An intelligent tractor unit path planning control method, device, equipment and medium

Abstract

The application discloses an intelligent container truck path planning control method and device, equipment and medium, relates to the path planning control field, and the method comprises the steps of: based on the time domain decomposition method, the path planning optimization problem is decomposed into a plurality of independent time domain sub-blocks, and a plurality of control periods of the prediction time domain are obtained;For each control period, based on the vehicle dynamics model, the state evolution equation and the running state data, the current state and the control input of the intelligent container truck are updated, and the updated state quantity and the updated control input are obtained;Based on the Lagrange function, the path planning sub-model of each time domain sub-block is established, the Lagrange dual variable is updated, and the updated dual variable is obtained;According to the updated dual variable and the updated state quantity, the block moment is calculated;Whether the stop criterion is met is judged based on the block moment and the path performance index;If yes, the current target trajectory is determined as the final path planning result, and the calculation efficiency and control accuracy are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of path planning control, in particular to an intelligent truck path planning control method, device, equipment and medium. BACKGROUND

[0002] In the field of autonomous driving, path planning is particularly important for the operation of intelligent trucks. However, the current intelligent truck autonomous driving system has many deficiencies in path planning control, especially in complex scene processing. The calculation efficiency and control accuracy of traditional path planning methods are low. SUMMARY

[0003] The purpose of the present application is to provide an intelligent truck path planning control method, device, equipment and medium, which can improve the calculation efficiency and control accuracy of path planning.

[0004] To achieve the above purpose, the present application provides the following solutions.

[0005] In a first aspect, the present application provides an intelligent truck path planning control method, comprising the following steps:

[0006] Obtaining the running state data of the intelligent truck;

[0007] Based on a time domain decomposition method, the path planning optimization problem is decomposed into a plurality of independent time domain sub-blocks, and a plurality of control periods of the prediction time domain are obtained; one control period corresponds to one time domain sub-block;

[0008] For each control period, based on the vehicle dynamics model, the state evolution equation and the running state data, the current state and control input of the intelligent truck are updated to obtain the updated state quantity and the updated control input;

[0009] Based on the Lagrange function, a path planning sub-model of each time domain sub-block is established, the Lagrange dual variables are updated to obtain updated dual variables, and the block moment is calculated according to the updated dual variables and the updated state quantity; the path planning sub-model includes an objective function and a constraint condition; the constraint condition includes a dynamics constraint and a consistency constraint; the consistency constraint is determined by a global consistency variable, and is used to constrain the coordination relationship between time domain sub-blocks; the block moment is composed of state changes;

[0010] Based on the block moment and the path performance index, it is judged whether the stopping criterion is met; if yes, the current target trajectory is determined as the final path planning result; the path performance index includes a tracking performance index, a comfort performance index and a steering performance index; the stopping criterion is that the number of iterations reaches the maximum number of iterations, the tracking performance index reaches the maximum allowed tracking error, the comfort performance index reaches the maximum comfort performance deviation or the steering performance index reaches the maximum steering error.

[0011] In a second aspect, the present application provides an intelligent tractor trailer path planning control device, comprising the following modules:

[0012] An operating state data acquisition module, configured to acquire operating state data of the intelligent tractor trailer;

[0013] A time domain decomposition module, configured to decompose the path planning optimization problem into a plurality of independent time domain sub-blocks based on a time domain decomposition method, to obtain a plurality of control periods in a prediction time domain; one control period corresponds to one time domain sub-block;

[0014] A state evolution module, configured to, for each control period, update a current state and a control input of the intelligent tractor trailer based on a vehicle dynamics model, a state evolution equation and the operating state data, to obtain an updated state quantity and an updated control input;

[0015] A block update calculation module, configured to establish a path planning sub-model of each time domain sub-block based on a Lagrange function, to update a Lagrange dual variable to obtain an updated dual variable, and to calculate a block moment based on the updated dual variable and the updated state quantity; the path planning sub-model comprises an objective function and a constraint condition; the constraint condition comprises a dynamics constraint and a consistency constraint; the consistency constraint is determined by a global consistency variable and is used to constrain a cooperative relationship between the time domain sub-blocks; the block moment is composed of state changes;

[0016] A stop criterion convergence module, configured to judge whether a stop criterion is met based on the block moment and a path performance index; if the stop criterion is met, a current target trajectory is determined as a final path planning result; the path performance index comprises a tracking performance index, a comfort performance index and a maneuvering performance index; the stop criterion is that an iteration number reaches a maximum iteration number, the tracking performance index reaches a maximum allowed tracking error, the comfort performance index reaches a maximum comfort performance deviation or the maneuvering performance index reaches a maximum maneuvering error.

[0017] In a third aspect, the present application provides a computer device, comprising a memory, a processor and a computer program stored in the memory and executable on the processor, and the processor executes the computer program to implement the intelligent tractor trailer path planning control method.

[0018] In a fourth aspect, the present application provides a computer readable storage medium, having a computer program stored thereon, and the computer program is executed by a processor to implement the intelligent tractor trailer path planning control method.

[0019] According to the embodiments of the present application, the following technical effects are achieved:

[0020] The application provides a smart container truck path planning control method, device, equipment and medium, a path planning optimization problem is decomposed into multiple independent time domain sub-blocks, a plurality of control cycles of a prediction time domain are obtained, path optimization results of each control cycle are calculated in parallel, states of each time domain sub-block are synchronized through consistent variables, and finally global optimization is realized; the application decomposes a complex global optimization problem into a plurality of parallel processable sub-problems through time domain decomposition and parallel calculation technology, greatly reduces calculation time, and improves calculation efficiency; a multi-dimensional performance index evaluation system is introduced, performance evaluation is performed in three aspects of tracking performance index, comfort performance index and steering performance index, path tracking performance and smart container truck dynamic control capability are comprehensively optimized, and control precision is improved. BRIEF DESCRIPTION OF DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed to be used in the embodiments will be briefly introduced as follows. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative effort on the basis of these drawings.

[0022] Figure 1 An application environment diagram of a smart container truck path planning control method in an embodiment of the present application;

[0023] Figure 2 A flowchart of a smart container truck path planning control method provided in an embodiment of the present application;

[0024] Figure 3 A specific process diagram of a smart container truck path planning control method provided in an embodiment of the present application;

[0025] Figure 4 A constraint optimization quantization flowchart based on time domain decomposition provided in an embodiment of the present application;

[0026] Figure 5 A time domain decomposition flowchart provided in an embodiment of the present application;

[0027] Figure 6 A functional module diagram of a smart container truck path planning control device provided in an embodiment of the present application;

[0028] Figure 7 A structural diagram of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0029] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0030] The existing path planning mainly has the following problems:

[0031] First, the ability to handle temporal coupling constraints is insufficient. Existing technologies typically treat path planning as a holistic optimization problem, failing to effectively decompose the temporal coupling constraints. This approach becomes rigid when dealing with multiple consecutive control cycles, unable to flexibly adjust the state transition relationships between cycles, leading to a significant reduction in computational efficiency. Furthermore, the lack of a robust temporal decomposition mechanism prevents the full utilization of the potential of parallel computing, thus limiting the system's real-time optimization capabilities.

[0032] Secondly, the dynamic characteristic modeling is not comprehensive enough. Existing solutions fail to fully characterize the lateral and longitudinal dynamic characteristics of intelligent trucks, especially under complex working conditions, where the prediction accuracy of the vehicle's motion state is significantly insufficient. In such cases, the prediction error is amplified in practical applications, reducing the reliability of path planning. More importantly, there is currently no systematic method for quantitatively evaluating dynamic characteristics, further limiting the direction of technological optimization.

[0033] Existing path planning systems also have significant technical shortcomings when dealing with global consistency constraints. Poor coordination of block computation is one prominent issue. Current technologies lack efficient block decoupling mechanisms, making it difficult to achieve consistent coordination of states between different computation modules. Although some solutions attempt to introduce Lagrange dual variables, the update strategies are not mature enough, leading to low solution efficiency and even affecting the global optimization effect.

[0034] The lack of a performance evaluation system further weakens the system's effectiveness. Current solutions rarely involve H2 / Key performance indicators such as norms and Lyapunov exponents cannot comprehensively evaluate the merits of path planning schemes. The lack of systematic quantitative evaluation methods for dynamics, comfort, and handling, and the absence of a unified indicator framework, makes performance evaluation difficult to standardize.

[0035] There is still significant room for improvement in existing stopping criteria for block-based optimization computation. Firstly, the evaluation metrics are too simplistic. Most existing stopping criteria focus on evaluating a single performance indicator, neglecting the comprehensive consideration of multiple dimensions such as vehicle spacing error and speed error. Especially under complex operating conditions, this single-dimensional evaluation method struggles to fully reflect the actual performance of the system. Currently, stopping criteria fail to effectively integrate H2 / The use of norms for comprehensive performance evaluation raises questions about the reliability of the optimization results. Secondly, dynamic adaptability is poor. Existing technologies lack the ability to adapt to the dynamic characteristics of the system, and the stopping criteria cannot automatically adjust the evaluation standards according to changes in different operating conditions. The response to external disturbances is also relatively slow, making it difficult to meet the real-time and adaptability requirements of complex operating environments.

[0036] Existing path planning techniques still face serious computational efficiency issues in practical applications, which further restricts their widespread adoption. First, the solution speed is insufficient: due to the failure to fully utilize time-domain decomposition techniques, the overall computational burden is heavy, resulting in slow convergence speed for path planning optimization. Furthermore, the imperfections in parallel computing mechanisms often significantly impact real-time control performance. Second, resource consumption is high: the global optimization process requires substantial computational resources, while existing technologies still have shortcomings in memory efficiency. This high resource consumption not only makes it difficult to meet real-time control requirements but also increases the hardware costs of system operation.

[0037] Existing path planning and control technologies have significant shortcomings in several aspects, including handling time-domain coupling constraints, global consistency constraints, stopping criterion design, and computational efficiency. These problems severely restrict the overall performance optimization of intelligent truck autonomous driving systems. To address these issues, this application provides a path planning and control method, apparatus, device, and medium for intelligent trucks.

[0038] (1) Basic technical issues

[0039] The core objective of this application is to address the fundamental technical challenges faced in path planning for autonomous driving of intelligent trucks, primarily focusing on two aspects: decoupling temporal coupling constraints and optimizing block-based computation. Firstly, decoupling temporal coupling constraints is a critical challenge in current path planning technologies. Existing technologies often struggle to effectively handle temporal coupling relationships between control cycles, while this application aims to achieve effective decoupling between different control cycles, ensuring independent optimization computation for each cycle. To this end, this application proposes a reasonable globally consistent variable, enabling efficient collaboration between different temporal blocks and avoiding redundant computational burdens caused by temporal coupling during the calculation process. Simultaneously, each decoupled subsystem must guarantee the convergence and stability of the solution, thereby preventing the negative impact of computational uncertainty on system performance.

[0040] Optimizing block-based computation is also a key focus of this application. To improve the computational efficiency of path planning, this application proposes an efficient block update mechanism aimed at optimizing the solution process for each computation block. Besides ensuring the real-time and accurate data exchange between blocks, it is also necessary to balance the allocation of computational resources to ensure that system resources are not excessively consumed while meeting performance requirements.

[0041] (2) Performance evaluation issues

[0042] To address the specific needs of intelligent truck autonomous driving systems in complex application scenarios, this application also needs to solve a series of performance evaluation problems. The core of these problems lies in how to comprehensively and accurately evaluate performance across multiple dimensions, including power, comfort, and handling, and effectively integrate these evaluations with optimization objectives. Firstly, power performance evaluation is a key issue in path planning. How to utilize… Accurately assessing vehicle spacing and speed errors using norms is one of the key technical challenges of this application. Based on this assessment method, this application will also establish a reasonable tracking performance index system to ensure real-time monitoring and evaluation of the system's power performance under different operating conditions, thereby guaranteeing the accuracy of path planning.

[0043] Building upon this foundation, comfort performance evaluation is equally crucial. To achieve an accurate assessment of driving comfort, this application employs the H2 norm for quantitative analysis, comprehensively considering the impact of factors such as control costs and external disturbances, and proposes a complete quantitative evaluation standard for comfort. This standard not only reflects the smoothness of intelligent truck handling but also effectively addresses the impact of disturbances under various operating conditions.

[0044] Furthermore, the handling performance evaluation focuses on assessing directional stability and trajectory error. By utilizing the Lyapunov index, this application can effectively evaluate the directional stability of intelligent trucks and establish a comprehensive trajectory error evaluation mechanism to ensure the continuous monitorability of handling performance in real-time dynamic environments.

[0045] (3) Algorithm implementation problem

[0046] To ensure the practical feasibility of this application, solving the algorithm implementation problem is crucial. First, optimizing computational efficiency is fundamental to improving system performance. This application proposes an efficient parallel computing strategy that significantly improves the system's real-time response capability by optimizing the iterative convergence speed and reducing resource consumption during computation. Furthermore, optimizing the iterative convergence speed involves not only improving solution efficiency but also reducing computational resource consumption to ensure the system can maintain stable operation under high load.

[0047] Secondly, autonomous driving systems must possess strong robustness, especially in complex and dynamically changing environments. To cope with changes and uncertainties in the external environment, this application proposes a robustness guarantee mechanism that enables the algorithm to maintain stability under different operating conditions and effectively resist the influence of external disturbances.

[0048] (4) Engineering implementation issues

[0049] From an engineering implementation perspective, this application still needs to address several engineering challenges, particularly in terms of real-time performance and reliability. First, real-time performance is crucial for the successful application of autonomous driving systems. Ensuring the real-time generation and execution of control commands within the system is a critical issue that this application must resolve. To address this problem, this application proposes an efficient control mechanism designed to reduce the impact of computational latency on control effectiveness and, by balancing control accuracy and real-time requirements, ensure the system's real-time response capability in various application scenarios.

[0050] Furthermore, reliability assurance plays a crucial role in engineering implementation. The long-term stability of an autonomous driving system directly impacts its safety and reliability. Therefore, addressing potential constraints during system operation and establishing effective fault detection and handling mechanisms under limited hardware resources is a key task of this application. By designing redundancy backup mechanisms and self-diagnostic functions, this application ensures system stability during long-term operation and effectively addresses potential hardware or software failures.

[0051] (5) Comprehensive optimization problem

[0052] This application also includes solutions to comprehensive optimization problems, particularly in multi-objective coordination and adaptive enhancement. Autonomous driving path planning requires balancing multiple performance indicators, especially power, comfort, and handling. Achieving dynamic trade-offs among different control objectives to ensure optimal overall performance is a significant technical challenge of this application. By introducing an adaptive adjustment mechanism, this application can flexibly adjust the weights of various performance indicators under different operating conditions, ensuring that the intelligent truck maintains its optimal state in dynamically changing environments.

[0053] Finally, adaptive enhancement is key to improving system flexibility. Autonomous driving systems need to cope with various complex operating scenarios; therefore, this application introduces an adaptive parameter adjustment mechanism, enabling the system to adjust in real time according to actual operating conditions to adapt to different scenarios. Based on the above, this application ensures the algorithm's wide applicability and high versatility, allowing it to operate stably in diverse environments.

[0054] By solving the above series of technical problems, this application aims to significantly improve the overall performance of the intelligent truck automatic driving system, thereby providing more reliable and efficient technical support for practical applications.

[0055] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0056] The intelligent truck route planning and control method provided in this application embodiment can be applied to, for example, Figure 1In the application environment shown, terminal 102 communicates with server 104 via a network. A data storage system can store the data that server 104 needs to process. The data storage system can be set up independently, integrated into server 104, or placed in the cloud or on other servers. Terminal 102 can send the intelligent truck's operating status data to server 104. After receiving the operating status data, server 104 decomposes the path planning optimization problem into multiple independent time-domain sub-blocks based on the time-domain decomposition method, obtaining several control cycles in the prediction time domain. For each control cycle, based on the vehicle dynamics model, state evolution equation, and operating status data, it updates the current state and control input of the intelligent truck. A path planning sub-model for each time-domain sub-block is established based on the Lagrangian function, and the Lagrangian dual variables are updated to obtain the updated dual variables. Based on the updated dual variables and the updated state variables, the block moment is calculated. Based on the block moment, path performance indicators, and stopping criteria, the final path planning result is determined. Server 104 can feed back the obtained final path planning result for the intelligent truck to terminal 102. In addition, in some embodiments, the intelligent truck path planning and control method can also be implemented by the server 104 or the terminal 102 separately. For example, the terminal 102 can directly perform path planning processing on the running status data, or the server 104 can obtain the running status data from the data storage system and perform path planning processing on the running status data.

[0057] The terminal 102 can be, but is not limited to, various desktop computers and laptops. The server 104 can be implemented using a standalone server or a server cluster consisting of multiple servers, or it can be a cloud server.

[0058] In one exemplary embodiment, such as Figure 2 and Figure 3 As shown, a method for intelligent truck route planning and control is provided. This method is executed by a computer device, specifically by a terminal or server alone, or by both a terminal and a server. In this embodiment, the method is applied to... Figure 1 Taking server 104 as an example, the explanation includes the following steps 201 to 205.

[0059] Step 201: Obtain the operational status data of the intelligent truck. Operational status data includes initial position, target path, real-time data, status information, and environmental information.

[0060] Step 202: Based on the time-domain decomposition method, the path planning optimization problem is decomposed into multiple independent time-domain sub-blocks to obtain several control cycles in the prediction time domain; each control cycle corresponds to one of the time-domain sub-blocks.

[0061] Step 203: For each control cycle, based on the vehicle dynamics model, state evolution equation and the operating state data, update the current state and control input of the intelligent truck to obtain the updated state variables and updated control input.

[0062] Step 204: Establish a path planning sub-model for each time-domain sub-block based on the Lagrange function, update the Lagrange dual variables to obtain the updated dual variables; calculate the block moments based on the updated dual variables and the updated state variables; the path planning sub-model includes an objective function and constraints; the constraints include dynamic constraints and consistency constraints; the consistency constraints are determined by global consistency variables and are used to constrain the cooperative relationship between time-domain sub-blocks; the block moments are composed of state changes.

[0063] Step 205: Determine whether the stopping criteria are met based on the block moment and path performance indicators; if met, the current target trajectory is determined as the final path planning result; the path performance indicators include tracking performance indicators, comfort performance indicators, and handling performance indicators; the stopping criteria are: the number of iterations reaches the maximum number of iterations, the tracking performance indicator reaches the maximum allowable tracking error, the comfort performance indicator reaches the maximum comfort performance deviation, or the handling performance indicator reaches the maximum handling error.

[0064] By implementing steps 201 to 205 above, this application ensures the efficiency and accuracy of path planning through time-domain decomposition, multi-dimensional performance index evaluation, and block-based parallel computing techniques. Specifically, the intelligent truck path planning control method provided by this application includes four core steps: time-domain decomposition, global consistency variable construction, block-based update calculation, and performance evaluation and stopping criterion judgment. These steps work together to achieve efficient optimization of path planning. Furthermore, the system architecture of this method is divided into three layers: an input layer, a processing layer, and an output layer. At the input layer, the system receives real-time operating status data of the intelligent truck, such as position, speed, and acceleration. At the processing layer, based on time-domain decomposition technology, the complex path planning problem is decomposed into multiple independent time-domain sub-blocks, and parallel computing is used to optimize the solution. At the output layer, path planning instructions that meet dynamic constraints and performance requirements are generated, ensuring that the system can operate stably in complex scenarios.

[0065] like Figure 4 and Figure 5 As shown, this application adopts a control cycle time domain decoupling method, which divides the entire prediction time domain into multiple independent control cycles to realize the modular solution of the path planning problem, specifically including the following steps 301 to 303.

[0066] Step 301: Time Domain Partitioning: Divide the entire prediction time domain into N control periods. The state of each control period is determined by the initial state variables. Input state variables and output state variables Characterization.

[0067] Step 302: Dynamic constraint modeling: Based on the state transition relationship obtained by time domain division in step (1) above, construct a dynamic constraint model to describe the state evolution of the system in each control cycle. The state evolution equation is shown in the following equation.

[0068] (1).

[0069] in, For the first Output state quantity per control cycle For the first The initial state quantities for each control cycle. For the first The control input state quantity for each control cycle. Here is the state transition matrix. To control the input matrix.

[0070] Step 303: Introduction of Consistency Variables: To ensure global consistency in block-based solutions, this application introduces global consistency variables. Furthermore, it establishes collaborative relationships between sub-blocks through consistency constraints, including input consistency constraints. Output consistency constraints ;in, For the first Globally consistent variables for each control cycle For the first The globally consistent variables for each control cycle consist of position state, velocity state, and heading angle.

[0071] The final output of time-domain decomposition is to divide the entire prediction time domain into multiple independent control periods, establish a dynamic constraint model within each control period, and introduce globally consistent variables to ensure global consistency in the block-based solution. Specifically, the output of this step includes: 1) Control period division: Dividing the prediction time domain into N control periods, where the state variables of each control period include initial state variables, input state variables, and output state variables. 2) Dynamic constraint model: Constructing a dynamic constraint model describing the state evolution of the system within each control period. 3) Globally consistent variables: Introducing globally consistent variables to establish cooperative relationships between sub-blocks through constraints, achieving time-domain decoupling between control periods.

[0072] The block-based decoupled calculation process is as follows: State variables include the intelligent truck's position, speed, and heading angle; control inputs include throttle, brake, acceleration, and steering angular velocity. Within each control cycle, the current state and control inputs are updated based on the vehicle dynamics model. Specifically, based on the intelligent truck's current state (including position, speed, and acceleration) and control inputs (e.g., throttle, brake, and steering), the state for the next control cycle is calculated using the intelligent truck's dynamics equations. This process needs to satisfy the intelligent truck's kinematic and dynamic constraints, including maximum acceleration and maximum steering angular velocity constraints. For example, if the current state is position... and speed The control input is acceleration. Then the position state of the next control cycle and speed state It can be calculated using the following equation.

[0073] (2).

[0074] (3).

[0075] In the formula, For the first Position status of each control cycle For the first Speed ​​status of each control cycle For the first Position status of each control cycle For the first Speed ​​status of each control cycle This is to control the time interval of the cycle.

[0076] In path planning, dual variables are used to determine the validity of constraints; that is, when the dual variable is non-zero, the corresponding constraint is either active or binding. Lagrangian dual variables are used to update the block states, optimizing the objective function of each block and ensuring global consistency. The Lagrangian function contains the objective function and constraints; updates to the dual variables must satisfy these constraints. For example, if the Lagrangian function is... ,in, It is a state variable. If the variable is the dual variable, then the update equation for the dual variable is as follows.

[0077] (4).

[0078] In the formula, For the updated dual variable, It's the learning rate. It is the gradient of the Lagrange function with respect to the state variable.

[0079] The objective function is expressed as ,in, Let be the objective function. , and The weights for the evaluation values ​​of the tracking performance index, comfort performance index, and handling performance index are respectively defined. The objective function aims to minimize the sum of these weights, which is determined by the sum of the tracking performance index values. Comfort performance index values and the index values ​​of handling performance indicators The result is obtained by weighted summation.

[0080] Within each control cycle, the path planning result for each control cycle is obtained by iteratively solving the objective function and constraints. The path planning result is evaluated by tracking performance indicators, comfort performance indicators, and handling performance indicators. Based on the stopping criterion, the final path planning result is determined.

[0081] Initialization of initial variables: At the beginning of each control cycle, initial variables are initialized based on the current state of the intelligent truck. Initial variables include state variables such as the intelligent truck's position, speed, and acceleration, as well as control inputs such as throttle, brake, and steering.

[0082] Block vector construction: Based on the original variables and control inputs, a block vector representing the current control cycle state is constructed. A block vector is the set of all variables related to path planning in the control cycle, including the state variables and control inputs for each control cycle.

[0083] Neighborhood characteristics refer to the environmental information of intelligent trucks. Different neighborhood characteristics refer to the specific attributes of intelligent trucks in different areas of their surrounding environment, such as obstacle distribution, road conditions, and traffic rules.

[0084] Residual Calculation and Optimization: In the path planning sub-model, the residual between the actual path and the planned path is calculated. The residual is... The residuals are used to update the Lagrange dual variables and block moments to optimize the path planning results. When the residuals are not less than the set residuals, the iteration continues. When the residuals are less than the set residuals, the iteration stops and the current path planning results are output.

[0085] The block moment quantities include changes in position, distance between vehicles, speed, acceleration, external disturbances, and trajectory error.

[0086] Based on the updated state variables and the updated dual variables, the block moments are calculated, and the input states for the next step are further adjusted. The calculation of block moments involves changes in the system state, such as position changes and velocity changes. For example, when the block moment represents a position change... and speed change When the value is 0, it can be calculated using the following equation.

[0087] (5).

[0088] (6).

[0089] To achieve a comprehensive evaluation of path planning performance, this application proposes three categories of path performance indicators: tracking performance, comfort performance, and handling performance.

[0090] 1) Tracking performance indicators: measured by the distance between vehicles. and vehicle speed error The evaluation of the system's ability to track the target trajectory is as follows: In the time-domain decomposition method, the state transitions and dynamic constraint modeling of each control cycle directly affect the deviation between the actual trajectory and the target trajectory of the intelligent truck. Therefore, tracking performance is closely related to the accuracy of the dynamic model and the division of the control cycle.

[0091] Performance evaluation logic: through The system quantifies the vehicle spacing error and vehicle speed error to evaluate the system's tracking performance of the target trajectory in different control cycles.

[0092] (7).

[0093] in, The metrics used to track performance indicators; and These are the weighting coefficients for vehicle spacing error and vehicle speed error, respectively.

[0094] Norm calculation: By solving the integral of the tracking performance index, the distance error and speed error can be obtained. Norm, thus evaluating tracking performance.

[0095] vehicle spacing error The formula for calculating the norm is shown below.

[0096] (8).

[0097] vehicle speed error The formula for calculating the norm is shown below.

[0098] (9).

[0099] The formula for calculating the evaluation value of the tracking performance index is shown below.

[0100] (10).

[0101] in, It is in time The distance between vehicles, It is in time Speed ​​error Vehicle spacing error of Norm; For vehicle speed error of Norm.

[0102] 2) Comfort performance indicators: By analyzing external disturbances and control costs (Acceleration Change) Evaluating the Driving Comfort of Intelligent Trucks: Comfort performance is related to control inputs (such as acceleration) and external disturbances (such as road surface unevenness) in the vehicle dynamics model. Globally consistent variables and block-based update calculations in the time-domain decomposition method ensure smooth transitions in the intelligent truck's state across different control cycles, thus affecting comfort. Performance Evaluation Logic: Quantifying the expected control cost and external disturbances using the H2 norm to evaluate the system's comfort performance during operation.

[0103] In a specific example, during real-vehicle testing, the tracking error or speed error of the intelligent truck can be used as an assessment of external disturbances. Indicators of impact. For example, if the tracking error or speed error of an intelligent truck exceeds a preset threshold at a specific speed, it indicates a significant external disturbance, such as uneven road surface. Tracking error or speed error can be obtained in real time through GPS data, speed sensors, etc., of the intelligent truck.

[0104] (11).

[0105] In the formula, These are the index values ​​for comfort performance. and These are the weighting coefficients for external disturbances and control costs, respectively.

[0106] H2 norm calculation: By solving the integral of the comfort performance index, the H2 norm of external disturbances and control costs can be obtained, thereby evaluating comfort performance.

[0107] External disturbances The formula for calculating the norm is shown below.

[0108] (12).

[0109] Controlling costs The formula for calculating the norm is shown below.

[0110] (13).

[0111] The formula for calculating the comfort performance index is shown below.

[0112] (14).

[0113] in, It is in time External disturbances It is in time The cost of control, For external disturbances of Norm; To control costs of Norm.

[0114] 3) Handling Performance Indicators: Based on the Lyapunov exponent, the rate of change of trajectory error is quantified to evaluate the system's handling stability. Handling performance is closely related to directional stability and trajectory error in the vehicle dynamics model. The time-domain decomposition method, by introducing globally consistent variables and block-based update calculations, can optimize the directional stability and reduce trajectory error of intelligent trucks. Performance Evaluation Logic: The rate of change of trajectory error is quantified using the Lyapunov exponent to evaluate the system's handling performance in real-time dynamic environments.

[0115] Lyapunov exponent calculation: By solving the formula for the handling performance index, the rate of change of trajectory error can be obtained, thereby evaluating the handling performance. The formula for calculating the Lyapunov exponent is shown in equation (15).

[0116] (15).

[0117] (16).

[0118] in, The index value of the handling performance indicator; This represents the rate of change of the trajectory error; Current time t Trajectory error; This represents the initial error.

[0119] By calculating norm, The norm and Lyapunov exponent are compared with preset performance indicator thresholds to obtain the evaluation results of the performance indicators for each path.

[0120] Step 205 specifically includes: comparing the evaluation value of the path performance index with the preset performance index threshold to obtain the evaluation result of each path performance index; when the evaluation value of any path performance index is less than the preset performance index threshold, stopping the iterative optimization and outputting the final path planning result.

[0121] If the tracking performance evaluation value is less than the preset maximum allowable tracking error, the tracking performance is considered to meet the requirements; otherwise, the weighting coefficients need to be adjusted or the path planning needs to be optimized. If the comfort performance evaluation value is less than the preset maximum comfort performance deviation, the comfort performance is considered to meet the requirements; otherwise, the weighting coefficients need to be adjusted or the path planning needs to be optimized. If the handling performance evaluation value is less than the preset maximum handling error, the handling performance is considered to meet the requirements; otherwise, the weighting coefficients need to be adjusted or the path planning needs to be optimized. The maximum allowable tracking error, maximum comfort performance deviation, and maximum handling error are derived from experiments or user experience.

[0122] This application can also use LQR controllers, mean absolute error (MAE) and root mean square error (RMSE), multi-objective evolutionary algorithm performance evaluation index, weighted summation method, analytic hierarchy process, fuzzy comprehensive evaluation method, data envelopment analysis method, nondominated sorting genetic algorithm II (NSGA-II) or multi-objective evolutionary algorithm based on decomposition (MOEA / D) for integral solution.

[0123] Overall evaluation value It can reflect the overall performance of the system in three aspects: tracking performance, comfort performance, and handling performance. It is used to balance the weights and influences among different performance indicators, thus obtaining a comprehensive system performance evaluation. Overall Evaluation Value The calculation formula is shown below.

[0124] (17).

[0125] in, , and These are the weights for the evaluation values ​​of tracking performance, comfort performance, and handling performance, respectively.

[0126] The following section uses Port X as an example to illustrate the intelligent truck path planning and control method proposed in this application.

[0127] In daily port logistics operations, straight road sections typically connect cargo loading / unloading areas and truck yards, forming a crucial component of logistics transportation. In this scenario, intelligent trucks need to travel along a 500-meter straight road section at a target speed of 20 km / h, tasked with transporting goods from the loading / unloading point to the yard, while simultaneously handling potential dynamic disturbances such as forklift traffic and static obstacles like containers. Port surfaces may be slippery or uneven due to environmental factors, requiring the system to dynamically adjust to these external disturbances.

[0128] The process of acquiring operational status data for intelligent container trucks is as follows: The initial position and target path of the intelligent container truck are provided by the port dispatching system, while real-time data is acquired through onboard sensors and the V2X communication system. Status information refers to the current coordinates of the intelligent container truck. Initial velocity Target speed Target location Maximum acceleration The environmental information includes the location of static obstacles, the trajectory of dynamic targets, and ground conditions. To ensure the real-time performance and accuracy of the path planning results, a control cycle of 0.1 seconds is used, with a prediction time domain of 3 seconds, meaning that the state and control strategy of the intelligent truck are optimized within the next 30 control cycles.

[0129] The path planning employs time-domain decomposition technology, dividing the 3-second prediction time domain into 30 independent control cycles. Within each control cycle, the intelligent truck vehicle's state variables... The description of the intelligent container truck's position, speed, and heading angle, while the control variables... This represents the acceleration and steering angular velocity of the intelligent container truck. This is achieved by introducing globally consistent variables. Among them, the consistency variables of each control cycle Includes location status Speed ​​state and heading angle This ensures that each block can be solved independently while maintaining the consistency of global optimization.

[0130] The state evolution of the intelligent container truck is modeled based on a dynamic model, and the state transition relationship is shown in Equation (1), where the state transition matrix is... and control input matrix , =0.1s is the time interval for each control cycle. After time-domain decoupling, the constraints are divided into input consistency constraints and output consistency constraints. Dynamic modeling can describe the motion of intelligent trucks on straight road segments, while fully considering the impact of external disturbances on state changes.

[0131] In each time-domain sub-block, the path planning algorithm performs the following steps. First, based on the vehicle dynamics model, the current state is updated. and control input The calculation results must satisfy the kinematic and dynamic constraints of the intelligent truck. Then, the block states are updated using Lagrange dual variables. The Lagrange dual variables, combined with dynamic and consistency constraints, optimize the objective function of each block, ensuring global consistency. Finally, based on the updated state variables and the updated dual variables, the block moments are calculated, and the input states for the next step are further adjusted.

[0132] Based on the specific requirements of straight road sections, the weighting of path performance indicators is set as follows: tracking performance has the highest priority, followed by vehicle spacing error. Set to 0.7, vehicle speed error weight Set to 0.3. To balance comfort and handling performance, the perturbation weight... and control cost weight Set them to 0.4 and 0.6 respectively.

[0133] The optimization process employs a block-parallel computation method, with each time-domain sub-block independently solving for the control strategy. The state of each block is synchronized through a consistency variable Z, ultimately achieving global optimization. To further improve computational efficiency, the system introduces an early stopping mechanism, halting iteration when performance metrics reach a preset threshold. The specific stopping criteria are: a maximum of 100 iterations and a maximum allowable tracking error. Maximum comfort performance deviation Maximum manipulation error The algorithm stops iterating and outputs the final path planning result when any condition is met. Performance metrics and test results are shown in Table 1.

[0134] Table 1 Performance Indicators and Test Results

[0135]

[0136] Performance analysis revealed a 30% improvement in tracking performance, approximately a 25% improvement in comfort, and a 35% improvement in handling stability. These results demonstrate that this application not only achieves high-precision path tracking in complex environments but also significantly optimizes the driving experience, providing reliable technical support for intelligent logistics in ports.

[0137] Compared to existing technologies, this application demonstrates significant advantages in computational efficiency, control accuracy, robustness, and adaptability. Through time-domain decomposition and constraint optimization methods, this application significantly improves the practical application performance of path planning algorithms.

[0138] In terms of computational efficiency, this application effectively utilizes time-domain decomposition and parallel computing techniques to break down complex global optimization problems into multiple sub-problems that can be processed in parallel, significantly reducing computation time. Test data shows that the computation time of this application is reduced by 40%–50% compared to traditional methods, and parallel computing efficiency is improved by 35%–45%. In addition, by optimizing memory allocation and data flow processing, the system's memory resource consumption is reduced by 30%–40%, which is particularly outstanding in environments with limited hardware resources.

[0139] Regarding control accuracy, this application comprehensively optimizes path tracking performance and the dynamic control capabilities of intelligent trucks by introducing a multi-dimensional performance index evaluation system. Experiments show that the intelligent truck path planning control method proposed in this application reduces path tracking error by 30%–40%, improves intelligent truck stability by 25%–35%, and increases dynamic response speed by 20%–30%. This improvement in accuracy and stability ensures that intelligent trucks can smoothly and efficiently complete path planning and navigation tasks in complex environments.

[0140] In terms of robustness and adaptability, this application significantly enhances resistance to external disturbances. Test results show that the anti-interference capability of this application is improved by 50%, and the control stability is significantly improved in complex environments (such as dynamic obstacles, uneven or slippery road surfaces). In addition, this application exhibits stronger adaptability for different working conditions (such as curved paths, long straight paths, etc.), and can quickly adjust algorithm parameters to meet the needs of different scenarios.

[0141] This application achieves significant improvements in multiple key dimensions, including computational efficiency, control accuracy, and system robustness, through time-domain decomposition and the construction of globally consistent variables. By introducing a multi-dimensional performance index evaluation system and an adaptive stopping criterion, this application not only solves the adaptability and efficiency bottlenecks of traditional methods in complex scenarios but also proposes a scientific and systematic quantitative evaluation method for path planning. These technological breakthroughs provide a novel technical solution for path planning in autonomous driving of intelligent trucks, possessing significant theoretical and practical value. The technical solution of this application demonstrates great application value in multiple fields, improving the path planning accuracy of autonomous driving in intelligent trucks and reducing operating costs and energy consumption caused by planning errors.

[0142] In the field of industrial automation, the path planning technology and performance evaluation method of this application can provide theoretical support for the navigation and control of mobile robots in complex environments, and promote the development of autonomous driving technology in the industrial field.

[0143] This application also provides an application scenario in which the above-described intelligent truck path planning and control method is applied. Specifically, the intelligent truck path planning and control method provided in this embodiment can be applied in an autonomous driving scenario. An autonomous driving scenario includes an information acquisition stage, a path planning and control link, and a driving stage; the intelligent truck's operating status data enters the path planning and control link from the information acquisition stage, obtains the corresponding final path planning result, and then enters the downstream driving stage. The intelligent truck path planning and control method provided in this embodiment belongs to the path planning and control link. Specifically, in the path planning and control process for intelligent trucks, the path planning optimization problem can be decomposed into multiple independent time-domain sub-blocks based on the time-domain decomposition method, resulting in several control cycles in the prediction time domain. For each control cycle, the current state and control input of the intelligent truck are updated based on the vehicle dynamics model, state evolution equation, and operating state data. A path planning sub-model for each time-domain sub-block is established based on the Lagrangian function, and the Lagrangian dual variables are updated to obtain the updated dual variables. Based on the updated dual variables and the updated state variables, the block moment is calculated. The final path planning result is determined based on the block moment, path performance indicators, and stopping criteria.

[0144] Based on the same inventive concept, this application also provides an intelligent truck route planning and control device for implementing the intelligent truck route planning and control method described above. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations of one or more intelligent truck route planning and control device embodiments provided below can be found in the limitations of the intelligent truck route planning and control method described above, and will not be repeated here.

[0145] In one exemplary embodiment, such as Figure 6 As shown, an intelligent truck route planning and control device is provided, comprising the following modules.

[0146] The operating status data acquisition module T1 is used to acquire the operating status data of the intelligent truck.

[0147] The time-domain decomposition module T2 is used to: decompose the path planning optimization problem into multiple independent time-domain sub-blocks based on the time-domain decomposition method, and obtain several control cycles in the prediction time domain; each control cycle corresponds to one of the time-domain sub-blocks.

[0148] The state evolution module T3 is used to: for each control cycle, update the current state and control input of the intelligent truck based on the vehicle dynamics model, state evolution equation and the operating state data, to obtain the updated state variables and updated control input.

[0149] The block update calculation module T4 is used for: establishing a path planning sub-model for each time-domain sub-block based on the Lagrange function; updating the Lagrange dual variables to obtain the updated dual variables; calculating the block moments based on the updated dual variables and the updated state variables; the path planning sub-model includes an objective function and constraints; the constraints include dynamic constraints and consistency constraints; the consistency constraints are determined by global consistency variables and are used to constrain the cooperative relationship between time-domain sub-blocks; the block moments are composed of state changes.

[0150] The stopping criterion convergence module T5 is used to: determine whether the stopping criterion is met based on the block moment and path performance index; if it is met, the current target trajectory is determined as the final path planning result; the path performance index includes tracking performance index, comfort performance index and handling performance index; the stopping criterion is that the number of iterations reaches the maximum number of iterations, the tracking performance index reaches the maximum allowable tracking error, the comfort performance index reaches the maximum comfort performance deviation, or the handling performance index reaches the maximum handling error.

[0151] In one exemplary embodiment, a computer device is provided, which may be a server or a terminal, and its internal structure diagram may be as follows. Figure 7 As shown, the computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database stores path planning and control data. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it implements a smart truck path planning and control method.

[0152] Those skilled in the art will understand that Figure 7The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0153] In one exemplary embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.

[0154] In one exemplary embodiment, a computer-readable storage medium is provided storing a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0155] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0156] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments described above. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM).

[0157] The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0158] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0159] This document uses specific examples to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this application. Furthermore, those skilled in the art will recognize that, based on the ideas of this application, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A method for intelligent truck path planning and control, characterized in that, The intelligent truck route planning and control method includes: Obtain the operating status data of the intelligent truck; Based on the time-domain decomposition method, the path planning optimization problem is decomposed into multiple independent time-domain sub-blocks, resulting in several control periods in the prediction time domain; each control period corresponds to one of the time-domain sub-blocks. For each control cycle, based on the vehicle dynamics model, state evolution equation and the operating state data, the current state and control input of the intelligent truck are updated to obtain the updated state variables and updated control inputs. A path planning sub-model is established for each time-domain sub-block based on the Lagrange function. The Lagrange dual variables are updated to obtain the updated dual variables. The block moments are calculated based on the updated dual variables and the updated state variables. The optimization process employs a block-parallel computing method, with each time-domain sub-block independently solving for the control strategy; the state of each block is synchronized through a consistency variable Z, ultimately achieving global optimization; The path planning sub-model includes an objective function and constraints; the constraints include dynamic constraints and consistency constraints; the consistency constraints are determined by global consistency variables and are used to constrain the cooperative relationship between time-domain sub-blocks; the block moments are composed of state changes. The globally consistent variable is Z = [Z0, Z1, ..., Zn]. n ] T Establish collaborative relationships between sub-blocks through consistency constraints; the consistency constraints include input consistency constraints x. t (t-1)=Z t-1 and output consistency constraint x t (t)=Z t ; where x t (t-1) represents the initial state quantity in the t-th control cycle, Z t-1 Let x be the globally consistent variable for the (t-1)th control cycle. t (t) represents the output state variable in the t-th control cycle, Z t Let be the global consistency variable for the t-th control cycle; The globally consistent variables consist of position state, velocity state, and heading angle; Based on the block moment and path performance indicators, it is determined whether the stopping criterion is met; if so, the current target trajectory is determined as the final path planning result; the path performance indicators include tracking performance indicators, comfort performance indicators, and handling performance indicators; the stopping criterion is that the number of iterations reaches the maximum number of iterations, the tracking performance indicator reaches the maximum allowable tracking error, the comfort performance indicator reaches the maximum comfort performance deviation, or the handling performance indicator reaches the maximum handling error; the calculation formula for the tracking performance indicator value is as follows: IT=w s ·H ∞,s +w v ·H ∞,Δv ; Where IT is the value of the performance metric being tracked; H ∞,s H∞ norm of the vehicle spacing error Δs; ∞,Δv w is the H∞ norm of the vehicle speed error Δv. s and w v These are the weighting coefficients for vehicle spacing error and vehicle speed error, respectively. The formula for calculating the value of the comfort performance index is as follows: IC=w d ·H 2,d +w x ·H 2,x ; Where IC is the index value of comfort performance; H 2,d H is the H2 norm of the external disturbance Δd; 2,x To control the cost Δx, the H2 norm; w d and w x These are the weighting coefficients for external disturbances and control costs, respectively. The formula for calculating the values ​​of the handling performance indicators is as follows: IM = λ; Where IM is the index value of the maneuvering performance index; λ is the rate of change of the trajectory error; e(t) is the current trajectory error; and e(0) is the initial error.

2. The intelligent truck path planning and control method according to claim 1, characterized in that, The state evolution equation is expressed as follows: x t (t)=A d ·x t (t-1)+B d ·u t (t-1); Where, x t (t) represents the output state variable of the t-th control cycle, x t (t-1) represents the initial state quantity of the t-th control cycle, u t (t-1) represents the control input state quantity in the t-th control cycle, A d Let B be the state transition matrix. d To control the input matrix.

3. The intelligent truck path planning and control method according to claim 1, characterized in that, The status parameters include the intelligent truck's position, speed, and heading angle; the control inputs include acceleration and steering angular velocity.

4. The intelligent truck path planning and control method according to claim 1, characterized in that, The block moment quantities include changes in position, vehicle spacing, speed, acceleration, external disturbances, and trajectory error.

5. A smart truck route planning and control device, characterized in that, The intelligent truck route planning and control device includes: The operation status data acquisition module is used to acquire the operation status data of the intelligent truck. The time-domain decomposition module is used to: decompose the path planning optimization problem into multiple independent time-domain sub-blocks based on the time-domain decomposition method, and obtain several control periods in the prediction time domain; each control period corresponds to one of the time-domain sub-blocks; The state evolution module is used to: for each control cycle, based on the vehicle dynamics model, state evolution equation and the operating state data, update the current state and control input of the intelligent truck to obtain the updated state variables and the updated control input; The block update calculation module is used for: establishing a path planning sub-model for each time-domain sub-block based on the Lagrange function; updating the Lagrange dual variables to obtain the updated dual variables; calculating the block moments based on the updated dual variables and the updated state variables; the path planning sub-model includes an objective function and constraints; the constraints include dynamic constraints and consistency constraints; the consistency constraints are determined by global consistency variables and are used to constrain the cooperative relationship between time-domain sub-blocks; the block moments are composed of state changes. The stopping criterion convergence module is used to: determine whether the stopping criterion is met based on the block moment and path performance indicators; if met, the current target trajectory is determined as the final path planning result; the path performance indicators include tracking performance indicators, comfort performance indicators, and handling performance indicators; the stopping criterion is that the number of iterations reaches the maximum number of iterations, the tracking performance indicator reaches the maximum allowable tracking error, the comfort performance indicator reaches the maximum comfort performance deviation, or the handling performance indicator reaches the maximum handling error; the calculation formula for the tracking performance indicator value is as follows: IT=w s ·H ∞,s +w v ·H ∞,Δv ; Where IT is the value of the performance metric being tracked; H ∞,s H∞ norm of the vehicle spacing error Δs; ∞,Δv w is the H∞ norm of the vehicle speed error Δv. s and w v These are the weighting coefficients for vehicle spacing error and vehicle speed error, respectively. The formula for calculating the value of the comfort performance index is as follows: IC=w d ·H 2,d +w x ·H 2,x ; Where IC is the index value of comfort performance; H 2,d H is the H2 norm of the external disturbance Δd; 2,x To control the cost Δx, the H2 norm; w d and w x These are the weighting coefficients for external disturbances and control costs, respectively. The formula for calculating the values ​​of the handling performance indicators is as follows: IM = λ; Where IM is the index value of the maneuvering performance index; λ is the rate of change of the trajectory error; e(t) is the current trajectory error; and e(0) is the initial error.

6. A computer device, comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that the processor executes the computer program to implement the intelligent truck path planning and control method according to any one of claims 1-4.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the intelligent truck path planning and control method according to any one of claims 1-4.

Images