CN114739388B - Indoor positioning navigation method and system based on UWB and laser radar - Google Patents
Indoor positioning navigation method and system based on UWB and laser radar Download PDFInfo
- Publication number
- CN114739388B CN114739388B CN202210417905.3A CN202210417905A CN114739388B CN 114739388 B CN114739388 B CN 114739388B CN 202210417905 A CN202210417905 A CN 202210417905A CN 114739388 B CN114739388 B CN 114739388B
- Authority
- CN
- China
- Prior art keywords
- target
- position information
- indoor
- uwb
- determining
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/005—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 with correlation of navigation data from several sources, e.g. map or contour matching
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/20—Instruments for performing navigational calculations
- G01C21/206—Instruments for performing navigational calculations specially adapted for indoor navigation
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/38—Electronic maps specially adapted for navigation; Updating thereof
- G01C21/3804—Creation or updating of map data
- G01C21/3807—Creation or updating of map data characterised by the type of data
- G01C21/3811—Point data, e.g. Point of Interest [POI]
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/38—Electronic maps specially adapted for navigation; Updating thereof
- G01C21/3804—Creation or updating of map data
- G01C21/3807—Creation or updating of map data characterised by the type of data
- G01C21/383—Indoor data
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/38—Electronic maps specially adapted for navigation; Updating thereof
- G01C21/3804—Creation or updating of map data
- G01C21/3833—Creation or updating of map data characterised by the source of data
- G01C21/3841—Data obtained from two or more sources, e.g. probe vehicles
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/30—Services specially adapted for particular environments, situations or purposes
- H04W4/33—Services specially adapted for particular environments, situations or purposes for indoor environments, e.g. buildings
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W64/00—Locating users or terminals or network equipment for network management purposes, e.g. mobility management
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks
Abstract
The invention relates to the technical field of positioning navigation, and discloses an indoor positioning navigation method and system based on UWB and laser radar, aiming at improving indoor positioning navigation precision and realizing real-time updating of an indoor map, wherein the scheme mainly comprises the following steps: determining first position information of a target to be positioned in real time through a UWB positioning device; acquiring indoor point cloud data in real time through a laser radar positioning device, constructing an indoor map based on the point cloud data, and detecting and obtaining all similar objects corresponding to a target to be positioned; and determining the target to be positioned from all similar objects according to the first position information, determining second position information of the target to be positioned through an indoor map, and determining real-time position information of the target to be positioned according to the second position information. The invention realizes the real-time update of the indoor map and improves the accuracy of indoor positioning navigation, and is particularly suitable for analyzing the activity condition of indoor personnel.
Description
Technical Field
The invention relates to the technical field of positioning navigation, in particular to an indoor positioning navigation method and system based on UWB and laser radar.
Background
The working principle of the laser radar is that laser is used as a signal source, pulse laser is emitted by a laser, the pulse laser causes scattering under the action of an object in reality, a part of light waves can be reflected to a receiver of the laser radar, the distance from the laser radar to a target point is obtained through calculation according to the laser ranging principle, the pulse laser continuously scans the target object, data of all the target points on the target object can be obtained, and an accurate three-dimensional image can be obtained after imaging processing is carried out by using the data.
Although the current method for indoor positioning and navigation based on the laser radar can accurately determine the relative position of a target to be positioned, the method can position the target only by taking an accurate indoor map as a reference system, and when the movable area is changed due to the change of the arrangement of indoor objects and the indoor map is not updated, navigation errors can be caused, so that the navigation precision is reduced.
Disclosure of Invention
The invention aims to provide an indoor positioning navigation method and system based on UWB and laser radar, so as to improve the accuracy of indoor positioning navigation and realize real-time update of an indoor map.
The technical scheme adopted by the invention for solving the technical problems is as follows:
in one aspect, an indoor positioning navigation method based on UWB and laser radar is provided, comprising the following steps:
determining first position information of a target to be positioned in real time through a UWB positioning device, wherein the UWB positioning device comprises at least three UWB base stations;
acquiring indoor point cloud data in real time through a laser radar positioning device, constructing an indoor map based on the point cloud data, and detecting and obtaining all similar objects corresponding to targets to be positioned, wherein the laser radar positioning device comprises at least three laser radars;
and determining the target to be positioned from all similar objects according to the first position information, determining second position information of the target to be positioned through the indoor map, and determining real-time position information of the target to be positioned according to the second position information.
Further, the determining, by the UWB positioning device, the first position information of the object to be positioned specifically includes:
each UWB base station receives a positioning signal sent by a target to be positioned in real time, and distance information between the target to be positioned and each UWB base station is respectively determined according to the transmission time of the positioning signal;
and correcting each distance information, and determining first position information of the target to be positioned based on the CKF algorithm according to the corrected distance information.
Further, the detecting obtains all similar objects corresponding to the target to be positioned, specifically including:
training a convolutional neural network for identifying the type of the target, inputting the point cloud data into the convolutional neural network, obtaining all similar objects corresponding to the target to be positioned, and labeling 3D rectangular frames on the similar objects.
Further, the training is used for identifying the convolutional neural network of the target type, and specifically comprises the following steps:
and acquiring training point cloud data in a data set ScanNet-V2, generating two types of mixed three-dimensional characteristics of voxel points and voxels based on the double-stream encoder according to the training point cloud data, and training according to the training point cloud data and the mixed three-dimensional characteristics to obtain a convolutional neural network for identifying the target type.
Further, the method for determining the second position information includes:
and determining a centroid corresponding to the 3D rectangular frame marked on the target to be positioned, taking the coordinate of the centroid as the real-time position coordinate of the target to be positioned, and obtaining second position information of the target to be positioned according to the real-time position coordinate and based on an indoor map.
Further, the construction method of the indoor map comprises the following steps:
and obtaining the scale perception characteristics of the indoor actual object based on the convolutional neural network according to the point cloud data, performing scale transformation on the indoor model corresponding to the indoor model library according to the scale perception characteristics to obtain the indoor model with the same size as the actual object, performing corresponding angle rotation and displacement on the indoor models with the same size to form an indoor environment, supplementing the missed object characteristics in the indoor environment, and finally performing visual output on RVIZ to complete the construction of an indoor map.
Further, the UWB positioning device comprises four UWB base stations, the laser radar positioning device comprises four laser radars, each UWB base station and one laser radar form integrated equipment, and the four integrated equipment are respectively arranged around the room.
Further, the method further comprises:
and acquiring the starting position information and the destination position information of the target to be positioned, and determining a navigation path based on Dijkstra algorithm according to the starting position information and the destination position information of the target to be positioned.
Further, the determining a navigation path according to the starting position information and the destination position information of the target to be positioned and based on Dijkstra algorithm specifically includes:
expanding layer by layer outwards by taking the starting position as the center until expanding to the destination position;
starting from the initial position, searching a plurality of path points capable of reaching the destination position of each layer according to a preset searching distance range, determining the path point with the shortest distance with the initial position, and repeating the operation until the path point on the penultimate layer is determined by taking the determined path point as the initial position;
and sequentially connecting the starting position, the determined path point and the destination position to obtain the navigation path.
In another aspect, there is provided an indoor positioning navigation system based on UWB and lidar, comprising:
the UWB positioning device comprises at least three UWB base stations and is used for determining first position information of a target to be positioned in real time;
the laser radar positioning device comprises at least three laser radars and is used for acquiring indoor point cloud data in real time, constructing an indoor map based on the point cloud data and detecting and obtaining all similar objects corresponding to a target to be positioned;
the data processing device is used for determining the target to be positioned from all similar objects according to the first position information, determining second position information of the target to be positioned through the indoor map, and determining real-time position information of the target to be positioned according to the second position information.
Further, the method further comprises the following steps:
the navigation device is used for acquiring the starting position information and the destination position information of the target to be positioned, and determining a navigation path based on Dijkstra algorithm according to the starting position information and the destination position information of the target to be positioned.
The beneficial effects of the invention are as follows: according to the indoor positioning navigation method and system based on the UWB and the laser radar, the laser radar positioning device is used for carrying out real-time 3D mapping, so that a more stable and accurate indoor map is obtained, and the accurate positioning of an indoor target to be positioned is realized by matching with the UWB positioning technology through a target detection algorithm of the laser radar. In addition, the invention builds the display environment map based on the existing database, can well avoid the interference generated by noise, and solves the problem of excessive map burrs.
Drawings
FIG. 1 is a schematic flow chart of an indoor positioning navigation method based on UWB and laser radar according to an embodiment of the invention;
FIG. 2 is a schematic flow chart of determining first position information of a UWB positioning device according to an embodiment of the invention;
FIG. 3 is a schematic diagram of deep learning of a lidar positioning device according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of an algorithm of navigation path planning according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of an indoor positioning navigation system based on UWB and lidar according to an embodiment of the present invention.
Detailed Description
Embodiments of the present invention will be described in detail below with reference to the accompanying drawings.
The invention provides an indoor positioning navigation method and system based on UWB and laser radar, which mainly adopts the technical conception as follows: determining first position information of a target to be positioned in real time through a UWB positioning device, wherein the UWB positioning device comprises at least three UWB base stations; acquiring indoor point cloud data in real time through a laser radar positioning device, constructing an indoor map based on the point cloud data, and detecting and obtaining all similar objects corresponding to targets to be positioned, wherein the laser radar positioning device comprises at least three laser radars; and determining the target to be positioned from all similar objects according to the first position information by the data processing device, determining the second position information of the target to be positioned by the indoor map, and determining the real-time position information of the target to be positioned according to the second position information.
Specifically, the invention requires the fixed arrangement of at least three UWB base stations and at least three laser radars in the room and the fixed arrangement of UWB tags on the target to be positioned before positioning navigation. When a target to be positioned is required to be positioned, a positioning signal is transmitted through a UWB tag carried by the target to be positioned, and the UWB positioning device determines first position information of the target to be positioned according to the positioning signal transmitted by the UWB tag, wherein the first position information is only approximate position information determined according to the UWB positioning device and cannot reflect the accurate position of the target to be positioned. Meanwhile, the laser radar positioning device emits pulse laser in real time and receives light waves reflected by indoor objects, so that real-time scanning of indoor environments is realized, indoor real-time point cloud data are obtained, an indoor map is constructed in real time according to the point cloud data, target detection is carried out, and targets to be positioned cannot be distinguished because the target detection can only detect the same type of objects, and therefore the targets to be positioned are determined from a plurality of similar objects according to first position information determined by the UWB positioning device. The coordinate information returned by the laser radar is a true value reflected by the laser, so that the accuracy is high, and therefore, after the target to be positioned is determined, the second position information of the target to be positioned in the indoor map is determined according to the target to be positioned detected by the laser radar positioning device, and finally, the real-time position information of the target to be positioned is determined according to the second position information, so that the real-time positioning of the target to be positioned is completed.
Examples
According to the indoor positioning navigation method based on UWB and laser radar, disclosed by the embodiment of the invention, the accurate positioning navigation of the target to be positioned can be realized by combining the laser radar point cloud deep learning technology with the indoor UWB positioning technology, wherein the target to be positioned can be a moving target such as a person, a robot and the like, as shown in fig. 1, and the method specifically comprises the following steps:
specifically, UWB (Ultra Wide Band) technology is a wireless carrier communication technology using a frequency bandwidth of 1GHz or more, which does not require the use of carriers in a conventional communication system, but transmits data by transmitting and receiving extremely narrow pulses having nanoseconds or less, thereby having a bandwidth of the order of GHz. The UWB has the advantages of strong penetrating power, low power consumption, good multipath resistance effect, high safety, low system complexity and the like, and has very high positioning accuracy and positioning precision.
In this embodiment, at least three UWB base stations are first fixedly disposed in a room, UWB tags are fixedly disposed on an object to be positioned, and then first position information of the object to be positioned is determined in real time by a UWB positioning device, which specifically includes:
each UWB base station receives a positioning signal sent by a target to be positioned in real time, and distance information between the target to be positioned and each UWB base station is respectively determined according to the transmission time of the positioning signal; and correcting each distance information, and determining first position information of the target to be positioned according to the corrected distance information and based on a CKF (Cubature Kalman Filter, volume Kalman filtering) algorithm.
It can be appreciated that the principle of operation of the UWB positioning device is: the distance radius is determined by the time difference between the positioning signals transmitted by the UWB tag and the UWB base stations, and the approximate position of the UWB tag can be determined by respectively drawing the communication radius of the received signals by at least three UWB base stations.
The main flow of the UWB positioning device for processing data information comprises the following steps: firstly, UWB is developed and driven in an ROS system, effective information is extracted after the original data of the ROS is obtained, CKF filtering calculation is carried out, and coordinate analysis is achieved.
The data transmitted by the UWB positioning device has three types in total, the header is ma, the original distance between the positioning tag and the UWB base station is mr, the corrected distance between the positioning tag and the UWB base station is mc, and the header is used for judging the data of the data valid bit.
As shown in fig. 2, the embodiment is divided into three parts altogether to perform coordinate analysis to obtain the first position information of the target to be positioned, which are respectively serial port data analysis, filtering and resolving, and node and coordinate system release.
The first part is serial data analysis, specifically, whether the fifth character is 07 is judged first, if not, if yes, the received data is packed, then the m-head packing is first identified, then a, r or c is identified, in order to improve the positioning accuracy, the embodiment uses corrected distance information, so that only the data after the mc-head is packed in a new array, hexadecimal data is analyzed, the distance information is split, and data in a Raw Message format is generated.
The second part is filtering and resolving, namely, the position of the UWB tag is resolved according to the distance information filtering of the UWB tag and a plurality of UWB base stations, specifically, in the embodiment, a file of Hpp relevant to a CKF filtering algorithm needs to be added in an include folder, after data analysis is completed, the position of the UWB tag can be resolved according to the distance values between the UWB tag and a plurality of positioning base stations and the coordinates of each UWB base station, and then the second position information of the target to be positioned is obtained.
The third part is information release, which is mainly released with nodes and a coordinate system, specifically, firstly manually setting the coordinate of a UWB base station, using a main base station as the origin of the coordinate system, configuring the node release to generate X and Y coordinates, then developing and using UWB in an ROS system, integrating the obtained information in a.launch file, and releasing the related node and the coordinate system of the UWB.
Step 2, acquiring indoor point cloud data in real time through a laser radar positioning device, constructing an indoor map based on the point cloud data, and detecting and obtaining all similar objects corresponding to targets to be positioned, wherein the laser radar positioning device comprises at least three laser radars;
in this embodiment, the UWB positioning device may include four UWB base stations, and the lidar positioning device may include four lidars, and each UWB base station and one lidar may form an integrated device, where the four integrated devices are respectively disposed around the room.
As shown in fig. 3, the laser radar positioning device in this embodiment trains a convolutional neural network based on deep learning, and performs indoor map construction and target detection according to the convolutional neural network obtained by training.
The training convolutional neural network specifically comprises the following steps: and acquiring training point cloud data in a data set ScanNet-V2, generating two types of mixed three-dimensional characteristics of voxel points and voxels based on the double-stream encoder according to the training point cloud data, and training according to the training point cloud data and the mixed three-dimensional characteristics to obtain a convolutional neural network for identifying the target type. The data set ScanNet-V2 is collected by a stanfu university team through collecting RGB-D video sequences and deepening sensors through ipad application, and then the video is uploaded to a server and automatically reconstructed, so that semantic interpretation is given to 3D data.
It will be appreciated that voxel point representations are features obtained by aggregating point-based features on single voxel-based features, whereas voxels are aggregated by memory terms rather than using point-based features, that is, the present embodiment uses memory modules to enhance point-based features and uses voxel-memory representations, i.e., hybrid three-dimensional features, for rapid inference at test time.
The indoor map construction specifically comprises the following steps: and obtaining the scale perception characteristics of the indoor actual object based on the convolutional neural network according to the point cloud data, performing scale transformation on the indoor model corresponding to the indoor model library according to the scale perception characteristics to obtain the indoor model with the same size as the actual object, performing corresponding angle rotation and displacement on the indoor models with the same size to form an indoor environment, supplementing the missed object characteristics in the indoor environment, and finally performing visual output on RVIZ (Robit Visualization tool, a robot visual tool) to complete the construction of an indoor map. According to the embodiment, the display environment map is built based on the existing database, so that interference caused by noise can be well avoided, and the problem of excessive map burrs is solved.
The target detection specifically comprises: and inputting the point cloud data into a convolutional neural network to obtain all similar objects corresponding to the target to be positioned, and marking 3D rectangular frames on the similar objects.
And 3, determining the target to be positioned from all similar objects according to the first position information, determining second position information of the target to be positioned through the indoor map, and determining real-time position information of the target to be positioned according to the second position information.
It can be understood that the convolutional neural network obtained by training has the capability of distinguishing different indoor object types, but can only distinguish object types, and when a plurality of objects which are similar to the object to be positioned exist, the object to be positioned cannot be accurately determined.
Specifically, firstly, determining a centroid corresponding to a 3D rectangular frame marked on a target to be positioned, taking the coordinate of the centroid as a real-time position coordinate of the target to be positioned, obtaining second position information of the target to be positioned according to the real-time position coordinate and based on an indoor map, and finally determining the real-time position information of the target to be positioned according to the second position information to realize accurate positioning of the target to be positioned.
And 4, acquiring the starting position information and the destination position information of the target to be positioned, and determining a navigation path based on Dijkstra algorithm (Dijkstra algorithm) according to the starting position information and the destination position information of the target to be positioned.
As shown in fig. 4, determining a navigation path based on Dijkstra algorithm in this embodiment specifically includes:
expanding layer by layer outwards by taking the starting position as the center until expanding to the destination position;
starting from the initial position, searching a plurality of path points capable of reaching the destination position of each layer according to a preset searching distance range, determining the path point with the shortest distance with the initial position, and repeating the operation until the path point on the penultimate layer is determined by taking the determined path point as the initial position;
and sequentially connecting the starting position, the determined path point and the destination position to obtain the navigation path.
In summary, according to the indoor positioning navigation method based on UWB and lidar in this embodiment, the deep learning technology of the lidar point cloud is combined with the indoor UWB positioning technology, so that the accurate positioning of the indoor target object is achieved together, and a more stable environment map is obtained through real-time 3D mapping of the lidar at a fixed position. Firstly, a plurality of laser radars are matched to update an indoor map in real time, so that complementation of vision blind areas can be performed; and secondly, the accurate positioning of the indoor moving object is tracked and supervised by a target detection algorithm of the laser radar and the UWB positioning technology, so that the error is further reduced, the blind area of the field of view is reduced, in addition, the deep learning map building function of the laser radar is realized, the environment map is built and displayed on the basis of the existing database through a deep learning network, the interference caused by noise can be well avoided, and the problem of excessive map burrs is solved.
Based on the above technical solution, this embodiment further provides an indoor positioning navigation system based on UWB and laser radar, as shown in fig. 5, including:
the UWB positioning device comprises at least three UWB base stations and is used for determining first position information of a target to be positioned in real time;
the laser radar positioning device comprises at least three laser radars and is used for acquiring indoor point cloud data in real time, constructing an indoor map based on the point cloud data and detecting and obtaining all similar objects corresponding to a target to be positioned;
the data processing device is used for determining the target to be positioned from all similar objects according to the first position information, determining second position information of the target to be positioned through the indoor map, and determining real-time position information of the target to be positioned according to the second position information.
It can be understood that, since the indoor positioning navigation system based on UWB and laser radar according to the embodiments of the present invention is a system for implementing the indoor positioning navigation method based on UWB and laser radar, for the system disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the description is simpler, and the relevant points will be referred to in the part of the description of the method.
Claims (9)
1. The indoor positioning navigation method based on UWB and laser radar is characterized by comprising the following steps:
determining first position information of a target to be positioned in real time through a UWB positioning device, wherein the UWB positioning device comprises at least three UWB base stations;
acquiring indoor point cloud data in real time through a laser radar positioning device, constructing an indoor map based on the point cloud data, and detecting and obtaining all similar objects corresponding to targets to be positioned, wherein the laser radar positioning device comprises at least three laser radars;
the detection is carried out to obtain all similar objects corresponding to the target to be positioned, specifically comprising the following steps:
training a convolutional neural network for identifying the type of the target, inputting the point cloud data into the convolutional neural network to obtain all similar objects corresponding to the target to be positioned, and marking 3D rectangular frames on the similar objects;
determining a target to be positioned from all similar objects according to the first position information, determining second position information of the target to be positioned through the indoor map, and determining real-time position information of the target to be positioned according to the second position information;
the method for determining the second position information comprises the following steps:
and determining a centroid corresponding to the 3D rectangular frame marked on the target to be positioned, taking the coordinate of the centroid as the real-time position coordinate of the target to be positioned, and obtaining second position information of the target to be positioned according to the real-time position coordinate and based on an indoor map.
2. The indoor positioning navigation method based on UWB and lidar of claim 1, wherein the determining, by the UWB positioning device, the first position information of the object to be positioned specifically comprises:
each UWB base station receives a positioning signal sent by a target to be positioned in real time, and distance information between the target to be positioned and each UWB base station is respectively determined according to the transmission time of the positioning signal;
and correcting each distance information, and determining first position information of the target to be positioned based on the CKF algorithm according to the corrected distance information.
3. The indoor positioning navigation method based on UWB and lidar of claim 1, wherein the training is used for identifying the convolutional neural network of the target type, in particular comprising:
and acquiring training point cloud data in a data set ScanNet-V2, generating two types of mixed three-dimensional characteristics of voxel points and voxels based on the double-stream encoder according to the training point cloud data, and training according to the training point cloud data and the mixed three-dimensional characteristics to obtain a convolutional neural network for identifying the target type.
4. The indoor positioning navigation method based on UWB and laser radar according to claim 1, wherein the indoor map construction method comprises:
and obtaining the scale perception characteristics of the indoor actual object based on the convolutional neural network according to the point cloud data, performing scale transformation on the indoor model corresponding to the indoor model library according to the scale perception characteristics to obtain the indoor model with the same size as the actual object, performing corresponding angle rotation and displacement on the indoor models with the same size to form an indoor environment, supplementing the missed object characteristics in the indoor environment, and finally performing visual output on RVIZ to complete the construction of an indoor map.
5. The indoor positioning navigation method based on UWB and lidar according to claim 1, wherein the UWB positioning device comprises four UWB base stations, the lidar positioning device comprises four lidars, each UWB base station and one lidar form an integrated device, and the four integrated devices are respectively arranged around the indoor.
6. An indoor positioning navigation method based on UWB and lidar according to any of claims 1 to 5, further comprising:
and acquiring the starting position information and the destination position information of the target to be positioned, and determining a navigation path based on Dijkstra algorithm according to the starting position information and the destination position information of the target to be positioned.
7. The indoor positioning navigation method based on UWB and lidar of claim 6, wherein the determining the navigation path based on Dijkstra algorithm based on the start position information and the destination position information of the target to be positioned specifically comprises:
expanding layer by layer outwards by taking the starting position as the center until expanding to the destination position;
starting from the initial position, searching a plurality of path points capable of reaching the destination position of each layer according to a preset searching distance range, determining the path point with the shortest distance with the initial position, and repeating the operation until the path point on the penultimate layer is determined by taking the determined path point as the initial position;
and sequentially connecting the starting position, the determined path point and the destination position to obtain the navigation path.
8. Indoor location navigation based on UWB and laser radar, characterized by, include:
the UWB positioning device comprises at least three UWB base stations and is used for determining first position information of a target to be positioned in real time;
the laser radar positioning device comprises at least three laser radars and is used for acquiring indoor point cloud data in real time, constructing an indoor map based on the point cloud data and detecting and obtaining all similar objects corresponding to a target to be positioned;
the detection is carried out to obtain all similar objects corresponding to the target to be positioned, specifically comprising the following steps:
training a convolutional neural network for identifying the type of the target, inputting the point cloud data into the convolutional neural network to obtain all similar objects corresponding to the target to be positioned, and marking 3D rectangular frames on the similar objects;
the data processing device is used for determining the target to be positioned from all similar objects according to the first position information, determining second position information of the target to be positioned through the indoor map, and determining real-time position information of the target to be positioned according to the second position information;
the method for determining the second position information comprises the following steps:
and determining a centroid corresponding to the 3D rectangular frame marked on the target to be positioned, taking the coordinate of the centroid as the real-time position coordinate of the target to be positioned, and obtaining second position information of the target to be positioned according to the real-time position coordinate and based on an indoor map.
9. An indoor positioning navigation system based on UWB and lidar of claim 8, further comprising:
the navigation device is used for acquiring the starting position information and the destination position information of the target to be positioned, and determining a navigation path based on Dijkstra algorithm according to the starting position information and the destination position information of the target to be positioned.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210417905.3A CN114739388B (en) | 2022-04-20 | 2022-04-20 | Indoor positioning navigation method and system based on UWB and laser radar |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210417905.3A CN114739388B (en) | 2022-04-20 | 2022-04-20 | Indoor positioning navigation method and system based on UWB and laser radar |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114739388A CN114739388A (en) | 2022-07-12 |
| CN114739388B true CN114739388B (en) | 2023-07-14 |
Family
ID=82284611
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210417905.3A Active CN114739388B (en) | 2022-04-20 | 2022-04-20 | Indoor positioning navigation method and system based on UWB and laser radar |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114739388B (en) |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106803071B (en) * | 2016-12-29 | 2020-02-14 | 浙江大华技术股份有限公司 | Method and device for detecting object in image |
| US11681303B2 (en) * | 2018-07-06 | 2023-06-20 | Verity Ag | Methods and systems for estimating the orientation of an object |
| CN109275093B (en) * | 2018-10-08 | 2021-03-09 | 深圳市锐曼智能装备有限公司 | Positioning method based on UWB positioning and laser map matching and mobile terminal |
| CN111275082A (en) * | 2020-01-14 | 2020-06-12 | 中国地质大学（武汉） | Indoor object target detection method based on improved end-to-end neural network |
| CN111798475B (en) * | 2020-05-29 | 2024-03-22 | 浙江工业大学 | Indoor environment 3D semantic map construction method based on point cloud deep learning |
| CN114047519A (en) * | 2021-09-26 | 2022-02-15 | 苏州摩擎科技有限公司 | AGV positioning system and method based on ultra-wideband and laser SLAM (synchronous map positioning and navigation) composite navigation technology |
-
2022
- 2022-04-20 CN CN202210417905.3A patent/CN114739388B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN114739388A (en) | 2022-07-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10872179B2 (en) | Method and apparatus for automated site augmentation | |
| CN102752855B (en) | Indoor personnel positioning system and method based on path rule and prediction | |
| CN104197928B (en) | Multi-camera collaboration-based method for detecting, positioning and tracking unmanned aerial vehicle | |
| CN110873570B (en) | Method and apparatus for sourcing, generating and updating a map representing a location | |
| US11468209B2 (en) | Method and apparatus for display of digital content associated with a location in a wireless communications area | |
| CN112823321B (en) | Position locating system and method for mixing position recognition results based on multiple types of sensors | |
| Cho et al. | Target-focused local workspace modeling for construction automation applications | |
| CN112698306A (en) | System and method for solving map construction blind area by combining multiple laser radars and camera | |
| CN113160292B (en) | Laser radar point cloud data three-dimensional modeling device and method based on intelligent mobile terminal | |
| Hu et al. | Accuracy improvement of indoor real-time location tracking algorithm for smart supermarket based on ultra-wideband | |
| Bingham et al. | Hypothesis grids: Improving long baseline navigation for autonomous underwater vehicles | |
| CN107607939B (en) | Optical target tracking and positioning radar device based on real map and image | |
| CN114739388B (en) | Indoor positioning navigation method and system based on UWB and laser radar | |
| US11704916B2 (en) | Three-dimensional environment analysis method and device, computer storage medium and wireless sensor system | |
| Dehbi et al. | Improving gps trajectories using 3d city models and kinematic point clouds | |
| WO2022083529A1 (en) | Data processing method and apparatus | |
| DE202016008129U1 (en) | Device for determining the three-dimensional pose of rigid bodies using opto-acoustic code division multiplexing and carrier phase distance measurements | |
| Wahl et al. | WIP: Real-world 3D models derived from mobile mapping for ray launching based propagation loss modeling | |
| Kulikov et al. | An Ultrasonic Vision based on a Neural Network for Navigating Robots Through Obstacles | |
| Catalano et al. | Towards robust uav tracking in gnss-denied environments: a multi-lidar multi-uav dataset | |
| CN116047537B (en) | Road information generation method and system based on laser radar | |
| Shetty | Particle filter approach to overcome multipath propagation error in slam indoor applications | |
| CN113640802B (en) | Robot space positioning method and system based on multiple fusion sensors | |
| Jabbar et al. | Develop indoor object detection and localization system based image processing | |
| Du et al. | Research on Multi-Sensor Data Collection and Mapping Methods |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |