Vehicle pose processing method and device, electronic equipment and automatic driving vehicle

Abstract

The invention provides a vehicle pose processing method and device, electronic equipment and an automatic driving vehicle, and relates to the field of artificial intelligence, in particular to the field of automatic driving. According to the specific implementation scheme, initial pose information of a vehicle at different moments is constructed, the initial pose information comprises an initial position and an initial pose, and the initial position is represented by longitude, latitude and elevation; real-time poses of the vehicle at different moments are collected, and the real-time poses are obtained through sensing of a plurality of sensors on the vehicle; and optimizing the initial pose information based on the real-time poses collected at different moments to obtain target pose information. In the process of optimizing the initial pose information by constructing the initial pose information and utilizing a plurality of sensors on the vehicle to sense and obtain the real-time pose, the used coordinates are longitude and latitude, switching of coordinate systems does not need to be considered, the global consistency is effectively ensured, and the accuracy of the optimization of the initial pose information is improved. The problem that in the prior art, in vehicle pose optimization, the coordinate origin needs to be replaced, and resetting is conducted continuously is solved.

Description

Technical Field

[0001] The present disclosure relates to the field of artificial intelligence technology, in particular to the field of autonomous driving technology, and specifically to a vehicle posture processing method, device, electronic device, storage medium, and autonomous driving vehicle. Background Art

[0002] During the autonomous driving operation of unmanned vehicles, the positioning system needs to output continuous, high-frequency and accurate positioning results in real time to ensure the normal operation of modules such as path planning and perception.

[0003] Traditional autonomous driving positioning modules use non-globally consistent coordinate systems, such as the Universal Transverse Mercator Grid (UTM), when integrating positioning information from multiple sensors through graph optimization. Coordinate system changes at the edges of the projection zone require constant resetting of the optimized graph, making programming complex and error-prone. Consequently, graph optimization requires constant resetting of the coordinate origin.

[0004] To address the above-mentioned problems, no effective solutions have been proposed so far. Summary of the Invention

[0005] The present disclosure provides a vehicle posture processing method, device, electronic device, storage medium and autonomous driving vehicle.

[0006] According to a first aspect of the present disclosure, a method for processing a vehicle posture is provided, comprising: constructing initial posture information of the vehicle at different times, wherein the initial posture information comprises: an initial position and an initial posture, and the initial position is represented by longitude, latitude, and elevation; collecting the real-time posture of the vehicle at different times, wherein the real-time posture is sensed based on multiple sensors on the vehicle; and optimizing the initial posture information based on the real-time posture collected at different times to obtain target posture information.

[0007] According to a second aspect of the present disclosure, a vehicle posture processing device is provided, comprising: a construction module for constructing initial posture information of the vehicle at different times, wherein the initial posture information comprises: an initial position and an initial posture, and the initial position is represented by longitude, latitude and elevation; a first acquisition module for acquiring the real-time posture of the vehicle at different times, wherein the real-time posture is acquired based on sensing by multiple sensors on the vehicle; and an optimization module for optimizing the initial posture information based on the real-time posture acquired at different times to obtain target posture information.

[0008] According to a third aspect of the present disclosure, an electronic device is provided, comprising: 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, and the instructions are executed by the at least one processor so that the at least one processor can execute the vehicle posture processing method of any one of the above-mentioned embodiments.

[0009] According to a fourth aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable a computer to execute the vehicle posture processing method according to any one of the above embodiments.

[0010] According to a fifth aspect of the present disclosure, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the vehicle posture processing method according to any one of the above embodiments.

[0011] According to a sixth aspect of the present disclosure, an autonomous driving vehicle is provided, comprising the electronic device in the third aspect above.

[0012] In the above-mentioned embodiments of the present disclosure, initial posture information of the vehicle at different times is constructed, and the real-time posture of the vehicle at different times is collected. The initial posture information is optimized based on the real-time posture collected at different times to obtain target posture information, thereby achieving the purpose of optimizing the vehicle posture. It is easy to notice that in the process of constructing the initial posture information and optimizing the initial posture information by sensing the real-time posture using multiple sensors on the vehicle, the coordinates used are longitude and latitude, and there is no need to consider the switching of coordinate systems, which effectively ensures global consistency and solves the problem of the existing technology requiring the replacement of the coordinate origin and constant resetting in vehicle posture optimization.

[0013] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present disclosure, nor are they intended to limit the scope of the present disclosure. Other features of the present disclosure will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] The accompanying drawings are provided to facilitate a better understanding of the present invention and do not constitute a limitation of the present disclosure.

[0015] Figure 1 It is a schematic diagram of the UTM 6-degree longitude zone in the prior art;

[0016] Figure 2 It is a schematic diagram of UTM projection coordinates in the prior art;

[0017] Figure 3 It is a schematic diagram of UTM zones in the prior art;

[0018] Figure 4is a flow chart of a method for processing vehicle posture according to an embodiment of the present disclosure;

[0019] Figure 5 It is a schematic diagram of the earth ellipsoid parameters in the prior art;

[0020] Figure 6 is a schematic diagram of an optional pose optimization framework according to an embodiment of the present disclosure;

[0021] Figure 7 is a structural diagram of a vehicle posture processing device according to an embodiment of the present disclosure;

[0022] Figure 8 is a schematic block diagram of an example electronic device for implementing an embodiment of the present disclosure. DETAILED DESCRIPTION

[0023] The following description of exemplary embodiments of the present disclosure is made in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding. These details should be considered as merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0024] In the existing technology, the location is expressed in coordinates under UTM. The full name of UTM projection is "Universal Transverse Mercator Projection". It is a "conformal transverse cylindrical projection". The elliptical cylinder divides the earth into two contour circles at 80 degrees south latitude and 84 degrees north latitude. After projection, there is no deformation on the two intersecting meridians, and the length ratio of the central meridian is 0.9996. The earth's ellipsoid is divided into several projection zones with a longitude difference of 6 degrees, such as Figure 1 As shown, the six zones are divided from the 0-degree meridian every 6 degrees of longitude from west to east, and the zones are numbered 1, 2, ... 60. Each zone is projected according to the zone division method, so the coordinates of each zone form an independent system. Each zone uses the central meridian (L0) as the vertical axis X and the equator as the horizontal axis Y. The intersection of the two axes is the coordinate origin of each zone, as shown in Figure 2 The UTM coordinates of each point can be directly expressed as X, Y and elevation H, in meters, and optimized in the pose graph.

[0025] Since the position variables in the existing pose graph optimization scheme are the coordinates (X, Y, H) under UTM, Figure 3 As shown in the UTM zones, when a vehicle travels across the zone boundary, the zone ID (zone number) will switch, causing the UTM coordinates of the vehicle position to change dramatically, resulting in position discontinuity. This requires changing the coordinate origin in the pose graph and reconstructing it. It also requires calculating the conversion parameters from the local coordinate system to the global coordinate system.

[0026] In order to solve the problem that the existing technology requires changing the coordinate origin and constantly resetting it in vehicle posture optimization, the present disclosure proposes a method for processing vehicle posture. This method constructs initial posture information (longitude, latitude and elevation), and uses multiple sensors on the vehicle to sense the real-time posture. In the process of optimizing the initial posture information, the coordinates used are longitude and latitude, and there is no need to consider the switching of coordinate systems, which effectively ensures global consistency.

[0027] Figure 4 is a flow chart of a method for processing vehicle posture according to an embodiment of the present disclosure, such as Figure 4 As shown, the method includes:

[0028] Step S401: constructing initial position information of the vehicle at different times, wherein the initial position information includes: initial position and initial attitude, and the initial position is represented by longitude, latitude and altitude.

[0029] The initial position and initial attitude information in the above steps can be directly obtained from the pre-planned route of the moving vehicle. The initial position can be expressed by longitude, latitude and elevation, that is, (l, b, h), and the attitude can be expressed by the fourth dimension q.

[0030] The vehicle in the above steps can be an autonomous driving vehicle or an ordinary vehicle, wherein the present disclosure plays a driving assistance function in an ordinary vehicle.

[0031] S402 , collecting real-time postures of the vehicle at different times, wherein the real-time postures are sensed based on multiple sensors on the vehicle.

[0032] The real-time posture in the above steps includes: real-time position and real-time posture. The real-time position can also be expressed by longitude, latitude and altitude, and the real-time posture can also be expressed by the fourth dimension q.

[0033] The multiple sensors in the above steps include, but are not limited to, measurements taken by a global navigation satellite system (GNSS), a light detection and ranging system (LiDAR), an intelligent camera / visual, and an inertial measurement unit (IMU). The LiDAR system is a system that integrates three technologies: laser, global positioning system (GPS), and inertial navigation system (INS). It is used to obtain point cloud data and generate accurate digital three-dimensional models. The inertial measurement unit (IMU) is a device used to measure the three-axis attitude angle (or angular rate) and acceleration of an object, and is generally installed at the center of gravity of the object being measured.

[0034] Step S403 : Optimizing the initial posture information based on the real-time postures collected at different times to obtain target posture information.

[0035] In the above steps, the real-time position and posture collected at different times can be used to construct an optimization equation using the real-time position and posture information and solve the equation to optimize the posture information in order to obtain more accurate position and posture information.

[0036] In the above-mentioned embodiments of the present disclosure, initial posture information of the vehicle at different times is constructed, and the real-time posture of the vehicle at different times is collected. The initial posture information is optimized based on the real-time posture collected at different times to obtain target posture information, thereby achieving the purpose of optimizing the vehicle posture. It is easy to notice that in the process of constructing the initial posture information and optimizing the initial posture information by sensing the real-time posture using multiple sensors on the vehicle, the coordinates used are longitude and latitude, and there is no need to consider the switching of coordinate systems, which effectively ensures global consistency and solves the problem of the existing technology requiring the replacement of the coordinate origin and constant resetting in vehicle posture optimization.

[0037] Optionally, optimizing the initial posture information based on the real-time posture collected at different times to obtain the target posture information includes: constructing a posture residual based on the real-time posture collected at different times and the initial posture information; performing least squares processing on the posture residual to obtain the target posture information.

[0038] In these steps, position and attitude residuals are constructed based on the real-time position and attitude information collected at different times. These residuals are then processed using the least squares method to obtain more accurate position and attitude information. This processing improves the accuracy of the position and attitude, eliminating the need to consider coordinate system switching and effectively ensuring global consistency.

[0039] Optionally, constructing posture residuals based on the real-time posture and initial posture information collected at different times includes: constructing longitude residuals based on the initial position, the real-time longitude, the target radius and the target eccentricity in the real-time posture; constructing latitude residuals based on the initial latitude and initial elevation in the initial posture information, the real-time latitude, the target radius and the target eccentricity in the real-time posture; constructing elevation residuals based on the initial elevation in the initial posture information and the real-time elevation in the real-time posture; constructing posture residuals based on the initial posture in the initial posture information and the real-time posture in the real-time posture; and obtaining posture residuals based on the longitude residuals, latitude residuals, elevation residuals and posture residuals.

[0040] The target radius and target eccentricity in the above steps can be basic parameters of the earth ellipsoid, wherein the target radius can be the major semi-axis of the earth ellipsoid, and the target eccentricity can be the first eccentricity of the earth ellipsoid, such as Figure 5 As shown, where a represents the major axis of the earth's ellipse, b' represents the minor axis of the earth's ellipse, and e represents the first eccentricity of the earth's ellipse.

[0041] In the above steps, the longitude residual, latitude residual, elevation residual and attitude residual are constructed respectively, and the residual equation is obtained by combining them as shown below:

[0042]

[0043] r h =hh sensor ,

[0044]

[0045] In the above formula, r represents the residual term, where r lon Represents the longitude residual, r lat represents the latitude residual, r h represents the elevation residual, r q Represents the attitude residual. Among them, (l sensor , b sensor , h sensor ) represents the real-time position represented by the real-time latitude, longitude and elevation obtained by the sensor (GNSS, LIDAR, Visual), sensorThe real-time attitude obtained by sensors (GNSS, LIDAR, Visual), expressed as a quaternion. (l, b, h) is the initial position expressed in latitude, longitude, and elevation, and q is the initial attitude expressed in the quaternion.

[0046] In the above steps, the residual equation is constructed and then used to optimize the initial pose. After the above processing, the accuracy of the pose is improved without considering the switching of the coordinate system, which effectively ensures global consistency.

[0047] Optionally, before optimizing the initial posture information based on the real-time posture to obtain the target posture information, the method further includes: collecting the real-time incremental posture of the vehicle at different times, wherein the real-time incremental posture is sensed based on at least one sensor on the vehicle; optimizing the initial posture information based on the real-time posture and real-time incremental posture collected at different times to obtain the target posture information.

[0048] In an optional embodiment, as Figure 6 As shown in the figure, the large white circle represents the optimized variable pose, the small white circle represents the pose obtained by the Global Navigation System (GNSS), the white triangle represents the pose obtained by the Laser Radar (LiDAR), the white rectangle represents the pose obtained by the smart camera (Camera / Visual), and the small black circle represents the incremental pose obtained from the vehicle's Inertial Measurement Unit (IMU) and wheel speedometer. The optimization variable of the entire pose optimization (pose graph) is pose. The known information used is the pose obtained by the Global Navigation System (GNSS), the Laser Radar (LiDAR), and the smart camera (Camera / Visual). The Inertial Measurement Unit (IMU) and wheel speedometer are used to obtain the incremental pose. The fusion of multiple sensors results in a more accurate pose, effectively ensuring global consistency.

[0049] Optionally, the initial pose information is optimized based on the real-time pose and real-time incremental pose collected at different moments to obtain the target pose information, including: constructing a pose residual based on the real-time pose and initial pose information collected at different moments; constructing an incremental pose residual based on the initial pose information at two adjacent moments and the real-time incremental pose corresponding to the two adjacent moments; performing least squares processing on the pose residual and the incremental pose residual to obtain the target pose information.

[0050] In the above steps, the pose residual equation is constructed based on the real-time pose and initial pose information collected at different times. The incremental pose residual equation is constructed based on the initial pose information of two adjacent times and the real-time incremental pose corresponding to the two adjacent times. The pose residual and incremental pose residual are processed using the least squares method to obtain the target pose information. This step can achieve a more accurate pose without considering coordinate system switching, effectively ensuring global consistency.

[0051] Optionally, constructing the incremental pose residual based on the initial pose information of two adjacent moments and the real-time incremental pose corresponding to the two adjacent moments includes: constructing the incremental longitude residual based on the initial position in the initial pose information of two adjacent moments, the real-time incremental longitude, target radius and target eccentricity in the real-time incremental pose corresponding to the two adjacent moments; constructing the incremental latitude residual based on the initial latitude and initial elevation in the initial pose information of two adjacent moments, the real-time incremental latitude, target radius and target eccentricity in the real-time incremental pose corresponding to the two adjacent moments; constructing the incremental elevation residual based on the initial elevation in the initial pose information of two adjacent moments and the real-time incremental elevation in the real-time incremental pose corresponding to the two adjacent moments; constructing the incremental pose residual based on the initial posture in the initial pose information of two adjacent moments and the real-time incremental posture in the real-time incremental pose corresponding to the two adjacent moments; obtaining the incremental pose residual based on the incremental longitude residual, the incremental latitude residual, the incremental elevation residual and the incremental posture residual.

[0052] The target radius and target eccentricity in the above steps can be basic parameters of the earth ellipsoid, wherein the target radius can be the major semi-axis of the earth ellipsoid, and the target eccentricity can be the first eccentricity of the earth ellipsoid, such as Figure 5 As shown, where a represents the major axis of the earth's ellipse, b' represents the minor axis of the earth's ellipse, and e represents the first eccentricity of the earth's ellipse.

[0053] In the above steps, the incremental longitude residual, incremental latitude residual, incremental elevation residual and incremental attitude residual are constructed respectively, and the incremental residual equation is obtained by combining them as shown below:

[0054]

[0055] r Δh =h tj -h ti -Δh sensor ,

[0056]

[0057] In the above formula, b represents the initial latitude at the current moment, h represents the initial altitude at the current moment, and r ΔRepresents the incremental residual between two moments, which refers to the increments at time ti and time tj. Δlon Indicates the incremental longitude residual, r Δlat represents the incremental latitude residual, r Δh Indicates the incremental elevation residual, r Δq Represents the incremental attitude residual. Where (Δl sensor , Δb sensor , Δh sensor ) represents the real-time incremental position represented by the real-time incremental longitude and latitude and real-time incremental elevation at time ti and time tj obtained by the sensor (GNSS, LIDAR, Visual), sensor is the real-time incremental attitude at time ti and time tj obtained by the sensor (GNSS, LIDAR, Visual), expressed as quaternion. tj , b tj , h tj ) is the initial position at time tj represented by the initial latitude, longitude and elevation at time tj, q tj is the initial posture at time tj expressed by quaternion. ti , b ti , h ti ) is the initial position at time ti represented by the initial latitude, longitude and elevation at time ti, q ti is the initial posture at time ti expressed by the quaternion.

[0058] In the above steps, the incremental residual equation is constructed, and then the incremental residual equation is used to optimize the initial pose. After the above processing, the accuracy of the pose is improved without considering the switching of the coordinate system, which effectively ensures global consistency.

[0059] In the technical solution disclosed herein, the acquisition, storage and application of vehicle posture information involved comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0060] According to the disclosed embodiments, the present disclosure provides a vehicle posture processing device for implementing the above-described embodiments and preferably in real-time. Details already described are omitted for clarity. As used below, the term "module" may refer to a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, implementation using hardware, or a combination of software and hardware, is also possible and contemplated.

[0061] Figure 7 is a structural diagram of a vehicle posture processing device according to an embodiment of the present disclosure, such as Figure 7 As shown, the device includes:

[0062] The construction module 72 is used to construct the initial posture information of the vehicle at different times, wherein the initial posture information includes: an initial position and an initial posture, and the initial position is represented by longitude, latitude and altitude.

[0063] The first acquisition module 74 is configured to acquire the real-time position and posture of the vehicle at different times, wherein the real-time position and posture is sensed based on a plurality of sensors on the vehicle.

[0064] The optimization module 76 is used to optimize the initial posture information based on the real-time posture collected at different times to obtain the target posture information.

[0065] In the above-mentioned embodiments of the present disclosure, initial posture information of the vehicle at different times is constructed, and the real-time posture of the vehicle at different times is collected. The initial posture information is optimized based on the real-time posture collected at different times to obtain target posture information, thereby achieving the purpose of optimizing the vehicle posture. It is easy to notice that in the process of constructing the initial posture information and optimizing the initial posture information by sensing the real-time posture using multiple sensors on the vehicle, the coordinates used are longitude and latitude, and there is no need to consider the switching of coordinate systems, which effectively ensures global consistency and solves the problem of the existing technology requiring the replacement of the coordinate origin and constant resetting in vehicle posture optimization.

[0066] Optionally, the optimization module includes: a first residual construction unit, used to construct a posture residual based on the real-time posture and initial posture information collected at different times; an optimization unit, used to perform least squares processing on the posture residual to obtain target posture information.

[0067] Optionally, the first residual construction unit is also used to construct a longitude residual based on the initial position, the real-time longitude, the target radius and the target eccentricity in the real-time posture; to construct a latitude residual based on the initial latitude and initial elevation in the initial posture information, the real-time latitude, the target radius and the target eccentricity in the real-time posture; to construct an elevation residual based on the initial elevation in the initial posture information and the real-time elevation in the real-time posture; to construct a posture residual based on the initial posture in the initial posture information and the real-time posture in the real-time posture; and to obtain a posture residual based on the longitude residual, the latitude residual, the elevation residual and the posture residual.

[0068] Optionally, the device also includes: a second acquisition module, used to collect the real-time incremental posture of the vehicle at different times, wherein the incremental posture is sensed based on at least one sensor on the vehicle; the optimization module is also used to optimize the initial posture information based on the real-time posture and real-time incremental posture collected at different times to obtain target posture information.

[0069] Optionally, the optimization module includes: a first residual construction unit, used to construct a pose residual based on the real-time pose and initial pose information collected at different times; a second residual construction unit, used to construct an incremental pose residual based on the initial pose information of two adjacent moments and the real-time incremental pose corresponding to the two adjacent moments; an optimization unit, used to perform least squares processing on the pose residual and the incremental pose residual to obtain the target pose information.

[0070] Optionally, the second residual construction unit is also used to construct an incremental longitude residual based on the initial position of two adjacent moments, the real-time incremental longitude, target radius and target eccentricity in the real-time incremental posture corresponding to the two adjacent moments; construct an incremental latitude residual based on the initial latitude and initial elevation in the initial posture information of two adjacent moments, the real-time incremental latitude, target radius and target eccentricity in the real-time incremental posture corresponding to the two adjacent moments; construct an incremental elevation residual based on the initial elevation in the initial posture information of two adjacent moments and the real-time incremental elevation in the real-time incremental posture corresponding to the two adjacent moments; construct an incremental posture residual based on the initial posture in the initial posture information of two adjacent moments and the real-time incremental posture in the real-time incremental posture corresponding to the two adjacent moments; and obtain an incremental posture residual based on the incremental longitude residual, the incremental latitude residual, the incremental elevation residual and the incremental posture residual.

[0071] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium, a computer program product and an autonomous driving vehicle.

[0072] Figure 8 A schematic block diagram of an example electronic device 800 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 can also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are provided as examples only and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0073] like Figure 8As shown, the device 800 includes a computing unit 801, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 802 or a computer program loaded from a storage unit 808 into a random access memory (RAM) 803. Various programs and data required for the operation of the device 800 can also be stored in the RAM 803. The computing unit 801, the ROM 802, and the RAM 803 are connected to each other via a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804.

[0074] Various components in device 800 are connected to I / O interface 805, including an input unit 806, such as a keyboard, mouse, etc.; an output unit 807, such as various types of displays, speakers, etc.; a storage unit 808, such as a magnetic disk, optical disk, etc.; and a communication unit 809, such as a network card, modem, wireless communication transceiver, etc. The communication unit 809 allows device 800 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0075] The computing unit 801 can be various general-purpose and / or specialized processing components with processing and computing capabilities. Some examples of the computing unit 801 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units that run machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The computing unit 801 performs the various methods and processes described above, such as the vehicle posture processing method. For example, in some embodiments, the vehicle posture processing method can be implemented as a computer software program that is tangibly contained in a machine-readable medium, such as the storage unit 808. In some embodiments, part or all of the computer program can be loaded and / or installed on the device 800 via the ROM 802 and / or the communication unit 809. When the computer program is loaded into the RAM 803 and executed by the computing unit 801, one or more steps of the vehicle posture processing method described above can be performed. Alternatively, in other embodiments, the computing unit 801 can be configured to perform the vehicle posture processing method by any other appropriate means (e.g., by means of firmware).

[0076] Various embodiments of the systems and techniques described 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), system-on-chip systems (SOCs), programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0077] The program code for implementing the method of the present disclosure can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device so that when the program code is executed by the processor or controller, the functions / operations specified in the flow chart and / or block diagram are implemented. The program code can be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0078] In the context of the present disclosure, a machine-readable medium can be a tangible medium that can contain or store a program for use by or in conjunction with an instruction execution system, device or equipment. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium can include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0079] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer 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 can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the 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 acoustic input, voice input, or tactile input).

[0080] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), and the Internet.

[0081] A computer system may include a client and a server. The client and server are generally remote from each other and typically interact through a communication network. The client-server relationship arises through computer programs running on the respective computers and having a client-server relationship with each other. The server may be a cloud server, a server in a distributed system, or a server integrated with a blockchain.

[0082] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in this disclosure can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved. This is not a limitation herein.

[0083] The above specific embodiments do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure shall be included within the scope of protection of this disclosure.

Claims

1. A method for processing vehicle posture, comprising: Constructing initial posture information of the vehicle at different times, wherein the initial posture information includes: an initial position and an initial posture, and the initial position is represented by longitude, latitude, and altitude; Collecting the real-time position and posture of the vehicle at the different moments, wherein the real-time position and posture are sensed based on a plurality of sensors on the vehicle; Collecting real-time incremental position and posture of the vehicle at the different moments, wherein the real-time incremental position and posture are sensed based on at least one sensor on the vehicle; Based on the initial pose information at two adjacent moments and the real-time incremental pose corresponding to the two adjacent moments, an incremental pose residual is obtained, wherein the incremental pose residual includes an incremental longitude residual, an incremental latitude residual, an incremental elevation residual, and an incremental attitude residual; Based on the real-time poses collected at the different moments and the incremental pose residuals, the initial pose information is optimized to obtain target pose information.

2. The method according to claim 1, wherein Based on the initial pose information of two adjacent moments and the real-time incremental pose corresponding to the two adjacent moments, the incremental pose residual is obtained, including: Constructing the incremental longitude residual based on the initial positions at the two adjacent moments, the real-time incremental longitude in the real-time incremental poses corresponding to the two adjacent moments, the target radius, and the target eccentricity; Constructing the incremental latitude residual based on the initial latitude and initial elevation in the initial pose information at the two adjacent moments, the real-time incremental latitude in the real-time incremental pose corresponding to the two adjacent moments, the target radius, and the target eccentricity; Constructing the incremental elevation residual based on the initial elevation in the initial posture information at the two adjacent moments and the real-time incremental elevation in the real-time incremental posture corresponding to the two adjacent moments; Constructing the incremental posture residual based on the initial posture in the initial posture information of the two adjacent moments and the real-time incremental posture in the real-time incremental posture corresponding to the two adjacent moments; The incremental posture residual is obtained based on the incremental longitude residual, the incremental latitude residual, the incremental elevation residual and the incremental posture residual.

3. The method according to claim 1, wherein Optimizing the initial pose information based on the real-time poses collected at different times and the incremental pose residuals to obtain the target pose information includes: Constructing a pose residual based on the real-time poses collected at the different moments and the initial pose information; Performing least squares processing on the pose residual and the incremental pose residual to obtain the target pose information.

4. The method according to claim 3, wherein: Constructing a pose residual based on the real-time poses collected at the different moments and the initial pose information, including: Constructing a longitude residual based on the initial position, the real-time longitude in the real-time pose, the target radius, and the target eccentricity; constructing a latitude residual based on the initial latitude and initial elevation in the initial pose information, the real-time latitude in the real-time pose, the target radius, and the target eccentricity; constructing an elevation residual based on the initial elevation in the initial pose information and the real-time elevation in the real-time pose; constructing a posture residual based on an initial posture in the initial posture information and a real-time posture in the real-time posture; The posture residual is obtained based on the longitude residual, the latitude residual, the elevation residual and the posture residual.

5. A vehicle posture processing device, comprising: A construction module is used to construct initial posture information of the vehicle at different times, wherein the initial posture information includes: an initial position and an initial posture, and the initial position is represented by longitude, latitude and altitude; A first acquisition module is configured to acquire the real-time position and posture of the vehicle at the different moments, wherein the real-time position and posture are sensed based on a plurality of sensors on the vehicle; A second acquisition module is configured to acquire real-time incremental postures of the vehicle at different moments, wherein the incremental postures are sensed based on at least one sensor on the vehicle; A second residual construction unit is configured to obtain incremental pose residuals based on initial pose information at two adjacent moments and real-time incremental poses corresponding to the two adjacent moments, wherein the incremental pose residuals include incremental longitude residuals, incremental latitude residuals, incremental elevation residuals, and incremental attitude residuals; The optimization unit is used to optimize the initial pose information based on the real-time pose collected at different times and the incremental pose residual to obtain target pose information.

6. The device according to claim 5, wherein The second residual construction unit is further used for: Constructing the incremental longitude residual based on the initial positions at the two adjacent moments, the real-time incremental longitude in the real-time incremental poses corresponding to the two adjacent moments, the target radius, and the target eccentricity; constructing the incremental latitude residual based on the initial latitude and initial elevation in the initial postures at the two adjacent moments, the real-time incremental latitude in the real-time incremental postures corresponding to the two adjacent moments, the target radius, and the target eccentricity; Constructing the incremental elevation residual based on the initial elevation in the initial posture information at the two adjacent moments and the real-time incremental elevation in the real-time incremental posture corresponding to the two adjacent moments; Constructing the incremental posture residual based on the initial posture in the initial posture information of the two adjacent moments and the real-time incremental posture in the real-time incremental posture corresponding to the two adjacent moments; The incremental posture residual is obtained based on the incremental longitude residual, the incremental latitude residual, the incremental elevation residual and the incremental posture residual.

7. The device according to claim 5, wherein The device further comprises: A first residual construction unit is used to construct a posture residual based on the real-time posture collected at different times and the initial posture information; The optimization unit is further used to perform least squares processing on the pose residual and the incremental pose residual to obtain the target pose information.

8. The apparatus according to claim 7, wherein the first residual construction unit is further configured to: Constructing a longitude residual based on the initial position, the real-time longitude in the real-time pose, the target radius, and the target eccentricity; constructing a latitude residual based on the initial latitude and initial elevation in the initial pose information, the real-time latitude in the real-time pose, the target radius, and the target eccentricity; constructing an elevation residual based on the initial elevation in the initial pose information and the real-time elevation in the real-time pose; constructing a posture residual based on an initial posture in the initial posture information and a real-time posture in the real-time posture; The posture residual is obtained based on the longitude residual, the latitude residual, the elevation residual and the posture residual.

9. 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, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 4.

10. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1-4.

11. A computer program product comprising a computer program, which, when executed by a processor, implements the method according to any one of claims 1 to 4.

12. An autonomous driving vehicle comprising the electronic device according to claim 9.

Images