Memory parking positioning method and device

Abstract

The invention provides a memory parking positioning method and device, and relates to the technical field of vehicles. The method comprises the following steps: determining the result of the pose of the current fusion positioning in a map coordinate system according to the current fusion positioning of a vehicle and the fusion positioning stored during mapping, then correcting the pose of the current fusion positioning in the map coordinate system through the current detection of a parking space, and finally searching a sub-map closest to the corrected pose, and according to the feature points and the parking space angular points, matching with corresponding features in the sub-graphs to obtain the pose of the vehicle in the map so as to realize memory parking positioning. Therefore, the result of the pose of the current fusion positioning in the map coordinate system is determined through the current fusion positioning and the fusion positioning stored during mapping, then the result is corrected, and the pose of the vehicle in the map is obtained according to the sub-map closest to the corrected pose and matching of the feature points and the parking space angular points with the corresponding features in the sub-maps. And the memory parking positioning can be simply and efficiently realized.

Description

Technical Field

[0001] The present application relates to the field of vehicle technology, and in particular to a positioning method and device for memory parking. Background Art

[0002] With the continuous development of the economy and the continuous improvement of people's living standards, the number of cars owned is also increasing. In daily travel, "difficult parking" has become a major problem for many car owners. Today, as smart driving is becoming more and more popular, more and more car manufacturers are beginning to pay attention to the memory parking function, which records the parking path of the car on the car side or in the cloud. When going to the same parking lot in the future, the owner does not need to drive the vehicle in person, but the car will drive to the target parking space autonomously, saving the owner's time in finding the parking space and parking to a certain extent. However, in the existing technology, it is impossible to simply and efficiently realize the positioning of memory parking.

[0003] In summary, how to simply and efficiently realize the positioning of memory parking is a problem that those skilled in the art need to solve urgently. Summary of the invention

[0004] In view of this, the present application provides a memory parking positioning method and device, aiming to achieve memory parking positioning simply and efficiently.

[0005] In a first aspect, the present application provides a positioning method for memory parking, comprising:

[0006] Determine the result of the pose of the current fused positioning in the map coordinate system according to the current fused positioning of the vehicle and the fused positioning saved during map building;

[0007] Correcting the posture of the fusion positioning in the map coordinate system through the current detection of the storage location;

[0008] The sub-graph closest to the corrected posture is searched, and the posture of the vehicle in the map is obtained by matching the feature points and the corner points of the storage location with the corresponding features in the sub-graph.

[0009] Optionally, determining the result of the pose of the current fused positioning in the map coordinate system according to the current fused positioning of the vehicle and the fused positioning saved during map building includes:

[0010] Obtaining a current fused position of the vehicle;

[0011] Loading the fusion positioning saved during the mapping;

[0012] Determining whether the vehicle has reached the vicinity of a starting point according to the current fused positioning of the vehicle and the fused positioning saved during the mapping;

[0013] If so, the result of the pose of the current fusion positioning in the map coordinate system is calculated.

[0014] Optionally, the correcting the posture of the fusion positioning in the map coordinate system through the current detection of the storage location includes:

[0015] Determine whether the storage location is currently detected;

[0016] If yes, the current storage location is transferred to the map coordinate system and matched with the storage location map to obtain a corrected position and posture;

[0017] If not, the visual feature points are received, the visual feature points are transferred to the map coordinate system, matched with the visual feature map, and the corrected posture is obtained.

[0018] Optionally, searching for a sub-graph closest to the corrected posture, and obtaining the posture of the vehicle in the map according to feature points and corner points of the storage location with corresponding features in the sub-graph, includes:

[0019] Searching for the subgraph closest to the corrected pose;

[0020] Determine whether the storage location can be detected in the current environment;

[0021] If yes, the current storage location information is matched with the storage location submap in the submap to determine the position of the vehicle in the map;

[0022] If not, the semantic information in the current environment is converted into a point cloud format and matched with the point cloud map in the sub-map to determine the position and posture of the vehicle in the map.

[0023] Optionally, after searching for the sub-graph closest to the corrected posture and obtaining the posture of the vehicle in the map by matching the feature points and the corner points of the storage location with the corresponding features in the sub-graph, the method further comprises:

[0024] The position and posture of the vehicle in the map are fused with the vehicle body information through EKF to obtain the positioning result.

[0025] Optionally, before determining the result of the pose of the current fused positioning in the map coordinate system according to the current fused positioning of the vehicle and the fused positioning saved during mapping, the method further includes:

[0026] The vehicle is fused and positioned based on the rtk sensor, IMU sensor data, and wheel encoder data;

[0027] The vehicle is fused and positioned according to the RTK sensor, IMU sensor data and wheel encoder data, including:

[0028] The fused positioning result obtained through the IMU sensor data and the wheel encoder data is used as the predicted value, and the rtk sensor data is used as the observed value, and the ESKF model is used to determine the position and posture of the vehicle.

[0029] Optionally, before determining the result of the pose of the current fused positioning in the map coordinate system according to the current fused positioning of the vehicle and the fused positioning saved during mapping, the method further includes:

[0030] Convert the pixel coordinates of the received perception information into physical coordinates in the vehicle body coordinate system;

[0031] Fill the four corner points of the storage location into a point cloud;

[0032] Obtaining target fusion positioning; the target fusion positioning is the fusion positioning saved during map building;

[0033] The position and posture of the vehicle in the map coordinate system are calculated by using the position and posture difference between the target fusion positioning and the rough positioning provided by the vehicle body sensor or the rough positioning module;

[0034] According to the posture of the vehicle in the map coordinate system, the point cloud and the storage location are transferred to the map coordinate system, matched with the storage location map and the point cloud map, and the matched posture is obtained;

[0035] Inserting the point cloud and the storage location into the sub-graph according to the matched posture;

[0036] The key frame pose and the subgraph are used as nodes, and for each node or subgraph, a subgraph or node within a certain range is searched to construct a node-subgraph pair, and for each pair of nodes and subgraphs, a warehouse location map or a point cloud map is matched to obtain a pose constraint;

[0037] The pose constraints are minimized by the least squares method to obtain an optimized pose.

[0038] In a second aspect, the present application provides a positioning device for memory parking, comprising:

[0039] A determination module, used to determine the result of the pose of the current fused positioning in the map coordinate system according to the current fused positioning of the vehicle and the fused positioning saved during map building;

[0040] A correction module, used for correcting the posture of the fusion positioning in the map coordinate system through the current detection of the storage location;

[0041] A matching module is used to search for a sub-graph closest to the corrected posture, and obtain the posture of the vehicle in the map by matching feature points and corner points of the storage location with corresponding features in the sub-graph.

[0042] Optionally, the determining module includes:

[0043] An acquisition unit, used for acquiring the current fused positioning of the vehicle;

[0044] A loading unit, used for loading the fusion positioning saved during the mapping;

[0045] A first judgment unit, configured to judge whether the vehicle has arrived near a starting point according to a current fused positioning of the vehicle and a fused positioning saved during the mapping;

[0046] A calculation unit is used to calculate the result of the current fusion positioning posture in the map coordinate system.

[0047] Optionally, the correction module includes:

[0048] The second judgment unit is used to judge whether the storage location is currently detected;

[0049] A first correction unit is used for, if yes, transferring the current storage location to the map coordinate system, matching it with the storage location map, and obtaining a corrected position and posture;

[0050] The second correction unit is used for receiving the visual feature points if no, transferring the visual feature points to the map coordinate system, matching with the visual feature map, and obtaining the corrected posture.

[0051] Optionally, the matching module includes:

[0052] A searching unit, configured to search for the sub-graph closest to the corrected pose;

[0053] The third judgment unit is used to judge whether the storage location can be detected in the current environment;

[0054] A first matching unit, configured to match the current storage location information with the storage location sub-map in the sub-map to determine the position of the vehicle in the map;

[0055] The second matching unit is used to, if not, convert the semantic information in the current environment into a point cloud format, and match it with the point cloud map in the sub-image to determine the position and posture of the vehicle in the map.

[0056] Optionally, the device further comprises:

[0057] The fusion module is used to fuse the position and posture of the vehicle in the map with the vehicle body information through EKF to obtain a positioning result.

[0058] Optionally, the device further comprises:

[0059] The fusion positioning module is used to perform fusion positioning of the vehicle based on the rtk sensor, IMU sensor data and wheel encoder data;

[0060] The fusion positioning module includes:

[0061] A fusion positioning unit is used to use the fusion positioning result obtained through the IMU sensor data and the wheel encoder data as a prediction value, and the rtk sensor data as an observation value, and use the ESKF model to determine the posture of the vehicle.

[0062] Optionally, the device further comprises:

[0063] A conversion module, used to convert the pixel coordinates of the received perception information into physical coordinates in the vehicle body coordinate system;

[0064] Filling module, used to fill the four corner points of the storage location into a point cloud;

[0065] An acquisition module is used to acquire a target fusion positioning; the target fusion positioning is a fusion positioning saved during map building;

[0066] A calculation module, used to calculate the posture of the vehicle in a map coordinate system through the posture difference between the target fusion positioning and the rough positioning provided by the vehicle body sensor or the rough positioning module;

[0067] A posture matching module is used to convert the point cloud and the storage location to the map coordinate system according to the posture of the vehicle in the map coordinate system, match them with the storage location map and the point cloud map, and obtain a matched posture;

[0068] An insertion module, used for inserting the point cloud and the storage location into the sub-map according to the matched posture;

[0069] A posture constraint module is used to use the key frame posture and the subgraph as nodes, search for subgraphs or nodes within a certain range for each node or subgraph, build node-subgraph pairs, and match the warehouse location map or point cloud map for each pair of nodes and subgraphs to obtain posture constraints;

[0070] The optimization module is used to minimize the posture constraints by using the least square method to obtain an optimized posture.

[0071] In a third aspect, an embodiment of the present application provides a computer device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the memory parking positioning method described in any one of the implementation modes in the first aspect of the embodiment of the present application is implemented.

[0072] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, in which instructions are stored. When the instructions are executed on a terminal device, the terminal device executes the memory parking positioning method described in any one of the implementation methods in the first aspect of the embodiment of the present application.

[0073] The present application provides a positioning method for memory parking. When executing the method, first determine the result of the current fusion positioning posture in the map coordinate system based on the current fusion positioning of the vehicle and the fusion positioning saved when building the map, then correct the posture of the fusion positioning in the map coordinate system through the current detection of the storage location, and finally, search for the sub-graph closest to the corrected posture, and obtain the posture of the vehicle in the map according to the feature points and the corner points of the storage location and the corresponding features in the sub-graph, so as to realize the positioning of memory parking. In this way, the result of the current fusion positioning posture in the map coordinate system is determined through the current fusion positioning and the fusion positioning saved when building the map, and then the result is corrected, and according to the sub-graph closest to the corrected posture, the posture of the vehicle in the map is obtained according to the feature points and the corner points of the storage location and the corresponding features in the sub-graph, so that the positioning of memory parking can be realized simply and efficiently. BRIEF DESCRIPTION OF THE DRAWINGS

[0074] In order to more clearly illustrate the technical solutions in this embodiment or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0075] Figure 1 A flowchart of a memory parking method provided in an embodiment of the present application;

[0076] Figure 2 A schematic diagram of the structure of a memory parking device provided in an embodiment of the present application;

[0077] Figure 3 A schematic diagram of the structure of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0078] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. The present application provides a memory parking positioning method and device, which are used in the field of vehicle technology. The above is only an example and does not limit the application field of the method and device provided by the present application.

[0079] With the continuous development of the economy and the continuous improvement of people's living standards, the number of cars owned is also increasing. In daily travel, "difficult parking" has become a major problem for many car owners. Today, as smart driving is becoming more and more popular, more and more car manufacturers are beginning to pay attention to the memory parking function, which records the parking path of the car on the car side or in the cloud. When going to the same parking lot in the future, the owner does not need to drive the vehicle in person, but the car will drive to the target parking space autonomously, saving the owner's time in finding the parking space and parking to a certain extent. However, in the existing technology, it is impossible to simply and efficiently realize the positioning of memory parking.

[0080] After research, the inventor proposed the technical solution of this application. First, according to the current fusion positioning of the vehicle and the fusion positioning saved when building the map, the result of the current fusion positioning posture in the map coordinate system is determined. Then, the posture of the fusion positioning in the map coordinate system is corrected through the current detection of the storage location. Finally, the sub-graph closest to the corrected posture is searched, and the posture of the vehicle in the map is obtained by matching the feature points and the corner points of the storage location with the corresponding features in the sub-graph, so as to realize the positioning of memory parking. In this way, the result of the current fusion positioning posture in the map coordinate system is determined through the current fusion positioning and the fusion positioning saved when building the map, and then the result is corrected, and according to the sub-graph closest to the corrected posture, the posture of the vehicle in the map is obtained by matching the feature points and the corner points of the storage location with the corresponding features in the sub-graph, so that the positioning of memory parking can be realized simply and efficiently.

[0081] In order to enable those skilled in the art to better understand the present application, the present application is further described in detail below in conjunction with the accompanying drawings and specific implementation methods. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of the present application. It should be noted that, for ease of description, only the parts related to the relevant invention are shown in the accompanying drawings. In the absence of conflict, the embodiments in the present application and the features in the embodiments can be combined with each other.

[0082] See also Figure 1 , Figure 1 A flowchart of a memory parking method provided in an embodiment of the present application includes:

[0083] S101: Determine the result of the current fused positioning in the map coordinate system according to the current fused positioning of the vehicle and the fused positioning saved during map building.

[0084] First, obtain the current fused positioning of the vehicle and load the fused positioning saved during map construction. Then, based on the current fused positioning of the vehicle and the fused positioning results saved during map construction, determine whether the vehicle has reached the vicinity. If so, calculate the result of the current fused positioning posture in the map coordinate system.

[0085] Before executing step S101, the current fusion positioning of the vehicle can be obtained first: the vehicle can be fusion positioned according to the rtk sensor, IMU sensor data and wheel encoder data. Specifically, the fusion positioning result obtained by the IMU sensor data and wheel encoder data can be used as the predicted value, and the rtk sensor data can be used as the observed value. The ESKF model is used to determine the posture of the vehicle. Even after the rtk signal disappears, a relatively accurate positioning result can be maintained. When the map is completed, the result of this fusion positioning is saved. When positioning, the result of the current fusion positioning can be compared with the fusion positioning result during mapping. When it is judged that it is near the starting point, the initial value of the positioning is determined, and the posture is corrected through the warehouse map or visual features.

[0086] Before executing step S101, a map construction operation is required, and the specific steps are as follows: the vehicle body sensor or fusion positioning module provides rough positioning, and the perception module extracts the contour points of the ground identification features and the corner point information of the storage location in real time through the surround camera. Among them, the vehicle body sensor includes but is not limited to wheel speed sensor, wheel encoder, gyroscope, steering wheel angle information, etc., and the ground identification includes but is not limited to storage line, zebra crossing, speed bump and arrow. The front end part constructs a local sub-graph with the input data of several consecutive frames, in which the contour points detected by vision are converted into "pseudo point cloud", the point cloud map is constructed, and the storage location corner points create a storage location map, and frame-sub-graph matching is performed. According to the rough positioning provided by the vehicle body sensor or fusion positioning as the initial value, the visual pseudo point cloud and the storage location corner points are converted to the sub-graph coordinate system, matched with the sub-graph, and two constraints of the storage location elements and the pseudo point cloud are constructed, and different weights are assigned to obtain the optimized posture, and the frame point cloud is inserted into the sub-graph to construct a grid map. The backend uses the poses and subgraphs of the keyframes as nodes to construct a pose graph. The nodes are matched with the nearest N subgraphs, and the newly completed subgraphs are matched with the nearest M nodes. The pose constraints are calculated based on the two features and solved by the least squares method to obtain the optimal solution for all poses. When the map is completed, the serialized point cloud map, warehouse location map, and the trajectory of the corresponding automatic initialization module are saved to the memory. At the beginning of the map, ORB feature points are extracted from the image of the front-view camera to create an ORB feature map.

[0087] S102: Correcting the posture of the fusion positioning in the map coordinate system through the current detection of the storage location.

[0088] First determine whether the current storage location can be detected. If so, transfer the current storage location to the map coordinate system, match it with the storage location map, and obtain the corrected posture. If not, receive the visual feature points, transfer the visual feature points to the map coordinate system, match it with the visual feature map, and obtain the corrected posture.

[0089] S103: Searching for the sub-graph closest to the corrected posture, and obtaining the posture of the vehicle in the map by matching the feature points and the corner points of the parking space with the corresponding features in the sub-graph.

[0090] Search the sub-graph closest to the corrected posture to determine whether the storage location can be detected in the current environment. If so, match the current storage location information with the storage location sub-graph in the sub-graph to determine the vehicle's posture in the map.

[0091] In some implementations, in order to make the positioning result smoother and conform to the vehicle control model, the map matching posture and vehicle body information are fused through the EKF model to reduce the jump of the positioning result.

[0092] In the embodiment provided in the present application, the result of the current fused positioning posture in the map coordinate system is first determined based on the current fused positioning of the vehicle and the fused positioning saved when the map is built, and then the posture of the fused positioning in the map coordinate system is corrected through the current detection of the storage location, and finally, the sub-graph closest to the corrected posture is searched, and the posture of the vehicle in the map is obtained according to the feature points and the corner points of the storage location and the corresponding features in the sub-graph, so as to realize the positioning of memory parking. In this way, the result of the current fused positioning posture in the map coordinate system is determined through the current fused positioning and the fused positioning saved when the map is built, and then the result is corrected, and according to the sub-graph closest to the corrected posture, the posture of the vehicle in the map is obtained according to the feature points and the corner points of the storage location and the corresponding features in the sub-graph, so that the positioning of memory parking can be realized simply and efficiently.

[0093] The above are some specific implementations of the memory parking positioning method provided in the embodiments of the present application. Based on this, the present application also provides a corresponding device. The device provided in the embodiments of the present application will be introduced from the perspective of functional modularization.

[0094] See also Figure 2 , Figure 2 The present invention provides a schematic diagram of a memory parking positioning device according to an embodiment of the present invention. The memory parking positioning device 200 includes:

[0095] The determination module 210 is used to determine the result of the pose of the current fused positioning in the map coordinate system according to the current fused positioning of the vehicle and the fused positioning saved during map construction;

[0096] A correction module 220, used for correcting the posture of the fusion positioning in the map coordinate system through the current detection of the storage location;

[0097] The matching module 230 is used to search for the sub-graph closest to the corrected posture, and obtain the posture of the vehicle in the map by matching the feature points and the corner points of the storage location with the corresponding features in the sub-graph.

[0098] Optionally, the determining module 210 includes:

[0099] An acquisition unit, used for acquiring the current fused positioning of the vehicle;

[0100] A loading unit, used for loading the fusion positioning saved during the mapping;

[0101] A first judgment unit, configured to judge whether the vehicle has arrived near a starting point according to a current fused positioning of the vehicle and a fused positioning saved during the mapping;

[0102] A calculation unit is used to calculate the result of the current fusion positioning posture in the map coordinate system.

[0103] Optionally, the correction module 220 includes:

[0104] The second judgment unit is used to judge whether the storage location is currently detected;

[0105] A first correction unit is used for, if yes, transferring the current storage location to the map coordinate system, matching it with the storage location map, and obtaining a corrected position and posture;

[0106] The second correction unit is used for receiving the visual feature points if no, transferring the visual feature points to the map coordinate system, matching with the visual feature map, and obtaining the corrected posture.

[0107] Optionally, the matching module 230 includes:

[0108] A searching unit, configured to search for the sub-graph closest to the corrected pose;

[0109] The third judgment unit is used to judge whether the storage location can be detected in the current environment;

[0110] A first matching unit, configured to match the current storage location information with the storage location sub-map in the sub-map to determine the position of the vehicle in the map;

[0111] The second matching unit is used to, if not, convert the semantic information in the current environment into a point cloud format, and match it with the point cloud map in the sub-image to determine the position and posture of the vehicle in the map.

[0112] Optionally, the device 200 further includes:

[0113] The fusion module is used to fuse the position and posture of the vehicle in the map with the vehicle body information through EKF to obtain a positioning result.

[0114] Optionally, the device 200 further includes:

[0115] The fusion positioning module is used to perform fusion positioning of the vehicle based on the rtk sensor, IMU sensor data and wheel encoder data;

[0116] The fusion positioning module includes:

[0117] A fusion positioning unit is used to use the fusion positioning result obtained through the IMU sensor data and the wheel encoder data as a prediction value, and the rtk sensor data as an observation value, and use the ESKF model to determine the posture of the vehicle.

[0118] Optionally, the device 200 further includes:

[0119] A conversion module, used to convert the pixel coordinates of the received perception information into physical coordinates in the vehicle body coordinate system;

[0120] Filling module, used to fill the four corner points of the storage location into a point cloud;

[0121] An acquisition module is used to acquire a target fusion positioning; the target fusion positioning is a fusion positioning saved during map building;

[0122] A calculation module, used to calculate the posture of the vehicle in a map coordinate system through the posture difference between the target fusion positioning and the rough positioning provided by the vehicle body sensor or the rough positioning module;

[0123] A posture matching module is used to convert the point cloud and the storage location to the map coordinate system according to the posture of the vehicle in the map coordinate system, match them with the storage location map and the point cloud map, and obtain a matched posture;

[0124] An insertion module, used for inserting the point cloud and the storage location into the sub-map according to the matched posture;

[0125] A posture constraint module is used to use the key frame posture and the subgraph as nodes, search for subgraphs or nodes within a certain range for each node or subgraph, build node-subgraph pairs, and match the warehouse location map or point cloud map for each pair of nodes and subgraphs to obtain posture constraints;

[0126] The optimization module is used to minimize the posture constraints by using the least square method to obtain an optimized posture.

[0127] The embodiments of the present application also provide corresponding devices and computer storage media for implementing the solutions provided by the embodiments of the present application.

[0128] like Figure 3 As shown, the computer device 01 is in the form of a general computing device. The components of the computer device 01 may include but are not limited to: one or more processors or processing units 03, a system memory 08, and a bus 04 connecting different system components (including the system memory 08 and the processing unit 03).

[0129] Bus 04 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor or a local bus using any of a variety of bus structures. For example, these architectures include but are not limited to Industry Standard Architecture (ISA) bus, Micro Channel Architecture (MAC) bus, Enhanced ISA bus, Video Electronics Standards Association (VESA) local bus and Peripheral Component Interconnect (PCI) bus.

[0130] The computer device 01 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the computer device 01, including volatile and non-volatile media, removable and non-removable media.

[0131] The system memory 08 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 09 and / or cache memory 10. The computer device 01 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the storage system 11 may be used to read and write non-removable, non-volatile magnetic media ( Figure 3 not shown, usually called a "hard drive"). Although Figure 3 Not shown in the figure, a disk drive for reading and writing a removable non-volatile disk (e.g., a "floppy disk"), and an optical disk drive for reading and writing a removable non-volatile optical disk (e.g., a CD-ROM, a DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to the bus 04 via one or more data medium interfaces. The memory 08 may include at least one program product having a set (e.g., at least one) of program modules that are configured to perform the functions of the various embodiments of the present invention.

[0132] A program / utility 12 having a set (at least one) of program modules 13 may be stored, for example, in the memory 08, such program modules 13 including but not limited to an operating system, one or more application programs, other program modules, and program data, each of which or some combination thereof may include an implementation of a network environment. The program modules 13 generally perform the functions and / or methods of the embodiments described herein.

[0133] The computer device 01 may also communicate with one or more external devices 02 (e.g., keyboard, pointing device, display 07, etc.), one or more devices that enable a user to interact with the computer device 01, and / or any device that enables the computer device 01 to communicate with one or more other computing devices (e.g., network card, modem, etc.). Such communication may be performed via input / output (I / O) interface 06. Furthermore, the computer device 01 may also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN) and / or public network, such as the Internet) via network adapter 05. Figure 3 As shown, the network adapter 05 communicates with other modules of the computer device 01 via the bus 04. It should be understood that although Figure 3 Not shown, other hardware and / or software modules may be used in conjunction with computer device 01, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0134] The processor unit 03 executes various functional applications and data processing by running the programs stored in the system memory 08, for example, implementing a memory parking positioning method provided in an embodiment of the present application.

[0135] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0136] Through the description of the above implementation methods, it can be known that those skilled in the art can clearly understand that all or part of the steps in the above-mentioned embodiment method can be implemented by means of software plus a general hardware platform. Based on such an understanding, the technical solution of the present application can be embodied in the form of a software product, which can be stored in a storage medium, such as a read-only memory (ROM) / RAM, a magnetic disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network communication device such as a router) to execute the methods described in each embodiment of the present application or some parts of the embodiments.

[0137] Each embodiment in this specification is described in a progressive manner, and the same and similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment. Some or all of the modules can be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative work.

[0138] The above description is merely an exemplary embodiment of the present application and is not intended to limit the protection scope of the present application.

Claims

1. A memory parking positioning method, characterized in that: include: According to the current fused positioning of the vehicle and the fused positioning saved during map building, determining the result of the pose of the current fused positioning in the map coordinate system; Correcting the posture of the fusion positioning in the map coordinate system through the current detection of the storage location; The sub-graph closest to the corrected posture is searched, and the posture of the vehicle in the map is obtained by matching the feature points and the corner points of the storage location with the corresponding features in the sub-graph.

2. The method according to claim 1, characterized in that The step of determining the result of the pose of the current fused positioning in the map coordinate system according to the current fused positioning of the vehicle and the fused positioning saved during map building includes: Obtaining a current fused position of the vehicle; Loading the fusion positioning saved during the mapping; Determining whether the vehicle has reached the vicinity of a starting point according to the current fused positioning of the vehicle and the fused positioning saved during the mapping; If so, the result of the pose of the current fusion positioning in the map coordinate system is calculated.

3. The method according to claim 1, characterized in that The correcting of the fusion positioning posture in the map coordinate system by detecting the current storage location includes: Determine whether the storage location is currently detected; If yes, the current storage location is transferred to the map coordinate system and matched with the storage location map to obtain a corrected position and posture; If not, the visual feature points are received, the visual feature points are transferred to the map coordinate system, matched with the visual feature map, and the corrected posture is obtained.

4. The method according to claim 1, characterized in that: The searching for the sub-graph closest to the corrected posture, and obtaining the posture of the vehicle in the map according to the matching of the feature points and the corner points of the storage location with the corresponding features in the sub-graph, comprises: Searching for the sub-graph closest to the corrected pose; Determine whether the storage location can be detected in the current environment; If yes, the current storage location information is matched with the storage location submap in the submap to determine the position of the vehicle in the map; If not, the semantic information in the current environment is converted into a point cloud format and matched with the point cloud map in the sub-map to determine the position and posture of the vehicle in the map.

5. The method according to claim 1, characterized in that After searching for the sub-graph closest to the corrected posture, and obtaining the posture of the vehicle in the map by matching the feature points and the corner points of the storage location with the corresponding features in the sub-graph, the method further includes: The position and posture of the vehicle in the map are fused with the vehicle body information through EKF to obtain the positioning result.

6. The method according to claim 1, characterized in that Before determining the result of the pose of the current fused positioning in the map coordinate system according to the current fused positioning of the vehicle and the fused positioning saved during map building, the method further includes: The vehicle is fused and positioned based on the RTK sensor, IMU sensor data, and wheel encoder data; The vehicle is fused and positioned according to the RTK sensor, IMU sensor data and wheel encoder data, including: The fused positioning result obtained through the IMU sensor data and the wheel encoder data is used as the predicted value, and the rtk sensor data is used as the observed value, and the ESKF model is used to determine the position and posture of the vehicle.

7. The method according to claim 1, characterized in that Before determining the result of the pose of the current fused positioning in the map coordinate system according to the current fused positioning of the vehicle and the fused positioning saved during map building, the method further includes: Convert the pixel coordinates of the received perception information into physical coordinates in the vehicle body coordinate system; Fill the four corner points of the storage location into a point cloud; Obtaining target fusion positioning; the target fusion positioning is the fusion positioning saved during map building; The position and posture of the vehicle in the map coordinate system are calculated by using the position and posture difference between the target fusion positioning and the rough positioning provided by the vehicle body sensor or the rough positioning module; According to the posture of the vehicle in the map coordinate system, the point cloud and the storage location are transferred to the map coordinate system, matched with the storage location map and the point cloud map, and the matched posture is obtained; Inserting the point cloud and the storage location into the sub-graph according to the matched posture; The key frame pose and the subgraph are regarded as nodes, and for each node or subgraph, a subgraph or node within a certain range is searched to construct a node-subgraph pair, and for each pair of nodes and subgraphs, a warehouse location map or a point cloud map is matched to obtain a pose constraint; The pose constraints are minimized by the least squares method to obtain an optimized pose.

8. A positioning device for memory parking, characterized in that: include: A determination module, used to determine the result of the pose of the current fused positioning in the map coordinate system according to the current fused positioning of the vehicle and the fused positioning saved during map building; A correction module, used for correcting the posture of the fusion positioning in the map coordinate system through the current detection of the storage location; A matching module is used to search for a sub-graph closest to the corrected posture, and obtain the posture of the vehicle in the map by matching feature points and corner points of the storage location with corresponding features in the sub-graph.

9. A computer device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the memory parking positioning method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores instructions, and when the instructions are executed on a terminal device, the terminal device executes the memory parking positioning method according to any one of claims 1 to 7.

Images