CN119207142B - Self-calibration intelligent traffic light and self-calibration intelligent traffic light control method - Google Patents
Self-calibration intelligent traffic light and self-calibration intelligent traffic light control methodInfo
- Publication number
- CN119207142B CN119207142B CN202411241628.0A CN202411241628A CN119207142B CN 119207142 B CN119207142 B CN 119207142B CN 202411241628 A CN202411241628 A CN 202411241628A CN 119207142 B CN119207142 B CN 119207142B
- Authority
- CN
- China
- Prior art keywords
- point cloud
- traffic light
- information
- self
- pose
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/09—Arrangements for giving variable traffic instructions
- G08G1/095—Traffic lights
- G08G1/0955—Traffic lights transportable
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/07—Controlling traffic signals
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Traffic Control Systems (AREA)
Abstract
本发明涉及一种自标定智能交通灯和自标定智能交通灯控制方法，应用于智能交通技术领域，自标定智能交通灯包括：灯杆主体和移动设备舱，所述灯杆主体安装在所述移动设备舱上，所述灯杆主体上安装有红绿灯、数据采集机构和通信设备，所述移动设备舱内设置有计算控制系统，所述数据采集机构与所述通信设备和所述计算控制系统电连接，所述计算控制系统与所述通信设备和所述红绿灯电连接。本申请具有实现交通信号灯能够灵活且快速投入使用的效果。
The present invention relates to a self-calibrating intelligent traffic light and a self-calibrating intelligent traffic light control method, which are applied to the field of intelligent traffic technology. The self-calibrating intelligent traffic light comprises: a light pole body and a mobile equipment compartment, the light pole body being mounted on the mobile equipment compartment, a traffic light, a data acquisition mechanism, and a communication device being mounted on the light pole body, a computing control system being provided within the mobile equipment compartment, the data acquisition mechanism being electrically connected to the communication device and the computing control system, and the computing control system being electrically connected to the communication device and the traffic light. This application has the effect of enabling traffic lights to be put into use flexibly and quickly.
Description
Technical Field
The application relates to the technical field of intelligent traffic, in particular to a self-calibration intelligent traffic light and a self-calibration intelligent traffic light control method.
Background
Traffic signals are an indispensable part of a traffic system, and in the current traffic system, the traffic signals are generally arranged in a fixed mode, namely, fixed traffic signals are arranged at intersections, relevant road information is calibrated in the traffic signals, and detection devices are installed on the traffic signals.
However, as more people select automobiles to travel, traffic conditions become more and more complex, the used fixed traffic signal lamps cannot meet the traffic conditions with complex changes, and a traffic signal lamp capable of being flexibly and rapidly put into use is needed.
Disclosure of Invention
In order to meet the requirement that the traffic signal lamp can be flexibly and rapidly put into use, the application provides a self-calibration intelligent traffic lamp and a self-calibration intelligent traffic lamp control method.
In a first aspect, the application provides a self-calibrating intelligent traffic light, which adopts the following technical scheme:
a self-calibrating intelligent traffic light comprising:
The intelligent traffic light comprises a lamp post main body and a mobile equipment cabin, wherein the lamp post main body is installed on the mobile equipment cabin, a traffic light, a data acquisition mechanism and communication equipment are installed on the lamp post main body, a calculation control system is arranged in the mobile equipment cabin, the data acquisition mechanism is electrically connected with the communication equipment and the calculation control system, and the calculation control system is electrically connected with the communication equipment and the traffic light.
Through adopting above-mentioned technical scheme, combine mobile device cabin and lamp pole main part, obtain mobilizable traffic light to be provided with data acquisition mechanism and communication equipment, can remove to any position as required when using, simultaneously, data acquisition mechanism and calculation control system carry out the collection and the control of data, carry out calculation processing according to actual application environment is automatic, thereby realize the demand that traffic signal lamp can nimble and put into use fast.
Optionally, the data acquisition mechanism includes laser radar, position appearance detection device, image detection device and millimeter wave radar, laser radar position appearance detection device image detection device with millimeter wave radar all installs the top of lamp pole main part.
Optionally, the computing control system includes a computing unit and a controller, and the computing unit is electrically connected with the controller.
In a second aspect, the application provides a self-calibration intelligent traffic light control method, which adopts the following technical scheme:
the self-calibration intelligent traffic light control method is applied to the self-calibration intelligent traffic light, and comprises the following steps:
acquiring initial pose information and surrounding environment information of target mapping equipment;
constructing an environment point cloud map based on the initial pose information and the surrounding environment information;
Introducing a target traffic light;
And the target traffic light performs self-positioning based on the environment point cloud map to generate traffic light self-positioning information.
By adopting the technical scheme, the environment point cloud map is constructed according to the initial pose information and the surrounding environment information of the mapping equipment, and when the environment point cloud map is used, the target traffic lamp is placed at the corresponding position and then is subjected to self-positioning treatment, so that the position of the environment point cloud map can be quickly determined, manual regulation and control are not needed, the environment point cloud map can be flexibly and quickly positioned and used according to the actual use environment, and the requirements that the traffic signal lamp can be flexibly and quickly put into use are met.
Optionally, the constructing the environment point cloud map based on the initial pose information and the surrounding environment information includes:
generating initial point cloud data based on the surrounding environment information;
performing data preprocessing on the initial pose information to generate corrected pose information;
acquiring the motion state of the target mapping equipment;
Performing point cloud prediction processing based on the motion state, the correction pose information and the initial point cloud data to generate a predicted point cloud map;
and optimizing the estimated point cloud map to generate an environment point cloud map.
Optionally, the performing the point cloud prediction processing based on the correction pose information and the initial point cloud data, and generating the predicted point cloud map includes:
Estimating displacement information of the target mapping equipment based on the initial point cloud data and a preset registration algorithm;
generating a mileage estimation result based on the correction pose information and the displacement information;
generating predicted pose 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;
Registering the initial point cloud data, the accurate prediction position and the mileage estimation result of each frame to generate an estimated point cloud map.
Optionally, the self-positioning the target traffic light based on the environment point cloud map, and generating the traffic light self-positioning information includes:
Acquiring positioning information of the target traffic light and traffic light point cloud data;
Registering the traffic light point cloud data with the environment point cloud map to generate a registration result;
and generating traffic light self-positioning information based on the registration result and the positioning information.
Optionally, the registering the traffic light point cloud data with the environment point cloud map, and generating a registration result includes:
constructing a pose conversion matrix based on the traffic light point cloud data and the environment point cloud map;
And registering the traffic light point cloud data and the environment point cloud map based on the pose conversion matrix and the maximum likelihood estimation model to generate a registration result.
Optionally, after the building of the environment point cloud map based on the initial pose information and the surrounding environment information, the method further includes:
responding to a frame selection calibration operation of a user, and acquiring a frame selection region and a region identifier corresponding to the frame selection region;
determining the region coordinates of the frame selection region based on the environment point cloud map;
acquiring the region type of the frame selection region;
and storing the frame selection region, the region identifier, the region coordinates and the region type, and marking on the environment point cloud map.
Optionally, after the self-positioning is performed on the target traffic light based on the environment point cloud map and the traffic light self-positioning information is generated, the method further includes:
Acquiring a structural pose relationship between the data acquisition mechanism and the lamp post main body;
Constructing a local coordinate system, wherein the local coordinate system comprises a lamp post main body coordinate system and a data acquisition mechanism coordinate system;
Constructing a conversion matrix between the lamp post main body coordinate system and the data acquisition mechanism;
and determining the equipment self-positioning information of the data acquisition mechanism based on the conversion matrix.
In summary, the present application includes at least one of the following beneficial technical effects:
1. The mobile equipment cabin is combined with the lamp post main body to obtain a movable traffic lamp, the movable traffic lamp is provided with a data acquisition mechanism and communication equipment, the movable traffic lamp can be moved to any position according to the needs when in use, meanwhile, the data acquisition mechanism and the calculation control system acquire and control data, and the calculation processing is automatically carried out according to the actual application environment, so that the requirements that the traffic lamp can be flexibly and quickly put into use are met;
2. The environment point cloud map is constructed according to the initial pose information and the surrounding environment information of the map construction equipment, when the map construction equipment is used, the target traffic light is placed at the corresponding position, then the target traffic light is subjected to self-positioning processing, the position of the target traffic light in the environment point cloud map can be rapidly determined, manual regulation and control are not needed, and the target traffic light can be rapidly positioned and used according to the actual use environment, so that the traffic signal lamp can be flexibly and rapidly put into use.
Drawings
Fig. 1 is a schematic structural diagram of a self-calibration intelligent traffic light according to an embodiment of the present application.
Fig. 2 is a block diagram of a self-calibration intelligent traffic light according to an embodiment of the present application.
Fig. 3 is a schematic flow chart of a method for self-calibrating intelligent traffic lights according to an embodiment of the present application.
The reference numerals indicate that 1, a lamp post main body, 2, a mobile equipment cabin, 3, a traffic light, 4, a data acquisition mechanism, 41, a laser radar, 42, a position and pose detection device, 43, an image detection device, 44, a millimeter wave radar, 5, communication equipment, 6, a calculation control system, 61, a calculation unit and 62, and a controller.
Detailed Description
The present application will be described in further detail with reference to the accompanying drawings.
The embodiment of the application discloses a self-calibration intelligent traffic light. Referring to fig. 1 and 2, the self-calibration intelligent traffic light mainly comprises a light pole main body 1 and a mobile equipment cabin 2, wherein the mobile equipment cabin 2 is a box body provided with mobile wheels, the box body is a rectangular box body such as a cube or a cuboid, the light pole main body 1 is arranged above the mobile equipment cabin 2, and the light pole main body 1 is driven to move together by pushing the mobile equipment cabin 2, so that the use position of the self-calibration intelligent traffic light is switched. The traffic light 3 for traffic prompt is installed on the lamp post main body 1, and the data acquisition mechanism 4 and the communication equipment 5, the data acquisition mechanism 4 and the communication equipment 5 are all installed in the one end of the lamp post main body 1 far away from ground, the mobile equipment cabin 2 is internally provided with the calculation control system 6, the data acquisition mechanism 4 is electrically connected with the communication equipment 5 and the calculation control system 6, the calculation control system 6 is electrically connected with the communication equipment 5 and the traffic light 3, wherein the communication equipment 5 is specifically a road side unit RSU, and is used for realizing functions such as basic vehicle identity recognition and electronic deduction.
Referring to fig. 1, the data acquisition mechanism 4 includes a laser radar 41 for constructing a point cloud map, a position and orientation detection device 42 for determining a position and orientation, an image detection device 43 for acquiring an image of an environment, and a millimeter wave radar 44 for detecting objects and obstacles in the environment, wherein the position and orientation detection device 42 is specifically a nine-axis gyroscope, and the image detection device 43 is specifically a camera.
Referring to fig. 1 and 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, where the computing unit 61 is mainly used to construct a point cloud map and implement self-calibration, the controller 62 is electrically connected with the computing unit 61, and simultaneously, the controller 62 is electrically connected with the laser radar 41, the position and pose detection device 42, the image detection device 43, the millimeter wave radar 44, and the communication device 5, and the controller 62 transmits data acquired by the above devices to the computing unit 61, and the computing unit 61 performs computing processing.
The embodiment of the application provides a self-calibration intelligent traffic light control method which can be executed by electronic equipment, wherein the electronic equipment can be a server or terminal equipment, the server can be an independent physical server, a server cluster or a distributed system formed by a plurality of physical servers, and a cloud server for providing cloud computing service. The terminal device may be, but is not limited to, a smart phone, a tablet computer, a desktop computer, etc.
Fig. 1 is a schematic flow chart of a self-calibration intelligent traffic light control method according to an embodiment of the present application.
As shown in FIG. 1, the main flow of the method is described as follows (steps S101-S104):
Step S101, initial pose information and surrounding environment information of target mapping equipment are obtained.
In this embodiment, the target map building device is also an intelligent traffic light with a self-calibration function, and when the environment map is created, one traffic light can be used for creation, and another traffic light can be used for creation.
Step S102, an environment point cloud map is constructed based on the initial pose information and the surrounding environment information.
Aiming at step S102, initial point cloud data is generated based on surrounding environment information, initial pose information is subjected to data preprocessing to generate corrected pose information, the motion state of target mapping equipment is obtained, point cloud pre-estimation processing is performed based on the motion state, the corrected pose information and the initial point cloud data to generate a pre-estimated point cloud map, and the pre-estimated point cloud map is subjected to optimization processing to generate an environment point cloud map.
Further, the displacement information of the target mapping equipment is estimated based on the initial point cloud data and a preset registration algorithm, a mileage estimation result is generated based on the correction pose information and the displacement information, predicted pose information is generated based on the preset motion model and the correction position information, state correction is carried out on the predicted pose information based on the initial point cloud data and a preset filter to generate an accurate predicted pose, and registration is carried out on the initial point cloud data, the accurate predicted position and the mileage estimation result of each frame to generate an estimated point cloud map.
The initial pose information of the target mapping equipment is acquired through a nine-axis gyroscope, namely a position pose detection device, wherein the initial pose information comprises acceleration, angular velocity, magnetic field data and the like, and the motion state of the target mapping equipment is provided. And scanning the surrounding environment in the advancing process by using a laser radar to generate high-precision three-dimensional point cloud data, and taking the unit point cloud data as initial point cloud data. It should be noted that, the initial point cloud data herein is not point cloud data of a single location, but point cloud data in the whole traveling process, that is, point cloud data including a whole traveling environment.
The initial pose information acquired by the pose detection device is filtered and calibrated, noise and errors are removed, accurate pose information is obtained, namely, the pose information is corrected, initial point cloud data acquired by the laser radar are synchronized and registered, and the corrected pose information is ensured to be aligned with the initial point cloud data in time.
And (3) carrying out point cloud registration by utilizing initial point cloud data of the laser radar through ICP (Iterative Closest Point) or NDT (Normal Distributions Transform) algorithm, and estimating relative displacement and rotation of the target mapping equipment in each frame. And combining the correction gesture information provided by the position and gesture detection device with the displacement information of the laser radar to obtain a more accurate odometer estimation result.
And then, predicting by using the preset motion model and the correction position information to generate predicted position information, wherein the predicted position information is the position and the posture of the target mapping equipment at the next moment. And fusing the predicted pose information with an odometer estimation result, and performing state correction by using a Kalman filter (KALMAN FILTER) or an Extended Kalman Filter (EKF) to obtain an accurate predicted pose. Registering the point cloud data of each frame through the result of the odometer estimation, accumulating the accurate predicted pose of each frame by frame, thus constructing a predicted point cloud map, optimizing the predicted point cloud map by using a graph optimization technology, correcting accumulated errors, obtaining an accurate environment map, and taking the accurate environment map finally obtained after stopping moving as the environment point cloud map by continuously iterating, updating the pose information of the target map building equipment in real time after the target map building equipment moves in real time, so that the LIO-SAM algorithm runs in real time and carries out the odometer estimation, the state prediction and the correction once every time new data of each frame is obtained.
Step S103, introducing a target traffic light.
In this embodiment, the target traffic light is a traffic light for formal use, which may be the same as the target mapping device, or may be a separate new traffic light that does not participate in the environment point cloud map, and the introduced target traffic light has the same functions and hardware facilities as the mapping device, that is, the traffic light includes a light pole main body, a mobile device cabin, a traffic light, a data acquisition mechanism and a communication device.
And step S104, the target traffic light performs self-positioning based on the environment point cloud map, and traffic light self-positioning information is generated.
Aiming at step S104, positioning information and traffic light point cloud data of a target traffic light are acquired, the traffic light point cloud data and an environment point cloud map are registered to generate a registration result, and traffic light self-positioning information is generated based on the registration result and the positioning information.
Further, a pose conversion matrix is built based on the traffic light point cloud data and the environment point cloud map, and registration is carried out on the traffic light point cloud data and the environment point cloud map based on the pose conversion matrix and the maximum likelihood estimation model, so that a registration result is generated.
In positioning modeling, the core thought is to acquire pose information of a lamp post theme in an environment point cloud map in real time, namely x, y, z, roll (roll angle), yaw (yaw angle) and pitch (pitch angle). Because pose information can be regarded as translational and rotational movement of the target mapping equipment and the target traffic, under the condition of a given movement model, parameters need to be calculated so as to construct a pose conversion matrix T of 3x4, and the method adopted in the application is to carry out local optimal solution through MLE (Maximum Likelihood Estimation ).
Because of the locally optimal solution, an initial value needs to be given to enable the final result to approach to the globally optimal solution, in the application, rough positioning information provided by a road side unit RSU or other additional devices with positioning functions are generally used to obtain positioning information, and the positioning information is used as a starting point for searching, so that the pose of the lamp post main body is calculated. In the maximum likelihood estimation MLE (xi|θ) model, that is, the maximum probability that a given sample x appears under different model parameters θ, xi is given to be set as a pose conversion matrix T, definition of θ is also required after definition of xi is given, since point cloud data is compared, at least one hundred thousand n data (n > =3) are provided for each frame of the point cloud data, and in order to ensure real-time performance without losing the characteristics of the data, a rasterization method is adopted to divide the space formed by the whole point cloud into a large number of grids, and the attribute of each grid is the gravity center of the point cloud in the grid, thereby completing data distillation. In order to improve the practicality and applicability of technical implementation, when the probability density function is calculated, a Gaussian distribution mode is adopted for calculation, so that the calculated amount of registration can be effectively reduced. Because each grid is provided with a probability density function, all probability density functions are subjected to cumulative multiplication to obtain probability density function products, so that a final maximum likelihood estimation MLE mathematical model is obtained, and the pose conversion matrix T to be solved after maximum likelihood estimation can be obtained by solving the maximum likelihood estimation MLE model. Therefore, the optimal objective function can be obtained by fast exponentiation through the mode of taking logs from two sides, and the first-order second-order derivative can be conveniently obtained and solved. In the process of numerical calculation, the least square regression of the completion parameters is taken by adopting a Gauss Newton method. Through the calculation processing, the traffic light point cloud data and the environment point cloud map are registered, 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 environment point cloud map, for example, the coordinates of the point cloud data A in the traffic light point cloud data are the same as the coordinates of the point cloud data B in the environment point cloud map, the pose of the traffic light in the environment point cloud map is determined according to the registration result and the positioning information, and the pose is used as the traffic light self-positioning information.
In the embodiment, a frame selection area and an area identification corresponding to the frame selection area are obtained in response to frame selection calibration operation of a user, area coordinates of the frame selection area are determined based on an environment point cloud map, area types of the frame selection area are obtained, and the frame selection area, the area identification, the area coordinates and the area types are stored and marked on the environment point cloud map.
In order to provide more perfect route planning and other functions for the automatic driving vehicle, a high-precision map is constructed according to the created environment point cloud map, the high-precision map comprises road information such as lane lines, crosswalk, road marks and the like, and monitoring area information is recorded, namely, the monitoring area information is marked on the high-precision map, the monitoring area can be a lane, a crosswalk and the like, and the marking processing can be realized only by manually selecting the map without measuring and inputting intersection data in the actual environment when the monitoring area is marked in the high-precision map.
The method comprises the steps that through the frame selection tool, region frame selection is carried out, a Graphical User Interface (GUI) tool or a program function is used, a user accurately frames the position and the boundary of a monitored region on an environment point cloud map by using a mouse or a touch screen, and when the user selects the region on the point cloud map by using the frame selection tool, region coordinates of all frame selection points are recorded, wherein the frame selection coordinate points are based on a map coordinate system, and the accuracy and the consistency of the position are ensured. The area identifier is allocated to each frame selection area, namely, the area ID of the frame selection area, and each area identifier is unique and not reusable, and when the area identifier is allocated, the area identifier can be allocated by a user, can be randomly generated and allocated, can be generated according to the area type of the frame selection area selected by the user, and needs to be set according to actual requirements, and is not particularly limited. The region type comprises lanes, sidewalks, intersections and the like, a user selects according to a preset region type list, and the region identifier can be a single number, a single letter or a combination of the number and the letter.
After the area selection is performed, the area identification and the area type corresponding to the frame selection area and the frame selection area are determined, the data are stored, the information of each frame selection area is stored by using a data structure or a database table, and after the storage, the stored information can be subjected to addition, deletion and modification. Therefore, the sensing and analyzing tasks of the specific area can be effectively supported, and the application value and reliability of real-time monitoring and data analysis are improved.
In the embodiment, the structural pose relation between the data acquisition mechanism and the lamp post main body is obtained, a local coordinate system is built, wherein the local coordinate system comprises the lamp post main body coordinate system and the data acquisition mechanism coordinate system, a conversion matrix between the lamp post main body coordinate system and the data acquisition mechanism is built, and the equipment self-positioning information of the data acquisition mechanism is determined based on the conversion matrix.
After the self-positioning of the target traffic light in the environment point cloud map is completed, the position and the gesture of the target traffic light are obtained, and the pose relation of each device is converted by using a conversion matrix based on the structural pose relation among the laser radar, the position and gesture detection device, the image detection device, the millimeter wave radar and the lamp post main body, so that the automatic calibration of the whole traffic light is realized, and the independent calibration of each device is not required.
First, an initial transformation matrix is constructed, a coordinate system is defined, and each device defines a local coordinate system. The local coordinate system comprises a lamp post coordinate system and a data acquisition mechanism coordinate system, specifically a lamp post coordinate system (hole, P), a laser radar coordinate system (LIDAR, L), a millimeter wave radar coordinate system (MILLIMETER WAVE RADAR, MW), a position and pose detection device coordinate system (IMU, I) and an image detection device system (Camera, C), after the local coordinate system is determined, a conversion matrix is calculated, and an initial conversion matrix is calculated based on a known geometric relationship between the lamp post main body and the data acquisition mechanism. The conversion matrix T_PL from the lamp post to the laser radar is (T_ { PL = \begin { bmatrix } R_ { PL } & t_ { PL } \0&1\end { bmatrix }), wherein R_PL is a rotation matrix calculated by angles θx, θy, θz, and t_PL is a translation vector (x, y, z). Similarly, a conversion matrix T_PMW between the lamp post body and the millimeter wave radar is calculated, wherein T_PMW is T_beta { bmatrix } R_PMW & t_PMW } \0& 1_end { bmatrix }, a conversion matrix T_PI from the lamp post body to the position and orientation detection device is T_PI = \beta { bmatrix } R_PI } t_pi _ { PI _, 0& 1_end { bmatrix }, and a conversion matrix T_PC from the lamp post body to the image detection device is T_PC = \ bmatrix } R_PC & t_PC } 0&1 } end batrix.
Each device is then converted to each other using an initial conversion matrix, for example, the pose of the lidar is converted to the pose of the lamp post body, i.e., the pose p_l of the lidar is converted to the pose p_p of the lamp post by the conversion matrix t_pl, p_ { P } = t_ { PL }. For example, the laser radar pose is converted to the pose of millimeter wave radar, p_ { MW } = t_ { PMW }, p_ { P }, and the like.
The terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
The above description is only illustrative of the preferred embodiments of the present application and of the principles of the technology employed. It will be appreciated by persons skilled in the art that the scope of the application is not limited to the specific combinations of the features described above, but also covers other embodiments which may be formed by any combination of the features described above or their equivalents without departing from the spirit of the application. Such as the above-mentioned features and the technical features having similar functions (but not limited to) applied for in the present application are replaced with each other.
Claims (5)
1. The self-calibration intelligent traffic light control method is characterized by being applied to the self-calibration intelligent traffic light, and the self-calibration intelligent traffic light comprises the following steps:
The intelligent lamp comprises a lamp post main body (1) and a mobile equipment cabin (2), wherein the lamp post main body (1) is installed on the mobile equipment cabin (2), a traffic light (3), a data acquisition mechanism (4) and communication equipment (5) are installed on the lamp post main body (1), a calculation control system (6) is arranged in the mobile equipment cabin (2), the data acquisition mechanism (4) is electrically connected with the communication equipment (5) and the calculation control system (6), and the calculation control system (6) is electrically connected with the communication equipment (5) and the traffic light (3);
The data acquisition mechanism (4) comprises a laser radar (41), a position and pose detection device (42), an image detection device (43) and a millimeter wave radar (44), wherein the laser radar (41), the position and pose detection device (42), the image detection device (43) and the millimeter wave radar (44) are all arranged at the top of the lamp post main body (1);
the computing control system (6) comprises a computing unit (61) and a controller (62), wherein the computing unit (61) is electrically connected with the controller (62);
The self-calibration intelligent traffic light control method comprises the following steps:
acquiring initial pose information and surrounding environment information of target mapping equipment;
constructing an environment point cloud map based on the initial pose information and the surrounding environment information;
Introducing a target traffic light;
the target traffic light performs self-positioning based on the environment point cloud map to generate traffic light self-positioning information;
After the building of the environment point cloud map based on the initial pose information and the surrounding environment information, further comprising:
responding to a frame selection calibration operation of a user, and acquiring a frame selection region and a region identifier corresponding to the frame selection region;
determining the region coordinates of the frame selection region based on the environment point cloud map;
acquiring the region type of the frame selection region;
storing the frame selection region, the region identifier, the region coordinates and the region type, and marking on the environment point cloud map;
After the self-positioning is performed on the target traffic light based on the environment point cloud map and the traffic light self-positioning information is generated, the method further comprises the following steps:
Acquiring a structural pose relationship between the data acquisition mechanism and the lamp post main body;
Constructing a local coordinate system, wherein the local coordinate system comprises a lamp post main body coordinate system and a data acquisition mechanism coordinate system;
Constructing a conversion matrix between the lamp post main body coordinate system and the data acquisition mechanism;
and determining the equipment self-positioning information of the data acquisition mechanism based on the conversion matrix.
2. The method of claim 1, wherein the constructing an ambient point cloud map based on the initial pose information and ambient environment information comprises:
generating initial point cloud data based on the surrounding environment information;
performing data preprocessing on the initial pose information to generate corrected pose information;
acquiring the motion state of the target mapping equipment;
Performing point cloud prediction processing based on the motion state, the correction pose information and the initial point cloud data to generate a predicted point cloud map;
and optimizing the estimated point cloud map to generate an environment point cloud map.
3. The method of claim 2, wherein performing a point cloud prediction process based on the correction pose information and the initial point cloud data, generating a predicted point cloud map comprises:
Estimating displacement information of the target mapping equipment based on the initial point cloud data and a preset registration algorithm;
generating a mileage estimation result based on the correction pose information and the displacement information;
Generating predicted pose information based on a preset motion model and the corrected pose 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;
registering the initial point cloud data, the accurate predicted pose and the mileage predicted result of each frame to generate a predicted point cloud map.
4. The method of claim 1, wherein the self-locating the target traffic light based on the ambient point cloud map, generating traffic light self-locating information comprises:
Acquiring positioning information of the target traffic light and traffic light point cloud data;
Registering the traffic light point cloud data with the environment point cloud map to generate a registration result;
and generating traffic light self-positioning information based on the registration result and the positioning information.
5. The method of claim 4, wherein registering the traffic light point cloud data with the ambient point cloud map, generating a registration result comprises:
constructing a pose conversion matrix based on the traffic light point cloud data and the environment point cloud map;
And registering the traffic light point cloud data and the environment point cloud map based on the pose conversion matrix and the maximum likelihood estimation model to generate a registration result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411241628.0A CN119207142B (en) | 2024-09-05 | 2024-09-05 | Self-calibration intelligent traffic light and self-calibration intelligent traffic light control method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411241628.0A CN119207142B (en) | 2024-09-05 | 2024-09-05 | Self-calibration intelligent traffic light and self-calibration intelligent traffic light control method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN119207142A CN119207142A (en) | 2024-12-27 |
| CN119207142B true CN119207142B (en) | 2025-07-29 |
Family
ID=94076749
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202411241628.0A Active CN119207142B (en) | 2024-09-05 | 2024-09-05 | Self-calibration intelligent traffic light and self-calibration intelligent traffic light control method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN119207142B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107144285A (en) * | 2017-05-08 | 2017-09-08 | 深圳地平线机器人科技有限公司 | Posture information determines method, device and movable equipment |
| CN112802352A (en) * | 2020-12-31 | 2021-05-14 | 无锡太机脑智能科技有限公司 | Method and device for realizing intelligent mobile traffic signal lamp |
| CN113587941A (en) * | 2020-05-01 | 2021-11-02 | 华为技术有限公司 | High-precision map generation method, positioning method and device |
| CN113658441A (en) * | 2021-07-08 | 2021-11-16 | 江苏大学 | High-flexibility variable-view-angle roadside sensing device and beyond-the-horizon sensing method for automatic driving |
| CN115793669A (en) * | 2022-12-27 | 2023-03-14 | 浙江大学 | Interactive robot autonomous inspection device and method based on 5G communication |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11987271B2 (en) * | 2018-12-07 | 2024-05-21 | Sony Semiconductor Solutions Corporation | Information processing apparatus, information processing method, mobile-object control apparatus, and mobile object |
| CN114667437B (en) * | 2019-08-31 | 2025-12-19 | 辉达公司 | Map creation and positioning for autonomous driving applications |
| CN114063090B (en) * | 2020-07-29 | 2025-05-09 | 北京图森未来科技有限公司 | A method and device for positioning a movable device and a movable device |
| KR102442775B1 (en) * | 2021-12-10 | 2022-09-14 | (주) 경성테크놀러지 | Creation of maps for the transportation vulnerable and customized route guidance system |
| CN118135816A (en) * | 2024-03-05 | 2024-06-04 | 东风悦享科技有限公司 | A method, system and medium for dynamically adjusting the duration of traffic lights based on multiple sensors |
-
2024
- 2024-09-05 CN CN202411241628.0A patent/CN119207142B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107144285A (en) * | 2017-05-08 | 2017-09-08 | 深圳地平线机器人科技有限公司 | Posture information determines method, device and movable equipment |
| CN113587941A (en) * | 2020-05-01 | 2021-11-02 | 华为技术有限公司 | High-precision map generation method, positioning method and device |
| CN112802352A (en) * | 2020-12-31 | 2021-05-14 | 无锡太机脑智能科技有限公司 | Method and device for realizing intelligent mobile traffic signal lamp |
| CN113658441A (en) * | 2021-07-08 | 2021-11-16 | 江苏大学 | High-flexibility variable-view-angle roadside sensing device and beyond-the-horizon sensing method for automatic driving |
| CN115793669A (en) * | 2022-12-27 | 2023-03-14 | 浙江大学 | Interactive robot autonomous inspection device and method based on 5G communication |
Non-Patent Citations (1)
| Title |
|---|
| 多激光雷达在线标定与同步定位建图研究;顾恒之;《中国优秀硕士学位论文全文数据库（电子期刊）》;20240815;全文21-22页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN119207142A (en) | 2024-12-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP7204823B2 (en) | VEHICLE CONTROL METHOD, VEHICLE CONTROL DEVICE, AND VEHICLE | |
| CN108763287B (en) | Construction method of large-scale passable regional driving map and unmanned application method thereof | |
| CN110832279B (en) | Align data captured by autonomous vehicles to generate high-definition maps | |
| CN110609290B (en) | Lidar matching and positioning method and device | |
| KR20200121274A (en) | Method, apparatus, and computer readable storage medium for updating electronic map | |
| CN114114367B (en) | AGV outdoor positioning switching method, computer device and program product | |
| CN110386142A (en) | Pitch angle calibration method for automatic driving vehicle | |
| CN108981730A (en) | For generating the method and system of reference path for operation automatic driving vehicle | |
| KR20210116576A (en) | How to use a visual robot-based map of the past | |
| CN112184906B (en) | A method and device for constructing a three-dimensional model | |
| CN111982133B (en) | Method and device for positioning vehicle based on high-precision map and electronic equipment | |
| CN111402387A (en) | Removing short timepoints from a point cloud of a high definition map for navigating an autonomous vehicle | |
| CN113503883B (en) | Method for collecting data for constructing map, storage medium and electronic equipment | |
| CN111862215B (en) | A computer equipment positioning method, device, computer equipment and storage medium | |
| CN115390088A (en) | Point cloud map establishment method, lane marking data acquisition method, equipment and medium | |
| CN118999577A (en) | Pose estimation method, pose estimation device, robot and storage medium | |
| CN119339010A (en) | A method and system for generating high-definition maps based on point cloud and multi-objective optimization | |
| CN119207142B (en) | Self-calibration intelligent traffic light and self-calibration intelligent traffic light control method | |
| CN115345944A (en) | Method and device for determining external parameter calibration parameters, computer equipment and storage medium | |
| CN119445259A (en) | A high-definition map processing method and device based on mobile laser radar data | |
| CN116883504B (en) | Method and device for calibrating vehicle orientation, computer equipment and storage medium | |
| CN119180156A (en) | Mapping method, mapping device, computer equipment, storage medium and program product | |
| CN117518176A (en) | Laser positioning method and device and self-moving equipment | |
| CN109901589B (en) | Mobile robot control method and device | |
| CN121498661B (en) | Map generation method, electronic equipment and robot |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |