Mobile charging pile collision prediction method and system based on model prediction control

Abstract

The invention discloses a mobile charging pile collision prediction method and system based on model prediction control, and relates to the technical field of electric vehicle charging. The method comprises the following steps: acquiring kinematics and dynamics parameters in the moving process of the mobile charging pile, and establishing a dynamic model of the charging pile; constructing a model prediction control algorithm, and setting a target function and a corresponding constraint condition; predicting a motion track in a period of time in the future by using a model prediction control algorithm according to the dynamic model of the charging pile; acquiring surrounding environment sensing data, and predicting a collision risk between the charging pile and surrounding obstacles according to the movement track and the environment sensing data to obtain a collision risk analysis result; and adjusting the motion strategy of the charging pile according to the collision risk analysis result. The collision risk can be effectively analyzed and avoided by predicting the behavior of the charging pile in a period of time in the future, and the safety and reliability of the charging process are ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of electric vehicle charging, and in particular to a mobile charging pile collision prediction method and system based on model predictive control. Background Art

[0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art.

[0003] Mobile charging piles are gaining more and more attention and applications due to their flexibility and convenience. In urban environments, mobile charging piles need to provide charging services for electric vehicles in limited spaces. However, while mobile charging piles provide convenient charging services for electric vehicles, they also face the problem of possible harm to the surrounding environment and personnel during movement. Due to space limitations and dynamically changing environmental conditions, there is a risk of collision with surrounding vehicles or obstacles during movement and positioning of charging piles. How to effectively analyze and prevent this risk has become an urgent problem to be solved.

[0004] Existing mobile charging piles mainly rely on simple obstacle avoidance systems, such as ultrasonic sensors, which are widely used due to their low cost and easy installation. However, their detection range is limited, and they may not be accurate enough and react slowly in certain environments (such as windy or echoy environments), making it impossible to effectively predict and avoid potential collision risks.

[0005] The Chinese invention patent with publication number CN104002808A and publication date of August 28, 2014, is a vehicle active anti-collision automatic braking control system and working method. This technology uses PID control to monitor the vehicle's driving status and surrounding environment in real time, but when it comes to complex and dynamically changing traffic environments, it may not be able to effectively predict and respond to future changes.

[0006] Model predictive control (MPC) uses a predictive model to predict future system behavior, and then controls based on these prediction results. It can better adapt to system changes and nonlinearity, has high flexibility, and can consider multiple control variables and constraints at the same time, such as limiting the maximum speed or maximum acceleration of physical equipment. Compared with traditional PID control, it has a higher degree of prediction and optimization capabilities and can provide better performance.

[0007] Currently, model predictive control (MPC) algorithms are widely used in the fields of automation and robotics, but their application in mobile charging pile collision risk analysis is still insufficient.

[0008] Therefore, the existing technology lacks accurate prediction of the movement trajectory of the charging pile and cannot achieve efficient and safe charging pile positioning in a complex environment. Summary of the invention

[0009] In view of the shortcomings of the prior art, the purpose of the present invention is to provide a mobile charging pile collision prediction method and system based on model predictive control, which can effectively analyze and avoid collision risks by predicting the behavior of the charging pile in the future, thereby ensuring the safety and reliability of the charging process.

[0010] In order to achieve the above object, the present invention is implemented through the following technical solutions:

[0011] A first aspect of the present invention provides a mobile charging pile collision prediction method based on model predictive control, comprising the following steps:

[0012] Obtain the kinematic and dynamic parameters of the mobile charging pile during movement and establish a dynamic model of the charging pile;

[0013] Build a model predictive control algorithm, set the objective function and corresponding constraints;

[0014] Use the model predictive control algorithm to predict the movement trajectory in the future based on the dynamic model of the charging pile;

[0015] Acquire surrounding environment perception data, predict the collision risk between the charging pile and surrounding obstacles based on the motion trajectory and environmental perception data, and obtain collision risk analysis results;

[0016] Adjust the movement strategy of the charging pile according to the collision risk analysis results.

[0017] Furthermore, the specific steps for obtaining the kinematic and dynamic parameters of the mobile charging pile during movement are as follows:

[0018] Get the real-time location and speed of the charging pile through GPS and IMU sensors;

[0019] The sensor data is fused using a Kalman filter.

[0020] Furthermore, after the dynamic model of the charging pile is established, a nonlinear dynamic model is established based on the dynamic model of the charging pile to describe the motion behavior of the charging pile, and the Taylor series expansion method is used to linearize the nonlinear dynamic model to adapt to the MPC algorithm.

[0021] Furthermore, the objective function is defined as minimizing the distance to obstacles, and the constraints include physical limitations and safety restrictions.

[0022] Furthermore, the specific steps of using the model predictive control algorithm to predict the motion trajectory in the future period of time according to the dynamic model of the charging pile are as follows:

[0023] According to the preset control parameters, in each control cycle, the dynamic model of the charging pile is used to predict the movement trajectory of the charging pile in the future based on the current state;

[0024] Optimize control inputs to satisfy objective functions and constraints;

[0025] Apply the optimized control parameters as input for the next cycle.

[0026] Furthermore, the specific steps for predicting the collision risk between the charging pile and surrounding obstacles based on the motion trajectory and environmental perception data are as follows:

[0027] Define the minimum safety distance. When the distance between the predicted trajectory and the obstacle is less than the minimum safety distance, it is considered that there is a collision risk.

[0028] Calculate the collision probability, based on the predicted trajectory and the location of obstacles, using statistical methods to estimate the likelihood of a collision.

[0029] Furthermore, the specific steps for adjusting the motion strategy of the charging pile according to the collision risk analysis results are as follows:

[0030] Update the control input of the charging pile according to the set obstacle avoidance strategy;

[0031] Apply updated control inputs to control the charging pile to move and avoid obstacles;

[0032] The control strategy is further adjusted according to the obstacle avoidance effect until the collision risk is less than the set threshold.

[0033] A second aspect of the present invention provides a mobile charging pile collision prediction system based on model predictive control, comprising:

[0034] A data acquisition module is configured to acquire kinematic and dynamic parameters of the mobile charging pile during movement and establish a dynamic model of the charging pile;

[0035] An algorithm configuration module, configured to build a model predictive control algorithm, set an objective function and corresponding constraints;

[0036] A motion trajectory prediction module is configured to use a model predictive control algorithm to predict the motion trajectory within a future period of time according to a dynamic model of the charging pile;

[0037] A collision risk prediction module is configured to obtain surrounding environment perception data, predict the collision risk between the charging pile and surrounding obstacles according to the motion trajectory and environmental data, and obtain a collision risk analysis result;

[0038] The motion strategy adjustment module is configured to adjust the motion strategy of the charging pile according to the collision risk analysis result.

[0039] A third aspect of the present invention provides a medium having a program stored thereon, which, when executed by a processor, implements the steps in the mobile charging pile collision prediction method based on model predictive control as described in the first aspect of the present invention.

[0040] The fourth aspect of the present invention provides a device, including a memory, a processor, and a program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps in the mobile charging pile collision prediction method based on model predictive control as described in the first aspect of the present invention are implemented.

[0041] One or more of the above technical solutions have the following beneficial effects:

[0042] The present invention discloses a collision prediction method and system for a mobile charging pile based on model predictive control. By predicting the motion trajectory of the mobile charging pile in real time and analyzing the potential collision risk, the possibility of the charging pile colliding with surrounding vehicles or obstacles can be significantly reduced. Reducing the occurrence of collision accidents can reduce the maintenance frequency and cost of the charging pile, while also reducing the service interruption time caused by accidents, thereby improving the availability of the charging pile and the safety of the charging process.

[0043] The charging pile of the present invention can autonomously perform environmental perception and decision-making, reducing dependence on manual operation, so that the charging pile can operate independently under a wider range of environmental conditions.

[0044] The present invention uses an effective collision risk avoidance strategy, so that the charging pile can locate the electric vehicle and charge it more quickly, reducing the time wasted in finding a safe path, thereby improving the charging efficiency. Since the charging pile can complete the charging task safely and quickly, users who use the charging service can enjoy a more convenient and reliable charging experience.

[0045] Advantages of additional aspects of the present invention will be given in part in the following description, and in part will become obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] The accompanying drawings in the specification, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0047] Figure 1 This is a flow chart of a mobile charging pile collision prediction method based on model predictive control in Embodiment 1 of the present invention;

[0048] Figure 2 This is a flow chart of collision risk analysis and control of a mobile charging pile in Embodiment 1 of the present invention. DETAILED DESCRIPTION

[0049] It should be noted that the following detailed descriptions are exemplary and are intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present invention belongs.

[0050] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present invention. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "include" and / or "include" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or their combinations;

[0051] Embodiment 1:

[0052] Embodiment 1 of the present invention provides a mobile charging pile collision prediction method based on model predictive control, such as Figure 1 As shown in the figure, by building an accurate dynamic model of the mobile charging pile, a model predictive control (MPC) algorithm is designed to analyze the movement trajectory and surrounding environment of the charging pile in real time. By collecting and preprocessing data from multiple sensors, the MPC algorithm can predict the possible movement paths of the charging pile in the future and analyze the potential collision risks of these paths with surrounding obstacles. Based on these analyses, the system will automatically generate and execute avoidance strategies, such as adjusting speed or changing direction, to ensure that the charging pile safely navigates to the electric vehicle and charges it while avoiding any collisions. During execution, the system monitors the effectiveness of the avoidance action and adjusts the control strategy through a feedback mechanism to optimize future predictions and avoidance actions, achieving high safety and efficiency for the entire charging process.

[0053] The specific steps include:

[0054] Step 1: Obtain the kinematic and dynamic parameters of the mobile charging pile during movement and establish a dynamic model of the charging pile.

[0055] Step 1.1: Obtain the kinematic and dynamic parameters of the mobile charging pile during movement.

[0056] Step 1.1.1: Get the real-time location and speed of the charging pile through GPS and IMU sensors.

[0057] Step 1.1.2: Use Kalman filter to fuse sensor data to improve the accuracy of state estimation.

[0058] Step 1.2: Establish a dynamic model of the charging pile.

[0059] Construct the equation of state:

[0060] State equation: State equation in the x direction: x(t+Δt)=x(t)+v x (t)Δt+1 / 2a x (t)(Δt) 2 .

[0061] Similarly, the state equation in the y direction can be obtained: y(t+Δt)=y(t)+v y (t)Δt+1 / 2a y (t)(Δt) 2。

[0062] Among them, x, y represent the position coordinates of the charging column on the two-dimensional plane, v x , v y Indicates the speed of the charging pile in the x-axis and y-axis directions; a x , a y Indicates the acceleration of the charging pile in the x-axis and y-axis directions.

[0063] Step 2: Build the model predictive control algorithm and set the objective function and corresponding constraints.

[0064] Step 2.1: After establishing the dynamic model of the charging pile, a nonlinear dynamic model is established based on the dynamic model of the charging pile to describe the motion behavior of the charging pile. The Taylor series expansion method is used to linearize the nonlinear dynamic model to adapt to the MPC algorithm.

[0065] Step 2.2: Define the objective function as minimizing the distance to the obstacle, and the constraints include physical limitations and safety restrictions.

[0066] In a specific implementation, the parameters are set as follows: prediction time range T=10s, control period Δt=0.1s, safety distance dsafe=2m, collision risk threshold Pthreshold=0.1.

[0067] In this embodiment, in addition to minimizing the distance to the obstacle, the objective function may also be defined as minimizing energy consumption or a change in control input.

[0068] Step 3: Use the model predictive control algorithm to predict the movement trajectory in the future based on the dynamic model of the charging pile.

[0069] Step 3.1: According to the preset control parameters, in each control cycle, the dynamic model of the charging pile is used to predict the movement trajectory of the charging pile in the future based on the current state and control input.

[0070] Step 3.2: Optimize the control input to satisfy the objective function and constraints.

[0071] Step 3.2.1: Set up an optimization problem that minimizes the objective function while satisfying the system dynamics and constraints.

[0072] The optimization problem formula is expressed as:

[0073] Where u is the control input sequence, x k is the state at the kth moment, l is the cost function of each control step, V is the cost function of the final state, and N is the length of the prediction time domain.

[0074] Step 3.2.2: Optimize control input. In each control cycle, solve the optimization problem and find the optimal control input sequence. Add constraints to the optimization problem. Constraints include physical limitations and safety limitations. Physical limitations include maximum speed and acceleration limits, and safety limitations include minimum safety distance. Dynamic limitations are also included. Dynamic limitations are based on the dynamic model of the charging pile to ensure that the control input is within the dynamic capability of the system.

[0075] Step 3.2.3: Input execution. In each control cycle, only the first control input u0 in the optimization sequence is executed into the system.

[0076] Step 3.3: Apply the optimized control parameters as input for the next cycle.

[0077] Step 3.4: The system monitors the effectiveness of the evasive action and adjusts the control strategy through a feedback mechanism to optimize future predictions and evasive actions.

[0078] In a specific implementation, the actual movement of the charging pile and environmental changes are monitored in real time, and the model and control strategy are adjusted according to the deviation between the actual and predicted. If the actual movement deviates significantly from the prediction, or the environment changes, the objective function and constraints are adjusted.

[0079] Step 4: Obtain surrounding environment perception data, predict the collision risk between the charging pile and surrounding obstacles based on the motion trajectory and environmental perception data, and obtain the collision risk analysis results, such as Figure 2 shown.

[0080] Step 4.1: Start: Start the collision risk analysis and the MPC control system.

[0081] Step 4.2: Initialize the system and MPC parameters: Set the initial conditions, including the initial position and speed of the charging pile, etc. The prediction time range is T = 10s, and the control period Δt = 0.1s.

[0082] Step 4.3: Get the current status of the charging pile: Charging pile status data fusion refers to dynamically obtaining the real-time operating status of the charging station, such as obtaining the real-time position (x, y) and speed (v) of the charging pile through sensors.x , v y ), also includes multiple groups of real-time usage information of multiple charging piles in the charging station, and then dynamically obtains the user's scheduled charging sequence, including the user's scheduled charging information.

[0083] Step 4.4: Obtain environmental perception data: Use sensors such as lidar and cameras to collect data about the surrounding environment, including the location of obstacles (o x , o y ) and speed (o vx , o vy ). Then, the decision-making characteristics of drivers and passengers are extracted through sensor data, and the charging station selection preferences and charging behavior characteristics of public charging station users are analyzed.

[0084] In this embodiment, obstacles can be divided into static and dynamic. Static obstacles can be read from high-precision maps or sensed in real time by sensors, while dynamic obstacles need to be analyzed through data obtained by sensors in multiple cycles to obtain their movement information. Obstacles cover static and dynamic obstacles, such as other vehicles, pedestrians, and buildings, which can be detected and tracked using sensor data.

[0085] The obstacle information is obtained by using existing technologies, which will not be described in detail here.

[0086] Step 4.5: MPC algorithm predicts future trajectory: Use the MPC algorithm to predict the movement trajectory of the charging pile in the next 10 seconds based on the current state and environment, and update the prediction every 0.1 seconds.

[0087] Step 4.6: Data fusion and dynamic model establishment: Fuse sensor data with charging pile status data to establish a dynamic model of the charging pile and the environment.

[0088] Step 4.6.1: Dynamic model framework establishment. A charging pile scheduling system based on dynamic data fusion, which is connected to multiple data sources, including the charging station end and the user end. Among them, the model building process needs to reflect the mobile relationship, that is, the mobile relationship between the charging pile and the obstacle, and the mobile relationship between the charging pile and the user's vehicle docking. In the process of model building, it is also possible to improve system performance and build a more comprehensive dynamic model of the charging pile and environment by analyzing user behavior, charging load prediction and guidance according to actual conditions. For example, based on mobile phone signal data and charging station data, the typical travel mode of vehicle users and its relationship with the charging load are explored and added as one of the influencing factors in the model training process.

[0089] Step 4.6.2: Solving model parameters. In the process of solving model parameters, the charging station candidate set is restored with the user's location 10 minutes before charging as the starting point. Taking into account the differences in the dimensions of different influencing factors, each factor is normalized to min-max, and the maximum likelihood method is used for parameter fitting. In the process of solving the model parameters, the influencing factors with a confidence level less than 0.95 are gradually eliminated. After solving the model parameters, the optimal dynamic model parameters of the charging pile and environment are obtained.

[0090] Step 4.7: Evaluate the collision risk of the predicted trajectory: Based on the dynamic model of the charging pile and the environment, evaluate the potential collision risk between the charging pile and the surrounding obstacles. Safety distance dsafe = 2m, collision probability Pcollision.

[0091] Among them, the risk assessment indicators are: defining the minimum safe distance dsafe. When the distance between the predicted trajectory and the obstacle is less than this value, it is considered that there is a collision risk; calculating the collision probability P, based on the predicted trajectory and the position of the obstacle, using statistical methods to estimate the possibility of collision.

[0092] Risk assessment process: For each predicted trajectory, calculate the minimum distance to surrounding obstacles; if the minimum distance is less than the safe distance, calculate the collision probability and compare it with the threshold; if the collision probability exceeds the threshold, trigger the emergency obstacle avoidance strategy.

[0093] Step 4.8: Risk assessment results: If the collision probability Pcollision>0.1, the risk is high and the MPC objective function needs to be adjusted to reduce the risk; if the collision probability Pcollision≤0.1, the risk is acceptable and the current MPC strategy continues to be executed.

[0094] Step 5: Adjust the movement strategy of the charging pile according to the collision risk analysis results.

[0095] Step 5.1: Update the control input of the charging pile according to the set obstacle avoidance strategy.

[0096] In this embodiment, a safe path avoiding obstacles is planned based on the position and speed information of the obstacles and the current position and speed of the charging pile.

[0097] Specifically, the adjustment and update of control input mainly includes setting of control parameters, model predictive control, real-time feedback, control input implementation, monitoring and iteration.

[0098] First, according to the obstacle avoidance strategy, set the control parameters, such as maximum acceleration, maximum deceleration, maximum steering angle, etc. Then use the MPC algorithm to optimize the control input according to the current state and predicted obstacle motion to achieve obstacle avoidance and path tracking. Through real-time feedback of environmental information from sensors, dynamically adjust the control input to cope with sudden obstacles or path changes. Implement the optimized control input into the control system of the charging pile, such as adjusting the power output of the motor and the steering angle of the steering system. In the next control cycle, monitor the environment and charging pile status again, and repeat the adjustment and update process of the obstacle avoidance strategy and control input.

[0099] In this embodiment, the risk is reduced by adjusting the MPC objective function: the objective function of the MPC algorithm is adjusted to increase the safety weight to reduce the collision risk.

[0100] Step 5.2: Apply the updated control input to control the charging pile to move and avoid obstacles.

[0101] In this embodiment, the control input is applied to the system: the control input calculated by the MPC algorithm, such as acceleration (a x ,a y ) and applied to the control system of charging piles.

[0102] Step 5.3: Further adjust the control strategy according to the obstacle avoidance effect until the collision risk is less than the set threshold.

[0103] Step 5.3.1: Monitor and adjust: If the obstacle avoidance effect is not ideal, further adjust the control strategy until the risk is acceptable. Update the status every Δt = 0.1s and continuously monitor the charging pile and environmental status.

[0104] Step 5.4: Monitor system status and environment: Continuously monitor the new status of the charging pile and environmental changes to provide data support for the next control cycle.

[0105] Step 5.5: Continue to execute the current MPC strategy or re-predict: If the risk is acceptable, continue to execute the current MPC strategy. If the risk is high, re-predict the trajectory and re-evaluate the collision risk.

[0106] Embodiment 2:

[0107] Embodiment 2 of the present invention provides a mobile charging pile collision prediction system based on model predictive control, including:

[0108] A data acquisition module is configured to acquire kinematic and dynamic parameters of the mobile charging pile during movement and establish a dynamic model of the charging pile;

[0109] An algorithm configuration module, configured to build a model predictive control algorithm, set an objective function and corresponding constraints;

[0110] A motion trajectory prediction module is configured to use a model predictive control algorithm to predict the motion trajectory within a future period of time according to a dynamic model of the charging pile;

[0111] A collision risk prediction module is configured to obtain surrounding environment perception data, predict the collision risk between the charging pile and surrounding obstacles according to the motion trajectory and environmental data, and obtain a collision risk analysis result;

[0112] The motion strategy adjustment module is configured to adjust the motion strategy of the charging pile according to the collision risk analysis result.

[0113] Embodiment three:

[0114] Embodiment 3 of the present invention provides a medium on which a program is stored. When the program is executed by a processor, the steps in the mobile charging pile collision prediction method based on model predictive control as described in Embodiment 1 of the present invention are implemented.

[0115] Embodiment 4:

[0116] Embodiment 4 of the present invention provides a device, including a memory, a processor, and a program stored in the memory and executable on the processor. When the processor executes the program, the steps in a mobile charging pile collision prediction method based on model predictive control as described in Embodiment 1 of the present invention are implemented.

[0117] The steps involved in the above embodiments 2, 3 and 4 correspond to the method embodiment 1. For the specific implementation methods, please refer to the relevant description part of embodiment 1.

[0118] Those skilled in the art should understand that the modules or steps of the present invention described above can be implemented by a general-purpose computer device, or alternatively, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. The present invention is not limited to any specific combination of hardware and software.

[0119] Although the above describes the specific implementation mode of the present invention in conjunction with the accompanying drawings, it is not intended to limit the scope of protection of the present invention. Those skilled in the art should understand that various modifications or variations that can be made by those skilled in the art on the basis of the technical solution of the present invention without creative work are still within the scope of protection of the present invention.

Claims

1. A mobile charging pile collision prediction method based on model predictive control, characterized in that: The following steps are involved: Obtain the kinematic and dynamic parameters of the mobile charging pile during movement and establish a dynamic model of the charging pile; Build a model predictive control algorithm, set the objective function and corresponding constraints; Use the model predictive control algorithm to predict the movement trajectory in the future based on the dynamic model of the charging pile; Acquire surrounding environment perception data, predict the collision risk between the charging pile and surrounding obstacles based on the motion trajectory and environmental perception data, and obtain collision risk analysis results; Adjust the movement strategy of the charging pile according to the collision risk analysis results.

2. The mobile charging pile collision prediction method based on model predictive control according to claim 1, characterized in that: The specific steps to obtain the kinematic and dynamic parameters of the mobile charging pile during movement are: Get the real-time location and speed of the charging pile through GPS and IMU sensors; The sensor data is fused using a Kalman filter.

3. The mobile charging pile collision prediction method based on model predictive control according to claim 1, characterized in that: After establishing the dynamic model of the charging pile, a nonlinear dynamic model is established based on the dynamic model of the charging pile to describe the motion behavior of the charging pile. The Taylor series expansion method is used to linearize the nonlinear dynamic model to adapt to the MPC algorithm.

4. The mobile charging pile collision prediction method based on model predictive control according to claim 1, characterized in that: The objective function is defined as minimizing the distance to obstacles, and the constraints include physical limitations and safety restrictions.

5. The mobile charging pile collision prediction method based on model predictive control according to claim 1, characterized in that: The specific steps of using the model predictive control algorithm to predict the motion trajectory in the future based on the dynamic model of the charging pile are: According to the preset control parameters, in each control cycle, the dynamic model of the charging pile is used to predict the movement trajectory of the charging pile in the future based on the current state; Optimize control inputs to satisfy objective functions and constraints; Apply the optimized control parameters as input for the next cycle.

6. The mobile charging pile collision prediction method based on model predictive control according to claim 1, characterized in that: The specific steps for predicting the collision risk between the charging pile and surrounding obstacles based on the motion trajectory and environmental perception data are as follows: Define the minimum safety distance. When the distance between the predicted trajectory and the obstacle is less than the minimum safety distance, it is considered that there is a collision risk. Calculate the collision probability, based on the predicted trajectory and the location of obstacles, using statistical methods to estimate the likelihood of a collision.

7. The mobile charging pile collision prediction method based on model predictive control according to claim 1, characterized in that: The specific steps to adjust the motion strategy of the charging pile according to the collision risk analysis results are: Update the control input of the charging pile according to the set obstacle avoidance strategy; Apply updated control inputs to control the charging pile to move and avoid obstacles; The control strategy is further adjusted according to the obstacle avoidance effect until the collision risk is less than the set threshold.

8. A mobile charging pile collision prediction system based on model predictive control, characterized in that: include: A data acquisition module is configured to acquire kinematic and dynamic parameters of the mobile charging pile during movement and establish a dynamic model of the charging pile; An algorithm configuration module, configured to build a model predictive control algorithm, set an objective function and corresponding constraints; A motion trajectory prediction module is configured to use a model predictive control algorithm to predict the motion trajectory within a future period of time according to a dynamic model of the charging pile; A collision risk prediction module is configured to obtain surrounding environment perception data, predict the collision risk between the charging pile and surrounding obstacles according to the motion trajectory and environmental data, and obtain a collision risk analysis result; The motion strategy adjustment module is configured to adjust the motion strategy of the charging pile according to the collision risk analysis result.

9. A computer-readable storage medium, characterized in that: A plurality of instructions are stored therein, and the instructions are suitable for being loaded by a processor of a terminal device and executing the mobile charging pile collision prediction method based on model predictive control as described in any one of claims 1-7.

10. A terminal device, characterized in that: It includes a processor and a computer-readable storage medium, the processor is used to implement each instruction; the computer-readable storage medium is used to store multiple instructions, and the instructions are suitable for being loaded by the processor and executing the mobile charging pile collision prediction method based on model predictive control described in any one of claims 1-7.

Images