Vehicle control method and device, electronic equipment and storage medium

By determining the slope information sequence of the vehicle in the mining environment and building a prediction model, the precise control of the acceleration and speed of the mine car is achieved, and the problem of difficulty in achieving precise control in complex environments in the existing technology is solved, which improves the mine car's Driving stability and safety.

CN119078885APending Publication Date: 2024-12-06SANY INTELLIGENT MINING TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411380435.3
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-09-30
Publication Date
2024-12-06

AI Technical Summary

Technical Problem

The existing longitudinal control strategy is difficult to achieve precise control of the speed and acceleration of the mine truck in complex mining environments, resulting in overspeed or insufficient power on sections with large slope changes, posing safety hazards.

Method used

By determining the slope information sequence of the vehicle during the predicted time period, a prediction model is constructed to determine the target compensation acceleration sequence, and based on this, the acceleration change of the vehicle is controlled, the vehicle speed is adjusted to achieve the target speed, ensuring that the optimized under different path conditions is achieved. Speed ​​and acceleration control.

Benefits of technology

Accurate control of vehicle acceleration and speed in complex mine paths is achieved, driving stability and safety are improved, and operating costs are reduced.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119078885A_ABST
    Figure CN119078885A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of vehicles, and provides a vehicle control method and device, electronic equipment and a storage medium, and the method comprises the steps: determining a gradient information sequence of a to-be-driven path of a vehicle in a prediction time period; based on the gradient information of the to-be-driven path corresponding to each moment, determining a target compensation acceleration sequence of the vehicle driving on the to-be-driven path; based on the target compensation acceleration sequence, determining a target acceleration variable quantity corresponding to an execution mechanism of the vehicle when the vehicle is driven on the to-be-driven path; and when the vehicle runs on the to-be-driven path, controlling the speed of the vehicle to be adjusted to the target speed based on the target acceleration variation. The problem that the speed and the acceleration cannot be accurately controlled due to the complexity of a mine environment is solved, and accurate control over the vehicle is achieved by combining the gradient information of the to-be-driven path, predicting the speed of the to-be-driven path and adjusting the control strategy in advance.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of vehicle technology, and in particular to a vehicle control method, device, electronic equipment and storage medium. Background Art

[0002] The unmanned driving technology in mines realizes the automatic operation of mine cars without human intervention through the coordinated work of sensors, control algorithms and communication systems. The application of this technology not only greatly improves the safety and stability of mine transportation operations, but also reduces labor costs and improves the overall production efficiency of mines. Unmanned mine cars can work stably for a long time in harsh environments, and can achieve the optimal configuration of transportation scheduling through seamless integration with mine production systems.

[0003] However, due to the complexity of the mining environment, the existing longitudinal control strategies face many challenges in practical application. For example, when the mine car is traveling on a road section with a large slope change, the existing longitudinal control strategy is difficult to achieve accurate control of the mine car speed and acceleration while ensuring safety, which may cause the mine car to overspeed when going downhill, lack power when going uphill, or even insufficient braking and other dangerous situations. Summary of the invention

[0004] The present invention provides a vehicle control method, device, electronic device and storage medium, which are used to solve the defect in the prior art that the speed and acceleration cannot be accurately controlled due to the complexity of the mine environment, and realize accurate control of the acceleration and speed of the vehicle in a complex mine path.

[0005] The present invention provides a vehicle control method, comprising the following steps: Determine a slope information sequence of a path to be driven by the vehicle within a predicted time period; the slope information sequence includes the slope information of the path to be driven corresponding to each moment within the predicted time period; Determining a target compensation acceleration sequence for the vehicle traveling on the path to be traveled based on the slope information of the path to be traveled corresponding to each moment; Determining a target acceleration change corresponding to an actuator of the vehicle when the vehicle is traveling on the path to be traveled based on the target compensation acceleration sequence; When the vehicle travels on the path to be traveled, the speed of the vehicle is controlled to be adjusted to the target speed based on the target acceleration change.

[0006] According to a vehicle control method provided by the present invention, based on a target compensation acceleration sequence, a target acceleration change corresponding to an actuator of the vehicle when the vehicle is traveling on a path to be traveled is determined, including: determining a state vector of the vehicle at a current moment; the state vector is used to characterize the motion state of the vehicle; using a prediction model, based on the state vector and the target compensation acceleration sequence, the target acceleration change is determined; the prediction model is used to predict the speed of the vehicle on the path to be traveled.

[0007] According to a vehicle control method provided by the present invention, a method for constructing a prediction model includes: determining a prediction state matrix of the prediction model and a prediction input matrix of the prediction model based on the first-order inertial system of the vehicle; based on an expression of a state vector, an expression of a target compensation acceleration sequence, an expression of a target acceleration change, a prediction state matrix and a prediction input matrix, and constructing a prediction model.

[0008] A vehicle control method provided by the present invention utilizes a prediction model to determine a target acceleration change based on a state vector and a target compensation acceleration sequence, including: substituting the state vector and the target compensation acceleration sequence into the prediction model to obtain a first function with the target acceleration change of the vehicle in a prediction time period as a variable; determining a target function based on the first function and an ideal speed sequence of the vehicle on a path to be driven; determining constraints based on the acceleration change of the vehicle, the acceleration of the vehicle and the speed of the vehicle; continuously optimizing the target function based on the difference between the predicted speed of the prediction model and the ideal speed corresponding to the predicted speed, as well as the constraints, to obtain a sequence of acceleration changes corresponding to the minimum value of the target function; and determining the target acceleration change based on the acceleration change sequence.

[0009] A vehicle control method provided by the present invention controls the speed of the vehicle to be adjusted to the target speed based on the target acceleration change, including: determining the target acceleration of the vehicle within a predicted time period based on the target acceleration change; determining the target speed of the vehicle within the predicted time period based on the target acceleration; when the target acceleration is greater than zero, determining the opening of the vehicle's accelerator pedal based on the target acceleration; when the target acceleration is less than zero, determining the opening of the vehicle's brake pedal based on the target acceleration; and controlling the speed of the vehicle to be adjusted to the target speed based on the opening of the accelerator pedal or the opening of the brake pedal.

[0010] According to a vehicle control method provided by the present invention, a target compensation acceleration sequence for the vehicle to travel on the path to be traveled is determined based on the slope information of the path to be traveled corresponding to each moment, including: determining the rolling friction of the vehicle on the path to be traveled and the wind resistance on the path to be traveled; determining an initial compensation acceleration sequence for the vehicle to travel on the path to be traveled based on the slope information of the path to be traveled corresponding to each moment, the rolling friction and the gravity acceleration of the vehicle; determining a target compensation acceleration sequence based on the wind resistance and the initial compensation acceleration sequence.

[0011] A vehicle control method provided by the present invention determines the state vector of the vehicle at the current moment, including: collecting the initial state vector of the vehicle at the current moment through a sensor; updating the initial state vector based on external environment information of the vehicle's environment and the vehicle's braking information to obtain the state vector of the vehicle at the current moment.

[0012] The present invention also provides a vehicle control device, comprising the following modules: The first determination module is used to determine the slope information sequence of the path to be driven by the vehicle within the predicted time period; the slope information sequence includes the slope information of the path to be driven corresponding to each moment within the predicted time period; A second determination module is used to determine a target compensation acceleration sequence for the vehicle traveling on the path to be traveled based on the slope information of the path to be traveled corresponding to each moment; A third determination module is used to determine, based on the target compensation acceleration sequence, a target acceleration change corresponding to the actuator of the vehicle when the vehicle is traveling on the path to be traveled; The control module is used to control the speed of the vehicle to be adjusted to a target speed based on a target acceleration change when the vehicle travels on a path to be traveled.

[0013] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, any one of the above-mentioned vehicle control methods is implemented.

[0014] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the computer program implements any of the above-mentioned vehicle control methods.

[0015] The present invention also provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements any of the above-mentioned vehicle control methods.

[0016] The vehicle control method, device, electronic device and storage medium provided by the present invention determine the slope information sequence of the path to be formed by the vehicle within the predicted time period, determine the target compensation acceleration sequence of the vehicle traveling on the path to be traveled, and compensate for the influence of the slope on the vehicle acceleration; on the basis of compensation, determine the target acceleration change of the vehicle's actuator when the vehicle travels on the path to be traveled according to the target compensation acceleration sequence, and when the vehicle travels on the path to be traveled, adjust the vehicle to the target speed according to the target acceleration change, thereby improving the accuracy of the target speed. In this way, the speed of the path to be traveled is predicted in combination with the slope information of the path to be traveled, and the control strategy is adjusted in advance to ensure that the speed and acceleration of the vehicle meet the optimization target under different path conditions, thereby achieving precise control of the vehicle. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0018] Figure 1 It is one of the flow charts of the vehicle control method provided by the present invention.

[0019] Figure 2 This is the second flow chart of the vehicle control method provided by the present invention.

[0020] Figure 3 It is a structural schematic diagram of the vehicle control device provided by the present invention.

[0021] Figure 4 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0022] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0023] As the global demand for mineral resources continues to increase, the mining industry faces the dual challenges of improving production efficiency and ensuring worker safety. Traditional mine transportation operations usually rely on manual operation, and mine cars work under harsh environmental conditions and face problems such as high temperature, high dust, and complex terrain. These factors not only increase operational risks, but may also lead to low production efficiency and increased operating costs. For this reason, mine unmanned driving technology has gradually become an important direction for the development of intelligent mines.

[0024] Unmanned driving technology in mines realizes the automatic operation of mine cars without human intervention through the coordinated work of sensors, control algorithms and communication systems. However, mine roads are usually unstructured and the path conditions are changeable. Parameters such as slope and curvature may change at any time. It is necessary to achieve precise control of mine cars in complex mining environments, especially longitudinal control.

[0025] At present, most of the existing longitudinal controls rely on fixed control strategies, which are often based on simple assumptions and preset parameters of vehicle dynamics. However, due to the complexity of the mining environment, these control strategies face many challenges in practical applications. For example, when the mine car is traveling on a road section with a large slope change, it is difficult for the existing longitudinal control strategy to achieve accurate control of the mine car speed and acceleration while ensuring safety. This deficiency may cause the mine car to overspeed when going downhill, lack of power when going uphill, and even dangerous situations such as insufficient braking. Although some existing technologies have introduced model-based control methods, such as model predictive control, most implementations are still limited to simple prediction models and fail to fully consider the dynamic characteristics of the mine path and the impact of future path information.

[0026] Based on the above problems, the present invention proposes a vehicle control method, which combines the slope information of the path to be traveled, predicts the speed of the path to be traveled, and adjusts the control strategy in advance to ensure that the speed and acceleration of the vehicle meet the optimization goals under different path conditions, thereby achieving precise control of the vehicle.

[0027] Combine the following Figure 1-Figure 2 The vehicle control method of the present invention is described. The vehicle control method of the present invention can be applied to speed control of any type of vehicle. The execution subject of the method can be an electronic device or a vehicle control device arranged in the electronic device. The vehicle control device can be implemented by software, hardware or a combination of both.

[0028] Figure 1 is one of the flow charts of the vehicle control method provided by the present invention, such as Figure 1 As shown, the method includes the following: Step 101: determine a slope information sequence of a path to be traveled by a vehicle within a predicted time period; the slope information sequence includes the slope information of the path to be traveled corresponding to each moment within the predicted time period.

[0029] Here, the prediction time period may include one or more moments, the duration between adjacent moments is a cycle, the duration of the cycle may be any appropriate duration, for example, 1 second (s) or 2s, and the prediction time period may be 5s or 20s, etc.

[0030] The road to be traveled refers to the road section that the vehicle is about to travel on, and the slope information refers to the angle between the travel path and the horizontal plane. The larger the angle, the greater the slope; the smaller the angle, the smaller the slope.

[0031] Here, the path to be driven can be a real-time path loaded in a high-precision map, which includes path length, path position, slope information, etc.

[0032] Here, the slope information refers to a slope angle indicating the degree of inclination of the path, for example, an angle between a road surface and a horizontal plane, or an angle between a road surface and a vertical plane.

[0033] It should be noted that the vehicle travels along a different path at each moment during its driving process. Therefore, the slope information corresponding to each moment may be the same or different, depending on the driving path.

[0034] Exemplarily, assuming that the prediction time period is 20 seconds and there are 20 moments, the distance traveled by the vehicle in the prediction time period is calculated, and the corresponding preview path length is intercepted. If there is no slope information at a certain moment, the slope information corresponding to the preview path length can be uniformly interpolated to determine the slope angle corresponding to each moment, and the slope information sequence in the prediction time period is obtained.

[0035] Step 102: Determine a target compensation acceleration sequence for the vehicle traveling on the path to be traveled based on the slope information of the path to be traveled corresponding to each moment.

[0036] Here, the target compensation acceleration sequence can be understood as an acceleration disturbance term, that is, the compensation of acceleration due to external factors, and the target compensation acceleration sequence can be determined by a corresponding relationship table between the slope information and the target compensation acceleration sequence, or can be calculated according to a formula based on the slope information, or can be obtained according to the output of a neural network model. The present invention does not limit this.

[0037] Here, the target compensation acceleration sequence includes the target compensation acceleration corresponding to each moment in the prediction time period.

[0038] It should be noted that when a slope appears on the driving path or when there are other external environmental interferences, the speed of the vehicle will be affected. In order to maintain the speed balance of the vehicle, the acceleration of the vehicle needs to be compensated to offset the influence of the slope on the vehicle speed.

[0039] Step 103: Based on the target compensation acceleration sequence, determine a target acceleration change corresponding to an actuator of the vehicle when the vehicle travels on the path to be traveled.

[0040] Here, the actuator refers to the braking force, traction force or internal system of the vehicle, etc. In other words, the target acceleration change here is essentially the acceleration change that the internal system of the vehicle needs to apply.

[0041] It should be noted that the target acceleration change is the first value or the first N values ​​selected from the optimized target acceleration sequence in chronological order.

[0042] The target acceleration variation may be determined based on a prediction model, or may be determined based on a correspondence table between a target compensation acceleration sequence and a target acceleration variation, and the present invention does not limit this.

[0043] Step 104: When the vehicle travels onto the path to be traveled, based on the target acceleration change, control the speed of the vehicle to be adjusted to a target speed.

[0044] Here, the target speed refers to the speed predicted based on the target acceleration change amount.

[0045] It should be noted that the prediction result is a sequence of velocities in the prediction time domain, and an acceleration sequence in the prediction time domain can also be obtained. By optimizing the target, the velocity and acceleration are optimized and constrained to improve accuracy and smoothness.

[0046] In an embodiment of the present invention, by determining the slope information sequence of the path to be traveled by the vehicle within the predicted time period, the target compensation acceleration sequence of the vehicle traveling on the path to be traveled is determined to compensate for the influence of the slope on the vehicle acceleration; on the basis of the compensation, the target acceleration change of the actuator of the vehicle when the vehicle is traveling on the path to be traveled is determined according to the target compensation acceleration sequence, and when the vehicle travels on the path to be traveled, the vehicle is adjusted to the target speed according to the target acceleration change, thereby improving the accuracy of the target speed. In this way, the speed of the path to be traveled is predicted by using the slope of the mine path, and the control strategy is adjusted in advance to ensure that the speed and acceleration of the mine car meet the optimization target under different path conditions, so as to achieve precise control of the vehicle, and the optimization and constraint of the speed and acceleration in the predicted time domain can improve the stability of the vehicle.

[0047] Further, determining the target acceleration change corresponding to the actuator of the vehicle when the vehicle is traveling on the to-be-traveled path based on the target compensation acceleration sequence includes: Determine a state vector of the vehicle at a current moment; the state vector is used to characterize a motion state of the vehicle; Here, the state vector may include one or more of speed, actual acceleration, and expected acceleration, wherein the more information the state vector includes, the more accurate the predicted state quantity is.

[0048] The target acceleration change is determined by using a prediction model based on the state vector and the target compensation acceleration sequence; the prediction model is used to predict the speed of the vehicle on the path to be driven.

[0049] Here, the prediction model can be pre-established or downloaded from a server.

[0050] In the embodiment of the present invention, target acceleration compensation is performed by combining the slope information of the path to be traveled, and then the target acceleration change is determined by utilizing the prediction model, using the state vector and the target compensation acceleration sequence, thereby improving the accuracy of the target acceleration.

[0051] Furthermore, the method for constructing the prediction model includes: Determining a prediction state matrix of the prediction model and a prediction input matrix of the prediction model based on a first-order inertial system of the vehicle; Here, the first-order inertial system refers to the dynamic response characteristics of the vehicle system to input signals (such as the driver's operating instructions, changes in the external environment, etc.). When the vehicle receives the driver's input signals (such as changes in the accelerator and brake pedal position), the vehicle's speed, acceleration and other output signals will not change immediately, but will gradually adjust to a new steady-state value according to a certain time constant.

[0052] The first-order inertial system is essentially a model that is constructed based on Newtonian kinematics, historical state vectors, and control variables (acceleration changes). The predicted state matrix and predicted input matrix are calculated based on the historical state vector and acceleration changes.

[0053] For example, the first-order inertial system is a discrete state space, and the established model is the following formula (1): (1)

[0054] in, is the state quantity of the next control cycle, is the state transfer matrix, is the state quantity observed at the current moment, B is the input matrix, is the expected acceleration change, is the compensation matrix, Compensate the acceleration for the target.

[0055] According to formula (1), the state vector of k+2 period can be derived as follows: (2)

[0056] Convert formula (2) into the following formula (3):

[0057] By analogy, we get the state vector of the k+Nth period, as shown in formula (4):

[0058] The equation obtains the state vector and system output of the next cycle through the current state vector, control variables and target compensation acceleration. According to formula (1)-formula (3), the expression of the state vector sequence X from k+1 to k+N can be obtained. The expression of the state vector sequence X is multiplied by vector C, and the vehicle speed is selected as the system output. Assume that the state vector sequence is [V aa 期望 ] T , C is [1 0 0], and the velocity sequence is obtained after multiplying the two. The predicted state matrix is ​​the matrix in front of the integrated state vector, and the predicted output matrix is ​​the matrix in front of the integrated acceleration change.

[0059] The prediction model is constructed based on the expression of the state vector, the expression of the target compensation acceleration sequence, the expression of the target acceleration change, the prediction state matrix and the prediction input matrix.

[0060] Here, the expression of the prediction model can be the sum of three addend expressions. The first addend expression can be the product of the expression of the prediction state matrix and the state vector, or the weighted product of the weighted expression of the prediction state matrix and the state vector; the second addend expression can be the product of the expression of the prediction input matrix and the target acceleration change, or the weighted product of the weighted expression of the prediction input matrix and the target acceleration change; the third addend expression can be the expression of the target compensation acceleration sequence, or the weighted expression of the target compensation acceleration sequence.

[0061] For example, the prediction model is expressed as the following formula (5): (5)

[0062] in, is the predicted system output, The predicted state matrix, is the prediction input matrix, is the system disturbance matrix, is the predicted system disturbance, i.e. the above target compensation acceleration sequence.

[0063] In an embodiment of the present invention, a prediction model is constructed based on a state vector, a target compensation acceleration sequence, a target acceleration change, a predicted state matrix and a predicted input matrix. By combining the slope information, a prediction model is constructed to improve the prediction accuracy of the model prediction and achieve precise control of the vehicle.

[0064] Further, the using the prediction model to determine the target acceleration change based on the state vector and the target compensation acceleration sequence includes: Substituting the state vector and the target compensation acceleration sequence into the prediction model, a first function is obtained with the target acceleration change of the vehicle within the prediction time period as a variable.

[0065] Here, the state vector may be directly acquired through a sensor, or may be acquired by updating an initial state vector acquired by the sensor.

[0066] Here, the state vector and the target compensation acceleration sequence are two specific values. After substituting them into formula (5), only the target acceleration change is an unknown quantity, and the first function is obtained. By solving the first function, the target acceleration change sequence is obtained.

[0067] The first function is actually an expression with the target acceleration change as the independent variable and the speed as the dependent variable. In other words, the value of the first function is the output speed.

[0068] Determining an objective function based on the first function and an ideal speed sequence of the vehicle on the path to be traveled; Here, the objective function can be the difference between the first function and the ideal speed sequence, or the difference between the weight of the first function and the weight of the ideal speed sequence. It should be understood that the smaller the difference between the first function value and the ideal speed, the more accurate the prediction result; in any case, the larger the difference, the less accurate the prediction result.

[0069] For example, the objective function is as follows: (6)

[0070] in, is the objective function, is the desired speed, Q matrix is ​​the state vector weight matrix, R is the control quantity weight matrix, and both Q and R matrices are positive definite matrices.

[0071] determining a constraint condition based on the acceleration change of the vehicle, the acceleration of the vehicle, and the speed of the vehicle; Here, the constraint conditions essentially set upper and lower limits for the acceleration change, acceleration and speed, respectively, wherein the upper and lower limits can be determined based on the vehicle's performance indicators or the vehicle's historical driving data, or can be determined by the staff based on experience.

[0072] For example, the constraint condition is the following formula (7):

[0073] in, Indicates the minimum value of the acceleration change. Indicates the maximum value of the acceleration change. represents the minimum value of acceleration, represents the maximum value of acceleration, Indicates the minimum value of speed, Indicates the maximum value of speed.

[0074] Based on the difference between the predicted speed of the prediction model and the ideal speed corresponding to the predicted speed, and the constraint conditions, the objective function is continuously optimized to obtain a sequence of acceleration changes corresponding to the minimum value of the objective function.

[0075] Based on the acceleration change sequence, the target acceleration change is determined.

[0076] Here, the method for determining the target acceleration variation may be any appropriate method, such as selecting the first one in the acceleration variation sequence as the target acceleration variation; or taking the first N acceleration variations as the target acceleration variation. The present invention does not limit this.

[0077] In the embodiment of the present invention, the optimal acceleration change is found through the objective function optimization algorithm, so as to improve the accuracy of the prediction model in predicting the speed, thereby achieving precise control of the vehicle.

[0078] Further, controlling the speed of the vehicle to adjust to a target speed based on the target acceleration change includes: Based on the target acceleration change, a target acceleration of the vehicle within the prediction period is determined.

[0079] Based on the target acceleration, a target speed of the vehicle during the prediction period is determined.

[0080] When the target acceleration is greater than zero, an opening degree of an accelerator pedal of the vehicle is determined based on the target acceleration.

[0081] It should be noted that if the target acceleration is greater than zero, it means that the vehicle needs to accelerate on the path to be driven, and the accelerator pedal can be controlled to accelerate.

[0082] Here, the degree of opening of the vehicle's accelerator pedal may be determined by any suitable method, for example, using an inverse engine model to directly output the degree of opening of the accelerator pedal; or for another example, using a preset mapping table to determine the degree of opening of the accelerator pedal corresponding to the target acceleration.

[0083] When the target acceleration is less than zero, an opening degree of a brake pedal of the vehicle is determined based on the target acceleration.

[0084] It should be noted that if the target acceleration is less than zero, it means that the vehicle needs to slow down on the path to be driven, and the brake pedal can be controlled to accelerate.

[0085] Here, the opening of the vehicle's brake pedal may be determined by any suitable method, for example, using an inverse brake model to directly output the opening of the brake pedal; or using a preset mapping table to determine the opening of the brake pedal corresponding to the target acceleration.

[0086] The speed of the vehicle is controlled to be adjusted to the target speed based on the opening degree of the accelerator pedal or the opening degree of the brake pedal.

[0087] Here, after obtaining the opening of the accelerator pedal or the opening of the brake pedal, the opening of the accelerator pedal or the opening of the brake pedal is converted into an executable physical instruction to control the speed of the vehicle to adjust to the target speed, ensuring that the vehicle can operate according to the optimal control strategy.

[0088] In an embodiment of the present invention, by using the acceleration change caused by the actuator as the control quantity, the changes in the opening of the accelerator pedal and the opening of the brake pedal are strictly constrained, thereby reducing sudden throttle or brake changes and frequent switching between the two, thereby effectively improving fuel economy and reducing operating costs.

[0089] Further, the determining of a target compensation acceleration sequence for the vehicle to travel on the path to travel based on the slope information of the path to travel corresponding to each moment includes: The rolling friction of the vehicle on the path to be traveled and the wind resistance on the path to be traveled are determined.

[0090] Here, rolling friction refers to the friction generated when the vehicle tires roll on the road. Wind resistance is the resistance from the air when the vehicle is driving.

[0091] It should be noted that the friction force and wind resistance at each location on the travel path may be the same or different, and are not specifically limited here.

[0092] Based on the slope information of the path to be driven corresponding to each moment, the rolling friction force and the gravitational acceleration of the vehicle, an initial compensation acceleration sequence for the vehicle to drive on the path to be driven is determined.

[0093] Here, the compensation acceleration can be the first difference, which is the difference between the first product and the second product. The first product can be the product of the sine value of the slope angle corresponding to the path and the gravitational acceleration, or it can be the weighted product of the sine value of the slope angle corresponding to the path and the weighted product of the gravitational acceleration; the second product can be the product of the cosine value of the slope angle corresponding to the path, the gravitational acceleration, and the rolling friction, or it can be the product of the weighted cosine value of the slope angle corresponding to the path, the gravitational acceleration, and the rolling friction.

[0094] The target compensation acceleration sequence is determined based on the wind resistance and the initial compensation acceleration sequence.

[0095] Here, the target compensation acceleration may be the difference between the initial compensation acceleration sequence and the wind resistance, or may be the difference between the weight of the initial compensation acceleration sequence and the weight of the wind resistance.

[0096] Exemplarily, the target compensation acceleration S is calculated as follows: (8)

[0097] in, represents the acceleration due to gravity, represents the slope angle, is the rolling friction, Indicates wind resistance.

[0098] It should be noted that formula (8) is a calculation of a target compensation acceleration. Different target compensation accelerations may correspond to Differently, the target compensation acceleration sequence includes the target compensation acceleration corresponding to each moment.

[0099] In the embodiment of the present invention, the prior information of the path is fully utilized, the slope of the path to be traveled is taken into consideration, the brake and throttle are controlled in advance, more accurate speed control is achieved, and the driving stability of the mine car under complex road conditions is significantly improved.

[0100] Further, determining the state vector of the vehicle at the current moment includes: Collecting the initial state vector of the vehicle at the current moment through a sensor; Based on the external environment information of the environment in which the vehicle is located and the braking information of the vehicle, the initial state vector is updated to obtain the state vector of the vehicle at the current moment.

[0101] Here, the initial state variables may include one or more of vehicle speed, acceleration, engine speed, brake state, and external environment information. The vehicle speed, acceleration, expected acceleration, etc. are updated according to the external environment information and the vehicle's brake information to obtain the current state vector.

[0102] It should be noted that the vehicle may need to continuously predict the speed at the next moment during driving. Therefore, the initial state vector of the vehicle at the current moment is continuously detected, and the initial state vector is updated based on the external environment information and vehicle braking information to obtain the state vector of the vehicle at the current moment. The state vector at the current moment is input into the prediction model for a new round of prediction.

[0103] In the embodiment of the present invention, the vehicle state fed back in real time can more accurately predict the future vehicle behavior, and dynamically adjust the control strategy based on these prediction results. The result of rolling optimization will generate a new set of control inputs, which not only consider the vehicle state of the current cycle, but also predict the state in multiple future cycles, so as to respond to possible path changes or environmental interference in advance.

[0104] The following are application scenarios of the vehicle control method provided by the present invention.

[0105] Figure 2 FIG. 2 is a flow chart of the vehicle control method provided by the present invention. Figure 2 As shown, the method includes: Step 201: Obtain a slope information sequence of the path to be driven from the preview path information.

[0106] Step 202: Determine a target compensation acceleration sequence according to the slope information sequence.

[0107] Here, the target compensation acceleration sequence can be understood as slope disturbance compensation.

[0108] Step 203: Determine an initial prediction model according to the first-order inertial system.

[0109] Step 204: Determine a discrete state velocity model according to the target compensation acceleration sequence and the initial prediction model.

[0110] Step 205: Determine a prediction model according to the discrete state velocity model.

[0111] Step 206: Establish an objective function.

[0112] Step S207: Determine the ideal speed.

[0113] Here, the ideal speed can be understood as a reference speed.

[0114] Step 208: Establish constraints.

[0115] Step 209: Optimize the objective function to obtain the target acceleration change.

[0116] Step 210: Determine whether the acceleration is greater than 0, if it is greater than 0, execute step 211, otherwise, execute step 212.

[0117] Step 211: Determine the accelerator pedal opening according to the acceleration using the inverse engine model.

[0118] Step 212: Determine the brake pedal opening according to the acceleration using the inverse brake model.

[0119] Step 213: The speed of the vehicle is adjusted to the target speed.

[0120] Step 214: Use sensors to collect the initial state vector of the vehicle at the current moment.

[0121] Step 215: Update the initial state vector to obtain a state vector.

[0122] Step 216: Use the prediction model to perform the next round of prediction.

[0123] The vehicle control method of the present invention has the following advantages over the prior art: it makes full use of the prior information of the preview path, considers the slope of the path to be traveled, controls the brake and throttle in advance, realizes more accurate speed control, and significantly improves the driving stability of the mine car under complex road conditions; by taking the acceleration change caused by the actuator as the control quantity, strictly constrains the changes in the throttle opening and the brake opening, reduces the sudden throttle or brake changes and the frequent switching between the two, thereby effectively improving fuel economy and reducing operating costs; since the mine car has a complex structure and it is difficult to establish an accurate dynamic model, the present invention uses feedback correction and rolling optimization to have lower requirements on the accuracy of model establishment, so the control method is not only suitable for mine cars, but can also be extended to other unmanned equipment in mines.

[0124] The vehicle control device provided by the present invention is described below. The vehicle control device described below and the vehicle control method described above can be referenced to each other.

[0125] Figure 3 : is a schematic diagram of the structure of the vehicle control device provided by the present invention, such as Figure 3 As shown, the vehicle control device 300 includes: a first determination module 301, a second determination module 302, a third determination module 303, and a control module 304, wherein: The first determination module 301 is used to determine the slope information sequence of the path to be driven by the vehicle within the predicted time period; the slope information sequence includes the slope information of the path to be driven corresponding to each moment within the predicted time period; A second determination module 302 is used to determine a target compensation acceleration sequence for the vehicle to travel on the path to travel based on the slope information of the path to travel corresponding to each moment; A third determination module 303 is used to determine, based on the target compensation acceleration sequence, a target acceleration change corresponding to the actuator of the vehicle when the vehicle travels on the to-be-traveled path; The control module 304 is used to control the speed of the vehicle to be adjusted to a target speed based on the target acceleration change when the vehicle travels on the path to be traveled.

[0126] In an exemplary embodiment, the third determination module 303 is specifically used to: determine the state vector of the vehicle at the current moment; the state vector is used to characterize the motion state of the vehicle; use a prediction model to determine the target acceleration change based on the state vector and the target compensated acceleration sequence; the prediction model is used to predict the speed of the vehicle on the path to be driven.

[0127] In an exemplary embodiment, the third determination module 303 is further specifically used to: determine a prediction state matrix of the prediction model and a prediction input matrix of the prediction model based on the first-order inertial system of the vehicle; and construct the prediction model based on an expression of the state vector, an expression of the target compensation acceleration sequence, an expression of the target acceleration change, the prediction state matrix and the prediction input matrix.

[0128] In an exemplary embodiment, the third determination module 303 is further specifically used to: substitute the state vector and the target compensated acceleration sequence into the prediction model to obtain a first function with the target acceleration change of the vehicle within the prediction time period as a variable; determine the objective function based on the first function and the ideal speed sequence of the vehicle on the path to be driven; determine constraints based on the acceleration change of the vehicle, the acceleration of the vehicle and the speed of the vehicle; continuously optimize the objective function based on the difference between the predicted speed of the prediction model and the ideal speed corresponding to the predicted speed, as well as the constraints, to obtain the acceleration change sequence corresponding to the minimum value of the objective function; and determine the target acceleration change based on the acceleration change sequence.

[0129] In an exemplary embodiment, the control module 304 is specifically used to: determine the target acceleration of the vehicle within the prediction time period based on the target acceleration change; determine the target speed of the vehicle within the prediction time period based on the target acceleration; when the target acceleration is greater than zero, determine the opening of the accelerator pedal of the vehicle based on the target acceleration; when the target acceleration is less than zero, determine the opening of the brake pedal of the vehicle based on the target acceleration; and control the speed of the vehicle to be adjusted to the target speed based on the opening of the accelerator pedal or the opening of the brake pedal.

[0130] In an exemplary embodiment, the second determination module 302 is specifically used to: determine the rolling friction of the vehicle on the path to be driven and the wind resistance on the path to be driven; determine an initial compensation acceleration sequence for the vehicle to travel on the path to be driven based on the slope information of the path to be driven corresponding to each moment, the rolling friction and the gravity acceleration of the vehicle; determine the target compensation acceleration sequence based on the wind resistance and the initial compensation acceleration sequence.

[0131] In an exemplary embodiment, the first determination module 301 is specifically used to: collect the initial state vector of the vehicle at the current moment through a sensor; update the initial state vector based on the external environment information of the vehicle's environment and the braking information of the vehicle to obtain the state vector of the vehicle at the current moment.

[0132] Figure 4 is a schematic diagram of the structure of the electronic device provided by the present invention, such as Figure 4 As shown, the electronic device may include: a processor 410, a communication interface 420, a memory 430 and a communication bus 440, wherein the processor 410, the communication interface 420 and the memory 430 communicate with each other through the communication bus 440. The processor 410 may call the logic instructions in the memory 430 to execute the vehicle control method, which includes: determining the slope information sequence of the path to be driven by the vehicle within the predicted time period; the slope information sequence includes the slope information of the path to be driven corresponding to each moment within the predicted time period; based on the slope information of the path to be driven corresponding to each moment, determining the target compensation acceleration sequence of the vehicle driving on the path to be driven; based on the target compensation acceleration sequence, determining the target acceleration change corresponding to the actuator of the vehicle when the vehicle drives on the path to be driven; when the vehicle drives on the path to be driven, based on the target acceleration change, controlling the speed of the vehicle to be adjusted to the target speed.

[0133] In addition, the logic instructions in the above-mentioned memory 430 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0134] On the other hand, the present invention also provides a computer program product, which includes a computer program, and the computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the vehicle control method provided by the above-mentioned methods, which includes: determining a slope information sequence of a path to be traveled by the vehicle within a predicted time period; the slope information sequence includes the slope information of the path to be traveled corresponding to each moment within the predicted time period; based on the slope information of the path to be traveled corresponding to each moment, determining a target compensation acceleration sequence for the vehicle to travel on the path to be traveled; based on the target compensation acceleration sequence, determining a target acceleration change corresponding to the vehicle's actuator when the vehicle travels on the path to be traveled; when the vehicle travels on the path to be traveled, controlling the vehicle speed to adjust to the target speed based on the target acceleration change.

[0135] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the vehicle control method provided by the above-mentioned methods, the method comprising: determining a slope information sequence of a path to be traveled by the vehicle within a predicted time period; the slope information sequence comprises the slope information of the path to be traveled corresponding to each moment within the predicted time period; based on the slope information of the path to be traveled corresponding to each moment, determining a target compensation acceleration sequence for the vehicle to travel on the path to be traveled; based on the target compensation acceleration sequence, determining a target acceleration change corresponding to the actuator of the vehicle when the vehicle travels on the path to be traveled; when the vehicle travels onto the path to be traveled, controlling the speed of the vehicle to be adjusted to the target speed based on the target acceleration change.

[0136] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0137] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0138] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A vehicle control method, characterized in that: include: Determine a slope information sequence of a path to be traveled by the vehicle within a predicted time period; the slope information sequence includes the slope information of the path to be traveled corresponding to each moment within the predicted time period; Determining a target compensation acceleration sequence for the vehicle to travel on the path to travel based on the slope information of the path to travel corresponding to each moment; Determining, based on the target compensation acceleration sequence, a target acceleration change corresponding to an actuator of the vehicle when the vehicle is traveling on the path to be traveled; When the vehicle travels on the to-be-traveled path, the speed of the vehicle is controlled to be adjusted to a target speed based on the target acceleration variation.

2. The vehicle control method according to claim 1, characterized in that: The determining, based on the target compensation acceleration sequence, a target acceleration change corresponding to the actuator of the vehicle when the vehicle travels on the to-be-traveled path comprises: Determine a state vector of the vehicle at a current moment; the state vector is used to characterize a motion state of the vehicle; The target acceleration change is determined by using a prediction model based on the state vector and the target compensation acceleration sequence; the prediction model is used to predict the speed of the vehicle on the path to be driven.

3. The vehicle control method according to claim 2, characterized in that: The method for constructing the prediction model includes: Determining a prediction state matrix of the prediction model and a prediction input matrix of the prediction model based on a first-order inertial system of the vehicle; The prediction model is constructed based on the expression of the state vector, the expression of the target compensation acceleration sequence, the expression of the target acceleration change, the prediction state matrix and the prediction input matrix.

4. The vehicle control method according to claim 2, characterized in that: The using the prediction model to determine the target acceleration change based on the state vector and the target compensation acceleration sequence includes: Substituting the state vector and the target compensation acceleration sequence into the prediction model to obtain a first function with the target acceleration change of the vehicle within the prediction time period as a variable; Determining an objective function based on the first function and an ideal speed sequence of the vehicle on the path to be driven; determining a constraint condition based on the acceleration change of the vehicle, the acceleration of the vehicle, and the speed of the vehicle; Based on the difference between the predicted speed of the prediction model and the ideal speed corresponding to the predicted speed, and the constraint condition, the objective function is continuously optimized to obtain a sequence of acceleration changes corresponding to the minimum value of the objective function; Based on the acceleration change sequence, the target acceleration change is determined.

5. The vehicle control method according to any one of claims 1 to 4, characterized in that: The controlling the speed of the vehicle to adjust to a target speed based on the target acceleration change includes: Determining a target acceleration of the vehicle within the prediction time period based on the target acceleration change; determining a target speed of the vehicle within the prediction time period based on the target acceleration; When the target acceleration is greater than zero, determining the opening of the accelerator pedal of the vehicle based on the target acceleration; When the target acceleration is less than zero, determining an opening degree of a brake pedal of the vehicle based on the target acceleration; The speed of the vehicle is controlled to be adjusted to the target speed based on the opening degree of the accelerator pedal or the opening degree of the brake pedal.

6. The vehicle control method according to any one of claims 1 to 4, characterized in that: The step of determining a target compensation acceleration sequence for the vehicle to travel on the path to travel based on the slope information of the path to travel corresponding to each moment includes: Determining the rolling friction of the vehicle on the path to be traveled and the wind resistance on the path to be traveled; Determining an initial compensation acceleration sequence for the vehicle to travel on the path to travel based on the slope information of the path to travel corresponding to each moment, the rolling friction force and the gravitational acceleration of the vehicle; The target compensation acceleration sequence is determined based on the wind resistance and the initial compensation acceleration sequence.

7. The vehicle control method according to claim 2, characterized in that: The determining of the state vector of the vehicle at the current moment includes: Collecting the initial state vector of the vehicle at the current moment through a sensor; Based on the external environment information of the environment in which the vehicle is located and the braking information of the vehicle, the initial state vector is updated to obtain the state vector of the vehicle at the current moment.

8. A vehicle control device, characterized in that: include: A first determination module is used to determine a slope information sequence of a path to be traveled by the vehicle within a predicted time period; the slope information sequence includes the slope information of the path to be traveled corresponding to each moment within the predicted time period; A second determination module is used to determine a target compensation acceleration sequence for the vehicle to travel on the path to travel based on the slope information of the path to travel corresponding to each moment; A third determination module is used to determine, based on the target compensation acceleration sequence, a target acceleration change amount corresponding to the actuator of the vehicle when the vehicle travels on the to-be-traveled path; The control module is used to control the speed of the vehicle to be adjusted to a target speed based on the target acceleration change when the vehicle travels on the path to be traveled.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the vehicle control method according to any one of claims 1 to 7 is implemented.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the vehicle control method according to any one of claims 1 to 7 is implemented.