mounted sensors and a driving assistance map; The coefficient prediction module is configured to predict future vehicle weight based on historical and current load information, and to predict future road adhesion coefficient based on wheel slip rate, vehicle acceleration and historical road adhesion coefficient data in the vehicle operation data; The function definition module is configured to construct state variables based on the real-time road condition information, the vehicle operation data and the road adhesion coefficient, to define control variables, to establish a cost function including safety items, fuel saving items and stability items, and to set constraint conditions of the vehicle state variables and the control variables; The function solving module is configured to solve a minimum value of the cost function based on a dynamic programming algorithm under the constraint conditions to obtain an optimal control variable sequence. The instruction execution module is configured to dynamically adjust gears, driving torque and braking torque of the vehicle through a driving assistance domain controller according to the optimal control variable sequence.

[0095] Figure 5 The heavy truck cruise control method provided by the embodiments of the present application can be applied to equipment. Those skilled in the art can understand that the equipment structure involved in the embodiments of the present application does not constitute a limitation on the equipment, and the equipment can include more or fewer components than the illustration, or combine certain components, or different component arrangements. In the embodiments of the present application, the equipment includes but is not limited to a laptop computer, a desktop computer, a workstation, a personal digital assistant, a server, a blade server, a mainframe computer, and other suitable computers. The equipment can also represent various forms of mobile devices, such as a personal digital processor, a cellular phone, a smart phone, a wearable device, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the embodiments of the present application described and / or claimed herein.

[0096] The device 500 can include a processor 510, a memory 520, and a communication unit 530. These components communicate through one or more buses. Those skilled in the art can understand that the structure of the server shown in the figure does not constitute a limitation on the present application, and it can be a bus structure or a star structure, and can include more or fewer components than the illustration, or combine certain components, or different component arrangements.

[0097] The memory 520 can be used to store the execution instructions of the processor 510, and the memory 520 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk or optical disk. When the execution instructions in the memory 520 are executed by the processor 510, the device 500 can perform part or all of the steps in the following method embodiments.

[0098] The processor 510 is the control center of the storage device, connects various parts of the entire electronic device through various interfaces and lines, and performs various functions of the electronic device and / or processes data by running or executing software programs and / or modules stored in the memory 520 and calling data stored in the memory. The processor can be composed of an integrated circuit (IC), for example, can be composed of a single packaged IC, or can be composed of multiple packaged ICs connected together. For example, the processor 510 can only include a central processing unit (CPU). In the embodiments of the present application, the CPU can be a single operation core or can include multiple operation cores.

[0099] The communication unit 530 is used to establish a communication channel, so that the storage device can communicate with other devices. Receive user data sent by other devices or send user data to other devices.

[0100] The present application also provides a computer storage medium, wherein the computer storage medium can store a program, and the program can include part or all of the steps in the embodiments provided by the present application when executed. The storage medium can be a magnetic disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM), etc.

[0101] Those skilled in the art can clearly understand that the technical solutions in the embodiments of the present application can be implemented by means of software plus necessary universal hardware platforms. Based on such an understanding, the technical solutions in the embodiments of the present application can be embodied in the form of a software product, which can be stored in a storage medium, such as a USB flash disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and the like, and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a second device, a network device, or the like) to execute all or part of the steps of the methods described in the embodiments of the present application.

[0102] In the present specification, the same or similar parts among various embodiments can be referred to each other. In particular, for the device embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the description in the method embodiments.

[0103] In several embodiments provided in the present application, it should be understood that the disclosed system and method can be implemented in other ways. For example, the system embodiments described above are merely schematic, for example, the division of the modules is only a logical function division, and actual implementation can have another division manner, for example, a plurality of modules or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the displayed or discussed modules can be indirect coupling or communication connection through some interfaces, systems or modules, and can be electrical, mechanical or other forms.

[0104] The modules described as separate components can or can not be physically separated, and the components displayed as modules can or can not be physical modules, that is, they can be located in one place, or can be distributed on a plurality of network modules. According to actual needs, some or all of the modules can be selected to achieve the purpose of the embodiments.

[0105] In addition, the functional modules in each of the embodiments of the present application can be integrated in one processing module, or each module can exist physically independently, or two or more modules can be integrated in one module.

[0106] Although the present application has been described in detail with reference to the preferred embodiments, it should be understood that the application is not limited to those preferred embodiments. Various modifications and equivalents can be made by those skilled in the art without departing from the spirit and scope of the application. Any and all modifications and equivalents are intended to be included within the scope of the present application.

Claims

1. A cruise control method for heavy-duty vehicles, characterized in that, include: Real-time traffic information and vehicle operation data are obtained by fusing onboard sensors with driver assistance maps; Predict future vehicle weight based on historical and current load information, and predict future road adhesion coefficient based on wheel slip ratio, vehicle acceleration and historical road adhesion coefficient data in vehicle operation data. State variables are constructed based on real-time road condition information, vehicle operation data, and road adhesion coefficient; control variables are defined; a cost function containing safety, fuel-saving, and stability terms is established, and constraints on vehicle state variables and control variables are set. Based on the dynamic programming algorithm, the minimum value of the cost function is solved under the constraints to obtain the optimal sequence of control variables; Based on the optimal control variable sequence, the vehicle's gear, drive torque, and braking torque are dynamically adjusted by the driving assistance domain controller.

2. The method according to claim 1, characterized in that, Real-time traffic information and vehicle operation data are obtained by fusing onboard sensors with driver assistance maps, including: By utilizing millimeter-wave radar, cameras, GPS positioning devices, and vehicle-to-everything (V2X) communication modules, and integrating driving assistance maps, real-time road condition information within a predetermined range in front of the vehicle is collected. The real-time road condition information includes the speed of the vehicle in front, distance to the vehicle, lane position, road curvature, and slope information. Meanwhile, vehicle operation data is acquired through vehicle body sensors, including wheel slip ratio, vehicle longitudinal and lateral acceleration, longitudinal speed, engine speed and torque.

3. The method according to claim 1, characterized in that, Predicting future vehicle weight based on historical and current load information includes: A time series forecasting model is used, taking historical and current load data as input, to output the predicted vehicle weight at future times.

4. The method according to claim 1, characterized in that, Predicting future road adhesion coefficients based on wheel slip ratio, vehicle acceleration, and historical road adhesion coefficient data from vehicle operation data, including: A support vector regression model is used, taking wheel slip ratio, vehicle acceleration and historical road adhesion coefficient data as input, and outputting the predicted road adhesion coefficient for future time.

5. The method according to claim 1, characterized in that, State variables are constructed based on real-time traffic information, vehicle operation data, and road adhesion coefficient; control variables are defined; a cost function including safety, fuel-saving, and stability terms is established, and constraints on vehicle state variables and control variables are set, including: Constructing state variables ,in For longitudinal velocity, The longitudinal distance to the vehicle in front, This is the lateral offset. For fuel consumption rate, For road slope, The road adhesion coefficient; Define control variables ,in To request a gear, To request positive torque, This is the negative braking torque; The cost function L(k) is the safety item L s (k) Fuel-saving items L e (k) and the stable term L st The weighted sum of (k), i.e. ,in , , These are the corresponding weight coefficients; in, To maintain a safe distance between vehicles; Minimum distance between vehicles; , The penalty coefficient is... This indicates a strong punishment; This represents the longitudinal velocity of the vehicle at time k. Request positive torque and request file The instantaneous fuel consumption rate is jointly determined; The torque change penalty weighting coefficient is a preset weighting coefficient; The positive torque is requested for the previous moment; These are preset weighting coefficients used to adjust the importance of centroid sideslip angle deviation in the total cost; Let be the centroid sideslip angle at time k; This is the yaw rate weighting coefficient; This is the actual yaw rate; The desired yaw rate; This is the horizontal offset weighting coefficient; This is the squared term of the horizontal offset; The constraints include longitudinal vehicle speed constraints, center of gravity sideslip angle constraints, yaw rate constraints, gear range constraints, and lateral offset constraints.

6. The method according to claim 5, characterized in that, The dynamic programming algorithm adopts a hierarchical optimization architecture that combines a macro-planning layer and a micro-control layer: The macro-planning layer, based on the slope and curvature information provided by the driving assistance map, generates a global reference speed trajectory in the long prediction time domain by using a simplified vehicle dynamics model and dynamic programming algorithm. The micro-control layer, based on the global reference velocity trajectory output by the macro-planning layer, employs a model predictive control framework within the short prediction time domain to perform rolling optimization using the state variables and the control variables, thereby solving for the minimum value of the cost function. The prediction time domain of the micro-control layer can be adaptively adjusted according to the complexity of real-time traffic conditions.

7. The method according to claim 1, characterized in that, The rolling optimization of the micro-control layer specifically involves: Its cost function is based on the weighted sum of the original safety, fuel-saving, and stability terms, with the addition of a term for tracking the global reference speed trajectory, forming a comprehensive cost function of the following form for optimization: Where L(k) is the cost function, These are the weighting coefficients for the speed tracking term. The vertical displacement given by the macro-planning layer is related to the current vertical displacement. The corresponding reference speed.

8. A cruise control system for heavy-duty vehicles, characterized in that, include: The data acquisition module is used to obtain real-time traffic information and vehicle operation data by fusing onboard sensors with driving assistance maps; The coefficient prediction module is used to predict the future vehicle weight based on historical and current load information, and to predict the future road adhesion coefficient based on wheel slip rate, vehicle acceleration and historical road adhesion coefficient data in vehicle operation data. The function definition module is used to construct state variables and define control variables based on real-time traffic information, vehicle operation data and road adhesion coefficient; to establish a cost function containing safety, fuel saving and stability terms, and to set constraints on vehicle state variables and control variables. The function solving module is used to solve for the minimum value of the cost function under the constraints based on the dynamic programming algorithm, and obtain the optimal control variable sequence. The instruction execution module is used to dynamically adjust the vehicle's gear, drive torque, and braking torque through the driving assistance domain controller according to the optimal control variable sequence.

9. A heavy-duty vehicle cruise control device, characterized in that, include: Memory used to store cruise control programs for heavy-duty vehicles; A processor for implementing the steps of the heavy-duty vehicle cruise control method as described in any one of claims 1-7 when executing the heavy-duty vehicle cruise control program.

10. A computer-readable storage medium storing a computer program, characterized in that, The readable storage medium stores a heavy-duty vehicle cruise control program, which, when executed by a processor, implements the steps of the heavy-duty vehicle cruise control method as described in any one of claims 1-7.

Images