Odometer initialization method and device, electronic equipment and autonomous vehicle

Abstract

The present disclosure provides a kind of odometer initialization method, device, electronic equipment and automatic driving vehicle, it is related to automatic driving technical field, especially it is related to laser radar inertial odometer technical field.The specific implementation scheme is: obtaining the point cloud data collected by vehicle laser radar in specified time period under vehicle static state, and extracting vertical line feature in the point cloud data;Determine the direction of the vertical line feature;Obtain the vehicle inertial measurement unit data in the specified time period;According to the direction and the vehicle inertial measurement unit data, the inertial measurement unit is initialized.Through the present disclosure, the vehicle inertial measurement unit of inertial odometer can be initialized, high precision, simple way, and easy convergence.

Description

Technical Field

[0001] This disclosure relates to the field of autonomous driving technology, and more particularly to the field of laser radar (LiDAR) inertial odometry technology, specifically to an odometry initialization method, device, electronic device, and autonomous vehicle. Background Technology

[0002] In autonomous vehicles, LiDAR Inertial Odometers are systems that use measurement data from LiDAR and onboard Inertial Measurement Units (IMUs) to reconstruct the vehicle's motion.

[0003] The system initialization of a LiDAR Inertial Odometry system involves estimating the direction of gravitational acceleration, IMU bias, and initial IMU motion. Accurate initialization is fundamental for the normal operation of the system. Summary of the Invention

[0004] This disclosure provides an odometer initialization method, apparatus, electronic device, and autonomous vehicle.

[0005] According to a first aspect of this disclosure, an odometer initialization method is provided, the method comprising:

[0006] The system acquires point cloud data collected by the vehicle-mounted LiDAR within a specified time period while the vehicle is stationary, and extracts vertical line features from the point cloud data; determines the direction of the vertical line features; acquires inertial measurement unit (IMU) data within the specified time period; and initializes the vehicle-mounted IMU based on the direction and the vehicle-mounted IMU data.

[0007] According to a second aspect of this disclosure, an odometer initialization device is provided, the device comprising:

[0008] The acquisition module is used to acquire point cloud data collected by the vehicle-mounted LiDAR within a specified time period while the vehicle is stationary, and extract vertical line features from the point cloud data; the determination module is used to determine the direction of the vertical line features; the acquisition module is also used to acquire vehicle-mounted inertial measurement unit data within the specified time period; the initialization module is used to initialize the vehicle-mounted inertial measurement unit according to the direction and the vehicle-mounted inertial measurement unit data.

[0009] According to a third aspect of this disclosure, an electronic device is provided, comprising:

[0010] At least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of the first aspect.

[0011] According to a fourth aspect of this disclosure, a non-transitory computer-readable storage medium is provided storing computer instructions, wherein the computer instructions are configured to cause the computer to perform the method according to the first aspect.

[0012] According to a fifth aspect of this disclosure, a computer product is provided, including a computer program that, when executed by a processor, implements the method according to the first aspect.

[0013] According to a fifth aspect of this disclosure, an autonomous vehicle is provided, including the electronic equipment described in the third aspect.

[0014] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0015] The accompanying drawings are provided to better understand this solution and do not constitute a limitation of this disclosure. Wherein:

[0016] Figure 1 A flowchart illustrating an odometer initialization method provided in an embodiment of this disclosure is shown.

[0017] Figure 2 A flowchart illustrating a method for obtaining vertical line features according to an embodiment of this disclosure is shown;

[0018] Figure 3 A flowchart illustrating a method for determining the characteristic direction of a vertical line according to an embodiment of this disclosure is shown.

[0019] Figure 4 A flowchart illustrating a method for determining the characteristic direction of a vertical line according to an embodiment of this disclosure is shown.

[0020] Figure 5 A flowchart illustrating a method for determining the characteristic direction of a vertical line according to an embodiment of this disclosure is shown.

[0021] Figure 6 A schematic diagram of the structure of an odometer initialization device provided in an embodiment of this disclosure is shown;

[0022] Figure 7 A schematic block diagram of an example electronic device that can be used to implement embodiments of the present disclosure is shown. Detailed Implementation

[0023] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0024] LiDAR Inertial Odometry is a system that uses measurement data from LiDAR and IMU to reconstruct the motion of a vehicle. It is widely used in mapping and localization of autonomous vehicles. Its accuracy significantly impacts the accuracy of mapping and localization.

[0025] The system initialization of a LiDAR Inertial Odometry (IMU) involves estimating the direction of gravitational acceleration, IMU bias, and initial IMU motion. Accurate initialization is fundamental for the normal operation of the system. Otherwise, it may lead to increased errors in the system state after normal operation and failure to converge properly.

[0026] In related technologies, the initialization methods for Inertial odometry include initialization under dynamic motion conditions and initialization under static motion conditions.

[0027] Initialization under dynamic motion conditions involves mapping the environment based on LiDAR point cloud and IMU data during a period of vehicle motion, and estimating the IMU pose, direction of gravitational acceleration, and IMU zero bias at each moment.

[0028] Initialization under static motion conditions: In this case, no mapping is required and the pose state of the IMU is constant. Assuming that the direction of gravitational acceleration coincides with the direction of IMU acceleration measurement, the direction of gravitational acceleration can be obtained directly. The estimated value of the IMU acceleration zero bias is obtained by subtracting the gravitational acceleration from the acceleration statistical mean. The measured mean of angular velocity is the estimated value of the IMU angular velocity zero bias.

[0029] However, dynamic initialization methods have certain requirements regarding motion conditions and environmental characteristics, making successful initialization relatively difficult. For example, they require the vehicle to perform steering movements and the environment to have rich linear and surface features. Static initialization methods, due to the assumption that the direction of gravity is the same as the direction of IMU acceleration measurement, can introduce certain errors in some cases.

[0030] Based on this, this application provides an odometer initialization method and apparatus. Under static motion conditions, the direction of gravitational acceleration is determined by identifying the direction of a vertical feature relative to the ground, utilizing the direction of the vertical feature as a constraint on the direction of gravity, and initialization is completed under static vehicle conditions, making odometer initialization data processing simple and convenient. Initializing the onboard inertial measurement unit (IMU) using data from the IMU and the determined direction reduces the requirements for the motion environment and conditions of the autonomous vehicle, resulting in high accuracy and easy convergence of the initialization data.

[0031] This application can be implemented using, but is not limited to, various personal computers, laptops, smartphones, tablets and portable wearable devices, servers or server clusters consisting of multiple servers.

[0032] It should be noted that the terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this disclosure 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 this disclosure described herein can be implemented in orders other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this disclosure. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this disclosure as detailed in the appended claims.

[0033] Figure 1 A flowchart illustrating an odometer initialization method provided in an embodiment of this disclosure is shown, as follows: Figure 1 As shown, the method may include:

[0034] In step S110, point cloud data collected by lidar within a specified time period while the vehicle is stationary is acquired, and vertical line features in the point cloud data are extracted.

[0035] In this embodiment, the vehicle can acquire LiDAR point cloud data, where each point in the LiDAR point cloud data contains three-dimensional coordinate information, namely, X, Y, and Z elements. It may also contain color information, reflection intensity information, echo count information, etc. The vehicle can be an autonomous vehicle.

[0036] This disclosure allows for the acquisition of any single-frame point cloud data from LiDAR point cloud data in a stationary vehicle state, and the determination of all single-frame point cloud data within a specified time period based on that single-frame point cloud data. It should be noted that the arbitrary single-frame point cloud data can be uncompensated single-frame point cloud data.

[0037] Furthermore, line features can be extracted from any single frame of point cloud data, and vertical line features can be determined from the extracted line features, where the vertical line features can be vertical line features of the ground.

[0038] In this disclosure, the average value of the direction of the vertical line feature can also be calculated to determine the direction of the vertical line feature.

[0039] In step S120, the direction of the vertical line feature is determined.

[0040] In this embodiment of the disclosure, the corresponding direction is determined based on the extracted vertical line features.

[0041] In step S130, the vehicle-mounted inertial measurement unit data within a specified time period is acquired.

[0042] In this embodiment of the disclosure, the data of the vehicle-mounted inertial measurement unit within the specified time period can be obtained. For example, the data of the vehicle-mounted inertial measurement unit may include the angular velocity measurement value, the acceleration measurement value, and the gravitational acceleration value of the vehicle-mounted inertial measurement unit.

[0043] In step S140, the vehicle inertial measurement unit is initialized based on the orientation and vehicle inertial measurement unit data.

[0044] In this embodiment of the disclosure, each frame of point cloud data within a specified time period can be determined one by one. If the point cloud data within the specified time period is determined to be point cloud data in a stationary state of the vehicle, the vehicle inertial measurement unit is initialized according to the direction and the data of the vehicle inertial measurement unit.

[0045] The odometer initialization method provided in this application initializes the onboard inertial measurement unit (IMU) while the vehicle is stationary, using the direction of vertical line features and the acquired IMU data. Acquiring point cloud data while the vehicle is stationary avoids complex scenarios arising from vehicle steering. Initializing the IMU using the direction of vertical line features and the acquired IMU data is accurate, simple, and easy to converge.

[0046] The following embodiments of this disclosure will illustrate the extraction of vertical line features.

[0047] Figure 2 A flowchart illustrating a method for obtaining vertical line features according to an embodiment of this disclosure is shown, as follows: Figure 2 As shown, the method may include:

[0048] In step S210, line features are extracted from the point cloud data, and the first angle value of the line features relative to the ground is obtained.

[0049] In step S220, among the online features, a first online feature whose first included angle value is greater than or equal to a first threshold is obtained.

[0050] In step S230, the first line feature is defined as a vertical line feature relative to the ground.

[0051] In this embodiment of the disclosure, as described in the above embodiments, line features can be extracted from each frame of point cloud data acquired. Furthermore, the angle values ​​of these line features relative to the ground are determined. For ease of distinction, this disclosure refers to the angle values ​​of the line features relative to the ground as the first angle value.

[0052] Furthermore, among the online features, roughly vertical line features can be filtered out. For example, the first line feature with an included angle greater than or equal to a first threshold can be selected. The first threshold can be preset or customized; for example, the first threshold could be 80 degrees. Thus, line features with an angle greater than or equal to 80 degrees are identified as vertical line features.

[0053] In this disclosure, it is also necessary to determine the direction of the acquired vertical line feature. The following embodiments will illustrate how to determine the direction of the vertical line feature.

[0054] Figure 3 A flowchart illustrating a method for determining the characteristic direction of a vertical line according to an embodiment of this disclosure is shown, such as... Figure 3 As shown, the method may include:

[0055] In step S310, the second included angle value between every two vertical line features is determined.

[0056] In step S320, at least one set of second line features whose second included angle value is less than or equal to the second threshold is determined.

[0057] In step S330, the group of second-line features with the largest number is selected from at least one group of second-line features.

[0058] In step S340, the average value of the directions of the group of second line features with the largest number is determined as the direction of the vertical line feature.

[0059] In this embodiment of the disclosure, there can be multiple vertical line features, thus requiring the determination of a second included angle value between every two vertical line features. For ease of distinction, this disclosure refers to the included angle value between every two vertical line features as the second included angle value.

[0060] In this disclosure, at least one set of second line features whose second included angle value is less than or equal to a second threshold can be determined using the Random Sample Consensus (RANSAC) method.

[0061] In other words, this disclosure can group the first line features, and the angle between each pair of vertical line features in each group is less than or equal to the second threshold.

[0062] For example, the second threshold is 5 degrees. Groups where the angle between any two first-line features is less than or equal to 5 degrees include groups with 3 first-line features, groups with 2 first-line features, and groups with 1 first-line feature. That is, among all first-line features, there are groups where the angle between any two first-line features with 3 features is 5 degrees, groups where the angle between two first-line features is 5 degrees, and groups where there is a single first-line feature whose angle with any other first-line feature exceeds 5 degrees. Therefore, the first-line features can be divided into 3 groups, and the group containing the most first-line features is selected.

[0063] In this disclosure, the average direction of the group of first line features that includes the largest number of first line features can also be calculated, thereby determining the determined average direction as the direction of the determined vertical line feature.

[0064] The data used in the odometer initialization method provided in this disclosure is based on the vehicle being stationary. Therefore, this disclosure also needs to determine that the point cloud data within a specified time period is the point cloud data of the vehicle being stationary.

[0065] The following examples will illustrate how to determine point cloud data within a specified time period as point cloud data of a stationary vehicle.

[0066] Figure 4 A flowchart illustrating a method for determining the characteristic direction of a vertical line according to an embodiment of this disclosure is shown, such as... Figure 4 As shown, the method may include:

[0067] In step S410, point cloud data collected by lidar within a specified time period is acquired.

[0068] In step S420, the first vertical line feature of the first frame of point cloud data within the specified time period is obtained.

[0069] In step S430, the second vertical line feature of any other frame of point cloud data within a specified time period is obtained.

[0070] In step S440, the matching degree and average distance between the first vertical line feature and the second vertical line feature are determined.

[0071] In step S450, in response to a matching degree greater than or equal to a third threshold and an average distance less than or equal to a fourth threshold, the point cloud data within the specified time period is determined to be point cloud data of a stationary vehicle.

[0072] In this embodiment of the disclosure, continuous single-frame point cloud data within a specified time period can be acquired to determine that the vehicle is stationary during that specified time period. For example, in this disclosure, any single-frame point cloud data can be selected to determine continuous single-frame point cloud data for a specified time period based on the arbitrary point cloud data.

[0073] Further, obtain the first vertical line feature of the first frame of point cloud data within the specified time period. Also, obtain the second vertical line feature of any other frame of point cloud data within the specified time period.

[0074] Any single frame of point cloud data is selected as the first single frame of point cloud data. The first single frame of point cloud data is the first single frame of point cloud data required for initializing the vehicle-mounted inertial measurement unit in this application.

[0075] After determining the first single-frame point cloud data, the time point of the first single-frame point cloud data can be determined. Then, based on the time point of the first single-frame point cloud data, single-frame point cloud data can be obtained sequentially until all the vehicle inertial measurement unit data within the specified time period are obtained.

[0076] For ease of description, this disclosure refers to any other frame of point cloud data as the second single-frame point cloud data, and the vertical line feature corresponding to the second single-frame point cloud data as the second vertical line feature.

[0077] The second vertical line feature of the second single frame point cloud data relative to the ground is extracted. The implementation method for determining the vertical line feature of the second single frame point cloud data is as described in the above embodiment, and will not be repeated here.

[0078] Match corresponding points on the first vertical line feature and the second vertical line feature, and determine the proportion of successfully matched points among all points as the matching degree. Calculate the average distance between the first and second vertical line features. The average distance can be the average distance between points and lines.

[0079] In one embodiment of this disclosure, in response to a matching degree greater than or equal to a third threshold and an average point-to-line distance less than or equal to a fourth threshold, the point cloud data within a specified time period is determined to be point cloud data in a stationary vehicle state. For example, if the third threshold is 90% and the fourth threshold is 5cm, then if the matching degree is greater than or equal to 90% and the average point-to-line distance is less than or equal to 5cm, the point cloud data within the specified time period is determined to be point cloud data in a stationary vehicle state.

[0080] In another embodiment of this disclosure, if the matching degree is greater than or equal to a third threshold, or the average distance between points and lines is less than or equal to a fourth threshold, the vertical line features relative to the ground in any single frame of point cloud data are reacquired. That is, point cloud data within a specified time period are reselected.

[0081] In this disclosure, it is necessary to perform the following operations on each frame of point cloud data within a specified time period: Figure 4 The aforementioned steps determine that the point cloud data within the specified time frame is point cloud data of a stationary vehicle. That is, it is also necessary to perform the following steps on the next frame of point cloud data from the second single-frame point cloud data: Figure 4 The steps shown specify that the time interval between the current single-frame point cloud data and the first single-frame point cloud data exceeds a specified time period.

[0082] In this embodiment of the disclosure, in response to the point cloud data within a specified time period being point cloud data in a non-stationary vehicle state, it is determined whether the point cloud data for the next specified time period is point cloud data in a stationary vehicle state.

[0083] The following embodiments of this disclosure will illustrate the implementation of the initialization of an on-board inertial measurement unit.

[0084] Figure 5 This illustration shows a flowchart of an inertial measurement unit initialization process according to an embodiment of the present disclosure, such as... Figure 5 As shown, the method may include:

[0085] In step S510, the angular velocity measurement value and acceleration measurement value of the vehicle-mounted inertial measurement unit within a specified time period are obtained.

[0086] In step S520, the gravitational acceleration value of the area where the vehicle-mounted inertial measurement unit is located is obtained.

[0087] In step S530, the first average value of the angular velocity measurements within a specified time period is calculated, and the second average value of the acceleration measurements within the specified time period is calculated.

[0088] In step S540, the direction is determined as the direction of the gravitational acceleration of the vehicle-mounted inertial measurement unit, the first average value is determined as the zero offset of the angular velocity of the vehicle-mounted inertial measurement unit, the difference between the second average value and the gravitational acceleration value is determined as the zero offset value of the acceleration of the vehicle-mounted inertial measurement unit, the velocity of the vehicle-mounted inertial measurement unit is set to zero, and the vehicle-mounted inertial measurement unit is initialized.

[0089] In this embodiment of the disclosure, as described above, the data from the vehicle-mounted inertial measurement unit includes the angular velocity measurement value, the acceleration measurement value, and the acquired gravitational acceleration value of the vehicle-mounted inertial measurement unit.

[0090] The angular velocity zero bias of the vehicle-mounted inertial measurement unit (VIMU) is set to the average of the angular velocities measured by all VIMUs within a specified time period. The acceleration zero bias of the VIMU is set to the average acceleration measured by all VIMUs within the specified time period minus the projection of gravitational acceleration onto the local coordinate system of the VIMU. The velocity of the VIMU is set to 0. This performs static initialization of the VIMU.

[0091] In this embodiment of the disclosure, in response to the time interval between the acquired current frame point cloud data and any single frame point cloud data being greater than or equal to a specified time period, it is determined that the vehicle-mounted inertial measurement unit initialization is complete.

[0092] For example, if the specified time period is 5 seconds, then it is determined that the time interval between the current frame point cloud data and the first frame point cloud data is greater than or equal to 5 seconds, and the initialization of the vehicle-mounted inertial measurement unit is completed.

[0093] It should be noted that the odometry initialization method provided in this disclosure, which uses vertical features for gravity direction constraints, can also be extended to dynamic initialization, or used as roll and pitch rotation constraints for the global pose of the IMU during normal operation of the odometry.

[0094] Based on and Figure 1 The method shown follows the same principle. Figure 6 A schematic diagram of the structure of an odometer initialization device provided in an embodiment of this disclosure is shown, as follows: Figure 6 As shown, the odometer initialization device 600 may include:

[0095] The acquisition module 601 is used to acquire point cloud data collected by the lidar within a specified time period while the vehicle is stationary, and extract vertical line features from the point cloud data; the determination module 602 is used to determine the direction of the vertical line features; the acquisition module 601 is also used to acquire vehicle-mounted inertial measurement unit data within the specified time period; the initialization module 603 is used to initialize the vehicle-mounted inertial measurement unit according to the direction and the vehicle-mounted inertial measurement unit data.

[0096] In this embodiment of the disclosure, the acquisition module 601 is used to extract line features from the point cloud data, and obtain a first angle value of the line feature relative to the ground; among the line features, obtain a first line feature whose first angle value is greater than or equal to a first threshold; and determine the first line feature as a vertical line feature relative to the ground.

[0097] In this embodiment of the disclosure, the determining module 602 is used to determine a second angle value between every two vertical line features; determine at least one set of second line features whose second angle value is less than or equal to a second threshold; select the set of second line features with the largest number of features from the at least one set of second line features; and determine the average value of the directions of the set of second line features with the largest number of features as the direction of the vertical line feature.

[0098] In this embodiment of the disclosure, the acquisition module 601 is used to acquire point cloud data collected by lidar within a specified time period; acquire a first vertical line feature of a first frame of point cloud data within the specified time period; acquire a second vertical line feature of any other frame of point cloud data within the specified time period; determine the matching degree and average distance between the first vertical line feature and the second vertical line feature; and determine that the point cloud data within the specified time period is point cloud data of a stationary vehicle when the matching degree is greater than or equal to a third threshold and the average distance is less than or equal to a fourth threshold.

[0099] In this embodiment of the disclosure, the determining module 602 is used to match corresponding points on the first vertical line feature and the second vertical line feature, determine the proportion of successfully matched points in all points as the matching degree, and calculate the average distance between the first vertical line feature and the second vertical line feature.

[0100] In this embodiment of the disclosure, the determining module 602 is further configured to determine whether the point cloud data in the next specified time period is point cloud data in a non-stationary vehicle state in response to the point cloud data in the specified time period being point cloud data in a non-stationary vehicle state.

[0101] In this embodiment of the disclosure, the initialization module 603 is used to acquire the angular velocity measurement value and acceleration measurement value of the vehicle-mounted inertial measurement unit within the specified time period; acquire the gravitational acceleration value of the area where the vehicle-mounted inertial measurement unit is located; calculate the first average value of the angular velocity measurement value within the specified time period, and calculate the second average value of the acceleration measurement value within the specified time period; determine the direction as the direction of the gravitational acceleration of the vehicle-mounted inertial measurement unit, determine the first average value as the angular velocity zero offset of the vehicle-mounted inertial measurement unit, determine the difference between the second average value and the gravitational acceleration value as the acceleration zero offset value of the vehicle-mounted inertial measurement unit, and set the velocity of the vehicle-mounted inertial measurement unit to zero.

[0102] The acquisition, storage, and application of user personal information involved in the technical solution disclosed herein comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0103] According to embodiments of this disclosure, this disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0104] According to embodiments of this disclosure, this disclosure also provides an autonomous driving vehicle that can utilize the electronic devices described in this disclosure.

[0105] Figure 7 A schematic block diagram of an example electronic device 700 that can be used to implement embodiments of the present disclosure 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 may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, 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 present disclosure described and / or claimed herein.

[0106] like Figure 7 As shown, device 700 includes a computing unit 701, which can perform various appropriate actions and processes based on a computer program stored in read-only memory (ROM) 702 or a computer program loaded from storage unit 708 into random access memory (RAM) 703. RAM 703 may also store various programs and data required for the operation of device 700. The computing unit 701, ROM 702, and RAM 703 are interconnected via bus 704. Input / output (I / O) interface 705 is also connected to bus 704.

[0107] Multiple components in device 700 are connected to I / O interface 705, including: input unit 706, such as keyboard, mouse, etc.; output unit 707, such as various types of monitors, speakers, etc.; storage unit 708, such as disk, optical disk, etc.; and communication unit 709, such as network card, modem, wireless transceiver, etc. Communication unit 709 allows device 700 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0108] The computing unit 701 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 701 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 computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 701 performs the various methods and processes described above, such as the odometer initialization method. For example, in some embodiments, the odometer initialization method may be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 708. In some embodiments, part or all of the computer program may be loaded and / or installed on device 700 via ROM 702 and / or communication unit 709. When the computer program is loaded into RAM 703 and executed by the computing unit 701, one or more steps of the odometer initialization method described above may be performed. Alternatively, in other embodiments, the computing unit 701 may be configured to perform the odometer initialization method by any other suitable means (e.g., by means of firmware).

[0109] 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.

[0110] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0111] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. 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 fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0112] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. 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).

[0113] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with embodiments 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., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0114] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact via communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other. Servers can be cloud servers, servers in distributed systems, or servers incorporating blockchain technology.

[0115] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0116] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. 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 disclosure should be included within the scope of protection of this disclosure.

Claims

1. An inertial measurement unit initialization method, the method comprising: Acquire point cloud data collected by the vehicle-mounted LiDAR within a specified time period while the vehicle is stationary, and extract the vertical line features from the point cloud data; Determine the direction of the vertical line feature; Acquire data from the vehicle-mounted inertial measurement unit within the specified time period; The vehicle-mounted inertial measurement unit is initialized based on the stated direction and the data from the vehicle-mounted inertial measurement unit. The initialization of the vehicle-mounted inertial measurement unit based on the direction and the data from the vehicle-mounted inertial measurement unit includes: Obtain the angular velocity and acceleration measurements of the vehicle-mounted inertial measurement unit within the specified time period; Obtain the gravitational acceleration value of the area where the vehicle-mounted inertial measurement unit is located; Calculate the first mean of the angular velocity measurements within the specified time period, and calculate the second mean of the acceleration measurements within the specified time period; The direction is determined as the direction of the gravitational acceleration of the vehicle-mounted inertial measurement unit, the first average value is determined as the zero offset of the angular velocity of the vehicle-mounted inertial measurement unit, the difference between the second average value and the gravitational acceleration value is determined as the zero offset of the acceleration of the vehicle-mounted inertial measurement unit, the velocity of the inertial measurement unit is set to zero, and the vehicle-mounted inertial measurement unit is initialized.

2. The method according to claim 1, wherein, The extraction of vertical line features from the point cloud data includes: Extract line features from the point cloud data and obtain the first angle value of the line features relative to the ground. Among the line features, a first line feature whose first included angle value is greater than or equal to a first threshold is obtained; The first line feature is defined as a vertical line feature relative to the ground.

3. The method according to claim 1 or 2, wherein, Determining the direction of the vertical line feature includes: Determine the second included angle value between every two of the vertical line features; Determine at least one set of second line features whose second included angle value is less than or equal to a second threshold; Among the at least one set of second line features, the set of second line features with the largest quantity is selected; The average value of the directions of the group of second line features with the largest quantity is determined as the direction of the vertical line feature.

4. The method according to claim 1, wherein, The acquisition of point cloud data collected by lidar within a specified time period while the vehicle is stationary includes: Acquire point cloud data collected by vehicle-mounted LiDAR within a specified time period; Obtain the first vertical line feature of the first frame of point cloud data within the specified time period; Obtain the second vertical line feature of any other frame of point cloud data within the specified time period; Determine the matching degree and average distance between the first vertical line feature and the second vertical line feature; In response to the matching degree being greater than or equal to a third threshold and the average distance being less than or equal to a fourth threshold, the point cloud data within the specified time period is determined to be point cloud data of a vehicle in a stationary state.

5. The method according to claim 4, wherein, Determining the matching degree and average distance between the first vertical line feature and the second vertical line feature includes: Match the corresponding points on the first vertical line feature and the second vertical line feature, and determine the proportion of successfully matched points among all points as the matching degree; Calculate the average distance between the first vertical line feature and the second vertical line feature.

6. The method according to claim 4, wherein, The method further includes: In response to the fact that the point cloud data within the specified time period is point cloud data in a non-stationary vehicle state, determine whether the point cloud data in the next specified time period is point cloud data in a stationary vehicle state.

7. An inertial measurement unit initialization device, the device comprising: The acquisition module is used to acquire point cloud data collected by the vehicle-mounted lidar within a specified time period when the vehicle is stationary, and to extract the vertical line features from the point cloud data. The determining module is used to determine the direction of the vertical line feature; The acquisition module is also used to acquire vehicle inertial measurement unit data within the specified time period; An initialization module is used to initialize the vehicle-mounted inertial measurement unit based on the direction and the data from the vehicle-mounted inertial measurement unit. The initialization module is defined as being used for: Obtain the angular velocity and acceleration measurements of the vehicle-mounted inertial measurement unit within the specified time period; Obtain the gravitational acceleration value of the area where the vehicle-mounted inertial measurement unit is located; Calculate the first mean of the angular velocity measurements within the specified time period, and calculate the second mean of the acceleration measurements within the specified time period; The direction is determined as the direction of the gravitational acceleration of the vehicle-mounted inertial measurement unit, the first average value is determined as the zero offset of the angular velocity of the vehicle-mounted inertial measurement unit, the difference between the second average value and the gravitational acceleration value is determined as the zero offset of the acceleration of the vehicle-mounted inertial measurement unit, and the velocity of the vehicle-mounted inertial measurement unit is set to zero.

8. The apparatus according to claim 7, wherein, The acquisition module is used for: Extract line features from the point cloud data and obtain the first angle value of the line features relative to the ground. Among the line features, a first line feature whose first included angle value is greater than or equal to a first threshold is obtained; The first line feature is defined as a vertical line feature relative to the ground.

9. The apparatus according to claim 7 or 8, wherein, The determining module is used for: Determine the second included angle value between every two of the vertical line features; Determine at least one set of second line features whose second included angle value is less than or equal to a second threshold; Among the at least one set of second line features, the set of second line features with the largest quantity is selected; The average value of the directions of the group of second line features with the largest quantity is determined as the direction of the vertical line feature.

10. The apparatus according to claim 7, wherein, The acquisition module is used for: Acquire point cloud data collected by vehicle-mounted LiDAR within a specified time period; Obtain the first vertical line feature of the first frame of point cloud data within the specified time period; Obtain the second vertical line feature of any other frame of point cloud data within the specified time period; Determine the matching degree and average distance between the first vertical line feature and the second vertical line feature; In response to the matching degree being greater than or equal to a third threshold and the average distance being less than or equal to a fourth threshold, the point cloud data within the specified time period is determined to be point cloud data of a vehicle in a stationary state.

11. The apparatus according to claim 10, wherein, The determining module is used for: Match the corresponding points on the first vertical line feature and the second vertical line feature, and determine the proportion of successfully matched points among all points as the matching degree; Calculate the average distance between the first vertical line feature and the second vertical line feature.

12. The apparatus according to claim 10, wherein, The determining module is further configured to: In response to the fact that the point cloud data within the specified time period is point cloud data in a non-stationary vehicle state, determine whether the point cloud data in the next specified time period is point cloud data in a stationary vehicle state.

13. An electronic device, comprising: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-6.

14. A non-transitory computer-readable storage medium storing computer instructions, wherein, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-6.

15. A computer product comprising a computer program that, when executed by a processor, implements the method according to any one of claims 1-6.

16. An autonomous vehicle, including the electronic equipment as claimed in claim 13.

Images