A vehicle positioning method, device, electronic equipment, storage medium and vehicle

Abstract

The application discloses a vehicle positioning method and device, electronic equipment, storage medium and vehicle. The method comprises the following steps: acquiring position information of a vehicle in a world coordinate system; loading a local map based on the position information, and converting the local map to a local coordinate system; constructing a map likelihood graph and a GNSS likelihood graph in the local coordinate system; wherein the map likelihood graph comprises a drivable area distinguishing a heading, and the GNSS likelihood graph is constructed based on GNSS information in a historical time window; determining a dead reckoning trajectory of the vehicle based on dead reckoning; and obtaining an optimal vehicle pose by maximum likelihood estimation based on the dead reckoning trajectory, the map likelihood graph and the GNSS likelihood graph. The method combines GNSS, dead reckoning and map information, and performs lane-level positioning through maximum likelihood estimation, and does not depend on the quality of GNSS signals, so that lane-level positioning accuracy can be realized in tunnel, viaduct and other scenes, and good generalization ability can be achieved in various scenes.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of autonomous driving technology, and in particular to a vehicle positioning method, device, electronic device, storage medium and vehicle. Background Technology

[0002] Positioning technology is a crucial technology in intelligent vehicle driving, providing the vehicle's position and orientation. Among intelligent vehicle positioning technologies, Global Navigation Satellite System (GNSS) technology is the most widely used.

[0003] Current lane-level positioning generally relies on high-precision GNSS positioning. However, in scenarios such as tunnels and overpasses, GNSS positioning accuracy cannot be guaranteed due to signal blockage and reflection. Summary of the Invention

[0004] This invention provides a vehicle positioning method, device, electronic device, storage medium, and vehicle to solve the problem that existing GNSS positioning cannot guarantee positioning accuracy in scenarios such as tunnels and elevated roads due to signal blockage and reflection.

[0005] According to one aspect of the present invention, a vehicle positioning method is provided, comprising:

[0006] Obtain the vehicle's position information in the world coordinate system;

[0007] A local map is loaded based on the location information, and the local map is converted to a local coordinate system;

[0008] A map likelihood map and a GNSS likelihood map are constructed in the local coordinate system; wherein, the map likelihood map includes a workable area that distinguishes flight paths, and the GNSS likelihood map is constructed based on GNSS information within a historical time window;

[0009] The dead reckoning trajectory of the vehicle is determined based on dead reckoning.

[0010] Based on the dead reckoning trajectory, the map likelihood diagram, and the GNSS likelihood diagram, the optimal vehicle pose is obtained using maximum likelihood estimation.

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

[0012] The GNSS module is used to obtain the vehicle's position information in the world coordinate system;

[0013] The conversion module is used to load a local map based on the location information and convert the local map to a local coordinate system.

[0014] A construction module is used to construct a map likelihood map and a GNSS likelihood map in the local coordinate system; wherein, the map likelihood map includes a workable area that distinguishes flight paths, and the GNSS likelihood map is constructed based on GNSS information within a historical time window;

[0015] The determination module is used to determine the dead reckoning trajectory of the vehicle based on dead reckoning.

[0016] The maximum likelihood estimation module is used to obtain the optimal vehicle pose using maximum likelihood estimation based on the dead reckoning trajectory, the map likelihood diagram, and the GNSS likelihood diagram.

[0017] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0018] At least one processor;

[0019] and a memory communicatively connected to the at least one processor;

[0020] The memory stores a computer program that can be executed by the at least one processor, which is then executed by the at least one processor to enable the at least one processor to perform the vehicle positioning method according to any embodiment of the present invention.

[0021] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the vehicle positioning method according to any embodiment of the present invention.

[0022] According to another aspect of the present invention, a vehicle is provided, including one or more of an inertial measurement unit, a wheel speedometer, and a vehicle speedometer, the vehicle further including electronic devices;

[0023] The inertial measurement unit is used to measure the vehicle's inertial navigation attitude information;

[0024] The wheel speed meter is used to collect wheel speed information;

[0025] The speedometer is used to collect vehicle speed information;

[0026] The electronic device is used to perform the vehicle positioning method according to any embodiment of the present invention.

[0027] The technical solution of this invention involves acquiring the vehicle's position information in a world coordinate system; loading a local map based on the position information and converting the local map to a local coordinate system; constructing a map likelihood map and a GNSS likelihood map in the local coordinate system; wherein the map likelihood map includes a navigable area that distinguishes the course, and the GNSS likelihood map is constructed based on GNSS information within a historical time window; determining the vehicle's dead reckoning trajectory based on dead reckoning; and obtaining the optimal vehicle pose using maximum likelihood estimation based on the dead reckoning trajectory, the map likelihood map, and the GNSS likelihood map. This solves the problem that existing GNSS positioning in tunnels, elevated roads, and other scenarios cannot guarantee positioning accuracy due to signal obstruction and reflection, achieving lane-level positioning accuracy independent of GNSS signal quality, and demonstrating good generalization ability in various scenarios.

[0028] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0029] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0030] Figure 1 This is a flowchart illustrating a vehicle positioning method provided in Embodiment 1 of the present invention;

[0031] Figure 2 This is a schematic diagram of the map likelihood diagram in a vehicle positioning method provided in Embodiment 1 of the present invention;

[0032] Figure 3 This is a schematic diagram of a GNSS likelihood diagram in a vehicle positioning method provided in Embodiment 1 of the present invention;

[0033] Figure 4 This is a schematic diagram illustrating the use of maximum likelihood estimation in a vehicle positioning method according to Embodiment 1 of the present invention.

[0034] Figure 5 This is a flowchart illustrating a vehicle positioning method provided in Embodiment 2 of the present invention;

[0035] Figure 6 This is an example flowchart of a vehicle positioning method provided in Embodiment 3 of the present invention;

[0036] Figure 7 This is a schematic diagram of the structure of a vehicle positioning device provided in Embodiment 4 of the present invention.

[0037] Figure 8 This is a schematic diagram of the electronic device used in the vehicle positioning method according to an embodiment of the present invention;

[0038] Figure 9 This is a structural schematic diagram of a vehicle provided in Embodiment Six of the present invention. Detailed Implementation

[0039] To enable those skilled in the art to better understand the present invention, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are merely some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention. It should be understood that the various steps described in the method embodiments of the present invention can be performed in different orders and / or in parallel. Furthermore, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present invention is not limited in this respect.

[0040] The term "comprising" and its variations as used herein are open-ended inclusions, meaning "including but not limited to". The term "based on" means "at least partially based on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". Definitions of other terms will be given in the description below.

[0041] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0042] It should be noted that the terms "a" and "a plurality of" used in this invention are illustrative rather than restrictive. Those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0043] The names of the messages or information exchanged between the multiple devices in the embodiments of the present invention are for illustrative purposes only and are not intended to limit the scope of these messages or information.

[0044] It's important to understand that GNSS positioning is based on satellite positioning technology and is divided into point positioning, differential GPS satellite positioning, and PTK GPS positioning. Among them, point positioning provides a positioning accuracy of 3 to 10 meters, differential GPS provides a positioning accuracy of 0.5 to 2 meters, and PTK GPS provides centimeter-level positioning accuracy.

[0045] According to the accuracy of positioning, positioning can be divided into the following types: (1) Road-level positioning, with an accuracy on the order of 10m, commonly used in the navigation field; (2) Lane-level positioning, with an accuracy on the order of 1m, commonly used in lane-level navigation and advanced driver assistance systems (ADAS); (3) High-precision positioning, with an accuracy on the order of 0.1m, commonly used in L2 to L4 level intelligent driving. Among them, lane-level positioning, compared with road-level positioning, improves the positioning accuracy of vehicles to within the lane, making applications such as lane-level navigation and ADAS a reality.

[0046] Example 1

[0047] Figure 1 This is a flowchart illustrating a vehicle positioning method according to Embodiment 1 of the present invention. This method is applicable to lane-level vehicle positioning and can be executed by a vehicle positioning device. This device can be implemented in software and / or hardware and is generally integrated into an electronic device. In this embodiment, the electronic device includes, but is not limited to, a control device. The control device can be a vehicle controller, etc.

[0048] like Figure 1 As shown, the vehicle positioning method provided in Embodiment 1 of the present invention includes the following steps:

[0049] S110. Obtain the vehicle's position information in the world coordinate system.

[0050] Here, a world coordinate system W is defined, which maintains a fixed relationship with the actual geographical location. For example, a geocentric coordinate system can be used; for instance, the world coordinate system can be the WGS84 coordinate system. Location information can include the current vehicle's latitude, longitude, and altitude coordinates, along with the corresponding confidence level. The latitude, longitude, and altitude coordinates are three-dimensional coordinates, including longitude, latitude, and altitude.

[0051] In this embodiment, obtaining the vehicle's position information in the world coordinate system can be understood as obtaining the vehicle's position information in the WGS84 coordinate system. Position information can be obtained through a GNSS module, which can acquire position information based on satellite positioning technology.

[0052] S120. Load a local map based on the location information and convert the local map to a local coordinate system.

[0053] This allows loading a suitable local map onto a satellite map. A local coordinate system is defined, with its origin at a reference point Porigin in a world coordinate system W. For example, the Local Frame–East-North-Up (ENU) coordinate system can be used as the local coordinate system.

[0054] In this embodiment, a corresponding local map can be loaded from a satellite map based on the latitude, longitude, and altitude coordinates in the location information. The method of loading the local map is not limited here.

[0055] Converting a local map to a local coordinate system can be understood as converting from a world coordinate system to a local coordinate system. For example, this could be a conversion from the WGS84 coordinate system to the ENU coordinate system. The specific conversion process is not limited here.

[0056] S130. Construct a map likelihood map and a GNSS likelihood map in the local coordinate system; wherein, the map likelihood map includes a workable area that distinguishes the heading, and the GNSS likelihood map is constructed based on GNSS information within a historical time window.

[0057] In the local coordinate system, a likelihood map can be constructed by combining lane lines and distinguishing flight directions, and the likelihood function corresponding to the map likelihood map is used as the first likelihood function. In the local coordinate system, a GNSS likelihood map including GNSS landing points can be constructed, and the likelihood function corresponding to the GNSS likelihood map is used as the second likelihood function.

[0058] Specifically, the construction of a map likelihood diagram can include: constructing a drivable region in a local coordinate system xoy based on lane lines; the drivable region is the area where vehicles can travel; and combining the drivable region with the heading allows for the construction of a drivable region that distinguishes different headings, thus obtaining the map likelihood diagram. For example... Figure 2 As shown, Figure 2 This is a schematic diagram of the map likelihood diagram in a vehicle positioning method provided in Embodiment 1 of the present invention.

[0059] The historical time window can be understood as a time interval within the past period obtained through the GNSS module. GNSS information can be understood as the vehicle's location information obtained through the GNSS module, including latitude, longitude, and altitude coordinates and their corresponding confidence levels.

[0060] Specifically, the construction method of GNSS likelihood diagram can include: transforming GNSS information within a historical time window into a local coordinate system, constructing GNSS landing points in the local coordinate system, taking the value of the current vehicle's attitude pose within the GNSS landing point as the first value, and taking the value of the vehicle outside the GNSS landing point as the second value, thereby constructing the GNSS likelihood diagram. For example... Figure 3 As shown, Figure 3 This is a schematic diagram of the GNSS likelihood diagram in a vehicle positioning method provided in Embodiment 1 of the present invention.

[0061] In this embodiment, the constructed map likelihood map and GNSS likelihood map can be used to estimate the current pose state of the vehicle.

[0062] S140. Determine the dead reckoning trajectory of the vehicle based on dead reckoning.

[0063] Dead reckoning (DR) calculates the vehicle's position from its previous location using motion data collected by sensors such as inertial measurement units (IMUs), wheel speedometers, and vehicle speedometers, providing relative positioning information. Its limitation is that the positioning error accumulates and increases with the calculated distance.

[0064] The dead reckoning trajectory can be the vehicle's historical driving trajectory, and it can be composed of multiple vehicle poses. The vehicle pose can include the vehicle's current position and attitude.

[0065] It should be noted that dead reckoning is performed within the dead reckoning coordinate system, which is defined by the DR (Dead Reach) and can generally be taken as the origin when the vehicle pose is obtained in the first frame of the DR observation.

[0066] In this embodiment, the vehicle pose TDB obtained through dead reckoning is in the DR coordinate system. T represents transformation, D represents the dead reckoning coordinate system, and B represents the vehicle coordinate system. The vehicle coordinate system can also be called the vehicle body coordinate system, which is fixed at a certain fixed position of the vehicle, such as the center of the rear axle.

[0067] Furthermore, the step of determining the dead reckoning trajectory of the vehicle based on dead reckoning includes: obtaining the relative pose of the vehicle through dead reckoning in the dead reckoning coordinate system based on at least one of wheel speed information, vehicle speed information, and vehicle inertial navigation attitude information; obtaining the relative poses of multiple vehicles within a historical time window; and converting the relative poses of multiple vehicles to the carrier coordinate system to obtain the dead reckoning trajectory of the vehicle.

[0068] Vehicle speed information can be obtained through the vehicle's speedometer; wheel speed information can be obtained through the vehicle's wheel speedometer; vehicle inertial navigation attitude information can be obtained through the vehicle's inertial measurement unit, which may include the vehicle's attitude angle and yaw angle. The relative poses of multiple vehicles within a historical time window can be understood as the relative poses of multiple vehicles within a past time window (Time-interval), i.e., dead reckoning points.

[0069] For example, the vehicle pose sequence in the DR coordinate system within a time-interval window over the past period is as follows:

[0070] SET TrjLocal ={TDB1, TDB2, TDB3,..., TDB n}

[0071] Among them, TDB i This represents the vehicle pose in the DR coordinate system at the i-th time point.

[0072] The vehicle pose sequence in the DR coordinate system can be transformed to the carrier coordinate system. The specific process includes: obtaining the TDB. n The inverse of TBnD is multiplied by the vehicle pose sequence in the DR coordinate system within the time window, and then converted into the vehicle pose sequence in the carrier coordinate system as follows:

[0073] SET TrjBody ={BP1, BP2, BP3,…, BP n}

[0074] Where BP1 = TBnB1, BP2 = TBnB2, BP3 = TBnB3, ..., BPn = TBnBn. The vehicle pose sequence in the carrier coordinate system can constitute the dead reckoning trajectory of the vehicle.

[0075] S150. Based on the dead reckoning trajectory, the map likelihood diagram, and the GNSS likelihood diagram, the optimal vehicle pose is obtained using maximum likelihood estimation.

[0076] The optimal vehicle pose can be the best vehicle pose among the multiple estimated vehicle poses.

[0077] In this embodiment, the dead reckoning trajectory in the carrier coordinate system is converted into the vehicle pose in the local coordinate system; the vehicle pose in the local coordinate system is used as the variable of the first likelihood function and the second likelihood function; a target likelihood function is constructed based on the first likelihood function corresponding to the map likelihood map and the second likelihood function corresponding to the GNSS likelihood map, and the vehicle pose is used as the variable of the target likelihood function; the optimal vehicle pose can be obtained by using maximum likelihood estimation on the target likelihood function.

[0078] Figure 4 This is a schematic diagram illustrating the use of maximum likelihood estimation in a vehicle positioning method according to Embodiment 1 of the present invention. Figure 4 As shown, by combining the vehicle's dead reckoning trajectory with the GNSS likelihood map and the map likelihood map, the optimal vehicle pose can be obtained using the maximum likelihood trajectory.

[0079] The vehicle positioning method provided in Embodiment 1 of this invention first acquires the vehicle's position information in a world coordinate system; secondly, it loads a local map based on the position information and transforms the local map to a local coordinate system; then, it constructs a map likelihood map and a GNSS likelihood map in the local coordinate system; wherein, the map likelihood map includes a navigable area distinguishing flight paths, and the GNSS likelihood map is constructed based on GNSS information within a historical time window; subsequently, it determines the vehicle's dead reckoning trajectory based on dead reckoning; finally, based on the dead reckoning trajectory, the map likelihood map, and the GNSS likelihood map, it uses maximum likelihood estimation to obtain the optimal vehicle pose. This method combines GNSS, dead reckoning, and map information for lane-level positioning, is independent of GNSS signal quality, and can still achieve lane-level positioning accuracy in scenarios such as tunnels and elevated roads, demonstrating good generalization ability across various scenarios.

[0080] Based on the above embodiments, modified embodiments of the above embodiments are proposed. It should be noted that, in order to keep the description brief, only the differences from the above embodiments are described in the modified embodiments.

[0081] Furthermore, the location information includes the current vehicle's latitude, longitude, and elevation coordinates, as well as confidence levels. The latitude, longitude, and elevation coordinates include longitude, latitude, and elevation, and the confidence levels include the confidence levels corresponding to longitude, latitude, and elevation.

[0082] Elevation refers to the distance from a point along the vertical line to the basal surface.

[0083] In one embodiment, loading a local map based on the location information and converting the local map to a local coordinate system includes: loading a map within a preset radius centered on the latitude, longitude, and altitude coordinates on a satellite map as a local map; and converting the local map to a local coordinate system with the latitude, longitude, and altitude coordinates as the origin.

[0084] The preset radius can be a pre-set radius value. For example, the preset radius can be 200 meters. On the satellite map, a circle is drawn with the latitude, longitude and altitude coordinates as the center point and the circle area is used as a local map.

[0085] Example 2

[0086] Figure 5 This is a flowchart illustrating a vehicle positioning method according to Embodiment 2 of the present invention, which is an optimization based on the above embodiments. In this embodiment, the process of constructing a map likelihood diagram and a GNSS likelihood diagram in the local coordinate system is specified. For details not covered in this embodiment, please refer to Embodiment 1.

[0087] like Figure 5 As shown, the vehicle positioning method provided in Embodiment 2 of the present invention includes the following steps:

[0088] S210. Obtain the vehicle's position information in the world coordinate system.

[0089] S220. Load a local map based on the location information and convert the local map to a local coordinate system.

[0090] S230. In the local coordinate system, construct a drivable area and construct a map likelihood diagram in combination with the lane driving direction.

[0091] The driving direction of a lane can be the direction of travel corresponding to that lane. The drivable area can be constructed based on lane lines, which can be three-lane or two-lane lane lines; there are no specific restrictions here.

[0092] Furthermore, a drivable area is constructed, and a map likelihood diagram is constructed in conjunction with the drivable heading, including: constructing a closed drivable area with lane lines as boundaries; and assigning values ​​to the drivable area with lane headings to obtain a map likelihood diagram.

[0093] Within the lane lines, the area can be considered a drivable area. By combining the lane heading values ​​with the drivable area, a drivable area that distinguishes different headings can be constructed. This drivable area constitutes the map likelihood diagram.

[0094] S240. In the local coordinate system, construct GNSS landing points based on GNSS information within the historical window, and construct a GNSS likelihood diagram based on the GNSS landing points.

[0095] The GNSS information includes multiple numerical pairs, each consisting of a coordinate point and an average confidence level. The coordinate point is the coordinate corresponding to the latitude, longitude, and altitude coordinates in the location information obtained by the GNSS module after transformation to the local coordinate system. The average confidence level is the average of the confidence levels corresponding to the longitude and latitude in the location information.

[0096] For example, after converting the GNSS information within a past time window (i.e., the history window) to the local coordinate system, it is stored in a queue in the following form:

[0097] SET GNSS ={(TL G1 STD G1 ), (TL G2 STD G2 ), ..., (TL Gn STD Gn )}

[0098] Among them, TL Gi STD represents the coordinate value of the i-th latitude, longitude, and altitude coordinates in the location information acquired by the GNSS module, transformed into the corresponding coordinate value in the local coordinate system. G1 This represents the average confidence level for longitude and latitude in the location information.

[0099] Furthermore, GNSS landing points are constructed based on GNSS information within the historical window, and a GNSS likelihood map is constructed based on the GNSS landing points, including: constructing circles with each coordinate point as the center point and the average confidence level as the radius as the GNSS landing point; and constructing a GNSS likelihood map by taking a first value for the vehicle's pose in the local coordinate system within the GNSS landing point and a second value for the vehicle's pose in the local coordinate system outside the GNSS landing point.

[0100] The number of GNSS landing points can be multiple. The first value can be 0, and the second value can be 1.

[0101] For example, such as Figure 3 As shown, the GNSS landing point is a circular area centered on the coordinate points included in the GNSS information, with the corresponding average confidence level as the radius.

[0102] The method for determining each GNSS landing point is the same. Taking a GNSS landing point as an example, we take a coordinate point in the GNSS information as the center point and draw a circle with the average confidence level corresponding to that coordinate point as the radius. This will give us a circular area as a GNSS landing point.

[0103] S250, Determine the dead reckoning trajectory of the vehicle based on dead reckoning.

[0104] S260. Based on the dead reckoning trajectory, the map likelihood diagram, and the GNSS likelihood diagram, the optimal vehicle pose is obtained using maximum likelihood estimation.

[0105] This invention provides a vehicle positioning method according to Embodiment 2, comprising: acquiring the vehicle's position information in a world coordinate system; loading a local map based on the position information and converting the local map to a local coordinate system; constructing a drivable area in the local coordinate system and constructing a map likelihood map in conjunction with the drivable heading of the lane; constructing GNSS landing points in the local coordinate system based on GNSS information within a historical window and constructing a GNSS likelihood map based on the GNSS landing points; determining the dead reckoning trajectory of the vehicle based on dead reckoning; and obtaining the optimal vehicle pose using maximum likelihood estimation based on the dead reckoning trajectory, the map likelihood map, and the GNSS likelihood map. This method uses lane edges to construct a drivable area and combines it with the drivable heading to construct a map likelihood map for estimating the vehicle's current pose. This method uses GNSS information within a historical time window to construct a GNSS likelihood map for estimating the vehicle's current pose. It can achieve lane-level positioning accuracy even in scenarios such as tunnels and elevated roads.

[0106] Furthermore, the step of obtaining the optimal vehicle pose using maximum likelihood estimation based on the dead reckoning trajectory, the map likelihood map, and the GNSS likelihood map includes: converting the relative pose of the vehicle on the dead reckoning trajectory into the vehicle pose in a local coordinate system; using the vehicle pose in the local coordinate system as a variable of the first likelihood function corresponding to the map likelihood map, and using the vehicle pose in the local coordinate system as a variable of the second likelihood function corresponding to the GNSS likelihood map to construct a target likelihood function; constructing the target likelihood function based on the first likelihood function and the second likelihood function; and performing maximum likelihood estimation on the target likelihood function to obtain the optimal vehicle pose.

[0107] In this embodiment, the expression for the first likelihood function is as follows:

[0108]

[0109] Among them, F map Let LP represent the first likelihood function. i H represents the vehicle pose in the local coordinate system. i H(LP) represents the heading angle corresponding to the vehicle's pose in the local coordinate system. i ) represents the LP on the map likelihood map. i The corresponding heading angle, Hthlres represents the preset angle threshold, which can be 90 degrees.

[0110] In this embodiment, the expression for the second likelihood function is as follows:

[0111]

[0112] Among them, F GNSS Let LP represent the second likelihood function. i This represents the vehicle's pose within the local coordinate system.

[0113] In this embodiment, the expression for the target likelihood function is as follows:

[0114] F(TLB) = SUM{F map (TLB*BP i )+F GNSS (TLB*BP i )}

[0115] Where TLB is the variable in the objective likelihood function, i.e., the vehicle pose, and BP... i This represents the relative pose of the vehicle at the i-th trajectory point on the dead reckoning trajectory, i.e., in the vehicle coordinate system, denoted by TLB*BP. i This represents converting trajectory points on the vehicle's dead reckoning trajectory into the vehicle's pose in a local coordinate system, TLB*BP. i It can be used as a variable in the first and second likelihood functions, and SUM{} represents summation.

[0116] In this embodiment, the maximum likelihood estimation process can be represented as follows:

[0117] TLB -MAX =argmin{F(TLB)}

[0118] Among them, TLB -MAX This represents the optimal vehicle pose obtained from the maximum likelihood estimation.

[0119] Example 3

[0120] Based on the technical solutions of the above embodiments, this invention provides a specific implementation method.

[0121] As one specific implementation method of this embodiment. Figure 6 This is an example flowchart of a vehicle positioning method provided in Embodiment 3 of the present invention, as follows: Figure 6 As shown, the method includes the following steps:

[0122] The system obtains vehicle location information from GNSS; loads the corresponding local map based on the vehicle location information; constructs the operable area in the local coordinate system, i.e., constructs the map likelihood map; performs GNSS preprocessing based on GNSS, i.e., constructs the GNSS likelihood map in the local coordinate system; calculates the vehicle's dead reckoning trajectory based on IMU and wheel / vehicle speed; and performs maximum likelihood estimation based on the operable area, the GNSS likelihood map obtained from GNSS preprocessing, and the dead reckoning trajectory obtained from dead reckoning to obtain the location output.

[0123] Example 4

[0124] Figure 7 This is a schematic diagram of a vehicle positioning device provided in Embodiment 4 of the present invention. The device is applicable to lane-level positioning of vehicles. The device can be implemented by software and / or hardware and is generally integrated into the vehicle's controller.

[0125] like Figure 7 As shown, the device includes: a GNSS module 110, a conversion module 120, a construction module 130, a determination module 140, and a maximum likelihood estimation module 150.

[0126] GNSS module 110 is used to acquire the vehicle's position information in the world coordinate system;

[0127] The conversion module 120 is used to load a local map based on the location information and convert the local map to a local coordinate system.

[0128] The construction module 130 is used to construct a map likelihood map and a GNSS likelihood map in the local coordinate system; wherein, the map likelihood map includes a workable area that distinguishes the heading, and the GNSS likelihood map is constructed based on GNSS information within a historical time window;

[0129] The determination module 140 is used to determine the dead reckoning trajectory of the vehicle based on dead reckoning.

[0130] The maximum likelihood estimation module 150 is used to obtain the optimal vehicle pose using maximum likelihood estimation based on the dead reckoning trajectory, the map likelihood map, and the GNSS likelihood map.

[0131] In this embodiment, the device first acquires the vehicle's position information in the world coordinate system through the GNSS module 110; then, the conversion module 120 loads a local map based on the position information and converts the local map to the local coordinate system; next, the construction module 130 constructs a map likelihood map and a GNSS likelihood map in the local coordinate system; wherein, the map likelihood map includes a runaway area that distinguishes the heading, and the GNSS likelihood map is constructed based on GNSS information within a historical time window; then, the determination module 140 determines the vehicle's dead reckoning trajectory based on dead reckoning; finally, the maximum likelihood estimation module 150 uses maximum likelihood estimation to obtain the optimal vehicle pose based on the dead reckoning trajectory, the map likelihood map, and the GNSS likelihood map.

[0132] This embodiment provides a vehicle positioning device that can achieve lane-level positioning accuracy in scenarios such as tunnels and elevated roads, regardless of the quality of GNSS signals, and has good generalization ability in various scenarios.

[0133] Furthermore, the location information includes the current vehicle's latitude, longitude, and elevation coordinates, as well as confidence levels. The latitude, longitude, and elevation coordinates include longitude, latitude, and elevation, and the confidence levels include the confidence levels corresponding to longitude, latitude, and elevation.

[0134] Furthermore, the conversion module 120 is specifically used to: load a map within a preset radius centered on the latitude, longitude, and altitude coordinates as a local map on the satellite map; and convert the local map to a local coordinate system with the latitude, longitude, and altitude coordinates as the origin.

[0135] Furthermore, the building module 130 includes a first building unit and a second building unit:

[0136] The first construction unit is used to: construct a drivable area in the local coordinate system, and construct a map likelihood diagram in combination with the drivable lane routes;

[0137] The second construction unit is used to: construct GNSS landing points based on GNSS information within the historical window in the local coordinate system, and construct a GNSS likelihood map based on the GNSS landing points;

[0138] The GNSS information includes multiple numerical pairs, each consisting of a coordinate point and an average confidence level. The coordinate point is the coordinate corresponding to the latitude, longitude, and altitude coordinates in the location information obtained by the GNSS module after transformation to the local coordinate system. The average confidence level is the average of the confidence levels corresponding to the longitude and latitude in the location information.

[0139] Based on the above optimizations, the first building unit is specifically used for:

[0140] A closed driving area is constructed using lane lines as boundaries;

[0141] The likelihood map is obtained by assigning values ​​to the drivable area based on the lane direction.

[0142] Based on the above optimizations, the second building unit is specifically used for:

[0143] A circle is constructed with each of the coordinate points as the center point and the average confidence level as the radius to serve as the GNSS landing point;

[0144] The GNSS likelihood diagram is constructed by taking the vehicle's pose in the local coordinate system as the first value within the GNSS landing point and the vehicle's pose in the local coordinate system as the second value outside the GNSS landing point.

[0145] Furthermore, the determination module 140 is specifically used to: obtain the relative pose of the vehicle through dead reckoning based on at least one of wheel speed information, vehicle speed information, and vehicle inertial navigation attitude information in the dead reckoning coordinate system; obtain the relative poses of multiple vehicles within a historical time window; and convert the relative poses of multiple vehicles to the carrier coordinate system to obtain the dead reckoning trajectory of the vehicle.

[0146] Furthermore, the maximum likelihood estimation module is specifically used for: converting the relative pose of the vehicle on the dead reckoning trajectory into the vehicle pose in a local coordinate system; using the vehicle pose in the local coordinate system as a variable of the first likelihood function corresponding to the map likelihood map, and using the vehicle pose in the local coordinate system as a variable of the second likelihood function corresponding to the GNSS likelihood map to construct a target likelihood function; constructing the target likelihood function based on the first and second likelihood functions; and performing maximum likelihood estimation on the target likelihood function to obtain the optimal vehicle pose.

[0147] The vehicle positioning device described above can execute the vehicle positioning method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of executing the method.

[0148] Example 5

[0149] Figure 8 A schematic diagram of an electronic device 10 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as vehicle controllers, laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0150] like Figure 8As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 may also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0151] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0152] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as vehicle positioning methods.

[0153] In some embodiments, the vehicle positioning method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the vehicle positioning method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the vehicle positioning method by any other suitable means (e.g., by means of firmware).

[0154] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0155] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0156] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0157] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0158] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0159] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0160] Example 6

[0161] Figure 9 This is a structural schematic diagram of a vehicle provided in Embodiment Six of the present invention, as shown below. Figure 9 As shown, the vehicle includes one or more of an inertial measurement unit 10, a wheel speedometer 20, and a vehicle speedometer 30, and the vehicle also includes electronic equipment 40;

[0162] The inertial measurement unit 10 is used to measure the vehicle's inertial navigation attitude information;

[0163] Wheel speed gauge 20 is used to collect wheel speed information;

[0164] Speedometer 30 is used to collect vehicle speed information;

[0165] Electronic device 40 is used to perform the vehicle positioning method according to any embodiment of the present invention.

[0166] In this system, the inertial measurement unit 10, wheel speedometer 20, and vehicle speedometer 30 can all function as sensors. A sensor coordinate system S, also known as the observation coordinate system, is defined. The measurement data acquired by the sensors—namely, vehicle inertial navigation attitude information, wheel speed information, and vehicle speed information—are all based on the sensor coordinate system. A fixed transformation relationship TBS, or extrinsic parameter, exists between the sensor coordinate system and the vehicle coordinate system (i.e., the vehicle body coordinate system).

[0167] The vehicle provided in Embodiment Six of the present invention, by executing a vehicle positioning method, can achieve lane-level positioning accuracy in scenarios such as tunnels and elevated roads without relying on the quality of GNSS signals, and has good generalization ability in various scenarios.

[0168] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0169] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A vehicle positioning method, characterized in that, The method includes: Obtain the vehicle's position information in the world coordinate system; A local map is loaded based on the location information, and the local map is converted to a local coordinate system; A map likelihood map and a GNSS likelihood map are constructed in the local coordinate system; wherein, the map likelihood map includes a workable area that distinguishes flight paths, and the GNSS likelihood map is constructed based on GNSS information within a historical time window; The dead reckoning trajectory of the vehicle is determined based on dead reckoning. Based on the dead reckoning trajectory, the map likelihood diagram, and the GNSS likelihood diagram, the optimal vehicle pose is obtained using maximum likelihood estimation. Constructing map likelihood diagrams and GNSS likelihood diagrams in the local coordinate system includes: In the local coordinate system, a drivable area is constructed, and a map likelihood diagram is generated by combining the drivable routes of the lanes. In the local coordinate system, GNSS landing points are constructed based on GNSS information within the historical window, and a GNSS likelihood diagram is constructed based on the GNSS landing points; The GNSS information includes multiple numerical pairs, each consisting of a coordinate point and an average confidence level. The coordinate point is the coordinate corresponding to the latitude, longitude, and altitude coordinates in the location information obtained by the GNSS module after transformation to the local coordinate system. The average confidence level is the average of the confidence levels corresponding to the longitude and latitude in the location information.

2. The method according to claim 1, characterized in that, The location information includes the current vehicle's latitude, longitude, and elevation coordinates, as well as confidence levels. The latitude, longitude, and elevation coordinates include longitude, latitude, and elevation, and the confidence levels include the confidence levels corresponding to longitude, latitude, and elevation.

3. The method according to claim 2, characterized in that, The step of loading a local map based on the location information and converting the local map to a local coordinate system includes: Load a local map onto the satellite map with the latitude, longitude, and altitude coordinates as the center point and within a preset radius; Using latitude, longitude, and altitude coordinates as the origin, the local map is transformed into a local coordinate system.

4. The method according to claim 1, characterized in that, Construct a drivable area and, in conjunction with the drivable heading, build a map likelihood diagram, including: A closed driving area is constructed using lane lines as boundaries; The likelihood map is obtained by assigning values ​​to the drivable area based on the lane direction.

5. The method according to claim 1, characterized in that, GNSS landing points are constructed based on GNSS information within a historical window, and a GNSS likelihood map is constructed based on the GNSS landing points, including: A circle is constructed with each of the coordinate points as the center point and the average confidence level as the radius to serve as the GNSS landing point; The GNSS likelihood diagram is constructed by taking the vehicle's pose in the local coordinate system as the first value within the GNSS landing point and the vehicle's pose in the local coordinate system as the second value outside the GNSS landing point.

6. The method according to claim 1, characterized in that, The determination of the vehicle's dead reckoning trajectory based on dead reckoning includes: In the dead reckoning coordinate system, the relative pose of the vehicle is obtained by dead reckoning based on at least one of wheel speed information, vehicle speed information, and vehicle inertial navigation attitude information. Obtain the relative poses of multiple vehicles within a historical time window; The relative poses of the multiple vehicles are transformed into the carrier coordinate system to obtain the dead reckoning trajectory of the vehicles.

7. The method according to claim 1, characterized in that, The process of obtaining the optimal vehicle pose using maximum likelihood estimation based on the dead reckoning trajectory, the map likelihood map, and the GNSS likelihood map includes: The relative pose of the vehicle on the dead reckoning trajectory is converted into the vehicle pose in the local coordinate system; The vehicle pose in the local coordinate system is used as the variable of the first likelihood function corresponding to the map likelihood map, and the vehicle pose in the local coordinate system is used as the variable of the second likelihood function corresponding to the GNSS likelihood map to construct the target likelihood function. Construct a target likelihood function based on the first likelihood function and the second likelihood function; The optimal vehicle pose is obtained by performing maximum likelihood estimation on the target likelihood function.

8. A vehicle positioning device, characterized in that, The device includes: The GNSS module is used to obtain the vehicle's position information in the world coordinate system; The conversion module is used to load a local map based on the location information and convert the local map to a local coordinate system. A construction module is used to construct a map likelihood map and a GNSS likelihood map in the local coordinate system; wherein, the map likelihood map includes a workable area that distinguishes flight paths, and the GNSS likelihood map is constructed based on GNSS information within a historical time window; The determination module is used to determine the dead reckoning trajectory of the vehicle based on dead reckoning. The maximum likelihood estimation module is used to obtain the optimal vehicle pose using maximum likelihood estimation based on the dead reckoning trajectory, the map likelihood diagram, and the GNSS likelihood diagram. The building module includes a first building unit and a second building unit: The first construction unit is used to: construct a drivable area in the local coordinate system, and construct a map likelihood diagram in combination with the drivable lane routes; The second construction unit is used to: construct GNSS landing points based on GNSS information within the historical window in the local coordinate system, and construct a GNSS likelihood map based on the GNSS landing points; The GNSS information includes multiple numerical pairs, each consisting of a coordinate point and an average confidence level. The coordinate point is the coordinate corresponding to the latitude, longitude, and altitude coordinates in the location information obtained by the GNSS module after transformation to the local coordinate system. The average confidence level is the average of the confidence levels corresponding to the longitude and latitude in the location information.

9. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the vehicle positioning method according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the vehicle positioning method according to any one of claims 1-7.

11. A vehicle, characterized in that, The vehicle includes one or more of an inertial measurement unit, a wheel speedometer, and a vehicle speedometer, and the vehicle also includes electronic equipment; The inertial measurement unit is used to measure the vehicle's inertial navigation attitude information; The wheel speed meter is used to collect wheel speed information; The speedometer is used to collect vehicle speed information; The electronic device is used to perform the vehicle positioning method as described in any one of claims 1-7.

Images