Self-calibration intelligent traffic light and self-calibration intelligent traffic light control method

Abstract

The invention relates to a self-calibration intelligent traffic light and a self-calibration intelligent traffic light control method, which are applied to the technical field of intelligent traffic, the self-calibration intelligent traffic light comprises a light pole main body and a mobile equipment cabin, the light pole main body is installed on the mobile equipment cabin, and the mobile equipment cabin is installed on the light pole main body. A traffic light, a data acquisition mechanism and a communication device are installed on the lamp pole main body, a calculation control system is arranged in the mobile device cabin, the data acquisition mechanism is electrically connected with the communication device and the calculation control system, and the calculation control system is electrically connected with the communication device and the traffic light. According to the invention, the traffic signal lamp can be flexibly and rapidly put into use.

Description

Technical Field

[0001] The present application relates to the technical field of intelligent transportation, and in particular to a self-calibrating intelligent traffic light and a self-calibrating intelligent traffic light control method. Background Art

[0002] Traffic lights are an indispensable part of the traffic system. In the current traffic system, traffic lights are usually set in a fixed manner, that is, fixed traffic lights are set at intersections, relevant road information is calibrated in the traffic lights, and detection devices are installed on the traffic lights.

[0003] However, as more and more people choose to travel by car, traffic conditions are becoming more and more complicated. The fixed traffic lights used are gradually unable to meet the complex and changing traffic conditions. There is an urgent need for a traffic light that can be put into use flexibly and quickly. Summary of the invention

[0004] In order to meet the requirement that traffic lights can be put into use flexibly and quickly, the present application provides a self-calibrating intelligent traffic light and a self-calibrating intelligent traffic light control method.

[0005] In a first aspect, the present application provides a self-calibrating intelligent traffic light, which adopts the following technical solution:

[0006] A self-calibrating intelligent traffic light, comprising:

[0007] A lamp pole body and a mobile equipment cabin, wherein the lamp pole body is mounted on the mobile equipment cabin, a traffic light, a data acquisition mechanism and a communication device are mounted on the lamp pole body, a computing control system is arranged in the mobile equipment cabin, the data acquisition mechanism is electrically connected to the communication device and the computing control system, and the computing control system is electrically connected to the communication device and the traffic light.

[0008] By adopting the above technical solution, the mobile equipment cabin and the lamp pole body are combined to obtain a movable traffic light, and a data acquisition mechanism and a communication device are provided. When in use, it can be moved to any position as needed. At the same time, the data acquisition mechanism and the computing control system collect and control data, and automatically perform computing and processing according to the actual application environment, thereby realizing the demand that the traffic light can be put into use flexibly and quickly.

[0009] Optionally, the data acquisition mechanism includes a laser radar, a position and posture detection device, an image detection device and a millimeter wave radar, and the laser radar, the position and posture detection device, the image detection device and the millimeter wave radar are all installed on the top of the lamp pole body.

[0010] Optionally, the computing control system includes a computing unit and a controller, and the computing unit is electrically connected to the controller.

[0011] In a second aspect, the present application provides a self-calibration intelligent traffic light control method, which adopts the following technical solution:

[0012] A self-calibration intelligent traffic light control method is applied to a self-calibration intelligent traffic light, and the self-calibration intelligent traffic light control method comprises:

[0013] Obtain the initial pose information and surrounding environment information of the target mapping device;

[0014] Constructing an environment point cloud map based on the initial posture information and the surrounding environment information;

[0015] Introducing target traffic lights;

[0016] The target traffic light performs self-positioning based on the environmental point cloud map to generate traffic light self-positioning information.

[0017] By adopting the above technical solution, an environmental point cloud map is constructed according to the initial posture information of the mapping device and the surrounding environment information. When in use, the target traffic light is placed at the corresponding position and then the target traffic light performs self-positioning processing. It can quickly determine its position in the environmental point cloud map without manual adjustment. It can be flexibly positioned and used according to the actual use environment, thereby meeting the demand that traffic lights can be put into use flexibly and quickly.

[0018] Optionally, constructing an environment point cloud map based on the initial posture information and surrounding environment information includes:

[0019] Generate initial point cloud data based on the surrounding environment information;

[0020] Performing data preprocessing on the initial posture information to generate corrected posture information;

[0021] Acquiring the motion state of the target mapping device;

[0022] Perform point cloud estimation processing based on the motion state, the corrected posture information and the initial point cloud data to generate an estimated point cloud map;

[0023] The estimated point cloud map is optimized to generate an environment point cloud map.

[0024] Optionally, performing point cloud estimation processing based on the corrected posture information and the initial point cloud data to generate an estimated point cloud map includes:

[0025] estimating the displacement information of the target mapping device based on the initial point cloud data and a preset registration algorithm;

[0026] Generate a mileage estimation result based on the corrected posture information and the displacement information;

[0027] Generate predicted posture information based on a preset motion model and the corrected position information;

[0028] Performing state correction on the predicted pose information based on the initial point cloud data and a preset filter to generate an accurate predicted pose;

[0029] The initial point cloud data, the precise predicted position and the mileage estimation result of each frame are aligned to generate an estimated point cloud map.

[0030] Optionally, the self-positioning the target traffic light based on the environmental point cloud map to generate traffic light self-positioning information includes:

[0031] Acquire the positioning information and traffic light point cloud data of the target traffic light;

[0032] Registering the traffic light point cloud data with the environment point cloud map to generate a registration result;

[0033] Traffic light self-positioning information is generated based on the registration result and the positioning information.

[0034] Optionally, registering the traffic light point cloud data with the environment point cloud map to generate a registration result includes:

[0035] Constructing a pose conversion matrix based on the traffic light point cloud data and the environment point cloud map;

[0036] The traffic light point cloud data and the environment point cloud map are registered based on the posture transformation matrix and the maximum likelihood estimation model to generate a registration result.

[0037] Optionally, after constructing the environment point cloud map based on the initial posture information and the surrounding environment information, the method further includes:

[0038] In response to a user's selection and marking operation, obtaining a selection area and an area identifier corresponding to the selection area;

[0039] Determine the area coordinates of the framed area based on the environmental point cloud map;

[0040] Get the area type of the selected area;

[0041] The framed area, the area identifier, the area coordinates and the area type are stored and marked on the environmental point cloud map.

[0042] Optionally, after the target traffic light is self-positioned based on the environmental point cloud map to generate traffic light self-positioning information, the method further includes:

[0043] Acquire the structural position relationship between the data acquisition mechanism and the lamp pole body;

[0044] Constructing a local coordinate system, wherein the local coordinate system includes a lamp pole main body coordinate system and a data acquisition mechanism coordinate system;

[0045] Constructing a transformation matrix between the light pole main body coordinate system and the data acquisition mechanism;

[0046] The device self-positioning information of the data acquisition mechanism is determined based on the transformation matrix.

[0047] In summary, the present application includes at least one of the following beneficial technical effects:

[0048] 1. Combine the mobile equipment cabin and the lamp pole body to obtain a movable traffic light, and set up a data collection mechanism and communication equipment. When in use, it can be moved to any position as needed. At the same time, the data collection mechanism and the computing control system collect and control data, and automatically perform computing and processing according to the actual application environment, so as to meet the needs of flexible and rapid use of traffic lights;

[0049] 2. Construct an environmental point cloud map based on the initial posture information of the mapping device and the surrounding environment information. When in use, place the target traffic light at the corresponding position and then perform self-positioning processing. It can quickly determine its position in the environmental point cloud map without manual adjustment. It can be flexibly positioned and used according to the actual use environment, thereby meeting the demand that traffic lights can be put into use flexibly and quickly. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 It is a structural schematic diagram of a self-calibrating intelligent traffic light provided in an embodiment of the present application.

[0051] Figure 2 This is a structural block diagram of a self-calibrated intelligent traffic light provided in an embodiment of the present application.

[0052] Figure 3 It is a flow chart of a method for self-calibration of intelligent traffic lights provided in an embodiment of the present application.

[0053] Explanation of the accompanying drawings: 1. Lamp pole body; 2. Mobile equipment cabin; 3. Traffic light; 4. Data acquisition mechanism; 41. Laser radar; 42. Position and posture detection device; 43. Image detection device; 44. Millimeter wave radar; 5. Communication equipment; 6. Computing control system; 61. Computing unit; 62. Controller. DETAILED DESCRIPTION

[0054] The present application is further described in detail below in conjunction with the accompanying drawings.

[0055] The present application embodiment discloses a self-calibrating intelligent traffic light. Figure 1 and Figure 2 The self-calibration intelligent traffic light mainly includes two main parts: a lamp pole body 1 and a mobile equipment cabin 2. The mobile equipment cabin 2 is a box body equipped with moving wheels. The box body is a rectangular box body such as a cube or a cuboid. The lamp pole body 1 is installed above the mobile equipment cabin 2. By pushing the mobile equipment cabin 2, the lamp pole body 1 is driven to move together, thereby realizing the switching of the use position of the self-calibration intelligent traffic light. A traffic light 3 for traffic prompts, as well as a data acquisition mechanism 4 and a communication device 5 are installed on the lamp pole body 1. The data acquisition mechanism 4 and the communication device 5 are both installed at the end of the lamp pole body 1 away from the ground. A computing control system 6 is arranged in the mobile equipment cabin 2. The data acquisition mechanism 4 is electrically connected to the communication device 5 and the computing control system 6. The computing control system 6 is electrically connected to the communication device 5 and the traffic light 3. The communication device 5 is specifically a roadside unit RSU, which is used to realize basic vehicle identity recognition and electronic deduction functions.

[0056] Reference Figure 1 The data acquisition mechanism 4 includes a laser radar 41 for constructing a point cloud map, a position and posture detection device 42 for determining a position and posture, an image detection device 43 for acquiring an environmental image, and a millimeter wave radar 44 for detecting objects and obstacles in the environment, wherein the position and posture detection device 42 is specifically a nine-axis gyroscope, and the image detection device 43 is specifically a camera.

[0057] Reference Figure 1 and Figure 2 The computing control system 6 is installed inside the mobile equipment cabin 2, and mainly includes a computing unit 61 and a controller 62. The computing unit 61 is mainly used to construct a point cloud map and realize self-calibration. The controller 62 is electrically connected to the computing unit 61. At the same time, the controller 62 is electrically connected to the laser radar 41, the position and posture detection device 42, the image detection device 43, the millimeter wave radar 44 and the communication device 5. The controller 62 transmits the data collected by the above devices to the computing unit 61, and the computing unit 61 performs calculation processing.

[0058] The embodiment of the present application provides a self-calibration intelligent traffic light control method, which can be executed by an electronic device, which can be a server or a terminal device, wherein the server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services. The terminal device can be a smart phone, a tablet computer, a desktop computer, etc., but is not limited thereto.

[0059] Figure 1 A schematic flow chart of a self-calibration intelligent traffic light control method provided in an embodiment of the present application.

[0060] like Figure 1 As shown, the main process of the method is described as follows (steps S101 to S104):

[0061] Step S101, obtaining initial pose information and surrounding environment information of the target mapping device.

[0062] In this embodiment, the target mapping device is also an intelligent traffic light with a self-calibration function. When creating an environment map, one traffic light can be used for creation and another traffic light can be used for creation.

[0063] Step S102: construct an environment point cloud map based on the initial posture information and the surrounding environment information.

[0064] For step S102, initial point cloud data is generated based on the surrounding environment information; the initial pose information is preprocessed to generate corrected pose information; the motion state of the target mapping device is obtained; point cloud estimation processing is performed based on the motion state, corrected pose information and initial point cloud data to generate an estimated point cloud map; the estimated point cloud map is optimized to generate an environmental point cloud map.

[0065] Furthermore, the displacement information of the target mapping device is estimated based on the initial point cloud data and a preset registration algorithm; the mileage estimation result is generated based on the corrected posture information and the displacement information; the predicted posture information is generated based on the preset motion model and the corrected position information; the predicted posture information is state-corrected based on the initial point cloud data and a preset filter to generate an accurate predicted posture; the initial point cloud data, the accurate predicted position and the mileage estimation result of each frame are registered to generate an estimated point cloud map.

[0066] The nine-axis gyroscope, i.e., the position and posture detection device, is used to obtain the initial posture information of the target mapping device, wherein the initial posture information includes acceleration, angular velocity, and magnetic field data, and provides the motion state of the target mapping device. The laser radar is used to scan the surrounding environment during the travel process to generate high-precision three-dimensional point cloud data, and the unit point cloud data is used as the initial point cloud data. It should be noted that the initial point cloud data here is not the point cloud data of a single position, but the point cloud data of the entire travel process, that is, the point cloud data of the entire travel environment.

[0067] The initial posture information collected by the position and posture detection device is filtered and calibrated to remove noise and errors to obtain accurate posture information, i.e., corrected posture information. The initial point cloud data collected by the lidar is synchronized and registered to ensure that the corrected posture information is aligned in time with the initial point cloud data.

[0068] Using the initial point cloud data of the LiDAR, the ICP (Iterative Closest Point) or NDT (Normal Distributions Transform) algorithm is used to perform point cloud registration to estimate the relative displacement and rotation of the target mapping device in each frame. The correction attitude information provided by the position and posture detection device is combined with the displacement information of the LiDAR to obtain a more accurate odometer estimation result.

[0069] After that, the preset motion model and the corrected position information are used for prediction to generate the predicted pose information, which is the position and pose of the target mapping device at the next moment. The predicted pose information is fused with the odometer estimation result, and the state is corrected using the Kalman filter (Kalman Filter) or the extended Kalman filter (EKF) to obtain the accurate predicted pose. The point cloud data of each frame is aligned with the result of the odometer estimation, and the accurate predicted pose of each frame is accumulated frame by frame to construct the estimated point cloud map. The estimated point cloud map is optimized using the graph optimization technology, and the accumulated error is corrected to obtain an accurate environmental map. Since the target mapping device is moving in real time, the LIO-SAM algorithm is running in real time. Every time a new frame of data is obtained, the above-mentioned odometer estimation, state prediction and correction, and map update will be performed. Through continuous iteration, the pose information and environmental map of the target mapping device are updated in real time until the final location is reached. The accurate environmental map finally obtained after stopping the movement is used as the environmental point cloud map.

[0070] Step S103, introducing the target traffic light.

[0071] In this embodiment, the target traffic light is a traffic light that is officially used. It can be the same as the target mapping device, or it can be a separate new traffic light that does not participate in the environmental point cloud map. The introduced target traffic light has the same functions and hardware facilities as the mapping device, that is, it has a lamp pole body, a mobile equipment cabin, a traffic light, a data acquisition mechanism and a communication device.

[0072] Step S104: The target traffic light performs self-positioning based on the environment point cloud map to generate traffic light self-positioning information.

[0073] For step S104, the positioning information of the target traffic light and the traffic light point cloud data are obtained; the traffic light point cloud data is registered with the environment point cloud map to generate a registration result; and the traffic light self-positioning information is generated based on the registration result and the positioning information.

[0074] Furthermore, a pose conversion matrix is ​​constructed based on the traffic light point cloud data and the environment point cloud map; the traffic light point cloud data and the environment point cloud map are registered based on the pose conversion matrix and the maximum likelihood estimation model to generate a registration result.

[0075] In positioning modeling, the core idea is to obtain the pose information of the light pole subject in the environmental point cloud map in real time, namely x, y, z, roll (roll angle), yaw (yaw angle), pitch (pitch angle). Since the pose information can be regarded as the translation and rotation of the target mapping equipment and target traffic, given the motion model, it is necessary to calculate the parameters to construct a 3x4 pose transformation matrix T. Therefore, the method adopted in this application is to solve the local optimal solution through MLE (Maximum Likelihood Estimation).

[0076] Since it is a local optimal solution, an initial value needs to be given so that the final result approaches the global optimal solution. In this application, the relatively rough positioning information provided by the roadside unit RSU or other additional devices with positioning functions are usually used to obtain positioning information. This positioning information is used as the starting point for searching, so as to calculate the posture of the main body of the lamp pole. The maximum likelihood estimation MLE (xi|θ) model, that is, the maximum probability of a given sample x under different model parameters θ. In the maximum likelihood estimation MLE model, xi has been given as the posture transformation matrix T. After the definition of xi is given, the definition of θ needs to be given. Since the point cloud data is compared, there are at least tens of thousands of n-dimensional data (n>=3) for each frame of the point cloud data. In order to ensure real-time performance without losing the characteristics of the data, the rasterization method is used to divide the space composed of the entire point cloud into a large number of grids. The attribute of each grid is the center of gravity of the point cloud in the grid, thereby completing the data distillation. In order to improve the practicality and applicability of the technical implementation, when calculating the probability density function, the Gaussian distribution method is used for calculation, which can effectively reduce the amount of calculation for registration. Since each grid has a probability density function, all probability density functions are multiplied to obtain the product of probability density functions, thereby obtaining the final maximum likelihood estimation MLE mathematical model. Solving the maximum likelihood estimation MLE model can obtain the pose transformation matrix T to be solved after maximum likelihood estimation. Therefore, by taking log on both sides, the optimization objective function can be quickly reduced to a power, which is convenient for obtaining first-order and second-order derivatives and solving them. In the process of numerical calculation, the Gauss-Newton method is used in this application to complete the least squares regression of the parameters. Through the above-mentioned calculation and processing, the traffic light point cloud data and the environmental point cloud map are aligned, so that the coordinates of each point cloud data in the traffic light point cloud data correspond to the coordinates of each point cloud data in the environmental point cloud map. For example, the coordinates of point cloud data A in the traffic light point cloud data are the same as the coordinates of point cloud data B in the environmental point cloud map. The pose of the traffic light in the environmental point cloud map is determined based on the alignment result and positioning information, and the pose is used as the self-positioning information of the traffic light.

[0077] In this embodiment, in response to the user's selection and calibration operation, the selected area and the area identifier corresponding to the selected area are obtained; the area coordinates of the selected area are determined based on the environmental point cloud map; the area type of the selected area is obtained; the selected area, area identifier, area coordinates and area type are stored and marked on the environmental point cloud map.

[0078] In order to provide autonomous driving vehicles with more complete route planning and other functions, a high-precision map is constructed based on the environmental point cloud map created above. The high-precision map includes road information such as lane lines, crosswalks, road signs, and the monitoring area information is entered, that is, the monitoring area information is marked on the high-precision map. The monitoring area can be a lane, a crosswalk, etc. When marking in the high-precision map, there is no need to measure and input intersection data in the actual environment. Manual selection in the map is required to achieve the marking process.

[0079] By using the box selection tool to select the area, using a graphical user interface (GUI) tool or program function, the user can use a mouse or touch screen to accurately select the location and boundaries of the monitoring area on the environmental point cloud map. When the user uses the box selection tool to select an area on the point cloud map, the regional coordinates of all the selected points are recorded, wherein the coordinate points of the box selection should be based on the map coordinate system to ensure the accuracy and consistency of the position. Assign an area identifier to each selected area. The area identifier is the area ID of the selected area. Each area identifier is unique and cannot be reused. When assigning area identifiers, it can be assigned by the user, randomly generated and assigned, or generated according to the area type of the selected area selected by the user. It needs to be set according to actual needs and is not specifically limited here. Among them, the area type includes lanes, sidewalks, intersections, etc. The user selects according to the preset area type list. The area identifier can be a single number, a single letter, or a combination of numbers and letters.

[0080] After selecting the area, determining the selected area and the area identifier and area type corresponding to the selected area, the above data is stored, and the information of each selected area is stored using a data structure or a database table. After storage, the stored information can also be added, deleted, modified, and queried. This can effectively support the perception and analysis tasks of specific areas and improve the application value and reliability of real-time monitoring and data analysis.

[0081] In this embodiment, the structural posture relationship between the data acquisition mechanism and the lamp pole body is obtained; a local coordinate system is constructed, wherein the local coordinate system includes the lamp pole body coordinate system and the data acquisition mechanism coordinate system; a transformation matrix between the lamp pole body coordinate system and the data acquisition mechanism is constructed; and the device self-positioning information of the data acquisition mechanism is determined based on the transformation matrix.

[0082] After the target traffic light completes self-positioning in the environmental point cloud map, the position and posture of the target traffic light are obtained. Based on the structural posture relationship between the laser radar, position and posture detection device, image detection device, millimeter-wave radar and the lamp pole body, the posture relationship of each device is converted using a transformation matrix, thereby realizing automatic calibration of the entire traffic light without the need to calibrate each device separately.

[0083] First, construct the initial transformation matrix and define the coordinate system. Each device defines a local coordinate system. The local coordinate system includes the light pole coordinate system and the data acquisition mechanism coordinate system, specifically the light pole coordinate system (Pole, P), the laser radar coordinate system (LIDAR, L), the millimeter wave radar coordinate system (Millimeter Wave Radar, MW), the position and posture detection device coordinate system (IMU, I), and the image detection device system (Camera, C). After determining the local coordinate system, calculate the transformation matrix. Based on the known geometric relationship between the light pole body and the data acquisition mechanism, calculate the initial transformation matrix. The transformation matrix T_PL from the light pole to the laser radar is: (T_{PL}=\begin{bmatrix}R_{PL}&t_{PL}\\0&1\end{bmatrix}), where R_PL is the rotation matrix, calculated by the angles θx, θy, θz, and t_PL is the translation vector (x, y, z). Similarly, the conversion matrices between other devices are calculated. The conversion matrix T_PMW from the lamp pole body to the millimeter wave radar is, T_{PMW}=\begin{bmatrix}R_{PMW}&t_{PMW}\\0&1\end{bmatrix}, the conversion matrix T_PI from the lamp pole body to the position and posture detection device is, T_{PI}=\begin{bmatrix}R_{PI}&t_{PI}\\0&1\end{bmatrix}, and the conversion matrix T_PC from the lamp pole body to the image detection device is, T_{PC}=\begin{bmatrix}R_{PC}&t_{PC}\\0&1\end{bmatrix}.

[0084] Then, the initial conversion matrix is ​​used to convert each device to each other. For example, the laser radar pose is converted to the pose of the lamp pole body, that is, the laser radar pose P_L is converted to the pose of the lamp pole P_P through the conversion matrix T_PL, P_{P} = T_{PL} * P_{L}. For example, the laser radar pose is converted to the millimeter wave radar pose: P_{MW} = T_{PMW} * P_{P}, etc.

[0085] The terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not expressly listed, or also includes elements inherent to such process, method, article, or apparatus.

[0086] The above description is only a preferred embodiment of the present application and an explanation of the technical principles used. Those skilled in the art should understand that the scope of application involved in the present application is not limited to the technical solution formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the aforementioned application concept. For example, the above features are replaced with (but not limited to) technical features with similar functions applied in the present application.

Claims

1. A self-calibrating intelligent traffic light, characterized in that: include: A lamp pole body (1) and a mobile equipment compartment (2), wherein the lamp pole body (1) is mounted on the mobile equipment compartment (2), a traffic light (3), a data acquisition mechanism (4) and a communication device (5) are mounted on the lamp pole body (1), a computing control system (6) is arranged in the mobile equipment compartment (2), the data acquisition mechanism (4) is electrically connected to the communication device (5) and the computing control system (6), and the computing control system (6) is electrically connected to the communication device (5) and the traffic light (3).

2. The self-calibrating intelligent traffic light according to claim 1, characterized in that: The data acquisition mechanism (4) comprises a laser radar (41), a position and posture detection device (42), an image detection device (43) and a millimeter wave radar (44); the laser radar (41), the position and posture detection device (42), the image detection device (43) and the millimeter wave radar (44) are all installed on the top of the lamp pole body (1).

3. The self-calibrating intelligent traffic light according to claim 1, characterized in that: The computing control system (6) comprises a computing unit (61) and a controller (62), wherein the computing unit (61) is electrically connected to the controller (62).

4. A self-calibration intelligent traffic light control method, characterized in that: Applied to a self-calibration intelligent traffic light, the self-calibration intelligent traffic light control method comprises: Obtain the initial pose information and surrounding environment information of the target mapping device; Constructing an environment point cloud map based on the initial posture information and the surrounding environment information; Introducing target traffic lights; The target traffic light performs self-positioning based on the environmental point cloud map to generate traffic light self-positioning information.

5. The method according to claim 4, characterized in that The constructing of the environment point cloud map based on the initial posture information and the surrounding environment information comprises: Generate initial point cloud data based on the surrounding environment information; Performing data preprocessing on the initial posture information to generate corrected posture information; Acquiring the motion state of the target mapping device; Perform point cloud estimation processing based on the motion state, the corrected posture information and the initial point cloud data to generate an estimated point cloud map; The estimated point cloud map is optimized to generate an environment point cloud map.

6. The method according to claim 5, characterized in that The performing point cloud estimation processing based on the corrected posture information and the initial point cloud data to generate an estimated point cloud map comprises: estimating the displacement information of the target mapping device based on the initial point cloud data and a preset registration algorithm; Generate a mileage estimation result based on the corrected posture information and the displacement information; Generate predicted posture information based on a preset motion model and the corrected position information; Performing state correction on the predicted pose information based on the initial point cloud data and a preset filter to generate an accurate predicted pose; The initial point cloud data, the precise predicted position and the mileage estimation result of each frame are aligned to generate an estimated point cloud map.

7. The method according to claim 4, characterized in that The self-positioning of the target traffic light based on the environmental point cloud map to generate traffic light self-positioning information includes: Acquire the positioning information and traffic light point cloud data of the target traffic light; Registering the traffic light point cloud data with the environment point cloud map to generate a registration result; Traffic light self-positioning information is generated based on the registration result and the positioning information.

8. The method according to claim 7, characterized in that The registering the traffic light point cloud data with the environment point cloud map to generate a registration result includes: Constructing a pose conversion matrix based on the traffic light point cloud data and the environment point cloud map; The traffic light point cloud data and the environment point cloud map are registered based on the posture transformation matrix and the maximum likelihood estimation model to generate a registration result.

9. The method according to claim 4, characterized in that After constructing the environment point cloud map based on the initial posture information and the surrounding environment information, the method further includes: In response to a user's selection and marking operation, obtaining a selection area and an area identifier corresponding to the selection area; Determine the area coordinates of the framed area based on the environmental point cloud map; Get the area type of the selected area; The framed area, the area identifier, the area coordinates and the area type are stored and marked on the environmental point cloud map.

10. The method according to claim 4, characterized in that After the target traffic light is self-positioned based on the environmental point cloud map to generate traffic light self-positioning information, the method further includes: Acquire the structural position relationship between the data acquisition mechanism and the lamp pole body; Constructing a local coordinate system, wherein the local coordinate system includes a lamp pole main body coordinate system and a data acquisition mechanism coordinate system; Constructing a transformation matrix between the light pole main body coordinate system and the data acquisition mechanism; The device self-positioning information of the data acquisition mechanism is determined based on the transformation matrix.

Images