A vehicle positioning system, method and medium

Abstract

The application discloses a kind of vehicle positioning system, method and medium.Therein, the system includes combined inertial navigation equipment, for determining the combined inertial navigation data of target vehicle, and combined inertial navigation data is sent to industrial computer;Wheel speed sensor, for determining the wheel speed information of target vehicle, and wheel speed information is sent to industrial computer;Laser radar, for determining original laser radar point cloud, and original laser radar point cloud is sent to industrial computer;Industrial computer, for determining laser point cloud feature map, according to each original laser radar point cloud and laser point cloud feature map determines first positioning information, and, according to combined inertial navigation data and wheel speed information determines the second positioning information of target vehicle, based on first positioning information and second positioning information determines the target positioning of target vehicle at current time instant. By executing the present scheme, the robustness and stability of high-precision positioning during vehicle driving can be effectively improved.

Description

Technical Field

[0001] This invention relates to the field of vehicle positioning technology, and in particular to a vehicle positioning system, method and medium. Background Technology

[0002] Autonomous driving technology can reduce accident rates and improve vehicle safety. Vehicle positioning technology is the foundation for accurate environmental perception and a key core technology for realizing autonomous driving. Especially in high-level autonomous driving urban scenarios, where lanes are complex, positioning accuracy needs to reach the centimeter level.

[0003] The vehicle positioning solutions in related technologies use a limited range of data types when determining vehicle location, and consider the factors affecting vehicle positioning in a one-sided manner. They cannot meet the needs of complex application scenarios, nor can they fully and flexibly leverage the advantages of various types of data, resulting in unsatisfactory high-definition vehicle positioning results. Summary of the Invention

[0004] This invention provides a vehicle positioning system, method, and medium that can effectively improve the robustness and stability of high-precision positioning during vehicle operation.

[0005] According to one aspect of the present invention, a vehicle positioning system is provided, the system comprising an industrial control computer, a combined inertial navigation system, a wheel speed sensor, and at least one lidar; wherein:

[0006] The industrial control computer is connected to the combined inertial navigation device, the wheel speed sensor, and each of the lidars, respectively.

[0007] The combined inertial navigation device is used to determine the combined inertial navigation data of the target vehicle and send the combined inertial navigation data to the industrial control computer; the combined inertial navigation data includes angular velocity information and acceleration information;

[0008] The wheel speed sensor is used to determine the wheel speed information of the target vehicle and send the wheel speed information to the industrial control computer;

[0009] The lidar is used to determine the original lidar point cloud and send the original lidar point cloud to the industrial control computer;

[0010] The industrial control computer is used to determine the laser point cloud feature map, determine the first positioning information based on the original laser radar point clouds and the laser point cloud feature map, and determine the second positioning information of the target vehicle based on the combined inertial navigation data and the wheel speed information, and determine the target positioning of the target vehicle at the current time based on the first positioning information and the second positioning information.

[0011] According to another aspect of the present invention, a vehicle positioning method is provided, the method comprising:

[0012] The combined inertial navigation data of the target vehicle is determined by the combined inertial navigation equipment, and the combined inertial navigation data is sent to the industrial control computer; the combined inertial navigation data includes angular velocity information and acceleration information;

[0013] The wheel speed information of the target vehicle is determined by the wheel speed sensor, and the wheel speed information is sent to the industrial control computer.

[0014] The original lidar point cloud is determined by lidar and then sent to the industrial control computer.

[0015] The industrial control computer determines the laser point cloud feature map, determines the first positioning information based on the original lidar point clouds and the laser point cloud feature map, and determines the second positioning information of the target vehicle based on the combined inertial navigation data and the wheel speed information. Based on the first positioning information and the second positioning information, the target positioning of the target vehicle at the current moment is determined.

[0016] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the vehicle positioning method according to any embodiment of the present invention.

[0017] The technical solution of this invention includes an industrial control computer, a combined inertial navigation system (INS), wheel speed sensors, and at least one lidar. The INS is connected to the INS, wheel speed sensors, and lidars. The INS determines the combined INS data of the target vehicle and sends it to the INS. The combined INS data includes angular velocity and acceleration information. The wheel speed sensors determine the wheel speed information of the target vehicle and send it to the INS. The lidars determine the original lidar point cloud and send it to the INS. The INS determines a feature map of the lidar point cloud, determines first positioning information based on the original lidar point clouds and the feature map, and determines second positioning information of the target vehicle based on the combined INS data and wheel speed information. Based on the first and second positioning information, the INS determines the target positioning of the target vehicle at the current moment. By implementing the solution provided in this invention, the robustness and stability of high-precision positioning during vehicle operation can be effectively improved.

[0018] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1a This is a schematic diagram of a vehicle positioning system structure provided in an embodiment of the present invention;

[0021] Figure 1b This is a flowchart of motion compensation for lidar point clouds provided in an embodiment of the present invention;

[0022] Figure 1c This is a flowchart provided by an embodiment of the present invention for determining the vehicle's pose using surrounding environment image information and visual map data;

[0023] Figure 1d This is a flowchart of the process of comprehensively processing various positioning information to obtain target positioning, provided by an embodiment of the present invention;

[0024] Figure 1e This is a schematic diagram illustrating the time synchronization settings for each device provided in an embodiment of the present invention;

[0025] Figure 2 This is a flowchart of a vehicle positioning method provided in an embodiment of the present invention;

[0026] Figure 3 This is a schematic diagram of the structure of an electronic device that implements the vehicle positioning method of this invention. Detailed Implementation

[0027] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0028] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0029] Figure 1a This is a schematic diagram of the vehicle positioning system structure provided in an embodiment of the present invention. Figure 1a As shown, the system includes: an industrial control computer 11, a combined inertial navigation system 12, a wheel speed sensor 13, and at least one lidar 14; wherein:

[0030] The industrial control computer 11 is connected to the combined inertial navigation equipment 12, the wheel speed sensor 13, and each lidar 14.

[0031] The integrated inertial navigation device 12 is used to determine the integrated inertial navigation data of the target vehicle and send the integrated inertial navigation data to the industrial control computer 11; the integrated inertial navigation data includes angular velocity information and acceleration information.

[0032] Wheel speed sensor 13 is used to determine the wheel speed information of the target vehicle and send the wheel speed information to the industrial control computer 11;

[0033] LiDAR 14 is used to determine the original LiDAR point cloud and send the original LiDAR point cloud to the industrial control computer 11;

[0034] The industrial control computer 11 is used to determine the laser point cloud feature map, determine the first positioning information based on the original laser radar point clouds and the laser point cloud feature map, and determine the second positioning information of the target vehicle based on the combined inertial navigation data and the wheel speed information, and determine the target positioning of the target vehicle at the current time based on the first positioning information and the second positioning information.

[0035] The target vehicle is the vehicle whose location is to be determined. The integrated inertial navigation system 12 can be an inertial measurement unit (IMU), including a gyroscope and an accelerometer. The gyroscope determines the vehicle's angular velocity, and the accelerometer determines its acceleration. There can be four lidar sensors 14, deployed at the front, rear, left, and right sides of the vehicle's roof. Wheel speed sensors 13 can be wheel speed meters, determining the vehicle's wheel speed. The laser point cloud feature map consists of multiple grid regions of a preset size, including the mean and covariance of each grid region, which can be pre-processed using the SLAM algorithm on each original lidar point cloud. This solution uses an industrial control computer 11 to determine the target vehicle's pose (first positioning information) using the original lidar point clouds and the laser point cloud feature map during the target vehicle's movement. It then determines the target vehicle's pose (second positioning information) using integrated inertial navigation data and wheel speed information. Finally, based on the first and second positioning information, the target vehicle's final pose at the current moment is determined, i.e., target localization. For example, based on the asynchronous nature of the acquisition frequency of the combined inertial navigation device 12, the acquisition frequency of the wheel speed sensor 13, and the acquisition frequency of the lidar 14, the first positioning information or the second positioning information can be used as the target positioning of the target vehicle at the current moment in real time.

[0036] The technical solution of this invention includes an industrial control computer, a combined inertial navigation system (INS), wheel speed sensors, and at least one lidar. The INS is connected to the INS, wheel speed sensors, and lidars. The INS determines the combined INS data of the target vehicle and sends it to the INS. The combined INS data includes angular velocity and acceleration information. The wheel speed sensors determine the wheel speed information of the target vehicle and send it to the INS. The lidars determine the original lidar point cloud and send it to the INS. The INS determines a feature map of the lidar point cloud, determines first positioning information based on the original lidar point clouds and the feature map, and determines second positioning information of the target vehicle based on the combined INS data and wheel speed information. Based on the first and second positioning information, the INS determines the target positioning of the target vehicle at the current moment. By implementing the solution provided in this invention, the robustness and stability of high-precision positioning during vehicle operation can be effectively improved.

[0037] In this embodiment, optionally, the industrial control computer 11 is specifically used to perform motion compensation on the original lidar point cloud based on the lidar's acquisition frequency, angular velocity information, and rotational speed information to obtain the target lidar point cloud; and to determine the first positioning information based on each of the target lidar point clouds and the lidar point cloud feature map.

[0038] One issue is that vehicle movement can cause distortion in the lidar sensor. For example... Figure 1bAs shown, this solution uses the industrial control computer 11 to provide translational compensation via wheel speed measurement and rotational compensation via IMU gyroscope, thus determining the relative motion value of the lidar within one radar cycle. For example, assuming the radar scanning cycle is 100ms, the integration start time is the start time of the cycle, and the integration end time is the end time of the cycle. Specifically, this solution transforms the original lidar point clouds acquired by the left, right, and rear lidars to the coordinate system of the front lidar, and transforms each original lidar point cloud in the front lidar coordinate system to the IMU coordinate system. Then, it integrates the gyroscope angular velocity within one radar cycle to obtain the rotational compensation of the original lidar point cloud in the IMU coordinate system. The lidar point cloud in the IMU coordinate system after rotational compensation is transformed to the vehicle coordinate system, and the wheel speed information within one radar cycle is integrated to obtain the translational compensation of the lidar point cloud in the vehicle coordinate system after rotational compensation, thus obtaining the target lidar point cloud. Then, based on each target lidar point cloud and the lidar point cloud feature map, the first positioning information of the target vehicle is determined. It can provide a reliable data source for high-precision vehicle positioning.

[0039] In this embodiment, optionally, the industrial control computer 11 is specifically used to determine ground points and non-ground points based on the point clouds of each target lidar; the vertical coordinate of the ground point is less than a preset value;

[0040] Determine planar points from the non-ground points;

[0041] The first positioning information is determined based on each of the ground points, each of the planar points, and the laser point cloud feature map.

[0042] The preset values ​​can be set according to actual needs. This solution uses an industrial control computer 11 to determine ground points and non-ground points in the target LiDAR point cloud based on the vertical coordinates of each radar point and the preset values. For example, radar points with vertical coordinates less than the preset value are considered ground points, and radar points with vertical coordinates greater than or equal to the preset value are considered non-ground points. Then, planar points are further filtered from the non-ground points, and the first positioning information is determined based on the ground points, planar points, and the LiDAR point cloud feature map. This provides a reliable data source for high-precision vehicle positioning.

[0043] In this embodiment, optionally, the industrial control computer 11 is specifically used to determine the adjacent radar points of each non-ground point based on the target lidar point cloud.

[0044] The target curvature of the non-ground point is determined based on each of the adjacent radar points and the non-ground point;

[0045] Non-ground points with a target curvature less than a preset curvature threshold are designated as plane points.

[0046] The preset curvature threshold can be set as needed. For the non-ground points identified in the preceding steps, this solution can determine multiple (at least four) adjacent radar points from the target LiDAR point cloud. Then, based on the non-ground point and its adjacent radar points, the curvature of the non-ground point, i.e., the target curvature, is determined. If the target curvature is less than the preset curvature threshold, it indicates that the non-ground point is not a corner point but a planar point. This provides a reliable data source for high-precision vehicle positioning.

[0047] In one feasible implementation, optionally, the industrial control computer 11 is specifically used to determine the candidate numbers of each of the ground points and the plane points;

[0048] At least one first spatial grid region is determined based on the laser point cloud feature map;

[0049] For each first spatial grid region, at least one second spatial grid region is determined;

[0050] For each second spatial grid region, determine the average size information of the second spatial grid region; the size information includes longitude, latitude, and altitude;

[0051] The grid number of the second spatial grid region is determined based on the average size information;

[0052] The radar points associated with the candidate numbers that match the grid numbers are used as the target radar points.

[0053] The first positioning information is determined based on each of the target radar points.

[0054] This scheme can determine the number of each radar point in the target lidar point cloud. For example, by dividing the longitude, latitude, and altitude of the radar point by a certain value, such as 10000, the x1, y1, and z1 values ​​of the radar point are obtained respectively. Then, based on the first spatial grid ID algorithm:

[0055] The ID = (z×300+y)×300+x is applied to x1, y1, and z1 to obtain the radar point's ID. This allows for the determination of ground points and planar points within the radar point, i.e., candidate IDs. The first spatial grid region can be a large grid region in the laser point cloud feature map. The size of the large grid region can be set according to actual needs, for example, 300m in length, width, and height. The second spatial grid region can be a small grid region within the first spatial grid region. The size of the small grid region can be set according to actual needs, for example, 30cm in length, width, and height. The second spatial grid region contains multiple points in the laser point cloud feature map. Each point's location corresponds to longitude, latitude, and altitude. This scheme can determine the average longitude, average latitude, and average altitude of each point in the second spatial grid region. Then, the average longitude, average latitude, and average altitude are divided by a certain value, such as 10000, to obtain x2, y2, and z2. Finally, x2, y2, and z2 are processed based on the first spatial grid ID algorithm to obtain the grid number of the second spatial grid region. Understandably, since radar point locations are associated one-to-one with candidate numbers, and the locations of the second spatial grid regions are associated one-to-one with grid numbers, if a grid number matches a candidate number, it means the radar point location matches the location of the second spatial grid region. Therefore, this scheme can use radar points associated with candidate numbers that match grid numbers as target radar points for vehicle localization, i.e., determining the initial localization information of the target vehicle. Determining the radar points for vehicle localization using a laser point cloud feature map provides a reliable data source for high-precision vehicle localization.

[0056] In another feasible implementation, optionally, the system further includes an image acquisition device and a satellite positioning device, wherein the image acquisition device and the satellite positioning device are respectively connected to the industrial control computer 11;

[0057] The image acquisition device is used to determine the surrounding environment image information of the target vehicle and send the surrounding environment image information to the industrial control computer 11;

[0058] The satellite positioning device is used to determine the third positioning information of the target vehicle and send the third positioning information to the industrial control computer 11;

[0059] The industrial control computer 11 is also used to determine the visual map data at the current moment, determine the fourth positioning information of the target vehicle based on the visual map data and the surrounding environment image information, and determine the target positioning of the target vehicle at the current moment based on the first positioning information, the second positioning information, the third positioning information and the fourth positioning information.

[0060] The image acquisition device can be a camera or webcam, the satellite positioning device can be GNSS, and the visual map data is an offline or online high-definition map. This solution can use an industrial control computer 11 to determine the fourth positioning information of the target vehicle based on the visual map data and surrounding environmental image information. For example... Figure 1c As shown, this scheme can transform the surrounding environment image information from the camera coordinate system to the map coordinate system. It obtains the predicted pose of the current frame by combining the optimized vehicle pose from the previous frame with the pre-integration result. Based on the predicted pose of the current frame, it acquires high-precision map vector element information such as lane lines and poles through a visual map data interface. It obtains visual semantic perception results of lane lines and poles around the current vehicle using the surrounding environment image information, completes the matching and association of the surrounding environment image information and visual map data based on nearest neighbors, and estimates the vehicle pose through nonlinear optimization to obtain the fourth localization information.

[0061] In another feasible implementation, optionally, the industrial control computer 11 is specifically used to process the first positioning information, the second positioning information, the third positioning information and the fourth positioning information based on the error state Kalman filter algorithm to obtain the target positioning of the target vehicle at the current time.

[0062] Among them, such as Figure 1d As shown, after obtaining the positioning information, this scheme can convert the positioning information to the vehicle coordinate system. The Error State Kalman Filter (ESKF) algorithm can be used to process the positioning information and perform multi-sensor fusion positioning to obtain the most accurate positioning information of the target vehicle at the current moment, i.e., target positioning.

[0063] A single sensor cannot meet the needs of complex application scenarios. GNSS performs well in open environments, but its positioning is inaccurate in urban elevated roads and areas with many tall buildings. GNSS signals may not be received or may be interfered with in urban canyons, and GNSS signals may not be received in tunnels, underground parking garages, and other areas. LiDAR performs well in the above scenarios, but its performance is slightly worse than GNSS in relatively open environments. Visual semantic information can provide rich environmental features. By recognizing long-standing semantic features through visual perception, the robustness of positioning functions in changing scenarios can be enhanced to some extent. Fusion of vehicle signals and IMU can, to some extent, suppress the degradation phenomenon of radar in scenarios with high similarity and provide a certain accuracy of prior values ​​for vision in scenarios with limited semantic features.

[0064] The technical solution provided by this invention effectively combines sensor information from GNSS, IMU, vehicle signals, LiDAR, and cameras. It achieves high-precision dead reckoning through IMU and vehicle signals; GNSS provides global pose correction in signal lock-on situations; and it pre-constructs LiDAR point cloud feature maps and high-precision vector maps. Positioning is achieved by matching real-time LiDAR feature extraction with the prior point cloud feature map, and by matching semantic information such as lane lines and poles perceived visually with the high-precision vector map, thus realizing high-precision positioning in GNSS lock-on scenarios. Furthermore, through fault-tolerant processing of inter-sensor data, the entire high-precision positioning system can still function normally even if a single sensor (GNSS, LiDAR, or vision sensor) fails. By fusing information from various vehicle-mounted sensors to estimate the carrier pose, the robustness and stability of high-precision positioning are effectively improved.

[0065] In another feasible implementation, the system may optionally include a time synchronization module, which is connected to the industrial control computer 11, the image acquisition device, the combined inertial navigation device 12 and the lidar 14 respectively, for unifying the time of the industrial control computer 11, the time of the image acquisition device, the time of the combined inertial navigation device 12 and the time of each lidar 14.

[0066] Among them, such as Figure 1e As shown, this solution uses the integrated inertial navigation device 12 as a clock source via a time synchronization module, and provides time synchronization to the time synchronization device through PPS and GPRMC signals. The time synchronization device provides time synchronization to the industrial control computer 11 and the Ethernet switch via PTP signals. By deploying an image acquisition device driver in the time synchronization device, the data from the image acquisition device is time-synchronized. The Ethernet switch then provides time synchronization to the four LiDARs 14 via PTP signals, ensuring that the vehicle's industrial control computer 11, image acquisition devices, integrated inertial navigation device 12, and LiDARs 14 are all in the same time dimension, avoiding data corruption and providing a reliable data source for high-precision vehicle positioning.

[0067] Figure 2 This is a flowchart of a vehicle positioning method provided in an embodiment of the present invention. This embodiment is applicable to situations requiring high-precision vehicle positioning. The method can be executed by a vehicle positioning system, which can be implemented in hardware and / or software and can be configured in an electronic device used for vehicle positioning. This vehicle positioning method and the vehicle positioning system provided in the above embodiments belong to the same disclosed concept. Details not described in detail in the method embodiment can be referred to the descriptions in the above embodiments.

[0068] like Figure 2 As shown, the vehicle positioning method in this embodiment of the invention may include:

[0069] S210: Determine the combined inertial navigation data of the target vehicle through the combined inertial navigation equipment, and send the combined inertial navigation data to the industrial control computer.

[0070] The combined inertial navigation data includes angular velocity information and acceleration information.

[0071] S220: Determine the wheel speed information of the target vehicle through the wheel speed sensor, and send the wheel speed information to the industrial control computer.

[0072] S230: Determine the original lidar point cloud using at least one lidar and send the original lidar point cloud to the industrial control computer.

[0073] S240: The industrial control computer determines the laser point cloud feature map, determines the first positioning information based on the original laser radar point clouds and the laser point cloud feature map, and determines the second positioning information of the target vehicle based on the combined inertial navigation data and the wheel speed information, and determines the target positioning of the target vehicle at the current moment based on the first positioning information and the second positioning information.

[0074] In this embodiment, optionally, determining the first positioning information based on each of the original lidar point clouds and the lidar point cloud feature map includes: using the industrial control computer to perform motion compensation on the original lidar point clouds based on the lidar's acquisition frequency, angular velocity information, and rotational speed information to obtain the target lidar point cloud; and determining the first positioning information based on each of the target lidar point clouds and the lidar point cloud feature map.

[0075] In this embodiment, optionally, determining the first positioning information based on the target lidar point clouds and the lidar point cloud feature map includes: determining ground points and non-ground points by the industrial control computer based on the target lidar point clouds; the vertical coordinate of the ground point is less than a preset value; determining planar points from the non-ground points; and determining the first positioning information based on the ground points, the planar points, and the lidar point cloud feature map.

[0076] In one feasible implementation, optionally, determining planar points from the non-ground points includes: using the industrial control computer to determine adjacent radar points of each non-ground point based on the target lidar point cloud; determining the target curvature of the non-ground point based on each adjacent radar point and the non-ground point; and designating non-ground points with target curvature less than a preset curvature threshold as planar points.

[0077] In another feasible implementation, optionally, determining the first positioning information based on each of the ground points, each of the planar points, and the laser point cloud feature map includes: determining candidate numbers for each of the ground points and the planar points via the industrial control computer; determining at least one first spatial grid region based on the laser point cloud feature map; determining at least one second spatial grid region for each first spatial grid region; determining the average size information of each second spatial grid region for each second spatial grid region; the size information including longitude, latitude, and altitude; determining the grid number of the second spatial grid region based on the average size information; using radar points associated with candidate numbers consistent with the grid numbers as target radar points; and determining the first positioning information based on each target radar point.

[0078] In another feasible implementation, optionally, after sending the original lidar point cloud to the industrial control computer, the method further includes: determining the surrounding environment image information of the target vehicle through an image acquisition device and sending the surrounding environment image information to the industrial control computer; determining the third positioning information of the target vehicle through a satellite positioning device and sending the third positioning information to the industrial control computer; determining a lidar point cloud feature map through the industrial control computer; determining first positioning information based on each of the original lidar point clouds and the lidar point cloud feature map; determining the second positioning information of the target vehicle based on the combined inertial navigation data and the wheel speed information; and determining the target positioning of the target vehicle at the current moment based on the first positioning information and the second positioning information, including: determining the visual map data at the current moment through the industrial control computer; determining the fourth positioning information of the target vehicle based on the visual map data and the surrounding environment image information; and determining the target positioning of the target vehicle at the current moment based on the first positioning information, the second positioning information, the third positioning information, and the fourth positioning information.

[0079] In another feasible implementation, optionally, determining the target location of the target vehicle at the current moment based on the first positioning information, the second positioning information, the third positioning information, and the fourth positioning information includes: processing the first positioning information, the second positioning information, the third positioning information, and the fourth positioning information by the industrial control computer based on the error state Kalman filter algorithm to obtain the target location of the target vehicle at the current moment.

[0080] In another feasible implementation, the method may optionally further include: unifying the time of the industrial control computer, the time of the image acquisition device, the time of the combined inertial navigation device, and the time of each of the lidars through a time synchronization module.

[0081] The technical solution of this invention involves determining combined inertial navigation data of a target vehicle using a combined inertial navigation system (INS), and sending the combined INS data to an industrial control computer. The combined INS data includes angular velocity and acceleration information. Wheel speed information of the target vehicle is determined using wheel speed sensors and sent to the industrial control computer. At least one lidar sensor is used to determine an original lidar point cloud, which is then sent to the industrial control computer. The industrial control computer determines a lidar point cloud feature map, and based on the original lidar point clouds and the lidar point cloud feature map, first positioning information is determined. Furthermore, based on the combined INS data and the wheel speed information, second positioning information of the target vehicle is determined. Finally, based on the first and second positioning information, the target positioning of the target vehicle at the current moment is determined. By implementing the solution provided by this invention, the robustness and stability of high-precision positioning during vehicle operation can be effectively improved.

[0082] Figure 3 A schematic diagram of an electronic device 40 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0083] like Figure 3 As shown, the electronic device 40 includes at least one processor 41 and a memory, such as a read-only memory (ROM) 42 or a random access memory (RAM) 43, communicatively connected to the at least one processor 41. The memory stores computer programs executable by the at least one processor. The processor 41 can perform various appropriate actions and processes based on the computer program stored in the ROM 42 or loaded into the RAM 43 from storage unit 48. The RAM 43 may also store various programs and data required for the operation of the electronic device 40. The processor 41, ROM 42, and RAM 43 are interconnected via a bus 44. An input / output (I / O) interface 45 is also connected to the bus 44.

[0084] Multiple components in electronic device 40 are connected to I / O interface 45, including: input unit 46, such as keyboard, mouse, etc.; output unit 47, such as various types of monitors, speakers, etc.; storage unit 48, such as disk, optical disk, etc.; and communication unit 49, such as network card, modem, wireless transceiver, etc. Communication unit 49 allows electronic device 40 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0085] Processor 41 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 41 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 41 performs the various methods and processes described above, such as vehicle positioning methods.

[0086] In some embodiments, the vehicle positioning method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 48. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 40 via ROM 42 and / or communication unit 49. When the computer program is loaded into RAM 43 and executed by processor 41, one or more steps of the vehicle positioning method described above may be performed. Alternatively, in other embodiments, processor 41 may be configured to perform the vehicle positioning method by any other suitable means (e.g., by means of firmware).

[0087] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0088] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0089] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0090] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0091] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0092] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0093] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0094] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A vehicle positioning system, characterized in that, It includes an industrial control computer, a combined inertial navigation system, wheel speed sensors, and at least one lidar; wherein: The industrial control computer is connected to the combined inertial navigation device, the wheel speed sensor, and each of the lidars, respectively. The combined inertial navigation device is used to determine the combined inertial navigation data of the target vehicle and send the combined inertial navigation data to the industrial control computer; the combined inertial navigation data includes angular velocity information and acceleration information; The wheel speed sensor is used to determine the wheel speed information of the target vehicle and send the wheel speed information to the industrial control computer; The lidar is used to determine the original lidar point cloud and send the original lidar point cloud to the industrial control computer; The industrial control computer is used to determine the laser point cloud feature map, determine the first positioning information based on each of the original lidar point clouds and the laser point cloud feature map, and determine the second positioning information of the target vehicle based on the combined inertial navigation data and the wheel speed information, and determine the target positioning of the target vehicle at the current moment based on the first positioning information and the second positioning information. The industrial control computer is specifically used to perform motion compensation on the original lidar point cloud based on the lidar's acquisition frequency, angular velocity information, and rotational speed information to obtain the target lidar point cloud; The first positioning information is determined based on the laser radar point cloud of each target and the feature map of the laser point cloud; The industrial control computer is specifically used to determine ground points and non-ground points based on the point clouds of each target lidar; the vertical coordinate of the ground point is less than a preset value. Determine planar points from the non-ground points; The first positioning information is determined based on each of the ground points, each of the planar points, and the laser point cloud feature map; The industrial control computer is specifically used to determine the candidate numbers of each of the ground points and the plane points; At least one first spatial grid region is determined based on the laser point cloud feature map; For each first spatial grid region, at least one second spatial grid region is determined; For each second spatial grid region, determine the average size information of the second spatial grid region; the size information includes longitude, latitude, and altitude; The grid number of the second spatial grid region is determined based on the average size information; The radar points associated with the candidate numbers that match the grid numbers are used as the target radar points. The first positioning information is determined based on each of the target radar points; Determine the ID of each radar point in the target lidar point cloud, and divide the longitude, latitude, and altitude of each radar point by a certain value simultaneously; obtain the x1, y1, and z1 values ​​of the radar point respectively, based on the first spatial grid ID algorithm: ID = (z 300 + y) Process x1, y1, and z1 using 300 + x to obtain the radar point number; determine the numbers of ground points and planar points among the radar points, which are then used as candidate numbers.

2. The system according to claim 1, characterized in that, The industrial control computer is specifically used to determine the adjacent radar points of each non-ground point based on the target lidar point cloud. The target curvature of the non-ground point is determined based on each of the adjacent radar points and the non-ground point; Non-ground points with a target curvature less than a preset curvature threshold are treated as plane points.

3. The system according to claim 1, characterized in that, The system also includes an image acquisition device and a satellite positioning device, which are respectively connected to the industrial control computer. The image acquisition device is used to determine the surrounding environment image information of the target vehicle and send the surrounding environment image information to the industrial control computer; The satellite positioning device is used to determine the third positioning information of the target vehicle and send the third positioning information to the industrial control computer; The industrial control computer is also used to determine the visual map data at the current moment, determine the fourth positioning information of the target vehicle based on the visual map data and the surrounding environment image information, and determine the target positioning of the target vehicle at the current moment based on the first positioning information, the second positioning information, the third positioning information and the fourth positioning information.

4. The system according to claim 3, characterized in that, The industrial control computer is specifically used to process the first positioning information, the second positioning information, the third positioning information, and the fourth positioning information based on the error state Kalman filter algorithm to obtain the target positioning of the target vehicle at the current moment.

5. The system according to claim 4, characterized in that, The system also includes a time synchronization module, which is connected to the industrial control computer, the image acquisition device, the combined inertial navigation device, and the lidar, respectively, for unifying the time of the industrial control computer, the image acquisition device, the combined inertial navigation device, and the lidar.

6. A vehicle positioning method, performed by the vehicle positioning system according to any one of claims 1-5, characterized in that, include: The combined inertial navigation data of the target vehicle is determined by the combined inertial navigation equipment, and the combined inertial navigation data is sent to the industrial control computer; The combined inertial navigation data includes angular velocity information and acceleration information; The wheel speed information of the target vehicle is determined by the wheel speed sensor, and the wheel speed information is sent to the industrial control computer. The original lidar point cloud is determined by at least one lidar, and the original lidar point cloud is sent to the industrial control computer; The industrial control computer determines the laser point cloud feature map, determines the first positioning information based on the original lidar point clouds and the laser point cloud feature map, and determines the second positioning information of the target vehicle based on the combined inertial navigation data and the wheel speed information. Based on the first positioning information and the second positioning information, the target positioning of the target vehicle at the current moment is determined.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the vehicle positioning method of claim 6.

Images