A likelihood map updating method, apparatus, device, and storage medium

Abstract

The application discloses a likelihood map updating method and device, equipment and a storage medium. The method comprises the following steps: acquiring an occupancy grid map corresponding to a current position; performing Gaussian processing on the occupancy grid map to obtain a multi-layer likelihood map; if it is determined that the multi-layer likelihood map has a deviation according to the occupancy grid map, the multi-layer likelihood map is updated to obtain a target likelihood map. Through the technical scheme of the application, the consumption of computing power of the likelihood map can be reduced, and the positioning efficiency is improved.

Description

TECHNICAL FIELD

[0001] Embodiments of the present application relate to the technical field of computer technology, and particularly relate to a likelihood map updating method and device, equipment and storage medium. BACKGROUND

[0002] With the development of automatic driving technology, vehicle positioning and mapping have become a research hotspot. In the prior art, vehicle positioning methods generally use sensors such as GPS for positioning, but this method has limitations, such as large positioning error and susceptibility to interference. Therefore, vehicle positioning methods based on vision, semantics and other technologies have attracted attention. However, the method of vehicle positioning based on semantic information has great computational consumption and low computational efficiency. SUMMARY

[0003] Embodiments of the present application provide a likelihood map updating method, device, equipment and storage medium, which can reduce the computational consumption of the likelihood map and improve the positioning efficiency.

[0004] According to an aspect of the present application, a likelihood map updating method is provided, comprising:

[0005] obtaining an occupancy grid map corresponding to a current position;

[0006] performing Gaussian processing on the occupancy grid map to obtain a multi-layer likelihood map;

[0007] if it is determined that the multi-layer likelihood map has a deviation according to the occupancy grid map, updating the multi-layer likelihood map to obtain a target likelihood map.

[0008] According to another aspect of the present application, a likelihood map updating device is provided, comprising:

[0009] an obtaining module configured to obtain an occupancy grid map corresponding to a current position;

[0010] a obtaining module configured to obtain an occupancy grid map corresponding to a current position;

[0011] an updating module configured to, if it is determined that the multi-layer likelihood map has a deviation according to the occupancy grid map, update the multi-layer likelihood map to obtain a target likelihood map.

[0012] According to another aspect of the present application, an electronic device is provided, comprising:

[0013] at least one processor; and

[0014] a memory in communication with the at least one processor; wherein

[0015] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to execute the likelihood map updating method according to any one of the embodiments of the application.

[0016] According to another aspect of the application, a computer readable storage medium is provided, which stores computer instructions for enabling a processor to implement the likelihood map updating method according to any one of the embodiments of the application when executed by the processor.

[0017] The embodiment of the application obtains an occupancy grid map corresponding to a current position, performs Gaussian processing on the occupancy grid map to obtain a multi-layer likelihood map, and updates the multi-layer likelihood map to obtain a target likelihood map if it is determined that the multi-layer likelihood map has a deviation according to the occupancy grid map, thereby solving the problem of low efficiency caused by large calculation consumption when vehicle positioning is performed based on semantic information, reducing the calculation power consumption of the likelihood map, and improving positioning efficiency.

[0018] It should be understood that the content described in this part is not intended to identify key or important features of the embodiments of the application, nor is it used to limit the scope of the application. Other features of the application will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0019] In order to more clearly illustrate the technical solutions of the embodiments of the application, the following will briefly introduce the drawings needed to be used in the embodiments. It should be understood that the following drawings only show some of the embodiments of the application, and therefore should not be considered as limiting the scope. For those skilled in the art, other related drawings can also be obtained from these drawings without creative labor.

[0020] Figure 1 is a flowchart of a likelihood map updating method in the first embodiment of the application;

[0021] Figure 2 is a structural schematic diagram of a likelihood map updating device in the second embodiment of the application;

[0022] Figure 3 is a structural schematic diagram of an electronic device in the third embodiment of the application. DETAILED DESCRIPTION

[0023] In the following, the technical solutions in the embodiments of the present application will be described clearly and completely with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all the other embodiments obtained by a person of ordinary skill in the art without creative work should belong to the protection scope of the present application.

[0024] It should be noted that the terms "first", "second" and the like in the description and claims of the present application and the above drawings are used to distinguish similar objects, and do not necessarily indicate a specific order or sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the application described herein can be implemented in other than the order illustrated or described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device that includes a list of steps or units need not be limited to those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to such processes, methods, products or devices.

[0025] It can be understood that, before using the technical solutions disclosed in the embodiments of the present application, the type, use range, use scenario and the like of the personal information involved in the present application should be informed to the user and the authorization of the user should be obtained according to relevant laws and regulations.

[0026] Embodiment one

[0027] Figure 1 is a flowchart of a likelihood map updating method in the embodiment one of the present application. The present embodiment can be applied to the case of updating a likelihood map. The method can be executed by a likelihood map updating device in the embodiments of the present application. The device can be realized in the form of software and / or hardware. As shown in Figure 1 , the method specifically includes the following steps:

[0028] S110, obtaining an occupancy grid map corresponding to a current position.

[0029] It should be noted that the current position can be the current position of a vehicle, or the position of other objects to be positioned, and is not limited to the current position of a vehicle.

[0030] The occupancy grid map is a multi-layer occupancy grid map, wherein the multi-layer can include: a semantic layer for semantic matching in positioning; a logic layer for vehicle route planning control in regulation control; a feature layer for repositioning, etc. For example, the multi-layer can be: a lane line layer, a ground marking separation line layer, a building layer, and an aerial marking layer.

[0031] Specifically, the occupancy grid map corresponding to the current position can be obtained by reading high-precision map data in the semantic positioning of the vehicle through a map engine or by obtaining information corresponding to the current position of the vehicle through a sensor of the vehicle to draw the occupancy grid map corresponding to the current position.

[0032] S120, Gaussian processing is performed on the occupancy grid map to obtain a multi-layer likelihood map.

[0033] The multi-layer in the multi-layer likelihood map corresponds to each layer in the occupancy grid map, that is, the multi-layer in the multi-layer likelihood map includes: a semantic layer for semantic matching in positioning; a logic layer for vehicle route planning control in regulation control; a feature layer for repositioning, etc.

[0034] Specifically, the multi-layer likelihood map can be obtained by performing Gaussian processing on each layer in the occupancy grid map according to the Gaussian kernel parameters corresponding to different types of map elements.

[0035] For example, if the high-precision map data used in the semantic positioning system of the vehicle is read and represented in the form of vector data F HD , the occupancy grid map F HD is drawn according to the vector data F grid , and the multi-layer likelihood map is obtained by convolution according to the occupancy grid map and the Gaussian model, and the implementation formula is as follows:

[0036]

[0037] F likelihood can be used to describe the possibility of each type of map element observed by the vehicle at the current position, and the multi-layer likelihood map is a map obtained by Gaussian processing on the multi-layer occupancy grid map.

[0038] S130, if it is determined that the multi-layer likelihood map exists deviation according to the occupancy grid map, the multi-layer likelihood map is updated to obtain a target likelihood map.

[0039] The target likelihood map is an updated likelihood map.

[0040] Specifically, if it is determined that the multi-layer likelihood map has a deviation according to the occupancy grid map, the multi-layer likelihood map is updated to obtain the target likelihood map in the following manner: the occupancy grid map is compared with a historical occupancy grid map, if the occupancy grid map is not the same as the historical occupancy grid map, the occupancy grid map has a deviation, that is, it is determined that the multi-layer likelihood map has a deviation, and the multi-layer likelihood map is updated according to the layer having the deviation to obtain the target likelihood map.

[0041] By obtaining the occupancy grid map corresponding to the current position, performing Gaussian processing on the occupancy grid map to obtain the multi-layer likelihood map, and updating the multi-layer likelihood map to obtain the target likelihood map if it is determined that the multi-layer likelihood map has a deviation according to the occupancy grid map, a more refined multi-layer likelihood map can be obtained through Gaussian processing, and the multi-layer likelihood map is updated according to the deviation of different layers to obtain the target likelihood map, thereby improving the accuracy of vehicle positioning and reducing the calculation consumption of multi-layer likelihood map updating.

[0042] Optionally, obtaining the occupancy grid map corresponding to the current position comprises:

[0043] Obtaining map data of the current position or sensor information of the current position.

[0044] Determining the occupancy grid map according to the map data or the sensor information of the current position.

[0045] The map data of the current position can be data in a high-definition map used by a semantic positioning system in the vehicle, for example, data in a SLAM map. The sensor information of the current position can be sensor information obtained according to a sensor carried by the vehicle, for example, information obtained by using an IMU (Inertial Measurement Unit) carried by the vehicle.

[0046] Specifically, the map data of the current position or the sensor information of the current position can be obtained in the following manner: if the semantic positioning system of the vehicle uses a high-definition map, the map data within a preset range around the current position of the vehicle is read through a map engine; if the semantic positioning system of the vehicle does not use a high-definition map, sensor information within a preset range of the current position is obtained through a sensor carried by the vehicle.

[0047] Specifically, the occupancy grid map can be determined according to the map data or the sensor information of the current position in the following manner: if the map data is read, the map data can be represented by vector data, and the occupancy grid map is drawn according to the vector data; if the sensor information of the current position is obtained, the scene of the current position is recognized based on the sensor information, and the occupancy grid map is drawn.

[0048] The map data of the current position or the sensor information of the current position is acquired, and an occupancy grid map is determined according to the map data or the sensor information of the current position, so that information of the current position of the vehicle can be flexibly determined according to a semantic positioning system of the vehicle, and the occupancy grid map can be drawn according to the information of the current position of the vehicle.

[0049] Optionally, the occupancy grid map is determined according to the sensor information of the current position, and the method comprises the following steps.

[0050] The target feature sequence of each type of map element is determined according to the sensor information of the current position.

[0051] The occupancy grid map of the current position is determined according to the target feature sequence of each type of map element and the preset feature sequence corresponding to each type of map element.

[0052] The target feature sequence of each type of map element is determined according to the sensor information of the current position.

[0053] Specifically, the target feature sequence of each type of map element can be determined according to the sensor information of the current position, and the target feature sequence of each type of map element in a preset range of the current position of the vehicle is obtained through scene recognition in the preset range of the current position of the vehicle.

[0054] Specifically, the target feature sequence of each type of map element can be determined according to the sensor information of the current position, and the target feature sequence of each type of map element in a preset range of the current position of the vehicle is obtained through scene recognition in the preset range of the current position of the vehicle.

[0055] The target feature sequence of each type of map element is determined according to the sensor information of the current position, and the occupancy grid map of the current position is determined according to the target feature sequence of each type of map element and the preset feature sequence corresponding to each type of map element, so that the accuracy of the occupancy grid map can be improved.

[0056] Optionally, the occupancy grid map is subjected to Gaussian processing to obtain a multi-layer likelihood map, comprising:

[0057] Obtaining Gaussian kernel parameters corresponding to various map elements in the occupancy grid map;

[0058] Subjecting the occupancy grid map to Gaussian processing according to the Gaussian kernel parameters corresponding to various map elements to obtain a multi-layer likelihood map.

[0059] It should be noted that the Gaussian kernel parameters corresponding to various map elements are different, and Gaussian processing according to the Gaussian kernel parameters corresponding to various map elements can obtain a multi-layer likelihood map with higher accuracy.

[0060] Specifically, the way to obtain the Gaussian kernel parameters corresponding to various map elements in the occupancy grid map can be: the Gaussian kernel parameters corresponding to various map elements can be directly pre-set, or the Gaussian kernel parameters corresponding to various map elements can be determined according to historical experience of Gaussian processing of various map elements, a parameter library can be generated according to the Gaussian kernel parameters corresponding to various map elements, and the Gaussian kernel parameters corresponding to various map elements in the occupancy grid map can be obtained by querying the parameter library.

[0061] Specifically, the way to subject the occupancy grid map to Gaussian processing according to the Gaussian kernel parameters corresponding to various map elements to obtain a multi-layer likelihood map can be: subjecting each layer of the occupancy grid map to Gaussian blur processing according to the Gaussian kernel parameters corresponding to various map elements to obtain a multi-layer likelihood map. Specifically, the Gaussian blur processing method can be: an efficient Gaussian blur processing method based on multi-threading, each layer of the occupancy grid map is cut into multiple small blocks, and each small block is allocated to a different thread for processing, thereby realizing multi-threading acceleration. In each thread, first, Gaussian kernel convolution operation is performed on the current small block to obtain a smoothing result of the current small block, then the smoothing result is merged to obtain a smoothing result of each layer, and a multi-layer likelihood map is obtained according to the smoothing result of each layer. It should be noted that in the positioning process of the vehicle, the possibility of the current position of the vehicle is calculated and updated according to the multi-layer likelihood map, in order to realize accurate positioning effect, real-time filtering registration can be performed in each thread, and confidence can be configured to improve the reliability of vehicle positioning.

[0062] Optionally, if the multi-layer likelihood map is determined to exist offset according to the occupancy grid map, the multi-layer likelihood map is updated to obtain a target likelihood map, comprising:

[0063] If the occupancy grid map and the historical occupancy grid map exist offset, and the historical occupancy grid map has a corresponding likelihood map, a target layer existing offset in the multi-layer likelihood map is obtained;

[0064] The target layer existing offset is incrementally loaded, and the multi-layer likelihood map is updated according to the incrementally loaded target layer and a first layer to obtain a target likelihood map, wherein the first layer is a layer in the multi-layer likelihood map without offset.

[0065] The historical occupancy grid map can be an occupancy grid map of a vehicle before a preset time threshold, and is also stored in a vehicle system memory. The target layer is a layer in the multi-layer likelihood map with offset, and the first layer is a layer in the multi-layer likelihood map without offset.

[0066] Specifically, if the occupancy grid map and the historical occupancy grid map exist offset, and the historical occupancy grid map has a corresponding likelihood map, the target layer existing offset in the multi-layer likelihood map can be obtained in the following manner: each layer in the occupancy grid map and the historical occupancy grid map is compared, if at least one layer of the occupancy grid map is not completely same as the corresponding layer in the historical occupancy grid map, it is indicated that the occupancy grid map and the historical occupancy grid map exist offset, and if the historical occupancy grid map has a corresponding likelihood map, it is indicated that the historical occupancy grid map has also been processed by Gauss, and then the layer with offset in the occupancy grid map and the historical occupancy grid map can be directly determined as the target layer.

[0067] Specifically, the target layer existing offset is incrementally loaded, and the multi-layer likelihood map is updated according to the incrementally loaded target layer and a first layer to obtain a target likelihood map, wherein the first layer is a layer in the multi-layer likelihood map without offset. The manner can be as follows: the range of the target layer with offset is calculated, the target layer is incrementally loaded according to the range of offset, the layer without offset, i.e. the first layer, is directly copied, and the target likelihood map is obtained according to the incrementally loaded target layer and the copied first layer.

[0068] Optionally, if the multi-layer likelihood map is determined to exist offset according to the occupancy grid map, the multi-layer likelihood map is updated to obtain a target likelihood map, including:

[0069] If the occupancy grid map and the historical occupancy grid map exist offset, and the historical occupancy grid map does not have a corresponding likelihood map, the multi-layer likelihood map is fully loaded to obtain a target likelihood map.

[0070] Specifically, if there is an offset between the occupied grid map and the historical occupied grid map, and the historical occupied grid map does not have a corresponding likelihood map, then the multi-layer likelihood map is fully loaded to obtain the target likelihood map.

[0071] If there is an offset between the occupied raster map and the historical occupied raster map, and the historical occupied raster map has a corresponding likelihood map, then the target layer with the offset in the multi-layer likelihood map is obtained. The target layer with the offset is incrementally loaded, and the multi-layer likelihood map is updated based on the incrementally loaded target layer and the first layer to obtain the target likelihood map. If there is an offset between the occupied raster map and the historical occupied raster map, and the historical occupied raster map does not have a corresponding likelihood map, then the multi-layer likelihood map is fully loaded to obtain the target likelihood map. This method can determine whether the historical occupied raster map has undergone effective Gaussian processing based on whether it has a corresponding likelihood map. If it has undergone effective Gaussian processing, the target layer is incrementally loaded; otherwise, the multi-layer likelihood map is fully loaded. This reduces the computational cost of updating the multi-layer likelihood map, thereby improving the update efficiency of the multi-layer likelihood map.

[0072] The technical solution of this embodiment obtains the occupied grid map corresponding to the current location; performs Gaussian processing on the occupied grid map to obtain a multi-layer likelihood map; if it is determined that the multi-layer likelihood map has an offset based on the occupied grid map, the multi-layer likelihood map is updated to obtain the target likelihood map. This solves the problem of low efficiency caused by high computational cost when locating vehicles based on semantic information, reduces the computational cost of the likelihood map, and improves the positioning efficiency.

[0073] Example 2

[0074] Figure 2 This is a schematic diagram of a likelihood map updating device according to Embodiment 2 of the present invention. This embodiment is applicable to likelihood map updating. The device can be implemented in software and / or hardware, and can be integrated into any device that provides likelihood map updating functionality, such as... Figure 2 As shown, the likelihood map update device specifically includes: an acquisition module 210, an acquisition module 220, and an update module 230.

[0075] The acquisition module 210 is used to acquire the occupied grid map corresponding to the current location;

[0076] The obtaining module 220 is configured to perform Gaussian processing on the occupancy grid map to obtain a multi-layer likelihood map.

[0077] The updating module 230 is configured to update the multi-layer likelihood map to obtain a target likelihood map if it is determined that the multi-layer likelihood map has a deviation according to the occupancy grid map.

[0078] Optionally, the obtaining module is specifically configured to:

[0079] obtain map data of a current position or sensor information of the current position.

[0080] determine an occupancy grid map according to the map data or the sensor information of the current position.

[0081] Optionally, the obtaining module is specifically configured to:

[0082] determine a target feature sequence of each type of map element according to sensor information of a current position.

[0083] determine an occupancy grid map of the current position according to the target feature sequence of each type of map element and a preset feature sequence corresponding to each type of map element.

[0084] Optionally, the obtaining module is specifically configured to:

[0085] obtain a Gaussian kernel parameter corresponding to each type of map element in the occupancy grid map.

[0086] perform Gaussian processing on the occupancy grid map according to the Gaussian kernel parameter corresponding to each type of map element to obtain a multi-layer likelihood map.

[0087] Optionally, the updating module is specifically configured to:

[0088] if the occupancy grid map has a deviation from a historical occupancy grid map and the historical occupancy grid map has a corresponding likelihood map, obtain a target layer having a deviation in the multi-layer likelihood map.

[0089] perform incremental loading on the target layer having a deviation, and update the multi-layer likelihood map according to the target layer after the incremental loading and a first layer to obtain a target likelihood map, wherein the first layer is a layer in the multi-layer likelihood map that does not have a deviation.

[0090] Optionally, the updating module is specifically configured to:

[0091] if the occupancy grid map has a deviation from a historical occupancy grid map and the historical occupancy grid map does not have a corresponding likelihood map, perform full loading on the multi-layer likelihood map to obtain a target likelihood map.

[0092] The above product can perform the method provided by any embodiment of the application, has the corresponding function modules and beneficial effects of performing the method.

[0093] Embodiment Three

[0094] Figure 3 is a structural schematic diagram of an electronic device in Embodiment Three of the application. The electronic device is intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular telephones, smart phones, wearable devices (such as headsets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the application described and / or claimed in this document.

[0095] As shown in Figure 3 The electronic device 10 includes at least one processor 11, and a memory, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., which is communicatively connected to the at least one processor 11, wherein the memory stores a computer program that can be executed by the at least one processor. The processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or loaded into the random access memory (RAM) 13 from the storage unit 18. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0096] A plurality of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, a loudspeaker, etc.; a storage unit 18, such as a magnetic disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network, such as the Internet, and / or various telecommunication networks.

[0097] The processor 11 can be various general and / or special purpose processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, and the like. The processor 11 performs various methods and processes described above, such as the likelihood map updating method.

[0098] In some embodiments, the likelihood map updating method can be implemented as a computer program tangibly embodied in a computer readable storage medium, such as the storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed onto the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded onto the RAM 13 and executed by the processor 11, one or more steps of the likelihood map updating method described above can be performed. Alternatively, in other embodiments, the processor 11 can be configured to perform the likelihood map updating method by any other suitable means, such as by means of firmware.

[0099] Various implementations of the systems and techniques described above can be realized in digital electronic circuitry, integrated circuitry, a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a system on a chip (SOC), a programmable logic device (PLD), a computer hardware, firmware, software, and / or combinations thereof. These various implementations can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0100] Computer programs used to implement the methods of the present application can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the computer program, when executed by the processor of the machine, implements the functions / acts specified in the flowcharts and / or block diagrams. The computer program can be executed entirely on a machine, partially on a machine, partially on a machine as a stand-alone software package, partially on a machine and partially on a remote machine or entirely on a remote machine or server.

[0101] In the context of the present application, a computer-readable storage medium can be a tangible medium that can contain or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. A computer-readable storage medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium can be a machine-readable signal medium. More specific examples of a machine-readable storage medium will include one or more lines of a program of instructions in a transitory signal, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0102] To provide for interaction with a user, the systems and techniques described here 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 a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the electronic device. Other kinds of devices can be used to provide for interaction with a user as well; 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 acoustic, speech, or tactile input.

[0103] The systems and techniques described here can be implemented in a computing system that includes a back end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front end component (e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back end, middleware, or front end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0104] The computing system can include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system, to solve the defects of large management difficulty and weak business scalability in traditional physical host and VPS service.

[0105] It should be understood that the various forms of flow shown above can be used to reorder, add or delete steps. For example, each step described in the present application can be executed in parallel, sequentially or in a different order, as long as the desired results of the technical solutions of the present application can be achieved, which is not limited herein.

[0106] The above detailed description does not constitute a limitation on the protection scope of the present application. 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 replacements and improvements made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A likelihood map update method, characterized in that, include: Get the occupied grid map corresponding to the current position; Gaussian processing is applied to the occupied grid map to obtain a multi-layer likelihood map; If it is determined from the occupied grid map that the multi-layer likelihood map has an offset, then the multi-layer likelihood map is updated to obtain the target likelihood map; The step of performing Gaussian processing on the occupied grid map to obtain a multi-layer likelihood map includes: Obtain the Gaussian kernel parameters corresponding to various map elements in the occupied grid map; Gaussian processing is performed on the occupied raster map based on the Gaussian kernel parameters corresponding to various map elements to obtain a multi-layer likelihood map. If, based on the occupied grid map, it is determined that the multi-layer likelihood map has an offset, then the multi-layer likelihood map is updated to obtain the target likelihood map, including: If there is an offset between the occupied grid map and the historical occupied grid map, and the historical occupied grid map has a corresponding likelihood map, then the target layer with the offset is obtained from the multi-layer likelihood map. Incrementally load the target layer with offset, and update the multi-layer likelihood map based on the incrementally loaded target layer and the first layer to obtain the target likelihood map, wherein the first layer is the layer in the multi-layer likelihood map that has no offset. Alternatively, if there is an offset between the occupied grid map and the historical occupied grid map, and the historical occupied grid map does not have a corresponding likelihood map, then the multi-layer likelihood map is fully loaded to obtain the target likelihood map.

2. The method according to claim 1, characterized in that, Retrieve the occupied grid map corresponding to the current location, including: Obtain map data or sensor information for the current location; The occupied grid map is determined based on map data or sensor information at the current location.

3. The method according to claim 2, characterized in that, Determine the occupied grid map based on sensor information at the current location, including: Determine the target feature sequence of various map elements based on sensor information at the current location; The current location is determined by the target feature sequence of various map elements and the preset feature sequence corresponding to various map elements.

4. A likelihood map updating device, characterized in that, include: The acquisition module is used to acquire the occupied grid map corresponding to the current location; The module is used to perform Gaussian processing on the occupied grid map to obtain a multi-layer likelihood map; The update module is used to update the multi-layer likelihood map to obtain the target likelihood map if it is determined from the occupied grid map that the multi-layer likelihood map has an offset. The module is specifically used to: obtain the Gaussian kernel parameters corresponding to various map elements in the occupied grid map; Gaussian processing is performed on the occupied raster map based on the Gaussian kernel parameters corresponding to various map elements to obtain a multi-layer likelihood map. The update module is specifically used for: if there is an offset between the occupied grid map and the historical occupied grid map, and the historical occupied grid map has a corresponding likelihood map, then obtain the target layer with the offset in the multi-layer likelihood map; incrementally load the target layer with the offset, and update the multi-layer likelihood map according to the incrementally loaded target layer and the first layer to obtain the target likelihood map, wherein the first layer is the layer in the multi-layer likelihood map that does not have an offset; The update module is further specifically used to: if there is an offset between the occupied grid map and the historical occupied grid map, and the historical occupied grid map does not have a corresponding likelihood map, then the multi-layer likelihood map is fully loaded to obtain the target likelihood map.

5. The apparatus according to claim 4, characterized in that, The acquisition module is specifically used for: Obtain map data or sensor information for the current location; The occupied grid map is determined based on map data or sensor information at the current location.

6. 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 likelihood map update method according to any one of claims 1-3.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the likelihood map update method according to any one of claims 1-3.

Images