Indoor positioning method, system and mobile tool

Abstract

Embodiments of the present invention relate to an indoor positioning method, system and mobile tool, the method comprising: obtaining a map of the second floor; obtaining first sensor data collected by an inertial measurement unit and second sensor data collected by a wheel speed meter, performing dead reckoning on the vehicle's driving trajectory, and obtaining first position information of the vehicle at the current moment; obtaining a single-frame laser point cloud collected by a lidar at the current moment; determining the automatic driving state mode of the vehicle at the current moment; when the automatic driving state mode is a positioning mode, matching the single-frame laser point cloud with the map of the second floor according to the first position information; when the match is successful, fusing the laser point clouds of a preset number of frames at and before the current moment with the first position information of a preset number of frames to obtain second position information.

Description

Technical Field

[0001] The present invention relates to the field of autonomous driving technology, and in particular to an indoor positioning method, system and mobile tool. Background Art

[0002] The domestic commercial floor cleaning sector has labor costs in the hundreds of billions of yuan, and the emergence of autonomous driving technology presents a significant opportunity to change this situation. However, indoor elevator scenarios are characterized by confined spaces, complex environments, rapid personnel flow, and a high probability of equipment being blocked. These limitations place higher demands on the stability and reliability of positioning technology. Positioning methods primarily based on visual sensors suffer from complex algorithms, high computational effort, low positioning reliability, and even inability to achieve accurate positioning. Positioning methods primarily based on multi-line lidar have drawbacks such as high cost, large data volumes, and slow positioning update frequency. Therefore, achieving accurate positioning of vehicles in indoor elevator scenarios without increasing costs is an urgent challenge. Summary of the Invention

[0003] The purpose of the present invention is to provide an indoor positioning method, system and mobile tool to address the defects of the existing technology. The method can enable the vehicle to maintain the reliability and stability of positioning in complex elevator scenarios.

[0004] To achieve the above objectives, the present invention provides an indoor positioning method in a first aspect, the indoor positioning method comprising:

[0005] Get a map of the second floor;

[0006] Obtaining first sensor data collected by the inertial measurement unit and second sensor data collected by the wheel speed meter, performing dead reckoning on the vehicle's driving trajectory, and obtaining first position information of the vehicle at a current moment;

[0007] Get the single-frame laser point cloud collected by the laser radar at the current moment;

[0008] When it is determined that the current automatic driving state mode of the vehicle is the positioning mode, matching the single-frame laser point cloud with the map of the second floor according to the first posture information;

[0009] When the match is successful, the laser point cloud of the preset number of frames at the current moment and before the current moment is fused with the first pose information of the preset number of frames to obtain the second pose information.

[0010] Preferably, before obtaining the map of the second floor, the method further includes:

[0011] When it is determined that the current vehicle's autonomous driving state mode is mapping mode;

[0012] Control the movement of vehicles starting from any position on the floor and build maps corresponding to different floors;

[0013] Mark the preset feature point positions in the map of each floor.

[0014] Further preferably, after marking the preset feature point positions in the map of each floor, the method further includes:

[0015] According to the positions and postures of the feature points of the multiple floors, a map mapping relationship between the floors is generated through a map mapping algorithm.

[0016] More preferably, obtaining the map of the second floor specifically includes:

[0017] Get the position of the vehicle at a certain point on the first floor;

[0018] Get the map mapping relationship between the first floor and the second floor;

[0019] Obtaining a position of the vehicle at a point corresponding to the second floor according to the position of the vehicle at a point on the first floor and a map mapping relationship between the first floor and the second floor;

[0020] The map of the second floor is loaded according to the position of the vehicle at a certain point corresponding to the second floor.

[0021] Preferably, the method further comprises:

[0022] When it is determined that the automatic driving state mode of the vehicle at the current moment is the ladder control mode, it is determined that the first posture information is credible.

[0023] Further preferably, the feature point position includes the coordinates and yaw angle of the feature point in the floor map.

[0024] A second aspect of the present invention provides an indoor positioning system, the indoor positioning system comprising:

[0025] A map acquisition module is used to obtain a map of the second floor;

[0026] a dead reckoning module, configured to acquire first sensor data collected by the inertial measurement unit and second sensor data collected by the wheel speed meter, perform dead reckoning on the vehicle's driving trajectory, and obtain first position information of the vehicle at a current moment;

[0027] The data receiving module is used to obtain the single-frame laser point cloud collected by the laser radar at the current moment;

[0028] A state determination module is used to determine whether the current automatic driving state mode of the vehicle is the positioning mode;

[0029] a laser matching module, configured to match the single-frame laser point cloud with a map of the second floor according to the first pose information;

[0030] The data fusion module is used to fuse the laser point cloud of the preset number of frames at the current moment and before the current moment with the first pose information of the preset number of frames to obtain the second pose information when the matching is successful.

[0031] A third aspect of the present invention provides a computer server comprising: a memory, a processor, and a transceiver;

[0032] The processor is configured to be coupled to the memory, read and execute instructions in the memory, so as to implement the indoor positioning method according to any one of the first aspects above;

[0033] The transceiver is coupled to the processor, and the processor controls the transceiver to send and receive messages.

[0034] In a fourth aspect of the present invention, a chip system is provided, comprising a processor, wherein the processor is coupled to a memory, and the memory stores program instructions. When the program instructions stored in the memory are executed by the processor, the indoor positioning method described in any one of the first aspects is implemented.

[0035] A fifth aspect of the present invention provides a mobile tool comprising the computer server described in the third aspect.

[0036] An embodiment of the present invention provides an indoor positioning method, system, and mobile tool. The method performs dead reckoning on the vehicle's driving trajectory by acquiring sensor data collected by an inertial measurement unit and a wheel speed meter to obtain predicted posture information. The predicted posture information is then used as input data for laser matching in combination with the vehicle's current automatic driving state mode, ultimately achieving accurate positioning of the vehicle in an indoor elevator scenario. This enables the vehicle to maintain reliable and stable positioning in complex elevator scenarios, solving the problem of easy loss of positioning and mispositioning in elevator scenarios faced by existing positioning methods. In addition, no hardware equipment is added during this process, which does not increase the cost of positioning. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 This is a flow chart of the indoor positioning method provided in the first embodiment of the present invention;

[0038] Figure 2 This is a second flow chart of the indoor positioning method provided in the first embodiment of the present invention;

[0039] Figure 3 This is a third flow chart of the indoor positioning method provided in the first embodiment of the present invention;

[0040] Figure 4 This is a structural diagram of the indoor positioning system provided in Example 2 of the present invention. DETAILED DESCRIPTION

[0041] To make the objectives, technical solutions, and advantages of the present invention more apparent, the present invention will be further described in detail below with reference to the accompanying drawings. It is apparent that the embodiments described are only some, not all, of the present invention. All other embodiments derived by persons of ordinary skill in the art based on the embodiments of the present invention without creative effort are intended to fall within the scope of protection of the present invention.

[0042] Those skilled in the art will appreciate that the embodiments of the present application may be implemented as a system, apparatus, device, method, or computer program product. Therefore, the present disclosure may be implemented in the following forms: entirely in hardware, entirely in software (including firmware, resident software, microcode, etc.), or in a combination of hardware and software.

[0043] For ease of understanding, the technical terms involved in this application are explained below:

[0044] The mobile tool referred to in this application may be a vehicle device or a robotic device having the following functions:

[0045] (1) Passenger-carrying function, such as family cars and buses;

[0046] (2) Cargo carrying function, such as ordinary trucks, box trucks, trailer trucks, closed trucks, tank trucks, flatbed trucks, container trucks, dump trucks, special structure trucks, etc.;

[0047] (3) Tool functions, such as logistics delivery vehicles, automated guided vehicles (AGVs), patrol cars, cranes, hoists, excavators, bulldozers, forklifts, rollers, loaders, off-road engineering vehicles, armored engineering vehicles, sewage treatment vehicles, sanitation vehicles, vacuum trucks, floor scrubbers, sprinkler trucks, sweeping robots, food delivery robots, shopping guide robots, lawn mowers, golf carts, etc.;

[0048] (4) Entertainment functions, such as entertainment vehicles, amusement park self-driving devices, balance vehicles, etc.;

[0049] (5) Special rescue functions, such as fire trucks, ambulances, power repair trucks, engineering rescue trucks, etc.

[0050] The above-mentioned various vehicles include but are not limited to vehicles with six autonomous driving technology levels, L0-L5, as established by the Society of Automotive Engineers International (SAE International) or the Chinese national standard "Automotive Driving Automation Classification".

[0051] In some embodiments, the mobile tool is a cleaning device with a cleaning function, for example, it can be a floor scrubber / floor scrubber, a floor sweeper / floor sweeper, a floor sweeping robot, a sanitation vehicle, a cleaning machine, a vacuum cleaner / dust pusher, and other equipment that utilizes autonomous driving technology. Its application scenarios include, for example, cleaning multi-story buildings.

[0052] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments.

[0053] The indoor positioning method provided by the embodiment of the present invention applies autonomous driving technology to indoor elevator scenarios, and can ensure the reliability and stability of vehicle positioning in indoor elevators without increasing costs.

[0054] Example 1

[0055] Figure 1 This is one of the flow charts of the indoor positioning method provided in the first embodiment of the present invention. The indoor positioning method is applicable to an indoor unmanned vehicle equipped with a laser radar, an inertial measurement unit, and a wheel speed meter, such as an unmanned sweeper. The execution subject of the method is a device with computing capabilities such as a processor, such as an automatic processing unit of an unmanned sweeper. For the sake of clarity, the unmanned sweepers in the following embodiments are referred to as vehicles. Figure 1 As shown in , the indoor positioning method provided by the embodiment of the present invention mainly includes the following steps:

[0056] Step 110: Get a map of the second floor.

[0057] Specifically, a map for each floor is pre-created and stored. Therefore, when the vehicle arrives at each floor, it can load the map for that floor based on the vehicle's initial position at that floor, enabling map switching between floors for positioning. The second floor can be understood as the floor the vehicle is currently on. For clarity, "second" does not necessarily refer to the second floor.

[0058] More specifically, the initial position of the vehicle on the second floor can be obtained by, but not limited to, the following methods:

[0059] Method A: By processing the data collected by the vehicle's sensors, the initial position of the vehicle on the floor is calculated.

[0060] Method B: Input the initial pose through the terminal device and send it to the vehicle.

[0061] Method C: Send an initial pose acquisition request to the cloud server and receive the initial pose returned by the cloud server based on the request.

[0062] In this example, the vehicle obtains its initial position on the floor through method A. Figure 2 The steps in implementation:

[0063] Step S1, obtaining the position of a certain point of the vehicle on the first floor.

[0064] Specifically, the first floor can be understood as the floor where the vehicle is before reaching the second floor. For ease of calculation, a point can be selected that is common to both the first and second floors. For example, an elevator waiting area, a restroom, or a representative location.

[0065] Step S2: Obtain a map mapping relationship between the first floor and the second floor.

[0066] Specifically, the map mapping relationship between different floors is established after the map of each floor is built. The vehicle can obtain the map mapping relationship between different floors based on the floor ID.

[0067] Before step 110, the method further includes constructing maps of each floor and establishing map mapping relationships. The specific process is as follows: Figure 3 As shown in:

[0068] Step 101: Determine whether the current automatic driving state mode of the vehicle is a mapping mode.

[0069] Specifically, due to the complexity of indoor elevator scenarios, and to ensure reliable and stable positioning, the present invention divides the vehicle's operating modes into idle and autonomous driving modes. Idle mode can be understood as the state when the vehicle is stationary and the wheel speed data is zero. Autonomous driving modes include mapping mode, positioning mode, and elevator control mode. The vehicle can receive platform dispatch instructions to switch between different modes. Therefore, when building a floor map, it is first necessary to ensure that the vehicle is in mapping mode.

[0070] Step 102: Control the movement of the vehicle starting from any position on the floor to construct maps corresponding to different floors.

[0071] Specifically, the maps corresponding to different floors are real-time positioning maps created through online nonlinear optimization. This application primarily uses an extended Kalman filter to fuse sensor data collected by an inertial measurement unit and wheel speedometer, recursively obtaining relatively accurate position information. Maps are then created through LiDAR point cloud matching. To facilitate subsequent calculations, the floor map can be a two-dimensional grid map.

[0072] Step 103: Mark the preset feature point positions in the map of each floor.

[0073] Specifically, the preset feature points can be understood as common to every floor, such as elevator waiting points or corridor corners. In this example, the elevator waiting points are used as feature points, and each floor's elevator waiting point is fixed at the center of the elevator interior, with the elevator car facing the elevator door. The feature point pose in this example can be understood as the coordinates and yaw angle of each floor's elevator waiting point within its corresponding floor map.

[0074] Assume that the position of the waiting point on the first floor is (x a ,y a ,θ a ), the waiting position of the same elevator on the second floor is (x b ,y b ,θ b ). Where x, y are the coordinates of the vehicle in the map of that floor relative to the map origin, and θ is the yaw angle of the vehicle relative to the map origin.

[0075] Step 104 : Generate a map mapping relationship between the floors using a map mapping algorithm based on the positions and postures of the feature points of the multiple floors.

[0076] Specifically, the map mapping relationship can be understood as the posture mapping relationship of any point on each floor.

[0077] Assume that the position of any point on the first floor is (x, y, θ), and the position of the corresponding point on the second floor is (x′, y′, θ′).

[0078] Among them, the pose of any point corresponding to the second floor and the pose of any point on the first floor satisfy the following mapping relationship:

[0079]

[0080] in,

[0081]

[0082] Step S3, obtaining the position of the vehicle at a point on the second floor according to the position of the vehicle at a point on the first floor and the map mapping relationship between the first floor and the second floor.

[0083] Specifically, for example, when a vehicle ascends / descends from the elevator on the first floor to the second floor, its position in the elevator on the first floor map is first recorded, and then the corresponding position of the vehicle in the elevator on the second floor map is obtained through the map mapping relationship.

[0084] Step S4: loading the map of the second floor according to the position of the vehicle corresponding to a certain point on the second floor.

[0085] Specifically, this step realizes map switching between different floors.

[0086] Step 120 , obtaining the first sensor data collected by the inertial measurement unit and the second sensor data collected by the wheel speed meter, performing dead reckoning on the vehicle's driving trajectory, and obtaining the first position information of the vehicle at the current moment.

[0087] Specifically, the first sensor data may include angular velocity information and acceleration information. The second sensor data may include wheel speed information for the vehicle's left and right wheels. Dead reckoning is performed on the first and second sensor data using a recursive filtering algorithm to obtain the vehicle's first position information at the current moment. The first position information includes position information and attitude information. It is understood that the first position information is predicted information.

[0088] It should be noted that dead reckoning will have a drift problem with time integration. Therefore, when the vehicle is in idle mode, dead reckoning is not performed to reduce the error of dead reckoning.

[0089] Step 130: Obtain a single-frame laser point cloud collected by the laser radar at the current moment.

[0090] Specifically, the laser radar can collect laser point clouds in real time, and the present application can process the laser point clouds frame by frame. The laser radar can be a low-beam laser radar, such as a single-line laser radar, a four-line laser radar, etc.

[0091] Step 140: Determine whether the current automatic driving state mode of the vehicle is the positioning mode.

[0092] Specifically, when the automatic driving state mode is the positioning mode, execute steps 150-160.

[0093] Step 150: Match the single-frame laser point cloud with the map of the second floor according to the first pose information.

[0094] Specifically, in order to achieve stable, accurate and high-frequency positioning data, the first pose information can be used not only as output data for real-time positioning, but also as input data for laser matching.

[0095] Because the pre-built floor map is a two-dimensional grid map, this step eliminates the need for rasterization. Centered on the first pose information, the laser matching is performed within a preset size range within the second floor map. The specific matching process utilizes existing techniques and will not be detailed here.

[0096] If the match is successful, step 160 is executed. If the match is unsuccessful, step 161 is executed, and steps 150-160 are repeated.

[0097] Step 160 , fusing the laser point cloud of the current moment and a preset number of frames before the current moment with the first pose information of the preset number of frames to obtain second pose information.

[0098] Specifically, the second pose information can be understood as the accurate pose of the vehicle. A sliding window filter can be used to fuse the laser point cloud of a preset number of frames with the first pose information of a preset number of frames. The preset number of frames can specifically be 10 frames.

[0099] Step 161: Reacquire the vehicle's position information and perform laser matching.

[0100] Specifically, if the current single-frame laser point cloud fails to match the second floor's grid map, or if the matching time exceeds a preset threshold, the laser matching is considered a failure. The user can resend the vehicle's position information through the user terminal as initialization data for laser matching and retry the laser matching. The vehicle can also retrieve new position information from the cloud server as initialization data for laser matching.

[0101] Step 170: When it is determined that the current automatic driving state mode of the vehicle is the elevator control mode, the first position information is determined to be credible.

[0102] Specifically, due to the inherent characteristics of LiDAR, when a vehicle encounters an elevator, laser matching positioning may result in errors or mispositioning. Therefore, in this example, when the vehicle enters the elevator, it switches to elevator control mode via platform dispatch instructions. At this point, the first position information is output as real-time positioning data. In other words, in elevator control mode, laser matching is no longer performed. After the vehicle exits the elevator, it switches to positioning mode as soon as possible. By switching between elevator control and positioning modes, and processing data differently in each mode, the vehicle can maintain reliable and stable positioning in complex elevator scenarios, solving the problem of easy loss of positioning and mispositioning in elevator scenarios faced by existing positioning methods. Furthermore, no hardware equipment is added during this process, which does not increase the cost of positioning.

[0103] An embodiment of the present invention provides an indoor positioning method, system, and mobile tool. The method performs dead reckoning on the vehicle's driving trajectory by acquiring sensor data collected by an inertial measurement unit and a wheel speed meter to obtain predicted posture information. The predicted posture information is then used as input data for laser matching in combination with the vehicle's current automatic driving state mode, ultimately achieving accurate positioning of the vehicle in an indoor elevator scenario. This enables the vehicle to maintain reliable and stable positioning in complex elevator scenarios, solving the problem of easy loss of positioning and mispositioning in elevator scenarios faced by existing positioning methods. In addition, no hardware equipment is added during this process, which does not increase the cost of positioning.

[0104] Example 2

[0105] Figure 4 This is a structural diagram of the indoor positioning system provided by the second embodiment of the present invention, such as Figure 4 As shown in , the indoor positioning system includes:

[0106] A map acquisition module 10 is used to acquire a map of the second floor;

[0107] The dead reckoning module 20 is configured to obtain the first sensor data collected by the inertial measurement unit and the second sensor data collected by the wheel speed meter, perform dead reckoning on the vehicle's driving trajectory, and obtain the first position information of the vehicle at the current moment;

[0108] The data receiving module 30 is used to obtain a single-frame laser point cloud collected by the laser radar at the current moment;

[0109] A state determination module 40 is used to determine whether the current automatic driving state mode of the vehicle is the positioning mode;

[0110] A laser matching module 50 is used to match the single-frame laser point cloud with the map of the second floor according to the first pose information;

[0111] The data fusion module 60 is used to fuse the laser point cloud of the current moment and a preset number of frames before the current moment with the first pose information of the preset number of frames to obtain the second pose information when the matching is successful.

[0112] An indoor positioning system provided in the second embodiment of the present invention can execute the method steps in the above-mentioned method embodiment one, wherein the map acquisition module 10 implements step 110, the track calculation module 20 implements step 120, the data receiving module 30 implements step 130, the state determination module 40 implements step 140, the laser matching module 50 implements step 150, and the data fusion module 60 implements step 160.

[0113] The specific implementation principles and technical effects are similar and will not be repeated here.

[0114] It should be noted that it should be understood that the division of the various modules of the above device is merely a division of logical functions. In actual implementation, they can be fully or partially integrated into one physical entity, or they can be physically separated. Moreover, these modules can all be implemented in the form of software called by a processing element; or they can all be implemented in the form of hardware; or some modules can be implemented in the form of software called by a processing element, and some modules can be implemented in the form of hardware. For example, the determination module can be a separately established processing element, or it can be integrated into a chip of the above device. In addition, it can also be stored in the memory of the above device in the form of program code, and called by a processing element of the above device to perform the functions of the above determination module. The implementation of other modules is similar. In addition, these modules can all or partly be integrated together, or they can be implemented independently. The processing element described here can be an integrated circuit with signal processing capabilities. In the implementation process, each step of the above method or each of the above modules can be completed by the hardware integrated logic circuit in the processor element or by instructions in the form of software.

[0115] For example, the above modules may be one or more integrated circuits configured to implement the above methods, such as one or more application-specific integrated circuits (ASICs), one or more microprocessors (DSPs), or one or more field programmable gate arrays (FPGAs). For another example, when a module is implemented by scheduling program code through a processing element, the processing element may be a general-purpose processor, such as a central processing unit (CPU) or other processor that can call program code. For another example, these modules may be integrated together and implemented in the form of a system-on-a-chip (SOC).

[0116] In the above embodiments, all or part of the embodiments may be implemented using software, hardware, firmware, or any combination thereof. When implemented using software, all or part of the embodiments may be implemented in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions described in the embodiments of the present application are generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The above-mentioned computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the above-mentioned computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center via wired (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, Bluetooth, microwave, etc.) means. The above-mentioned computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that includes one or more available media. The above-mentioned available medium can be a magnetic medium (such as a floppy disk, hard disk, tape), an optical medium (such as a DVD), or a semiconductor medium (such as a solid state disk (SSD)), etc.

[0117] Example 3

[0118] A third embodiment of the present invention provides a computer server, comprising: a memory, a processor, and a transceiver;

[0119] The processor is configured to be coupled to the memory, read and execute instructions in the memory, so as to implement the indoor positioning method of any one of the above-mentioned embodiments;

[0120] The transceiver is coupled to the processor, and the processor controls the transceiver to send and receive messages.

[0121] Example 4

[0122] A fourth embodiment of the present invention provides a chip system, including a processor, wherein the processor is coupled to a memory, and the memory stores program instructions. When the program instructions stored in the memory are executed by the processor, the indoor positioning method of any one of the above-mentioned embodiments is implemented.

[0123] Example 5

[0124] A fifth embodiment of the present invention provides a mobile tool, including the computer server described in the third embodiment above.

[0125] Professionals should also be further aware that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the above description has generally described the components and steps of each example according to their functions. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0126] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein may be implemented using hardware, a software module executed by a processor, or a combination of the two. The software module may be placed in a random access memory (RAM), internal memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0127] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. An indoor positioning method, characterized in that: The indoor positioning method comprises: Get the map of the second floor; Obtaining first sensor data collected by the inertial measurement unit and second sensor data collected by the wheel speed meter, performing dead reckoning on the vehicle's driving trajectory, and obtaining first position information of the vehicle at a current moment; Get the single-frame laser point cloud collected by the laser radar at the current moment; When it is determined that the current automatic driving state mode of the vehicle is the positioning mode, matching the single-frame laser point cloud with the map of the second floor according to the first posture information; When the match is successful, the laser point cloud of the current moment and the preset number of frames before the current moment is fused with the first pose information of the preset number of frames to obtain the second pose information; Before obtaining the map of the second floor, the method further includes: When the vehicle's current autonomous driving mode is determined to be mapping mode, the vehicle is controlled to move starting from any position on the floor to construct maps corresponding to different floors. Mark the preset feature point positions in the map of each floor; After marking the preset feature point positions in the map of each floor, the method further includes: According to the positions of the feature points of the multiple floors, a map mapping relationship between the floors is generated by a map mapping algorithm; The obtaining of the map of the second floor specifically includes: Get the position of the vehicle at a certain point on the first floor; Get the map mapping relationship between the first floor and the second floor; Obtaining a position of the vehicle at a point corresponding to the second floor according to the position of the vehicle at a point on the first floor and a map mapping relationship between the first floor and the second floor; Loading a map of the second floor according to the position of the vehicle at a certain point corresponding to the second floor; The method further comprises: When it is determined that the automatic driving state mode of the vehicle at the current moment is the ladder control mode, it is determined that the first posture information is credible.

2. The indoor positioning method according to claim 1, characterized in that: The feature point position includes the coordinates and yaw angle of the feature point in the floor map.

3. An indoor positioning system, characterized in that: The indoor positioning system comprises: The map acquisition module is used to obtain the map of the second floor; specifically includes: Get the position of the vehicle at a certain point on the first floor; Get the map mapping relationship between the first floor and the second floor; Obtaining a position of the vehicle at a point corresponding to the second floor according to the position of the vehicle at a point on the first floor and a map mapping relationship between the first floor and the second floor; Loading a map of the second floor according to the position of the vehicle at a certain point corresponding to the second floor; a dead reckoning module, configured to acquire first sensor data collected by the inertial measurement unit and second sensor data collected by the wheel speed meter, perform dead reckoning on the vehicle's driving trajectory, and obtain first position information of the vehicle at a current moment; The data receiving module is used to obtain the single-frame laser point cloud collected by the laser radar at the current moment; a state determination module for determining whether the current autonomous driving state mode of the vehicle is a positioning mode, and matching the single-frame laser point cloud with the map of the second floor based on the first pose information; the state determination module is further configured to determine whether the first pose information is credible when the current autonomous driving state mode of the vehicle is an elevator control mode; and before obtaining the map of the second floor, the state determination module is further configured to control vehicle movement starting from any position on the floor to construct maps corresponding to different floors when the current autonomous driving state mode of the vehicle is a mapping mode; and mark preset feature point poses in the map of each floor; a laser matching module, configured to match the single-frame laser point cloud with a map of the second floor according to the first pose information; The data fusion module is used to fuse the laser point cloud of the current moment and a preset number of frames before the current moment with the first pose information of a preset number of frames to obtain the second pose information when the match is successful; the data fusion module is also used to mark the preset feature point poses in the map of each floor, and then generate the map mapping relationship between the floors according to the feature point poses of multiple floors through a map mapping algorithm.

4. A computer server, characterized in that: include: memory, processors, and transceivers; The processor is configured to be coupled to the memory, read and execute instructions in the memory, so as to implement the indoor positioning method according to any one of claims 1 to 2; The transceiver is coupled to the processor, and the processor controls the transceiver to send and receive messages.

5. A chip system, characterized in that: The invention comprises a processor coupled to a memory, wherein the memory stores program instructions, and when the program instructions stored in the memory are executed by the processor, the indoor positioning method according to any one of claims 1 to 2 is implemented.

6. A mobile tool, characterized in that: The computer server comprising the above-mentioned claim 4.

Images