Absolute positioning method for target object on road based on multi-sensor fusion
By fusing RTK and radar data, high-precision absolute positioning of target objects in autonomous driving is achieved, solving the problems of high cost of high-precision maps and difficulty in real-time positioning in dynamic environments, and supporting subsequent data analysis and trajectory prediction.
Patent Information
- Application Number
- CN202511141054.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-08-15
- Publication Date
- 2025-10-31
AI Technical Summary
Existing autonomous driving perception solutions rely on high-precision maps, which are costly to build and maintain, and are difficult to achieve real-time global positioning of target objects in dynamic environments.
By fusing RTK and radar data, the vehicle's high-precision latitude, longitude, and heading angle are obtained using RTK. Combined with the relative position information from the radar, coordinate transformation is performed, ultimately converting the relative position of the target object to a global coordinate system to achieve high-precision absolute positioning.
It achieves high-precision acquisition of latitude, longitude, and absolute velocity of dynamic targets, supports subsequent data analysis and trajectory prediction, and solves the problems of high cost and difficulty in real-time updating of high-precision maps in existing technologies.
Smart Images
Figure FDA0005549580310000011 
Figure FDA0005549580310000021 
Figure FDA0005549580310000022
Abstract
Description
Technical Field
[0001] This invention belongs to the field of target precision measurement and positioning technology, specifically relating to an absolute positioning method for target objects on a road based on multi-sensor fusion. Background Technology
[0002] Millimeter-wave radar and lidar are widely used for target detection in autonomous driving, intelligent transportation, and environmental perception systems. However, these radars typically only provide relative position information (such as distance and angle) of the target, and cannot directly obtain its absolute position (latitude and longitude) in the Earth's coordinate system. RTK technology can provide vehicle positioning information with centimeter-level accuracy, but how to combine radar data with RTK data to achieve accurate global positioning of target objects remains a current technological challenge.
[0003] Existing autonomous driving perception solutions mainly rely on high-precision maps for target matching, but the construction and maintenance of high-precision maps are costly, and there are challenges in real-time updates in dynamic environments. Summary of the Invention
[0004] To overcome the shortcomings of existing technologies, this invention proposes an absolute positioning method for target objects on roads based on multi-sensor fusion. By fusing RTK and radar data, the relative position sensed by radar is transformed into a global coordinate system, thereby obtaining high-precision latitude, longitude and absolute speed of dynamic targets.
[0005] The technical solution adopted in this invention is as follows: A method for absolute positioning of target objects on a road based on multi-sensor fusion is provided, comprising the following steps: S1, Data Acquisition and Fusion: Real-time high-precision latitude and longitude coordinates and heading angle of the vehicle are acquired via RTK, while the relative position and speed of the target are acquired via radar. RTK and radar data are fused to obtain the fixed offset of the radar relative to the RTK antenna and the high-precision position of the target in the radar coordinate system; S2, Coordinate Transformation and Absolute Target Positioning: First, the position of the target in the radar coordinate system is transformed to the vehicle coordinate system. Then, the position of the target in the vehicle coordinate system is transformed to the global coordinate system through rotation transformation. Then, based on the latitude and longitude of RTK, the planar coordinates of the target are converted to absolute geographic coordinates, finally obtaining the high-precision latitude and longitude of the dynamic target; S3, Absolute Coordinate Transformation of Target Speed; S4, Data Storage and Periodic Updates: After the absolute coordinate information and speed calculation of the target are completed, the data is stored in a database, and batch storage is performed every 3-10 minutes to support subsequent data analysis and trajectory prediction.
[0006] Preferably, in step S2, the position of the target in the radar coordinate system is transformed to the vehicle coordinate system, and the transformation formula is as follows: Where: x veh ,y vehd represents the target's coordinates in the vehicle's coordinate system; d represents the target distance measured by the radar; α represents the target's azimuth angle relative to the radar; Δx and Δy represent the fixed offsets of the radar relative to the RTK antenna.
[0007] Preferably, the rotation transformation in step S2 converts the target's position in the vehicle coordinate system to the global coordinate system, and the transformation formula is as follows: Where: x global ,y global It is the target's position in the global coordinate system after the transformation from the vehicle's coordinate system; θ RTK The vehicle heading angle obtained by RTK indicates the vehicle's current orientation.
[0008] Preferably, in step S2, the planar coordinates of the target are converted into absolute geographic coordinates based on RTK latitude and longitude, and the calculation formula for the latitude and longitude change is as follows: Where: R is the Earth's radius; cos(lat) RTK It corrects the effect of latitude variation on longitude distance.
[0009] Preferably, step S3, which calculates the absolute velocity of the target, requires a coordinate transformation, the transformation formula of which is as follows: Where: V x rel V y rel V is the relative velocity of the target as measured by radar. x ego V y ego V is the vehicle speed measured by RTK. x abs V y abs That is, the velocity of the target in the global coordinate system.
[0010] Preferably, after the absolute coordinate information and velocity calculation of the target are completed in step S4, the data is stored in the database and batch stored every 5 minutes to support subsequent data analysis and trajectory prediction.
[0011] The beneficial effects of this invention are as follows:
[0012] This invention integrates RTK, millimeter-wave radar, and lidar data to obtain high-precision absolute target positioning. Based on the RTK heading angle, it performs a rotation transformation to convert the radar-sensed relative position to a global coordinate system. Furthermore, through centimeter-level precision calculations using RTK, it obtains the high-precision latitude, longitude, and absolute velocity of the dynamic target. Finally, it periodically stores the target's latitude, longitude, and absolute velocity into a database to support subsequent analysis, mapping, and trajectory prediction, enabling real-time updates of the target's position in a dynamic environment. Detailed Implementation
[0013] Unless otherwise defined, the technical or scientific terms used in this patent document shall have the ordinary meaning understood by one of ordinary skill in the art to which this invention pertains. The terms "first," "second," and similar terms used in this patent specification and claims do not indicate any order, quantity, or importance, but are merely used to distinguish different components. Similarly, the terms "an," "a," or "the" do not indicate a quantity limitation, but rather indicate the presence of at least one. The terms "comprising" or "including" indicate that the element or object preceding "comprising" encompasses the element or object listed following "comprising" or its equivalents, and do not exclude other elements or objects. Terms such as "center," "upper," "lower," "left," "right," "vertical," "horizontal," "inner," and "outer" are used only to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly. These terms are only for the convenience of describing the invention and for simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the invention.
[0014] Some embodiments of the present invention will be described in detail below. Unless otherwise specified, features in the following embodiments can be combined with each other.
[0015] Specifically, a method for absolute localization of target objects on a road based on multi-sensor fusion is provided, including the following steps:
[0016] S1, Data Acquisition and Fusion: Real-time high-precision latitude and longitude coordinates and heading angle of the vehicle are obtained through RTK, and the relative position and speed of the target are obtained through radar. The RTK and radar data are fused to obtain the fixed offset of the radar relative to the RTK antenna and the high-precision position of the target in the radar coordinate system.
[0017] S2, Coordinate Transformation and Absolute Target Positioning: First, the target's position in the radar coordinate system is transformed to the vehicle's coordinate system. The transformation formula is as follows: Where: x veh ,y veh d represents the target's coordinates in the vehicle's coordinate system; d represents the target distance measured by the radar; α represents the target's azimuth angle relative to the radar; Δx and Δy represent the fixed offsets of the radar relative to the RTK antenna.
[0018] Next, the target's position in the vehicle coordinate system is transformed to the global coordinate system through rotation transformation. The transformation formula is as follows: Where: x global ,y globalIt is the target's position in the global coordinate system after the transformation from the vehicle's coordinate system; θ RTK The vehicle's heading angle, obtained from RTK, indicates the vehicle's current orientation.
[0019] Then, based on RTK latitude and longitude, the target's planar coordinates are converted into absolute geographic coordinates. The formula for calculating the latitude and longitude changes is as follows: Where: R is the Earth's radius; cos(lat) RTK The effect of latitude variation on longitude distance has been corrected.
[0020] Finally, the high-precision latitude and longitude of the dynamic target are obtained;
[0021] S3, Absolute coordinate transformation of the target velocity: The transformation formula is as follows: Where: V x rel V y rel V is the relative velocity of the target as measured by radar. x ego V y ego V is the vehicle speed measured by RTK. x abs V y abs That is, the velocity of the target in the global coordinate system;
[0022] S4, Data Storage and Regular Updates: After the target's absolute coordinates and velocity are calculated, the data is stored in the database and batch-stored every 3-10 minutes to support subsequent data analysis and trajectory prediction.
[0023] Furthermore, after the absolute coordinate information and velocity calculation of the target are completed in step S4, the data is stored in the database and batch stored every 5 minutes to support subsequent data analysis and trajectory prediction.
[0024] The method of sequentially storing data in batches every 5 minutes can better and more accurately support subsequent data analysis and trajectory prediction.
[0025] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the invention can be implemented in other specific forms without departing from its spirit or basic characteristics. Therefore, the embodiments should be considered exemplary and non-limiting in all respects. The scope of the invention is defined by the appended claims rather than the foregoing and description, and thus all variations falling within the meaning and scope of equivalents of the claims are intended to be included within the present invention.
Claims
1. A method for absolute localization of target objects on a road based on multi-sensor fusion, characterized in that: Includes the following steps: S1, Data Acquisition and Fusion: Real-time high-precision latitude and longitude coordinates and heading angle of the vehicle are obtained through RTK, and the relative position and speed of the target are obtained through radar. The RTK and radar data are fused to obtain the fixed offset of the radar relative to the RTK antenna and the high-precision position of the target in the radar coordinate system. S2, Coordinate Transformation and Absolute Target Positioning: First, the target's position in the radar coordinate system is transformed to the vehicle coordinate system. Then, the target's position in the vehicle coordinate system is transformed to the global coordinate system through rotation transformation. Finally, the target's planar coordinates are transformed into absolute geographic coordinates based on the latitude and longitude of RTK, and the high-precision latitude and longitude of the dynamic target are obtained. S3, absolute coordinate transformation of the target velocity; S4, Data Storage and Regular Updates: After the target's absolute coordinates and velocity are calculated, the data is stored in the database and batch-stored every 3-10 minutes to support subsequent data analysis and trajectory prediction.
2. The absolute positioning method for target objects on a road based on multi-sensor fusion according to claim 1, characterized in that: In step S2, the target's position in the radar coordinate system is transformed to the vehicle coordinate system using the following formula: Where: x veh ,y veh The coordinates of the target in the vehicle's coordinate system; d is the target distance measured by the radar, and α is the target's azimuth angle relative to the radar; Δx and Δy are the fixed offsets of the radar relative to the RTK antenna.
3. The absolute positioning method for target objects on a road based on multi-sensor fusion according to claim 1, characterized in that: The rotation transformation in step S2 converts the target's position in the vehicle coordinate system to the global coordinate system. The transformation formula is as follows: Where: x global ,y global It is the target's position in the global coordinate system after the vehicle's coordinate system has been transformed; θ RTK The vehicle heading angle obtained by RTK indicates the vehicle's current orientation.
4. The absolute positioning method for target objects on a road based on multi-sensor fusion according to claim 1, characterized in that: In step S2, the planar coordinates of the target are converted into absolute geographic coordinates based on RTK latitude and longitude. The formula for calculating the latitude and longitude changes is as follows: Where: R is the Earth's radius; cos(lat RTK It corrects the effect of latitude variation on longitude distance.
5. The absolute positioning method for target objects on a road based on multi-sensor fusion according to claim 1, characterized in that: Step S3, which calculates the target's absolute velocity, requires a coordinate transformation, the formula of which is as follows: Where: V x rel V y rel The relative velocity of the target as measured by radar; V x ego V y ego The vehicle speed measured by RTK; V x abs V y abs That is, the velocity of the target in the global coordinate system.
6. The absolute positioning method for target objects on a road based on multi-sensor fusion according to claim 5, characterized in that: After the absolute coordinates and velocity of the target are calculated in step S4, the data is stored in the database and batch stored every 5 minutes to support subsequent data analysis and trajectory prediction.