Vehicle moving control method and system based on trajectory tracking

Abstract

The present invention discloses a vehicle travel control method and system based on trajectory tracking, including: obtaining a vehicle travel task; querying a preset path data table according to the travel task to obtain a target path; tracking the vehicle's trajectory to obtain a trajectory tracking result while the vehicle is executing the travel task according to the target path; generating a vehicle travel control strategy according to the target path and the trajectory tracking result, and controlling the vehicle to execute the travel control strategy. Accurately track the trajectory during the vehicle's travel, control the vehicle's travel according to the trajectory tracking result, avoid deviations during the vehicle's travel, and improve the safety of the vehicle's travel.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle control, and in particular to a vehicle travel control method and system based on trajectory tracking. Background Art

[0002] In recent years, the issue of energy consumption has attracted great attention in China and around the world, and the new energy industry is seeking breakthroughs in rapid development. In addition, the vigorous development of the Internet economy has put forward new requirements for traditional logistics and other industries. The inefficient and high-cost operation mode composed of staff and traditional transportation methods can no longer adapt to the huge market represented by urban freight business. The four-wheel steering wire-controlled chassis with electricity as the core power source has become the focus of research in the fields of transportation and transportation, and is a breakthrough point for solving the problem of imbalance between demand and efficiency. The four-wheel steering wire-controlled chassis adopts a modular design from the driving system, braking system, drive system to the steering system, and innovatively concentrates the key design technologies and indicators of traditional automobiles into a high-performance chassis. It can be seamlessly connected with shared travel, unmanned express delivery in parks, unmanned food delivery vehicles in hospitals, unmanned sweepers, and other services closely related to people's travel, shopping, and public health. It can also be easily converted into an unmanned bus to realize intelligent driving and interconnected operations. It can greatly save labor and ensure the highest work efficiency.

[0003] However, the existing technology cannot accurately track the trajectory of the vehicle during its movement, and is even more unable to control the movement of the vehicle based on the trajectory tracking results, which causes deviations in the vehicle during its movement and poses a major safety hazard. Summary of the invention

[0004] The present invention aims to solve at least one of the technical problems in the above-mentioned technology to a certain extent. To this end, the first purpose of the present invention is to propose a vehicle travel control method based on trajectory tracking, accurately track the trajectory during the vehicle travel, control the vehicle travel according to the trajectory tracking result, avoid deviation of the vehicle during the travel process, and improve the safety of the vehicle travel.

[0005] The second object of the present invention is to provide a vehicle travel control system based on trajectory tracking.

[0006] To achieve the above object, a first embodiment of the present invention proposes a vehicle moving control method based on trajectory tracking, comprising:

[0007] Get the vehicle's travel mission;

[0008] According to the travel task, query the preset path data table to obtain the target path;

[0009] When the vehicle is executing the traveling task according to the target path, the trajectory of the vehicle is tracked to obtain the trajectory tracking result;

[0010] According to the target path and trajectory tracking results, the vehicle's travel control strategy is generated, and the vehicle is controlled to execute the travel control strategy.

[0011] According to some embodiments of the present invention, the travel task includes a travel starting point, a travel end point and a travel requirement; the travel requirement includes at least one of a time requirement and a distance requirement.

[0012] According to some embodiments of the present invention, during the process of the vehicle performing a traveling task according to a target path, the vehicle is tracked to obtain a trajectory tracking result, including:

[0013] Get vehicle data;

[0014] Establishing a three-degree-of-freedom dynamics model of the vehicle based on vehicle data;

[0015] The road curvature of the vehicle in the sample data is obtained, and a trajectory tracking error model with global asymptotic stability is established through the Lyapunov direct method;

[0016] When the vehicle is performing the traveling task according to the target path, the detection information is obtained and input into the trajectory tracking error model to determine the trajectory tracking result.

[0017] According to some embodiments of the present invention, during the process of the vehicle performing a traveling task according to a target path, the vehicle is tracked to obtain a trajectory tracking result, including:

[0018] Acquire several frames of scene images when the vehicle is performing a traveling task according to a target path;

[0019] Determine the local area corresponding to the vehicle in the first frame scene image, determine the pixel values ​​of all pixels in the local area, and classify the pixels with consistent pixel values ​​to obtain a number of pixel sets, each of which corresponds to the target pixel value;

[0020] Determine the color frequency of a pixel having a target pixel value in a color scale histogram corresponding to the first frame scene image;

[0021]

[0022] Among them, a ε λ is the color level histogram a corresponding to the first frame scene image ε The color frequency of the pixel with the target pixel value in ; λ is the target pixel value; d(w j , p) is the distance between the jth pixel and the center pixel p in the color level histogram corresponding to the first frame scene image; d max is d(w j, p) maximum value; w j is the jth pixel in the color level histogram corresponding to the first frame scene image; k(w j ) is the pixel value of the jth pixel in the color scale histogram corresponding to the first frame scene image; for The weight coefficient is (0,1). The larger the distance between the jth pixel and the center pixel p in the color level histogram corresponding to the first frame scene image, the larger the weight coefficient. a is the number of pixels of the vehicle in the color scale histogram corresponding to the first frame of the scene image; T is the number of pixels with the target pixel value in the color scale histogram corresponding to the first frame of the scene image;

[0023] Determine the color frequency of the pixel point having the target pixel value in the color level histogram corresponding to the second frame scene image, and calculate the coincidence function of the first frame scene image and the second frame scene image;

[0024]

[0025] Wherein, sim(a, b) is the overlap function of the first frame scene image and the second frame scene image; b ε λ is the color level histogram b corresponding to the scene image in the second frame ε The color frequency of the pixel with the target pixel value in ; d a is the moving distance of the vehicle in the first frame scene image a; d b is the moving distance of the vehicle in the second frame scene image b; d(a0, b0) is the distance between the midpoint a0 of the vehicle in the first frame scene image and the midpoint b0 of the vehicle in the second frame scene image; A1 is the first weight related to the moving distance of the vehicle; M a is the number of pixels of the vehicle in the first frame of the scene image; M b is the number of pixels included in the vehicle in the second frame scene image; A2 is a second weight related to the number of pixels included in the vehicle; A3 is a third weight related to the color level histogram corresponding to the vehicle; A1+A2+A3=1; C is the number of target pixel sets, also the number of pixels with target values;

[0026] According to the coincidence function of the first frame scene image and the second frame scene image, the trajectory of the vehicle from the first frame scene image to the second frame scene image is tracked, and the coincidence function of the previous frame scene image and the adjacent next frame scene image is calculated in sequence to obtain the trajectory tracking result.

[0027] According to some embodiments of the present invention, a vehicle travel control strategy is generated based on the target path and trajectory tracking results, including:

[0028] Calculate the deviation coefficient H between the trajectory tracking result and the target path;

[0029]

[0030] Where N is the number of vehicle trajectory points included in the trajectory tracking result; F is the driving force of the vehicle; D i is the coordinate of the i-th trajectory point on the moving trajectory of the vehicle determined by the trajectory tracking result; D i ' is the coordinate of the trajectory point at the corresponding moment on the target path;

[0031] It is determined whether the deviation coefficient is within a preset deviation coefficient range. When it is determined that the deviation coefficient is not within the preset deviation coefficient range, a correction instruction for the vehicle is generated as a vehicle travel control strategy to make the deviation coefficient within the preset deviation coefficient range.

[0032] According to some embodiments of the present invention, during the vehicle executing the travel control strategy, the process further includes:

[0033] The distance value L between the vehicle and the surrounding human bodies is detected based on the human body sensing sensor arranged on the vehicle;

[0034]

[0035] Where U is the output signal strength of the human body sensing sensor; W λ is the power of human radiation sensed by the human body sensing sensor; λ0 is the minimum working wavelength of the human body sensing sensor; λ1 is the maximum working wavelength of the human body sensing sensor; p is the sensitivity of the human body sensing sensor; s is the infrared sensing area of ​​the human body sensing sensor; z is the light transmittance of the human body sensing sensor;

[0036] When it is determined that the distance between the vehicle and the surrounding human bodies is less than a preset distance threshold, the travel control strategy is adjusted so that the distance between the vehicle and the surrounding human bodies is greater than or equal to the preset distance threshold.

[0037] According to some embodiments of the present invention, before controlling the vehicle to execute the travel control strategy, the method further includes:

[0038] Construct the vehicle trajectory simulation environment in the Carsim simulation platform, build the simulation model in the Simulink module, and coordinate Carsim and Simulink to perform joint simulation of trajectory tracking control to obtain simulation results;

[0039] When it is determined that the simulation result is consistent with the preset result, it means that the travel control strategy is verified and the vehicle is controlled to execute the travel control strategy.

[0040] To achieve the above object, a second embodiment of the present invention proposes a vehicle travel control system based on trajectory tracking, comprising:

[0041] An acquisition module, used to acquire the vehicle's travel mission;

[0042] A query module is used to query the preset path data table according to the travel task to obtain the target path;

[0043] A determination module is used to track the trajectory of the vehicle and obtain a trajectory tracking result when the vehicle performs a traveling task according to a target path;

[0044] The generation module is used to generate a vehicle's travel control strategy based on the target path and trajectory tracking results, and control the vehicle to execute the travel control strategy.

[0045] According to some embodiments of the present invention, the determining module includes:

[0046] The first computing module is used for:

[0047] Acquire several frames of scene images when the vehicle is performing a traveling task according to a target path;

[0048] Determine the local area corresponding to the vehicle in the first frame scene image, determine the pixel values ​​of all pixels in the local area, and classify the pixels with consistent pixel values ​​to obtain a number of pixel sets, each of which corresponds to the target pixel value;

[0049] Determine the color frequency of a pixel having a target pixel value in a color scale histogram corresponding to the first frame scene image;

[0050]

[0051] Among them, a ε λ is the color level histogram a corresponding to the first frame scene image ε The color frequency of the pixel with the target pixel value in ; λ is the target pixel value; d(w j , p) is the distance between the jth pixel and the center pixel p in the color level histogram corresponding to the first frame scene image; d max is d(w j , p) maximum value; w j is the jth pixel in the color level histogram corresponding to the first frame scene image; k(w j ) is the pixel value of the jth pixel in the color scale histogram corresponding to the first frame scene image; for The weight coefficient is (0,1). The larger the distance between the jth pixel and the center pixel p in the color level histogram corresponding to the first frame scene image, the larger the weight coefficient. ais the number of pixels of the vehicle in the color scale histogram corresponding to the first frame of the scene image; T is the number of pixels with the target pixel value in the color scale histogram corresponding to the first frame of the scene image;

[0052] Determine the color frequency of the pixel point having the target pixel value in the color level histogram corresponding to the second frame scene image, and calculate the coincidence function of the first frame scene image and the second frame scene image;

[0053]

[0054] Wherein, sim(a, b) is the overlap function of the first frame scene image and the second frame scene image; b ε λ is the color level histogram b corresponding to the scene image in the second frame ε The color frequency of the pixel with the target pixel value in ; d a is the moving distance of the vehicle in the first frame scene image a; d b is the moving distance of the vehicle in the second frame scene image b; d(a0, b0) is the distance between the midpoint a0 of the vehicle in the first frame scene image and the midpoint b0 of the vehicle in the second frame scene image; A1 is the first weight related to the moving distance of the vehicle; M a is the number of pixels of the vehicle in the first frame of the scene image; M b is the number of pixels included in the vehicle in the second frame scene image; A2 is a second weight related to the number of pixels included in the vehicle; A3 is a third weight related to the color level histogram corresponding to the vehicle; A1+A2+A3=1; C is the number of target pixel sets, also the number of pixels with target values;

[0055] The trajectory tracking module is used to track the trajectory of the vehicle from the first frame scene image to the second frame scene image according to the coincidence function of the first frame scene image and the second frame scene image, and sequentially calculate the coincidence function of the previous frame scene image and the adjacent next frame scene image to obtain the trajectory tracking result.

[0056] According to some embodiments of the present invention, the generating module comprises:

[0057] A second calculation module is used to calculate the deviation coefficient H between the trajectory tracking result and the target path;

[0058]

[0059] Where N is the number of vehicle trajectory points included in the trajectory tracking result; F is the driving force of the vehicle; D i is the coordinate of the i-th trajectory point on the moving trajectory of the vehicle determined by the trajectory tracking result; D i' is the coordinate of the trajectory point at the corresponding moment on the target path;

[0060] The judgment module is used to judge whether the deviation coefficient is within a preset deviation coefficient range. When it is determined that the deviation coefficient is not within the preset deviation coefficient range, a correction instruction for the vehicle is generated as a vehicle travel control strategy to make the deviation coefficient within the preset deviation coefficient range.

[0061] The present invention discloses a vehicle travel control method and system based on trajectory tracking, which accurately tracks the trajectory of the vehicle during its travel, controls the vehicle travel according to the trajectory tracking result, avoids deviation of the vehicle during its travel, and improves the safety of the vehicle travel.

[0062] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description and the accompanying drawings.

[0063] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0065] Figure 1 is a flow chart of a vehicle travel control method based on trajectory tracking according to an embodiment of the present invention;

[0066] Figure 2 is a block diagram of a vehicle travel control system based on trajectory tracking according to an embodiment of the present invention. DETAILED DESCRIPTION

[0067] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0068] like Figure 1 As shown, the first embodiment of the present invention proposes a vehicle travel control method based on trajectory tracking, including steps S1-S4:

[0069] S1. Obtain the vehicle's travel mission;

[0070] S2. Query the preset path data table according to the travel task to obtain the target path;

[0071] S3, when the vehicle is executing the traveling task according to the target path, tracking the trajectory of the vehicle to obtain a trajectory tracking result;

[0072] S4. Generate a vehicle travel control strategy based on the target path and trajectory tracking results, and control the vehicle to execute the travel control strategy.

[0073] The working principle of the above technical solution: In this embodiment, the preset path data table is a data table that can query the path information of the corresponding travel task based on the travel task.

[0074] In this embodiment, a vehicle travel control strategy is generated based on the target path and trajectory tracking results. The travel control strategy includes adjusting the trajectory of the vehicle to make it conform to the target path and ensuring safe driving of the vehicle to avoid collision with pedestrians.

[0075] The beneficial effects of the above technical solution are: accurately tracking the trajectory of the vehicle during its movement, controlling the movement of the vehicle according to the trajectory tracking result, avoiding deviation of the vehicle during its movement, and improving the safety of the vehicle's movement.

[0076] According to some embodiments of the present invention, the travel task includes a travel starting point, a travel end point, and a travel requirement; the travel requirement includes at least one of a time requirement and a distance requirement. The time requirement is that the time of the path from the travel starting point to the travel end point is within a preset time range. The preset time range is the approximate time range from the travel starting point to the travel end point determined under safe driving conditions. The distance requirement is that the distance of the planned path from the travel starting point to the travel end point is within a preset distance range. The preset distance range is the approximate distance range determined from the travel starting point to the travel end point.

[0077] According to some embodiments of the present invention, during the process of the vehicle performing a traveling task according to a target path, the vehicle is tracked to obtain a trajectory tracking result, including:

[0078] Get vehicle data;

[0079] Establishing a three-degree-of-freedom dynamics model of the vehicle based on vehicle data;

[0080] The road curvature of the vehicle in the sample data is obtained, and a trajectory tracking error model with global asymptotic stability is established through the Lyapunov direct method;

[0081] When the vehicle is performing the traveling task according to the target path, the detection information is obtained and input into the trajectory tracking error model to determine the trajectory tracking result.

[0082] The working principle and beneficial effects of the above technical solution: Vehicle data include vehicle mass, vehicle moment of inertia around its center of mass, lateral stiffness of front and rear wheels, vehicle wheelbase, friction coefficient between tire and ground, vehicle current speed, vehicle acceleration, vehicle yaw rate, vehicle lateral position (y) and longitudinal position (x), vehicle heading angle (ψ). These data can be directly obtained through vehicle sensors (such as GPS, inertial measurement unit IMU, wheel speed sensor, etc.) and vehicle CAN bus, or indirectly obtained through calculation. Establish a three-degree-of-freedom dynamic model, establish a three-degree-of-freedom dynamic model (longitudinal, lateral and yaw). Includes longitudinal motion, lateral motion and yaw motion of the vehicle. Model equation: Longitudinal motion: mv˙=F x -F drag -F roll , lateral movement: mv y ˙=F yf +F yr , yaw motion: I z r˙=aF yf -bF yr Among them, F x is the longitudinal force, F drag and F roll They are resistance and rolling resistance, F yf and F yr are the lateral forces of the front and rear wheels, respectively, which can be calculated through tire models (such as Pacejka model) and sideslip angles. The road curvature can be obtained through map data, GPS data or vehicle sensors (such as lidar or camera) combined with image processing technology. Using the Lyapunov direct method, it is first necessary to define trajectory tracking errors, such as lateral error (lateral distance between the actual position of the vehicle and the target path) and heading error (angle between the vehicle heading and the tangent direction of the target path). Then, based on these errors and the vehicle dynamics model, a control law is designed to make the error system globally asymptotically stable. Obtain detection information during vehicle movement and input it into the trajectory tracking error model: During the actual driving process of the vehicle, the vehicle's state information (such as position, speed, acceleration, yaw rate, etc.) and road information (such as curvature) are obtained in real time. This information is input into the previously established trajectory tracking error model, and the model calculates the control input (such as front wheel angle, acceleration, etc.) according to the current state and road conditions to achieve tracking of the target path.

[0083] According to some embodiments of the present invention, during the process of the vehicle performing a traveling task according to a target path, the vehicle is tracked to obtain a trajectory tracking result, including:

[0084] Acquire several frames of scene images when the vehicle is performing a traveling task according to a target path;

[0085] Determine the local area corresponding to the vehicle in the first frame scene image, determine the pixel values ​​of all pixels in the local area, and classify the pixels with consistent pixel values ​​to obtain a number of pixel sets, each of which corresponds to the target pixel value;

[0086] Determine the color frequency of a pixel having a target pixel value in a color scale histogram corresponding to the first frame scene image;

[0087]

[0088] Among them, a ε λ is the color level histogram a corresponding to the first frame scene image ε The color frequency of the pixel with the target pixel value in ; λ is the target pixel value; d(w j , p) is the distance between the jth pixel and the center pixel p in the color level histogram corresponding to the first frame scene image; d max is d(w j , p) maximum value; w j is the jth pixel in the color level histogram corresponding to the first frame scene image; k(w j ) is the pixel value of the jth pixel in the color scale histogram corresponding to the first frame scene image; for The weight coefficient is (0,1). The larger the distance between the jth pixel and the center pixel p in the color level histogram corresponding to the first frame scene image, the larger the weight coefficient. a is the number of pixels of the vehicle in the color scale histogram corresponding to the first frame of the scene image; T is the number of pixels with the target pixel value in the color scale histogram corresponding to the first frame of the scene image;

[0089] Determine the color frequency of the pixel point having the target pixel value in the color level histogram corresponding to the second frame scene image, and calculate the coincidence function of the first frame scene image and the second frame scene image;

[0090]

[0091] Wherein, sim(a, b) is the overlap function of the first frame scene image and the second frame scene image; b ε λ is the color level histogram b corresponding to the scene image in the second frame ε The color frequency of the pixel with the target pixel value in ; d a is the moving distance of the vehicle in the first frame scene image a; d bis the moving distance of the vehicle in the second frame scene image b; d(a0, b0) is the distance between the midpoint a0 of the vehicle in the first frame scene image and the midpoint b0 of the vehicle in the second frame scene image; A1 is the first weight related to the moving distance of the vehicle; M a is the number of pixels of the vehicle in the first frame of the scene image; M b is the number of pixels included in the vehicle in the second frame scene image; A2 is a second weight related to the number of pixels included in the vehicle; A3 is a third weight related to the color level histogram corresponding to the vehicle; A1+A2+A3=1; C is the number of target pixel sets, also the number of pixels with target values;

[0092] According to the coincidence function of the first frame scene image and the second frame scene image, the trajectory of the vehicle from the first frame scene image to the second frame scene image is tracked, and the coincidence function of the previous frame scene image and the adjacent next frame scene image is calculated in sequence to obtain the trajectory tracking result.

[0093] The working principle and beneficial effects of the above technical solution are as follows: the central pixel point is the geometric center point of the scene image on the coordinate axis. The midpoint of the vehicle can be the geometric center point of the vehicle. Each set of pixel points corresponds to a pixel value. Determine the color frequency of the corresponding target pixel point in the color scale histogram corresponding to each frame of the scene image, so as to facilitate the determination of the color distribution of the image. Based on calculating the coincidence function of adjacent frames of scene images, compare the difference between the two frames of scene images, and track the trajectory of the vehicle from the first frame of scene image to the second frame of scene image based on the coincidence function of the first frame of scene image and the second frame of scene image, calculate the coincidence function of the previous frame of scene image and the adjacent next frame of scene image in turn, and obtain the trajectory tracking result. By comparing adjacent frames of scene images, the coincidence information and difference information are determined to achieve the trajectory tracking of the vehicle.

[0094] According to some embodiments of the present invention, a vehicle travel control strategy is generated based on the target path and trajectory tracking results, including:

[0095] Calculate the deviation coefficient H between the trajectory tracking result and the target path;

[0096]

[0097] Where N is the number of vehicle trajectory points included in the trajectory tracking result; F is the driving force of the vehicle; D i is the coordinate of the i-th trajectory point on the moving trajectory of the vehicle determined by the trajectory tracking result; D i ' is the coordinate of the trajectory point at the corresponding moment on the target path;

[0098] It is determined whether the deviation coefficient is within a preset deviation coefficient range. When it is determined that the deviation coefficient is not within the preset deviation coefficient range, a correction instruction for the vehicle is generated as a vehicle travel control strategy to make the deviation coefficient within the preset deviation coefficient range.

[0099] The working principle and beneficial effects of the above technical solution are as follows: when generating a vehicle's travel control strategy based on the target path and trajectory tracking results, the deviation coefficient between the trajectory tracking result and the target path is calculated, and it is determined whether the deviation coefficient is within the preset deviation coefficient range. When it is determined that the deviation coefficient is not within the preset deviation coefficient range, a correction instruction for the vehicle is generated as the vehicle's travel control strategy to make the deviation coefficient within the preset deviation coefficient range. This prevents the actual trajectory of the vehicle from seriously deviating from the planned target path, achieves precise control of the vehicle, and improves the safety of vehicle driving.

[0100] According to some embodiments of the present invention, during the vehicle executing the travel control strategy, the process further includes:

[0101] The distance value L between the vehicle and the surrounding human bodies is detected based on the human body sensing sensor arranged on the vehicle;

[0102]

[0103] Where U is the output signal strength of the human body sensing sensor; W λ is the power of human radiation sensed by the human body sensing sensor; λ0 is the minimum working wavelength of the human body sensing sensor; λ1 is the maximum working wavelength of the human body sensing sensor; p is the sensitivity of the human body sensing sensor; s is the infrared sensing area of ​​the human body sensing sensor; z is the light transmittance of the human body sensing sensor;

[0104] When it is determined that the distance between the vehicle and the surrounding human bodies is less than a preset distance threshold, the travel control strategy is adjusted so that the distance between the vehicle and the surrounding human bodies is greater than or equal to the preset distance threshold.

[0105] The working principle and beneficial effects of the above technical solution are as follows: When the vehicle executes the travel control strategy, the distance between the vehicle and the surrounding human body is detected based on the human body sensing sensor installed on the vehicle; when it is determined that the distance between the vehicle and the surrounding human body is less than the preset distance threshold, the travel control strategy is adjusted to make the distance between the vehicle and the surrounding human body greater than or equal to the preset distance threshold. Avoid collision between the vehicle and pedestrians during driving, flexibly control the appearance of dynamic obstacles, adjust the movement of the vehicle, and improve the safety of vehicle driving.

[0106] According to some embodiments of the present invention, before controlling the vehicle to execute the travel control strategy, the method further includes:

[0107] Construct the vehicle trajectory simulation environment in the Carsim simulation platform, build the simulation model in the Simulink module, and coordinate Carsim and Simulink to perform joint simulation of trajectory tracking control to obtain simulation results;

[0108] When it is determined that the simulation result is consistent with the preset result, it means that the travel control strategy is verified and the vehicle is controlled to execute the travel control strategy.

[0109] The working principle and beneficial effects of the above technical solution: Step 1: Install and configure Carsim and Simulink: Install software: MATLAB, Simulink and Carsim software are installed on the computer. Configure path: Configure the path of Carsim in MATLAB so that Simulink can recognize Carsim's S-Function Block. Step 2: Build a vehicle model and simulation environment in Carsim: Open Carsim: Start the Carsim software and select or create a new vehicle model. Set vehicle parameters: Adjust the physical parameters of the vehicle as required, such as mass, size, suspension system, etc. Define roads and trajectories: Design your roads and expected driving trajectories in Carsim. You can use the built-in road editor of Carsim or import external road data. Configure sensors: If the control algorithm requires real-time status information of the vehicle (such as position, speed, acceleration, etc.), make sure to configure these sensors accordingly in Carsim. Step 3: Build a control model in Simulink: Open Simulink: Start Simulink in MATLAB and create a new model. Add Carsim S-FunctionBlock: Find and add Carsim's S-Function Block to the model in the Simulink library. Build control logic: Use Simulink's module library (such as PID controller, state machine, logical operator, etc.) to build trajectory tracking control logic. Interface configuration: Ensure that the Carsim S-Function Block is correctly interfaced with the control logic, including the matching of input and output signals. Step 4: Joint simulation settings: Parameter transfer: Set the parameter transfer between the Carsim S-Function Block and the Simulink model to ensure that the vehicle state and control signals can be exchanged correctly. Simulation parameter configuration: Set simulation parameters such as simulation time and solver type in Simulink. Step 5: Run the simulation and analyze the results: Start the simulation: Click the Run button in Simulink to start the simulation. Observe the results: Use Simulink's Scope or other analysis tools to observe the simulation results, such as vehicle position, speed, tracking error, etc. Adjust the control strategy: If the simulation results do not meet expectations, return to Simulink to adjust the control strategy and rerun the simulation. Step 6: Verify the travel control strategy comparison results: Compare the simulation results with the preset trajectory or performance indicators to verify the effectiveness of the control strategy. Iterative optimization: If necessary, repeat the above steps to iteratively optimize the control strategy. Carry out vehicle trajectory tracking control simulation in the joint environment of Carsim and Simulink, verify whether the driving control strategy is qualified, and improve the accuracy of determining the driving control strategy.

[0110] like Figure 2 As shown, the second embodiment of the present invention proposes a vehicle travel control system based on trajectory tracking, comprising:

[0111] An acquisition module, used to acquire the vehicle's travel mission;

[0112] A query module is used to query the preset path data table according to the travel task to obtain the target path;

[0113] A determination module is used to track the trajectory of the vehicle and obtain a trajectory tracking result when the vehicle performs a traveling task according to a target path;

[0114] The generation module is used to generate a vehicle's travel control strategy based on the target path and trajectory tracking results, and control the vehicle to execute the travel control strategy.

[0115] The beneficial effects of the above technical solution are: accurately tracking the trajectory of the vehicle during its movement, controlling the movement of the vehicle according to the trajectory tracking result, avoiding deviation of the vehicle during its movement, and improving the safety of the vehicle's movement.

[0116] According to some embodiments of the present invention, the determining module includes:

[0117] The first computing module is used for:

[0118] Acquire several frames of scene images when the vehicle is performing a traveling task according to a target path;

[0119] Determine the local area corresponding to the vehicle in the first frame scene image, determine the pixel values ​​of all pixels in the local area, and classify the pixels with consistent pixel values ​​to obtain a number of pixel sets, each of which corresponds to the target pixel value;

[0120] Determine the color frequency of a pixel having a target pixel value in a color scale histogram corresponding to the first frame scene image;

[0121]

[0122] Among them, a ε λ is the color level histogram a corresponding to the first frame scene image ε The color frequency of the pixel with the target pixel value in ; λ is the target pixel value; d(w j , p) is the distance between the jth pixel and the center pixel p in the color level histogram corresponding to the first frame scene image; d max is d(w j , p) maximum value; w j is the jth pixel in the color level histogram corresponding to the first frame scene image; k(w j) is the pixel value of the jth pixel in the color scale histogram corresponding to the first frame scene image; for The weight coefficient is (0,1). The larger the distance between the jth pixel and the center pixel p in the color level histogram corresponding to the first frame scene image, the larger the weight coefficient. a is the number of pixels of the vehicle in the color scale histogram corresponding to the first frame of the scene image; T is the number of pixels with the target pixel value in the color scale histogram corresponding to the first frame of the scene image;

[0123] Determine the color frequency of the pixel point having the target pixel value in the color level histogram corresponding to the second frame scene image, and calculate the coincidence function of the first frame scene image and the second frame scene image;

[0124]

[0125] Wherein, sim(a, b) is the overlap function of the first frame scene image and the second frame scene image; b ε λ is the color level histogram b corresponding to the scene image in the second frame ε The color frequency of the pixel with the target pixel value in ; d a is the moving distance of the vehicle in the first frame scene image a; d b is the moving distance of the vehicle in the second frame scene image b; d(a0, b0) is the distance between the midpoint a0 of the vehicle in the first frame scene image and the midpoint b0 of the vehicle in the second frame scene image; A1 is the first weight related to the moving distance of the vehicle; M a is the number of pixels of the vehicle in the first frame of the scene image; M b is the number of pixels included in the vehicle in the second frame scene image; A2 is a second weight related to the number of pixels included in the vehicle; A3 is a third weight related to the color level histogram corresponding to the vehicle; A1+A2+A3=1; C is the number of target pixel sets, also the number of pixels with target values;

[0126] The trajectory tracking module is used to track the trajectory of the vehicle from the first frame scene image to the second frame scene image according to the coincidence function of the first frame scene image and the second frame scene image, and sequentially calculate the coincidence function of the previous frame scene image and the adjacent next frame scene image to obtain the trajectory tracking result.

[0127] The working principle and beneficial effects of the above technical solution are as follows: the central pixel point is the geometric center point of the scene image on the coordinate axis. The midpoint of the vehicle can be the geometric center point of the vehicle. Each set of pixel points corresponds to a pixel value. Determine the color frequency of the corresponding target pixel point in the color scale histogram corresponding to each frame of the scene image, so as to facilitate the determination of the color distribution of the image. Based on calculating the coincidence function of adjacent frames of scene images, compare the difference between the two frames of scene images, and track the trajectory of the vehicle from the first frame of scene image to the second frame of scene image based on the coincidence function of the first frame of scene image and the second frame of scene image, calculate the coincidence function of the previous frame of scene image and the adjacent next frame of scene image in turn, and obtain the trajectory tracking result. By comparing adjacent frames of scene images, the coincidence information and difference information are determined to achieve the trajectory tracking of the vehicle.

[0128] According to some embodiments of the present invention, the generating module comprises:

[0129] A second calculation module is used to calculate the deviation coefficient H between the trajectory tracking result and the target path;

[0130]

[0131] Where N is the number of vehicle trajectory points included in the trajectory tracking result; F is the driving force of the vehicle; D i is the coordinate of the i-th trajectory point on the moving trajectory of the vehicle determined by the trajectory tracking result; D i ' is the coordinate of the trajectory point at the corresponding moment on the target path;

[0132] The judgment module is used to judge whether the deviation coefficient is within a preset deviation coefficient range. When it is determined that the deviation coefficient is not within the preset deviation coefficient range, a correction instruction for the vehicle is generated as a vehicle travel control strategy to make the deviation coefficient within the preset deviation coefficient range.

[0133] The working principle and beneficial effects of the above technical solution are as follows: when generating a vehicle's travel control strategy based on the target path and trajectory tracking results, the deviation coefficient between the trajectory tracking result and the target path is calculated, and it is determined whether the deviation coefficient is within the preset deviation coefficient range. When it is determined that the deviation coefficient is not within the preset deviation coefficient range, a correction instruction for the vehicle is generated as the vehicle's travel control strategy to make the deviation coefficient within the preset deviation coefficient range. This prevents the actual trajectory of the vehicle from seriously deviating from the planned target path, achieves precise control of the vehicle, and improves the safety of vehicle driving.

[0134] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A vehicle moving control method based on trajectory tracking, characterized in that: include: Get the vehicle's travel mission; According to the travel task, query the preset path data table to obtain the target path; When the vehicle is executing the traveling task according to the target path, the trajectory of the vehicle is tracked to obtain the trajectory tracking result; Generate a vehicle's travel control strategy based on the target path and trajectory tracking results, and control the vehicle to execute the travel control strategy; When the vehicle is executing the moving task according to the target path, the vehicle trajectory is tracked to obtain the trajectory tracking results, including: Acquire several frames of scene images when the vehicle is performing a traveling task according to a target path; Determine the local area corresponding to the vehicle in the first frame scene image, determine the pixel values ​​of all pixels in the local area, and classify the pixels with consistent pixel values ​​to obtain a number of pixel sets, each of which corresponds to the target pixel value; Determine the color frequency of a pixel having a target pixel value in a color scale histogram corresponding to the first frame scene image; in, is the color level histogram corresponding to the scene image in the first frame The color frequency of the pixel points with the target pixel value in ; is the target pixel value; is the first frame of the scene image corresponding to the color level histogram Pixels and center pixel The distance between for The maximum value of is the first frame of the scene image corresponding to the color level histogram pixels; is the first frame of the scene image corresponding to the color level histogram The pixel value of a pixel; for The weight coefficient is (0,1). Pixels and center pixel The greater the distance between them, the greater the weight coefficient; is the number of pixels included in the vehicle in the color scale histogram corresponding to the first frame of the scene image; is the number of pixels with target pixel values ​​in the color scale histogram corresponding to the first frame scene image; Determine the color frequency of the pixel point having the target pixel value in the color level histogram corresponding to the second frame scene image, and calculate the coincidence function of the first frame scene image and the second frame scene image; in, is the coincidence function of the first frame scene image and the second frame scene image; is the color level histogram corresponding to the scene image in the second frame The color frequency of the pixel points with the target pixel value in ; is the moving distance of the vehicle in the first frame scene image a; is the moving distance of the vehicle in the second frame scene image b; is the midpoint of the vehicle in the first frame of the scene image and the midpoint of the vehicle in the second frame scene image The distance between is a first weight related to the moving distance of the vehicle; is the number of pixels of the vehicle in the first frame of scene image; is the number of pixels included in the vehicle in the second frame scene image; is a second weight related to the number of pixels included in the vehicle; is a third weight related to the color level histogram corresponding to the vehicle; ; is the number of target pixel points, and also the number of target pixel values; According to the coincidence function of the first frame scene image and the second frame scene image, the trajectory of the vehicle from the first frame scene image to the second frame scene image is tracked, and the coincidence function of the previous frame scene image and the adjacent next frame scene image is calculated in sequence to obtain the trajectory tracking result.

2. The vehicle moving control method based on trajectory tracking according to claim 1, characterized in that: The travel task includes a travel starting point, a travel end point and travel requirements; the travel requirements include at least one of a time requirement and a distance requirement.

3. The vehicle moving control method based on trajectory tracking according to claim 1, characterized in that: When the vehicle is executing the moving task according to the target path, the vehicle trajectory is tracked to obtain the trajectory tracking results, including: Get vehicle data; Establishing a three-degree-of-freedom dynamics model of the vehicle based on vehicle data; Obtain the road curvature of the vehicle in the sample data, and establish a trajectory tracking error model with global asymptotic stability through the Lyapunov direct method; When the vehicle is executing the moving task according to the target path, the detection information is obtained and input into the trajectory tracking error model to determine the trajectory tracking result.

4. The vehicle moving control method based on trajectory tracking according to claim 1, characterized in that: According to the target path and trajectory tracking results, the vehicle's travel control strategy is generated, including: Calculate the deviation coefficient between the trajectory tracking result and the target path ; in, The number of vehicle trajectory points included in the trajectory tracking result; The driving force of the vehicle; is the first moving trajectory of the vehicle determined by the trajectory tracking result. The coordinates of the trajectory points; is the coordinate of the trajectory point at the corresponding time on the target path; It is determined whether the deviation coefficient is within a preset deviation coefficient range. When it is determined that the deviation coefficient is not within the preset deviation coefficient range, a correction instruction for the vehicle is generated as a vehicle travel control strategy to make the deviation coefficient within the preset deviation coefficient range.

5. The vehicle moving control method based on trajectory tracking according to claim 1, characterized in that: The vehicle's execution of the driving control strategy also includes: The distance between the vehicle and the surrounding human bodies is detected by the human body sensing sensor installed on the vehicle. ; in, is the output signal strength of the human body sensing sensor; The power of human body radiation sensed by the human body sensing sensor; It is the minimum working wavelength of the human body sensing sensor; is the maximum operating wavelength of the human body sensing sensor; is the sensitivity of the human body sensing sensor; is the infrared sensing area of ​​the human body sensing sensor; is the light transmittance of the human body sensing sensor; Represents a variable The differential of λ is in the range of [ , ]; When it is determined that the distance between the vehicle and the surrounding human bodies is less than a preset distance threshold, the travel control strategy is adjusted so that the distance between the vehicle and the surrounding human bodies is greater than or equal to the preset distance threshold.

6. The vehicle moving control method based on trajectory tracking according to claim 1, characterized in that: Before controlling the vehicle to execute the driving control strategy, it also includes: Construct the vehicle trajectory simulation environment in the Carsim simulation platform, build the simulation model in the Simulink module, and coordinate Carsim and Simulink to perform joint simulation of trajectory tracking control to obtain simulation results; When it is determined that the simulation result is consistent with the preset result, it means that the travel control strategy is verified and the vehicle is controlled to execute the travel control strategy.

7. A vehicle travel control system based on trajectory tracking, characterized in that: include: An acquisition module, used to acquire the vehicle's travel mission; A query module is used to query the preset path data table according to the travel task to obtain the target path; A determination module is used to track the trajectory of the vehicle and obtain a trajectory tracking result when the vehicle performs a traveling task according to a target path; A generation module, used to generate a vehicle travel control strategy according to the target path and trajectory tracking results, and control the vehicle to execute the travel control strategy; The determining module comprises: The first computing module is used for: Acquire several frames of scene images when the vehicle is performing a traveling task according to a target path; Determine the local area corresponding to the vehicle in the first frame scene image, determine the pixel values ​​of all pixels in the local area, and classify the pixels with consistent pixel values ​​to obtain a number of pixel sets, each of which corresponds to the target pixel value; Determine the color frequency of a pixel having a target pixel value in a color scale histogram corresponding to the first frame scene image; in, is the color level histogram corresponding to the scene image in the first frame The color frequency of the pixel points with the target pixel value in ; is the target pixel value; is the first frame of the scene image corresponding to the color level histogram Pixels and center pixel The distance between for The maximum value of is the first frame of the scene image corresponding to the color level histogram pixels; is the first frame of the scene image corresponding to the color level histogram The pixel value of a pixel; for The weight coefficient is (0,1). Pixels and center pixel The greater the distance between them, the greater the weight coefficient; is the number of pixels included in the vehicle in the color scale histogram corresponding to the first frame of the scene image; is the number of pixels with target pixel values ​​in the color scale histogram corresponding to the first frame scene image; Determine the color frequency of the pixel point having the target pixel value in the color level histogram corresponding to the second frame scene image, and calculate the coincidence function of the first frame scene image and the second frame scene image; in, is the coincidence function of the first frame scene image and the second frame scene image; is the color level histogram corresponding to the scene image in the second frame The color frequency of the pixel points with the target pixel value in ; is the moving distance of the vehicle in the first frame scene image a; is the moving distance of the vehicle in the second frame scene image b; is the midpoint of the vehicle in the first frame of the scene image and the midpoint of the vehicle in the second frame scene image The distance between is a first weight related to the moving distance of the vehicle; is the number of pixels of the vehicle in the first frame of scene image; is the number of pixels included in the vehicle in the second frame scene image; is a second weight related to the number of pixels included in the vehicle; is a third weight related to the color level histogram corresponding to the vehicle; ; is the number of target pixel points, and also the number of target pixel values; The trajectory tracking module is used to track the trajectory of the vehicle from the first frame scene image to the second frame scene image according to the coincidence function of the first frame scene image and the second frame scene image, and sequentially calculate the coincidence function of the previous frame scene image and the adjacent next frame scene image to obtain the trajectory tracking result.

8. The vehicle travel control system based on trajectory tracking as claimed in claim 7, characterized in that: The generating module comprises: The second calculation module is used to calculate the deviation coefficient between the trajectory tracking result and the target path ; in, The number of vehicle trajectory points included in the trajectory tracking result; The driving force of the vehicle; is the first moving trajectory of the vehicle determined by the trajectory tracking result. The coordinates of the trajectory points; is the coordinate of the trajectory point at the corresponding time on the target path; The judgment module is used to judge whether the deviation coefficient is within a preset deviation coefficient range. When it is determined that the deviation coefficient is not within the preset deviation coefficient range, a correction instruction for the vehicle is generated as a vehicle travel control strategy to make the deviation coefficient within the preset deviation coefficient range.

Images