CN120689399A

CN120689399A - Vehicle posture processing method, device, electronic device and autonomous driving vehicle

Info

Publication number: CN120689399A
Application number: CN202510787636.3A
Authority: CN
Inventors: 刘文杰; 程风; 蔡仁澜; 邱笑晨; 徐国梁
Original assignee: Apollo Intelligent Technology Beijing Co Ltd
Current assignee: Apollo Intelligent Technology Beijing Co Ltd
Priority date: 2021-11-26
Filing date: 2021-11-26
Publication date: 2025-09-23
Also published as: CN114170297B; CN114170297A

Abstract

The disclosure provides a vehicle pose processing method, a vehicle pose processing device, electronic equipment and an automatic driving vehicle, and relates to the field of artificial intelligence, in particular to the field of automatic driving. The method comprises the steps of constructing initial pose information of a vehicle at different moments, wherein the initial pose information comprises an initial position and an initial pose, the initial position is expressed by longitude, latitude and elevation, real-time poses of the vehicle at the different moments are collected, the real-time poses are obtained based on sensing of a plurality of sensors on the vehicle, and the initial pose information is optimized based on the real-time poses collected at the different moments, so that target pose information is obtained. The method has the advantages that the initial pose information is constructed, the coordinates used in the process of optimizing the initial pose information by utilizing a plurality of sensors on the vehicle to sense the real-time pose are longitude and latitude, the switching of a coordinate system is not needed to be considered, the global consistency is effectively ensured, and the problems that in the prior art, the origin of the coordinates needs to be replaced and the pose of the vehicle needs to be constantly reset in the process of optimizing the pose of the vehicle are solved.

Description

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

Technical Field

The disclosure relates to the technical field of artificial intelligence, in particular to the technical field of automatic driving, and specifically relates to a vehicle pose processing method, a device, electronic equipment, a storage medium and an automatic driving vehicle.

Background

In the automatic driving operation process of the unmanned automobile, a positioning system is required to output a continuous high-frequency and accurate positioning result in real time so as to ensure the normal operation of the modules such as path planning, perception and the like.

The traditional unmanned positioning module uses a universal transverse ink card bracket network system (UniversalTransverse Mercartor GRID SYSTEM, UTM) and other non-global consistent coordinate systems in the process of fusion of positioning information of a plurality of sensors by adopting graph optimization. Changes occur in the edge coordinate system of the projection band, resulting in a graph that requires constant reset optimization, which is complex in programming and prone to error. Therefore, there is a problem in that the origin of coordinates needs to be replaced and constantly reset in the map optimization.

In view of the above problems, no effective solution has been proposed at present.

Disclosure of Invention

The disclosure provides a vehicle pose processing method, a vehicle pose processing device, electronic equipment, storage media and an automatic driving vehicle.

According to the first aspect of the disclosure, a vehicle pose processing method is provided, and the vehicle pose processing method comprises the steps of constructing initial pose information of a vehicle at different moments, wherein the initial pose information comprises an initial position and an initial pose, the initial position is expressed by longitude, latitude and elevation, acquiring real-time poses of the vehicle at the different moments, wherein the real-time poses are sensed based on a plurality of sensors on the vehicle, and optimizing the initial pose information based on the real-time poses acquired at the different moments to obtain target pose information.

According to a second aspect of the disclosure, a vehicle pose processing device is provided, and the vehicle pose processing device comprises a construction module and an optimization module, wherein the construction module is used for constructing initial pose information of a vehicle at different moments, the initial pose information comprises an initial position and an initial pose, the initial position is expressed by longitude, latitude and altitude, the first acquisition module is used for acquiring real-time poses of the vehicle at different moments, the real-time poses are obtained based on sensing of a plurality of sensors on the vehicle, and the optimization module is used for optimizing the initial pose information based on the real-time poses acquired at different moments to obtain target pose information.

According to a third aspect of the present disclosure, there is provided an electronic device comprising at least one processor, and a memory communicatively coupled 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 processing vehicle pose according to any of the above embodiments.

According to a fourth aspect of the present disclosure, there is provided a non-transitory computer-readable storage medium storing computer instructions for causing a computer to execute the processing method of the vehicle pose according to any of the above-described embodiments.

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

According to a sixth aspect of the present disclosure, there is provided an autonomous vehicle comprising the electronic apparatus of the third aspect described above.

In the embodiment of the disclosure, initial pose information of a vehicle at different moments is constructed, real-time poses of the vehicle at different moments are collected, the initial pose information is optimized based on the real-time poses collected at different moments, target pose information is obtained, and the purpose of optimizing the pose of the vehicle is achieved. It is easy to notice that constructing initial pose information, and in the process of optimizing the initial pose information by utilizing a plurality of sensors on the vehicle to sense the real-time pose, the used coordinates are longitude and latitude, the switching of a coordinate system is not required to be considered, the global consistency is effectively ensured, and the problems that in the prior art, the origin of coordinates needs to be replaced and the pose of the vehicle needs to be constantly reset in the pose optimization of the vehicle are solved.

It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the disclosure, nor is it intended to be used to limit the scope of the disclosure. Other features of the present disclosure will become apparent from the following specification.

Drawings

The drawings are for a better understanding of the present solution and are not to be construed as limiting the present disclosure. Wherein:

FIG. 1 is a schematic illustration of a UTM 6 degree longitude of the prior art;

FIG. 2 is a schematic view of UTM projection coordinates in the prior art;

FIG. 3 is a prior art UTM banding schematic;

FIG. 4 is a flow chart of a method of processing vehicle pose according to an embodiment of the present disclosure;

FIG. 5 is a schematic diagram of an earth ellipsoid parameter of the prior art;

FIG. 6 is a schematic diagram of an alternative pose optimization framework according to an embodiment of the present disclosure;

Fig. 7 is a block diagram of a processing apparatus of a vehicle pose according to an embodiment of the present disclosure;

fig. 8 is a schematic block diagram of an example electronic device used to implement embodiments of the present disclosure.

Detailed Description

Exemplary embodiments of the present disclosure are described below in conjunction with the accompanying drawings, which include various details of the embodiments of the present disclosure to facilitate understanding, and should be considered as merely exemplary. Accordingly, one of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.

In the prior art, the position is expressed by coordinates under UTM. UTM projection is fully called as universal transverse ink card support projection, is an 'equiangular transverse axis cut cylinder projection', and elliptical cylinders cut the earth at two equal-height circles of 80 degrees in south latitude and 84 degrees in north latitude, after projection, two mutually cut warps are not deformed, and the length ratio of the central warp is 0.9996. Dividing the ellipsoid of the earth into a plurality of casting belts according to 6 degrees of the difference, and dividing the six-degree belt from 0 degree meridian to east from west at intervals of 6 degrees of the difference, wherein the belt numbers are sequentially numbered as 1 st belt, 2 nd belt. The projections are respectively carried out according to the zoning method, so that the coordinates of each zone form an independent system, each zone is projected by taking a central meridian (L0) as a vertical axis X, the equatorial projection as a horizontal axis Y, and the intersection point of the two axes is the origin of the coordinates of each zone, as shown in figure 2. The UTM coordinates of each point may be directly represented by X, Y and elevation H, in meters, optimized in the pose map (pose graph).

Since the position variable in the existing pose diagram optimization scheme is the coordinates (X, Y, H) under UTM, as shown by UTM zoning in fig. 3, when the vehicle runs at the boundary line of the zone, zone id (zone number) will switch, resulting in severe UTM coordinate change of the vehicle position and discontinuous position, so that the origin of coordinates needs to be replaced in pose graph, and the reconstruction is needed, and the conversion parameters from the local coordinate system to the global coordinate system need to be calculated.

In order to solve the problems of the prior art that the origin of coordinates needs to be replaced and continuously reset in the vehicle pose optimization, the present disclosure proposes a vehicle pose processing method, which adopts the construction of initial pose information (longitude, latitude and elevation), in the process of optimizing the initial pose information by sensing the real-time poses by utilizing a plurality of sensors on the vehicle, the used coordinates are longitude and latitude, the switching of a coordinate system is not required to be considered, and the global consistency is effectively ensured.

Fig. 4 is a flowchart of a method of processing a vehicle pose according to an embodiment of the present disclosure, as shown in fig. 4, the method including:

In step S401, initial pose information of the vehicle at different moments is constructed, wherein the initial pose information comprises an initial position and an initial pose, and the initial position is expressed by longitude, latitude and elevation.

The initial position and the initial posture information in the above steps can be directly obtained from a route which is planned in advance by the running vehicle, the initial position can be expressed by longitude, latitude and elevation, namely, the initial position can be expressed as (l, b, h), and the posture can be expressed by a four-time element q.

The vehicle in the above steps may be an autonomous vehicle or a general vehicle, wherein the present disclosure functions as an auxiliary driving in the general vehicle.

S402, acquiring real-time poses of the vehicle at different moments, wherein the real-time poses are sensed based on a plurality of sensors on the vehicle.

The real-time pose in the steps comprises a real-time position and a real-time pose, wherein the real-time position can be expressed by longitude, latitude and altitude, and the real-time pose can be expressed by a four-time element number q.

The plurality of sensors in the above steps include, but are not limited to, a global navigation system (Global Navigation SATELLITE SYSTEM, abbreviated as GNSS), a LiDAR system (Light Deteation AND RANGING SYSTEM, abbreviated as LiDAR), a smart camera (INTELLIGENT CAMERA/Visual), and an inertial measurement unit (Inertial Measurement Unit, abbreviated as IMU). The laser radar system is a system integrating laser, a global positioning system (GlobalPositioning System, GPS for short) and an inertial navigation system (InertialNavigation System, INS for short) into a whole, and is used for obtaining point cloud data and generating an accurate digital three-dimensional model, and an Inertial Measurement Unit (IMU) is used for measuring three-axis attitude angles (or angular rates) of an object and an acceleration device, and is generally arranged on the gravity center of the measured object.

Step S403, optimizing the initial pose information based on the real-time poses acquired at different moments to obtain target pose information.

According to the real-time position and the gesture acquired at different moments, an optimization equation is constructed by utilizing the real-time position and the gesture acquired at different moments and initial position and gesture information, and the equation is solved to optimize the gesture information so as to acquire more accurate position and gesture information.

Optionally, optimizing the initial pose information based on real-time poses acquired at different moments to obtain target pose information, wherein the obtaining of the target pose information comprises constructing pose residual errors based on the real-time poses acquired at different moments and the initial pose information, and carrying out least square processing on the pose residual errors to obtain the target pose information.

And constructing position and posture residual errors according to the real-time position and posture information acquired at different moments, and performing least square processing on the constructed position and posture residual errors to obtain more accurate position and posture information. After the processing is performed, the pose accuracy is improved, the switching of a coordinate system is not needed to be considered, and the global consistency is effectively ensured.

The method comprises the steps of selecting real-time pose and initial pose information acquired at different moments, constructing a pose residual error based on the initial position, real-time longitude in the real-time pose, target radius and target eccentricity, constructing a longitude residual error based on initial latitude and initial altitude in the initial pose information, real-time latitude in the real-time pose, target radius and target eccentricity, constructing a latitude residual error based on the initial altitude in the initial pose information and real-time altitude in the real-time pose, constructing a pose residual error based on the initial pose in the initial pose information and the real-time pose in the real-time pose, and obtaining the pose residual error based on the longitude residual error, the latitude residual error, the altitude residual error and the pose residual error.

The target radius and the target eccentricity in the above steps may be basic parameters of an earth ellipsoid, wherein the target radius may be a major half axis of the earth ellipsoid, the target eccentricity may be a first eccentricity of the earth ellipsoid, as shown in fig. 5, wherein a represents a major half axis of the earth ellipsoid, b' represents a minor half axis of the earth ellipse, e represents the first eccentricity of the earth ellipsoid,

In the above steps, longitude residual error, latitude residual error, elevation residual error and attitude residual error are respectively constructed, and the residual error equations are obtained by combining, as follows:

r_h＝h-h_sensor,

In the above formula, r represents a residual term, where r _lon represents a longitude residual, r _lat represents a latitude residual, r _h represents a height Cheng Cancha, and r _q represents a posture residual. Where, (l _sensor,b_sensor,h_sensor) denotes the real-time position represented by the real-time latitude and longitude and real-time elevation obtained by the sensor (GNSS, LIDAR, visual), and q _sensor is the real-time pose obtained by the sensor (GNSS, LIDAR, visual), represented by a quaternion. Where (l, b, h) is the initial position represented by the initial longitude, latitude and elevation, and q is the initial pose represented by the quaternion.

And constructing a residual equation in the steps, optimizing the initial pose by using the residual equation, and improving the accuracy of the pose after the processing, so that the global consistency is effectively ensured without considering the switching of a coordinate system.

Optionally, before optimizing the initial pose information based on the real-time poses to obtain target pose information, the method further comprises the steps of collecting real-time increment poses of the vehicle at different moments, wherein the real-time increment poses are obtained based on at least one sensor on the vehicle in a sensing mode, and optimizing the initial pose information based on the real-time poses and the real-time increment poses collected at different moments to obtain the target pose information.

In an alternative embodiment, as shown in FIG. 6, where a white large circle represents the optimal variable pose, a white small circle represents the pose obtained by a Global navigation System (GNSS), a white triangle represents the pose obtained by a laser radar System (LiDAR), a white rectangle represents the pose obtained by a smart Camera (Camera/Visual), and a black small circle represents the incremental pose obtained from an Inertial Measurement Unit (IMU) and wheel speed meter on the vehicle. The optimized variable of the whole pose optimization (pose graph) is a pose (pose), the known information is a pose obtained by a global navigation system (GNSS), a laser radar system (LiDAR) and an intelligent Camera (Camera/Visual), an incremental pose is obtained by an Inertial Measurement Unit (IMU) and a wheel speed meter, a more accurate pose is obtained by fusing a multi-element sensor, and global consistency is effectively ensured.

Optionally, optimizing initial pose information based on real-time poses and real-time increment poses acquired at different moments to obtain target pose information, wherein the obtaining of the target pose information comprises the steps of constructing pose residual errors based on the real-time poses and the initial pose information acquired at different moments, constructing increment pose residual errors based on the initial pose information at two adjacent moments and the real-time increment poses corresponding to the two adjacent moments, and carrying out least square processing on the pose residual errors and the increment pose residual errors to obtain the target pose information.

In the steps, a pose residual equation is built according to the real-time pose and initial pose information acquired at different moments, an increment pose residual equation is built according to the initial pose information at two adjacent moments and the real-time increment pose corresponding to the two adjacent moments, and the pose residual and the increment pose residual are subjected to least square processing to obtain target pose information. Through the steps, more accurate pose can be obtained without considering the switching of a coordinate system, and the global consistency is effectively ensured.

The method comprises the steps of constructing an increment position residual error based on initial position in initial position information of two adjacent moments, real-time increment longitude in real-time increment position corresponding to the two adjacent moments, target radius and target eccentricity, constructing an increment longitude residual error based on initial latitude and initial elevation in initial position information of the two adjacent moments, real-time increment latitude in real-time increment position corresponding to the two adjacent moments, target radius and target eccentricity, constructing an increment latitude residual error based on initial elevation in initial position information of the two adjacent moments and real-time increment elevation in real-time increment position corresponding to the two adjacent moments, constructing an increment height Cheng Cancha based on initial elevation in initial position information of the two adjacent moments and real-time increment position corresponding to the two adjacent moments, constructing an increment position residual error based on initial position in initial position information of the two adjacent moments and real-time increment position corresponding to the two adjacent moments, and obtaining an increment position residual error based on the increment longitude residual error, the increment elevation residual error and the increment position residual error.

Respectively constructing an increment longitude residual error, an increment latitude residual error, an increment elevation residual error and an increment posture residual error in the steps, and combining to obtain an increment residual error equation, wherein the increment residual error equation is as follows:

r_Δh＝h_tj-h_ti-Δh_sensor,

In the above formula, b represents the initial latitude at the current time, h represents the initial elevation at the current time, r _Δ represents the increment residual error at two times, which means the increment at the time ti and the time tj. Where r _Δlon represents an incremental longitude residual, r _Δlat represents an incremental latitude residual, r _Δh represents an incremental height Cheng Cancha, and r _Δq represents an incremental pose residual. Wherein, (Deltal _sensor,Δb_sensor,Δh_sensor) represents the real-time increment longitude and latitude and real-time increment elevation representation of the time ti and the time tj obtained by the sensor (GNSS, LIDAR, visual), and q _sensor is the real-time increment attitude of the time ti and the time tj obtained by the sensor (GNSS, LIDAR, visual) and is represented by quaternion. Where (l _tj,b_tj,h_tj) is the initial longitude and latitude at time tj and the initial position at time tj represented by the elevation, and q _tj is the initial pose at time tj represented by the quaternion. Where (l _ti,b_ti,h_ti) is the initial position at time ti represented by the initial longitude and latitude and elevation at time ti, and q _ti is the initial pose at time ti represented by the quaternion.

And constructing an incremental residual equation in the steps, optimizing the initial pose by using the incremental residual equation, and improving the accuracy of the pose after the processing, so that the switching of a coordinate system is not needed to be considered, and the global consistency is effectively ensured.

In the technical scheme of the disclosure, the acquisition, storage, application and the like of the related vehicle pose information all conform to the regulations of related laws and regulations, and the public sequence is not violated.

According to an embodiment of the present disclosure, the present disclosure provides a device for processing a vehicle pose, which is used to implement the above embodiment and a preferred real-time manner, and is not described again. As used below, the term "module" may be a combination of software and/or hardware that implements a predetermined function, although the apparatus described in the following embodiments is preferably implemented in software, implementation of hardware, or a combination of software and hardware is also possible and contemplated.

Fig. 7 is a block diagram of a processing apparatus of a vehicle pose according to an embodiment of the present disclosure, as shown in fig. 7, the apparatus including:

The construction module 72 is configured to construct initial pose information of the vehicle at different moments, where the initial pose information includes an initial position and an initial pose, and the initial position is represented by longitude, latitude and altitude.

The first acquisition module 74 is configured to acquire real-time poses of the vehicle at different moments in time, where the real-time poses are sensed based on a plurality of sensors on the vehicle.

The optimizing module 76 is configured to optimize the initial pose information based on the real-time poses acquired at different moments, so as to obtain the target pose information.

Optionally, the optimization module comprises a first residual error construction unit and an optimization unit, wherein the first residual error construction unit is used for constructing a pose residual error based on real-time pose and initial pose information acquired at different moments, and the optimization unit is used for carrying out least square processing on the pose residual error to obtain target pose information.

Optionally, the first residual error constructing unit is further configured to construct a longitude residual error based on the initial position, the real-time longitude in the real-time pose, the target radius and the target eccentricity, construct a latitude residual error based on the initial latitude and the initial altitude in the initial pose information, the real-time latitude in the real-time pose, the target radius and the target eccentricity, construct an elevation residual error based on the initial altitude in the initial pose information and the real-time altitude in the real-time pose, construct a pose residual error based on the initial pose in the initial pose information and the real-time pose in the real-time pose, and obtain a pose residual error based on the longitude residual error, the latitude residual error, the elevation residual error and the pose residual error.

Optionally, the device further comprises a second acquisition module for acquiring real-time increment pose of the vehicle at different moments, wherein the increment pose is sensed by at least one sensor on the vehicle, and an optimization module is further used for optimizing initial pose information based on the real-time pose and the real-time increment pose acquired at different moments to obtain target pose information.

Optionally, the optimization module comprises a first residual error construction unit, a second residual error construction unit and an optimization unit, wherein the first residual error construction unit is used for constructing a residual error of the pose based on the real-time pose and the initial pose information acquired at different moments, the second residual error construction unit is used for constructing an incremental pose residual error based on the initial pose information at two adjacent moments and the real-time incremental pose corresponding to the two adjacent moments, and the optimization unit is used for carrying out least square processing on the residual error of the pose and the incremental pose residual error to obtain target pose information.

The second residual error constructing unit is further used for constructing an increment longitude residual error based on initial positions of two adjacent moments, real-time increment longitudes, target radiuses and target eccentricities in real-time increment postures corresponding to the two adjacent moments, constructing an increment latitude residual error based on initial latitudes and initial altitudes in initial pose information of the two adjacent moments, real-time increment latitudes, target radiuses and target eccentricities in real-time increment postures corresponding to the two adjacent moments, constructing an increment height Cheng Cancha based on initial altitudes in initial pose information of the two adjacent moments and real-time increment elevations in real-time increment pose corresponding to the two adjacent moments, constructing an increment pose residual error based on the initial poses in initial pose information of the two adjacent moments and real-time increment poses corresponding to the two adjacent moments, and obtaining an increment pose residual error based on the increment longitude residual error, the increment latitude residual error, the increment altitude residual error and the increment pose residual error.

According to embodiments of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium, a computer program product, and an autonomous vehicle.

Fig. 8 illustrates a schematic block diagram of an example electronic device 800 that may be used to implement embodiments of the present disclosure. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the disclosure described and/or claimed herein.

As shown in fig. 8, the apparatus 800 includes a computing unit 801 that 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. In the RAM 803, various programs and data required for the operation of the device 800 can also be stored. The computing unit 801, the ROM 802, and the RAM 803 are connected to each other by a bus 804. An input/output (I/O) interface 805 is also connected to the bus 804.

Various components in the device 800 are connected to the I/O interface 805, including an input unit 806, such as a keyboard, a 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 the device 800 to exchange information/data with other devices via a computer network such as the internet and/or various telecommunication networks.

The computing unit 801 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of computing unit 801 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized 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 calculation unit 801 performs the respective methods and processes described above, for example, a processing method of the vehicle pose. For example, in some embodiments, the method of processing vehicle pose may be implemented as a computer software program tangibly embodied on a machine-readable medium, such as the storage unit 808. In some embodiments, part or all of the computer program may be loaded and/or installed onto device 800 via ROM 802 and/or communication unit 809. When a computer program is loaded into the RAM 803 and executed by the computing unit 801, one or more steps of the vehicle pose processing method described above may be performed. Alternatively, in other embodiments, the computing unit 801 may be configured to perform the processing method of the vehicle pose by any other suitable means (e.g., by means of firmware).

Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuit systems, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems On Chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include being implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be a special or general purpose programmable processor, operable to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

Program code for carrying out methods of the present disclosure may be written in any combination of one or more programming languages. These 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 the program code, when executed by the processor or controller, causes the functions/operations specified in the flowchart and/or block diagram to be implemented. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.

In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. The machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, 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 disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

To provide for interaction with a user, the systems and techniques described here 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 a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user, for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback), and input from the user may be received in any form, including acoustic input, speech input, or tactile input.

The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, 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.

The computer system may include a client and a server. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server may be a cloud server, a server of a distributed system, or a server incorporating a blockchain.

It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps recited in the present disclosure may be performed in parallel or sequentially or in a different order, provided that the desired results of the technical solutions of the present disclosure are achieved, and are not limited herein.

The above detailed description should not be taken as limiting the scope of the present disclosure. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present disclosure are intended to be included within the scope of the present disclosure.

Claims

1. A method of processing vehicle pose, comprising:

constructing initial pose information of a vehicle at different moments, wherein the initial pose information comprises an initial position and an initial pose, and the initial position is expressed by longitude, latitude and elevation;

acquiring real-time poses of the vehicle at different moments, wherein the real-time poses are sensed based on a plurality of sensors on the vehicle;

Acquiring real-time increment positions and postures of the vehicle at different moments, wherein the real-time increment positions and postures are sensed based on at least one sensor on the vehicle;

Based on initial pose information of two adjacent moments and real-time increment poses corresponding to the two adjacent moments, obtaining increment pose residual errors, wherein the increment pose residual errors comprise increment longitude residual errors, increment latitude residual errors, increment elevation residual errors and increment pose residual errors;

And optimizing the initial pose information based on the real-time pose collected at different moments and the incremental pose residual errors to obtain target pose information.

2. The method of claim 1, wherein obtaining an incremental pose residual based on initial pose information for two adjacent moments and real-time incremental poses corresponding to the two adjacent moments, comprises:

Constructing an increment longitude residual error based on the initial positions of the adjacent two moments, the real-time increment longitude in the real-time increment pose corresponding to the adjacent two moments, a target radius and a target eccentricity;

Constructing an incremental latitude residual error based on initial latitude and initial elevation in the initial pose information of the adjacent two moments, real-time incremental latitude in the real-time incremental pose corresponding to the adjacent two moments, the target radius and the target eccentricity;

constructing an incremental elevation residual error based on the initial elevation in the initial pose information of the adjacent two moments and the real-time incremental elevation in the real-time incremental poses corresponding to the adjacent two moments;

Constructing an incremental gesture residual error based on the initial gesture in the initial gesture information of the adjacent two moments and the real-time incremental gesture in the real-time incremental gestures corresponding to the adjacent two moments;

And obtaining the increment pose residual error based on the increment longitude residual error, the increment latitude residual error, the increment elevation residual error and the increment pose residual error.

3. The method of claim 1, wherein optimizing the initial pose information based on the real-time pose and the incremental pose residuals acquired at the different moments to obtain the target pose information comprises:

constructing pose residual errors based on the real-time poses acquired at different moments and the initial pose information;

And carrying out least square processing on the pose residual error and the increment pose residual error to obtain the target pose information.

4. The method of claim 3, wherein constructing a pose residual based on the real-time pose acquired at the different moments in time and the initial pose information comprises:

constructing a longitude residual based on the initial position, the real-time longitude in the real-time pose, a target radius and a target eccentricity;

constructing a latitude residual error 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 error based on the initial elevation in the initial pose information and the real-time elevation in the real-time pose;

constructing a gesture residual error based on the initial gesture in the initial gesture information and the real-time gesture in the real-time gesture;

and obtaining the pose residual error based on the longitude residual error, the latitude residual error, the elevation residual error and the pose residual error.

5. A processing device of vehicle pose, comprising:

the construction module is used for constructing initial pose information of the vehicle at different moments, wherein the initial pose information comprises an initial position and an initial pose, and the initial position is expressed by longitude, latitude and elevation;

The first acquisition module is used for acquiring real-time poses of the vehicle at different moments, wherein the real-time poses are obtained based on sensing of a plurality of sensors on the vehicle;

The second acquisition module is used for acquiring real-time increment positions and postures of the vehicle at different moments, wherein the increment positions and postures are sensed and obtained based on at least one sensor on the vehicle;

the second residual error construction unit is used for obtaining an incremental position residual error based on initial position and orientation information of two adjacent moments and real-time incremental position and orientation corresponding to the two adjacent moments, wherein the incremental position and orientation residual error comprises an incremental longitude residual error, an incremental latitude residual error, an incremental elevation residual error and an incremental position and orientation residual error;

And the optimizing unit is used for optimizing the initial pose information based on the real-time pose collected at different moments and the incremental pose residual errors to obtain target pose information.

6. The apparatus of claim 5, wherein the second residual construction unit is further configured to:

Constructing an incremental latitude residual error based on initial latitude and initial elevation in the initial pose of the adjacent two moments, real-time incremental latitude in the real-time incremental pose corresponding to the adjacent two moments, the target radius and the target eccentricity;

7. The apparatus of claim 5, wherein the apparatus further comprises:

the first residual error construction unit is used for constructing a residual error of the pose based on the real-time pose acquired at different moments and the initial pose information;

and the optimizing unit is further used for carrying out least square processing on the pose residual error and the increment pose residual error to obtain the target pose information.

8. The apparatus of claim 7, the first residual construction unit further to:

9. An electronic device, comprising:

at least one processor, and

A memory communicatively coupled 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 any one of claims 1-4.

10. A non-transitory computer readable storage medium storing computer instructions for causing the computer to perform the method of 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 of claims 1-4.

12. An autonomous vehicle comprising the electronic device of claim 9.