Automatic driving vehicle high-precision positioning system, method, medium and equipment

Abstract

The invention provides an automatic driving vehicle high-precision positioning system and method based on AOA and laser radar, a medium and equipment, and the method comprises the steps: S1, receiving a Bluetooth signal transmitted by a vehicle through an AOA module, and calculating the arrival angle of the signal; s2, combining the arrival angle and vehicle position information provided by a GPS module to obtain position prediction; s3, laser pulses are emitted through a laser radar module, reflected signals are received, and point cloud data of the surrounding environment are obtained; s4, comparing the point cloud data with a prior positioning map, determining the number of a grid where the vehicle is located, and obtaining a positioning result through online normal distribution transformation; and S5, based on the information provided by the GPS module and the inertia module, the calculation module optimizes the positioning result to obtain a precision positioning result. The method does not affect the positioning accuracy and stability even in an underground scene, improves the positioning precision, reduces the calculation resource demand, can adapt to a complex environment, and also reduces the dependence on the initial position.

Description

Technical Field

[0001] The present invention relates to the field of autonomous driving technology, and in particular to a high-precision positioning system, method, medium and equipment for an autonomous driving vehicle based on AOA and laser radar. Background Art

[0002] With the development of autonomous driving technology, high-precision positioning technology has become one of the key technologies. In underground scenarios, traditional satellite-based positioning methods cannot be used because GPS signals cannot be covered, so other positioning methods are needed. Among them, SLAM (Simultaneous Localization and Mapping) is a common positioning method that obtains environmental information through sensors such as cameras or lidars and estimates the position and posture of the vehicle. However, the SLAM method has problems such as changes in lighting conditions and feature point matching errors in underground scene applications, which affect the accuracy and stability of positioning.

[0003] In the prior art, one solution is to achieve repositioning through visual / laser feature matching. Although the matching feature point pairs are found by comparing the feature points of the current frame and the reference frame, and then the position change of the camera or lidar is calculated by triangulation to achieve positioning, underground scenes lack sufficient robustness due to the small number of feature points and large changes in lighting conditions, and the error rate of feature point matching is high.

[0004] In summary, existing high-precision positioning methods have many problems in underground scenes. First, the characteristics of underground scenes affect the accuracy and stability of positioning. Second, a large amount of computing resources are required, which is a challenge for the vehicle system. In addition, facing complex underground environments, such as multi-fork intersections and narrow passages, the positioning performance may decline. Finally, repositioning relies on a high-precision initial position, which is difficult to achieve in practical applications.

[0005] Therefore, it is an urgent task to study a high-precision positioning system, method, medium and equipment for autonomous driving vehicles based on AOA and lidar. Summary of the invention

[0006] In response to the defects in the prior art, the present invention aims to solve the technical problems existing in underground scenes, such as the high error rate of feature point matching due to the small number of feature points and large changes in lighting conditions, which in turn affects the positioning accuracy and stability; the technical problem of placing a burden on the on-board system; the technical problem of reduced positioning performance when facing complex underground environments; and the problem of relying on high-precision initial position which is difficult to achieve in practical applications.

[0007] According to the present invention, a high-precision positioning system for an autonomous driving vehicle based on AOA and laser radar includes: an AOA module, a laser radar module, a GPS module, an inertial module and a computing module;

[0008] The AOA module is used to receive the Bluetooth signal sent by the vehicle and send the calculated arrival angle to the calculation module. The AOA module includes multiple AOA devices, and the AOA devices are installed in the parking lot;

[0009] The laser radar module is used to obtain point cloud data of the surrounding environment and send the point cloud data to the computing module. The laser radar module is installed on the vehicle;

[0010] GPS module, which provides vehicle location information to the computing module when the vehicle can receive satellite signals. The GPS module is installed on the vehicle;

[0011] Inertial module, which provides vehicle motion status information to the computing module when the GPS signal is lost or interfered with. The inertial module is installed on the vehicle.

[0012] The computing module receives the arrival angle, vehicle position information, vehicle motion status information and point cloud data, matches the point cloud data with the prior positioning map, and provides vehicle positioning. The computing module is installed on the vehicle.

[0013] Preferably, the AOA module includes 3 AOA devices pre-installed in the parking lot.

[0014] Preferably, the model of the AOA device is Honeywell HMC5883L, the operating frequency is 2.4 GHz, and the angle measurement accuracy is ±1°.

[0015] Preferably, the model of the laser radar module is Velodyne HDL-64E, the scanning frequency is 5 Hz, and the ranging accuracy is ±2 cm.

[0016] Preferably, the model of the GPS module is u-blox M8N, and the positioning accuracy is ±1m.

[0017] Preferably, the model of the inertial module is Inertial Labs IMU-3200, and the positioning accuracy is ±0.1° / s.

[0018] Preferably, the computing module has a model of Intel Core i7-8700K, a memory of 16 GB, and a hard disk of 500 GB.

[0019] The present invention also provides a high-precision positioning method for an autonomous driving vehicle based on AOA and laser radar, and the method uses the above-mentioned high-precision positioning system for an autonomous driving vehicle based on AOA and laser radar, comprising the following steps:

[0020] S1, receives the Bluetooth signal sent by the vehicle through the AOA module and calculates the arrival angle of the signal;

[0021] S2, combining the arrival angle and the vehicle location information provided by the GPS module, and matching it with the prior positioning map to obtain the location prediction;

[0022] S3, emits laser pulses through the laser radar module and receives the reflected signals to obtain point cloud data of the surrounding environment;

[0023] S4, based on the position prediction, combines the point cloud data with the prior positioning map to determine the grid number where the vehicle is located, and obtains the positioning result through online normal distribution transformation;

[0024] S5, based on the information provided by the GPS module and the inertial module, the calculation module optimizes the positioning result to obtain an accurate positioning result.

[0025] The present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the above-mentioned high-precision positioning method for an autonomous driving vehicle based on AOA and lidar.

[0026] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the computer program is executed by the processor, the steps of the above-mentioned high-precision positioning method for an autonomous driving vehicle based on AOA and lidar are implemented.

[0027] Compared with the prior art, the present invention has the following beneficial effects:

[0028] 1. Improve positioning accuracy: The present invention realizes repositioning through AOA, and combines the prior positioning map with lidar positioning, which can achieve robustness while ensuring positioning accuracy, and effectively solves the problems of inaccurate and unstable positioning caused by feature point matching errors in the prior art.

[0029] 2. Reduce the demand for computing resources: The positioning method of the present invention is highly mature and low-cost. It only requires the pre-installation of several scattered AOA devices in the parking lot, or the use of existing Bluetooth beacons to achieve coarse-grained repositioning, which greatly reduces the demand for computing resources and is suitable for vehicle-mounted systems.

[0030] 3. Adaptability to complex environments: The positioning method of the present invention not only performs well in open underground scenes, but also has strong adaptability when facing complex underground environments, such as multi-fork intersections, narrow passages, etc., and the positioning performance will not decrease.

[0031] 4. Reduce dependence on initial position: The positioning method of the present invention does not need to rely on high-precision initial position when implementing repositioning, which is superior to the existing technology and makes its practical application more extensive. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Other features, objects and advantages of the present invention will become more apparent from the detailed description of non-limiting embodiments made with reference to the following drawings:

[0033] Figure 1 This is a flow chart of a high-precision positioning method for an autonomous driving vehicle based on AOA and laser radar in an embodiment of the present invention. DETAILED DESCRIPTION

[0034] The present invention is described in detail below in conjunction with specific embodiments. The following embodiments will help those skilled in the art to further understand the present invention, but are not intended to limit the present invention in any form. It should be noted that, for those of ordinary skill in the art, several changes and improvements can also be made without departing from the concept of the present invention. These all belong to the protection scope of the present invention.

[0035] The present invention adopts AOA (angle of arrival) positioning technology, and realizes coarse-grained relocation of vehicles by pre-installing several scattered AOA devices in the parking lot, or borrowing existing Bluetooth beacons. The advantage of this method is that even in underground scenes, there are fewer feature points and the lighting conditions vary greatly, it will not affect the accuracy and stability of positioning. Secondly, the present invention combines the prior positioning map with laser radar positioning. After completing the AOA relocation, the location information of the vehicle is matched with the prior positioning map to further improve the positioning accuracy. At the same time, combined with laser radar positioning, it can be achieved in complex underground environments, such as multi-fork intersections, narrow passages, etc., and high positioning performance can be maintained. Then, high-precision positioning is achieved by using online NDT: after determining the grid number where the vehicle is located, high-precision positioning is achieved by online NDT (Normal Distributions Transform). The advantage of this method is that it does not require a large amount of computing resources, which reduces the burden on the vehicle-mounted system. Finally, the present invention optimizes the algorithm to improve robustness. Through the above technical means, the technical solution can improve the robustness of positioning while ensuring positioning accuracy. This means that even in complex underground environments or when implementing repositioning, stable positioning can be achieved without relying on a high-precision initial position.

[0036] Embodiment 1:

[0037] This embodiment provides a high-precision positioning system for an autonomous driving vehicle based on AOA and laser radar, including: an AOA module, a laser radar module, a GPS module, an inertial module and a computing module.

[0038] The AOA module is used to receive the Bluetooth signal sent by the vehicle and send the calculated arrival angle to the calculation module to achieve coarse-grained relocation of the vehicle.

[0039] The AOA module includes multiple AOA devices, and the AOA devices are installed in the parking lot.

[0040] In this embodiment, three scattered AOA devices are pre-installed in the parking lot. The model of the AOA device is Honeywell HMC5883L, the operating frequency is 2.4 GHz, and the angle measurement accuracy is ±1°.

[0041] The LiDAR module emits laser pulses and receives reflected signals to obtain point cloud data of the surrounding environment for subsequent positioning and map matching. The LiDAR module sends the point cloud data to the computing module, which is installed on the vehicle.

[0042] The model of the lidar module is Velodyne HDL-64E, with a scanning frequency of 5Hz and a ranging accuracy of ±2cm.

[0043] The GPS module provides the computing module with approximate vehicle location information when the vehicle can receive satellite signals, which is used to assist the positioning of the AOA device and the LiDAR module. The GPS module is installed on the vehicle.

[0044] The model of the GPS module is u-blox M8N, and the positioning accuracy is ±1m.

[0045] The inertial module provides the computing module with vehicle motion status information when the GPS signal is lost or interfered with, which is used to assist the positioning of the AOA device and the LiDAR module. The inertial module is installed on the vehicle.

[0046] The model of the inertial module is Inertial Labs IMU-3200, and the positioning accuracy is ±0.1° / s.

[0047] The computing module receives the arrival angle, vehicle position information, vehicle motion status information and point cloud data, runs the positioning algorithm, matches the point cloud data with the prior positioning map, and provides the vehicle's positioning. The computing module is installed on the vehicle.

[0048] The computing module model is Intel Core i7-8700K, the memory is 16GB, and the hard disk is 500GB.

[0049] When the vehicle is driving, the AOA module of this system will continuously receive the Bluetooth signal sent by the vehicle, and realize the coarse-grained relocation of the vehicle by calculating the arrival angle of the signal. Then, the calculation module will match the vehicle location information with the prior positioning map to further improve the positioning accuracy. At the same time, the lidar module obtains the point cloud data of the surrounding environment by emitting laser pulses and receiving the reflected signals for subsequent positioning and map matching. After determining the grid number where the vehicle is located, the calculation module will achieve high-precision positioning through online normal distribution transformation (NDT).

[0050] Specifically, first, the AOA positioning device is used to determine the position P0 (x, y) of the vehicle in the local coordinate system. Then, in the constructed prior positioning map, P0 is used as the center position of the search, and all points containing location information within the rectangular area formed by the four points (x-20, y-20), (x+20, y+20), (x-20, y+20), and (x+20, y-20) are extracted from the map. Finally, the real-time lidar point cloud is matched online with the extracted map point cloud to ultimately determine the precise position of the vehicle.

[0051] The advantage of the above system is that it does not require a large amount of computing resources, which reduces the burden on the vehicle system. During the entire positioning process, the computing module will optimize the positioning results based on the information provided by the GPS module and the inertial module to improve the robustness of positioning. Even in the face of complex underground environments or when repositioning, it does not need to rely on high-precision initial positions and can achieve stable positioning results.

[0052] Embodiment 2:

[0053] Figure 1 This is a flow chart of a high-precision positioning method for an autonomous driving vehicle based on AOA and laser radar in an embodiment of the present invention.

[0054] like Figure 1 As shown, this embodiment provides a high-precision positioning method for an autonomous driving vehicle based on AOA and laser radar, and the high-precision positioning system for an autonomous driving vehicle based on AOA and laser radar of Example 1 is applied, including the following steps:

[0055] S1, receives the Bluetooth signal sent by the vehicle through the AOA module and calculates the arrival angle of the signal;

[0056] S2, combining the arrival angle and the vehicle location information provided by the GPS module, and matching it with the prior positioning map to obtain the location prediction;

[0057] S3, emits laser pulses through the laser radar module and receives the reflected signals to obtain point cloud data of the surrounding environment;

[0058] S4, based on the position prediction, combines the point cloud data with the prior positioning map for comparison, determines the grid number where the vehicle is located, and obtains the positioning result through online normal distribution transformation (NDT).

[0059] S5, based on the information provided by the GPS module and the inertial module, the calculation module optimizes the positioning result to obtain an accurate positioning result.

[0060] Embodiment 3:

[0061] This embodiment provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, the steps of the high-precision positioning method for an autonomous driving vehicle based on AOA and lidar in the above-mentioned embodiment 2 are implemented.

[0062] Embodiment 4:

[0063] This embodiment provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the computer program is executed by the processor, the steps of the high-precision positioning method for an autonomous driving vehicle based on AOA and lidar in the above-mentioned embodiment 2 are implemented.

[0064] Due to the advanced nature of this technical solution, it can be widely used in application fields such as self-driving cars, intelligent robots, mining, and underground facility management. First of all, for self-driving cars, high-precision positioning technology is one of its core technologies. The high-precision positioning method for self-driving vehicles based on AOA and lidar proposed in the present invention can improve the positioning accuracy and stability of self-driving cars in underground scenes, thereby improving its safety and reliability. Secondly, when intelligent robots operate in underground environments, they also need high-precision positioning technology, and the method of the present invention can meet this demand. Thirdly, fields such as mining and underground facility management often need to operate in underground environments, and the method of the present invention can provide an effective positioning solution. Finally, the method of the present invention is low-cost and easy to implement, so it has a broad market demand.

[0065] Those skilled in the art know that, in addition to realizing the system and its various devices, modules, and units provided by the present invention in a purely computer-readable program code, it is entirely possible to realize the same functions in the form of logic gates, switches, application-specific integrated circuits, programmable logic controllers, and embedded microcontrollers by logically programming the method steps. Therefore, the system and its various devices, modules, and units provided by the present invention can be considered as a hardware component, and the devices, modules, and units included therein for realizing various functions can also be regarded as structures within the hardware component; the devices, modules, and units for realizing various functions can also be regarded as both software modules for realizing the method and structures within the hardware component.

[0066] The above describes the specific embodiments of the present invention. It should be understood that the present invention is not limited to the above specific embodiments, and those skilled in the art can make various changes or modifications within the scope of the claims, which does not affect the essence of the present invention. In the absence of conflict, the embodiments of the present application and the features in the embodiments can be combined with each other arbitrarily.

Claims

1. A high-precision positioning system for autonomous driving vehicles based on AOA and laser radar, characterized in that: include: AOA module, LiDAR module, GPS module, inertial module and computing module; The AOA module is used to receive the Bluetooth signal sent by the vehicle and send the calculated arrival angle to the calculation module. The AOA module includes multiple AOA devices, and the AOA devices are installed in the parking lot; The laser radar module is used to obtain point cloud data of the surrounding environment and send the point cloud data to the computing module. The laser radar module is installed on the vehicle; The GPS module provides the computing module with vehicle location information when the vehicle is able to receive satellite signals, and the GPS module is installed on the vehicle; The inertial module provides the computing module with vehicle motion state information when the GPS signal is lost or interfered with, and the inertial module is installed on the vehicle; The computing module receives the arrival angle, the vehicle position information, the vehicle motion state information and the point cloud data, matches the point cloud data with the prior positioning map, and provides vehicle positioning. The computing module is installed on the vehicle.

2. The high-precision positioning system for autonomous driving vehicles based on AOA and laser radar according to claim 1, characterized in that: The AOA module includes three AOA devices pre-installed in the parking lot.

3. The high-precision positioning system for autonomous driving vehicles based on AOA and laser radar according to claim 2, characterized in that: The model of the AOA device is Honeywell HMC5883L, the operating frequency is 2.4 GHz, and the angle measurement accuracy is ±1°.

4. The high-precision positioning system for autonomous driving vehicles based on AOA and laser radar according to claim 1, characterized in that: The model of the laser radar module is Velodyne HDL-64E, the scanning frequency is 5Hz, and the ranging accuracy is ±2cm.

5. The high-precision positioning system for autonomous driving vehicles based on AOA and laser radar according to claim 1, characterized in that: The model of the GPS module is u-blox M8N, and the positioning accuracy is ±1m.

6. The high-precision positioning system for autonomous driving vehicles based on AOA and laser radar according to claim 1, characterized in that: The model of the inertial module is Inertial Labs IMU-3200, and the positioning accuracy is ±0.1° / s.

7. The high-precision positioning system for autonomous driving vehicles based on AOA and laser radar according to claim 1, characterized in that: The computing module has an Intel Core i7-8700K model, a 16GB memory, and a 500GB hard disk.

8. A high-precision positioning method for an autonomous driving vehicle based on AOA and laser radar, using the high-precision positioning system for an autonomous driving vehicle based on AOA and laser radar as claimed in any one of claims 1 to 7, characterized in that: The steps include: S1, receives the Bluetooth signal sent by the vehicle through the AOA module and calculates the arrival angle of the signal; S2, combining the arrival angle and the vehicle position information provided by the GPS module, and matching them with the prior positioning map to obtain a position prediction; S3, emits laser pulses through the laser radar module and receives the reflected signals to obtain point cloud data of the surrounding environment; S4, based on the position prediction, the point cloud data is compared with the prior positioning map to determine the grid number where the vehicle is located, and a positioning result is obtained through online normal distribution transformation; S5, based on the information provided by the GPS module and the inertial module, the calculation module optimizes the positioning result to obtain an accurate positioning result.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by the processor, the steps of the high-precision positioning method for an autonomous driving vehicle based on AOA and lidar as described in claim 8 are implemented.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the computer program is executed by the processor, the steps of the high-precision positioning method for an autonomous driving vehicle based on AOA and lidar as described in claim 8 are implemented.

Images