CN110865393A - Positioning method and system based on laser radar, storage medium and processor - Google Patents
Positioning method and system based on laser radar, storage medium and processor Download PDFInfo
- Publication number
- CN110865393A CN110865393A CN201911206878.XA CN201911206878A CN110865393A CN 110865393 A CN110865393 A CN 110865393A CN 201911206878 A CN201911206878 A CN 201911206878A CN 110865393 A CN110865393 A CN 110865393A
- Authority
- CN
- China
- Prior art keywords
- laser
- cluster
- electronic map
- positioning
- matching
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 84
- 230000008569 process Effects 0.000 claims abstract description 23
- 238000013507 mapping Methods 0.000 claims description 15
- 230000004888 barrier function Effects 0.000 claims description 14
- 238000005516 engineering process Methods 0.000 abstract description 6
- 238000010586 diagram Methods 0.000 description 7
- 230000007613 environmental effect Effects 0.000 description 7
- 238000001514 detection method Methods 0.000 description 4
- 238000005259 measurement Methods 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000006872 improvement Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 230000003068 static effect Effects 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 230000004927 fusion Effects 0.000 description 2
- 230000001788 irregular Effects 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 238000003064 k means clustering Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000010408 sweeping Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
- G01S17/88—Lidar systems specially adapted for specific applications
- G01S17/89—Lidar systems specially adapted for specific applications for mapping or imaging
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
- G01S7/48—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S17/00
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Remote Sensing (AREA)
- General Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Computer Networks & Wireless Communication (AREA)
- Databases & Information Systems (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Probability & Statistics with Applications (AREA)
- Electromagnetism (AREA)
- Traffic Control Systems (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
- Optical Radar Systems And Details Thereof (AREA)
Abstract
The application discloses a positioning method based on a laser radar, a robot, a storage medium and a processor. Wherein, the method comprises the following steps: acquiring laser radar data of a laser radar; clustering laser radar data to obtain a plurality of laser clusters; in the process of positioning a target object, matching each laser cluster with an electronic map respectively; and determining whether the positioning result of the target object is accurate or not based on the matching result of each laser cluster and the electronic map. The method and the device solve the technical problem that whether the positioning result is reliable or not can not be judged in a dynamic scene in the related technology.
Description
Technical Field
The present application relates to the field of radar positioning, and in particular, to a positioning method and system based on a laser radar, a storage medium, and a processor.
Background
In applications such as laser radar-based robot positioning, scene reconstruction, indoor and outdoor mapping and the like, original laser point cloud data are directly adopted for processing at present. The environment is required to be relatively static when positioning and scene reconstruction are carried out, and the positioning and scene reconstruction are often poor in effect (for example, moving objects such as people and vehicles appear in the environment, or the position and the posture of the objects in the environment are changed) in a dynamic environment.
One of the situations that frequently occurs when the mobile robot locates a target object indoors is that after the environment map is built, the environment changes, for example, an object (such as a chair or a table) originally on the map is moved to another position, or some objects not on the map are newly added in the environment. For example, when the mobile robot is positioned in an environment such as a garage, the number of vehicles and the positions of the vehicles in the garage may change at any time because the garage is a highly dynamic environment. In these situations, the difference between the environmental information obtained by the robot and the memorized information (i.e. the stored information) will cause a certain positioning error, and when the information difference is too large, the positioning may also be disabled. Positioning failure will cause robot navigation accidents, so positioning results need to be judged in actual use.
The judgment of the positioning result is a guarantee measure for the navigation safety of the robot, and the current solution method comprises the following steps:
whether the current positioning is reliable or not is judged through the positioning covariance, but the results obtained by most methods for calculating the positioning covariance at present can only reflect the positioning accuracy under the condition that the positioning is basically correct, and two conditions can occur when the positioning has larger deviation: (1) some laser points are wrongly matched with the map, so that the positioning covariance is still converged, and the positioning failure cannot be judged by using the positioning covariance; (2) when the positioning loss is very serious, the positioning covariance becomes larger gradually, and a larger delay exists in the detection of the positioning failure, which is very unsafe for the navigation of the mobile robot.
And after a positioning result is obtained, directly projecting the laser radar data onto a map, and judging whether the current positioning is reliable or not according to the matching condition of all the laser radar data and the map. When the environment changes greatly, the measured data obtained by the laser radar is greatly different from the map, and even if the positioning is completely correct, the matching degree of the laser radar data and the map is not high. Therefore, this method is not suitable for dynamic scenes with large environmental changes.
In view of the above problems, no effective solution has been proposed.
Disclosure of Invention
The embodiment of the application provides a positioning method and system based on a laser radar, a storage medium and a processor, so as to at least solve the technical problem that whether the positioning result is reliable or not cannot be judged in a dynamic scene in the related technology.
According to an aspect of an embodiment of the present application, there is provided a positioning method based on a lidar, including: acquiring laser radar data of a laser radar; clustering laser radar data to obtain a plurality of laser clusters; in the process of positioning a target object, matching each laser cluster with an electronic map respectively; and determining whether the positioning result of the target object is accurate or not based on the matching result of each laser cluster and the electronic map.
Optionally, in the process of locating the target object, matching each laser cluster with the electronic map respectively includes: obtaining a positioning result of a target object; mapping each laser cluster into an electronic map based on the positioning result; and matching each laser cluster with the corresponding area respectively mapped in the electronic map to obtain a matching result.
Optionally, mapping each laser cluster into an electronic map based on the positioning result, including: reading a positioning coordinate in a positioning result; and projecting the laser point of each laser cluster into the electronic map based on the positioning coordinates, and determining the position of the laser point of each laser cluster mapped in the electronic map.
Optionally, matching each laser cluster with a corresponding area respectively mapped in the electronic map to obtain a matching result, wherein the matching result comprises the steps of obtaining a plurality of laser points in any one laser cluster; calculating the occupation point of the obstacle closest to each laser point on the electronic map and the closest distance value between each laser point and the corresponding occupation point; counting the number of laser points with the closest distance value smaller than a first preset threshold value; and if the statistical quantity exceeds a second preset threshold value, determining that the laser cluster is matched with the electronic map.
Optionally, after calculating the occupation point of the obstacle on the electronic map at the closest distance from each laser point, the method further includes: and establishing a cache map based on the occupied points corresponding to each laser point, wherein each coordinate point on the cache map represents a closest distance value.
Matching each laser cluster with the corresponding area respectively mapped in the electronic map, and obtaining a matching result comprises the following steps: taking each laser cluster as a center, and acquiring coordinates of an obstacle closest to each laser cluster on the electronic map; obtaining the distance between each laser cluster and the nearest barrier to obtain a plurality of distance values; and if the distance value is less than or equal to a third preset threshold value, determining that the corresponding laser cluster is matched with the electronic map.
Optionally, the obtaining coordinates of an obstacle closest to each laser cluster on the electronic map with each laser cluster as a center includes: taking a mapping point of any laser cluster on the electronic map as a center, and acquiring at least one obstacle in a corresponding area on the electronic map; calculating the distance between the laser cluster and each obstacle in the corresponding area, and acquiring the obstacle closest to the laser cluster; and traversing each laser cluster to obtain the coordinates of the obstacle closest to each laser cluster on the electronic map.
Optionally, determining whether the positioning result of the target object is accurate based on the matching result of each laser cluster and the electronic map includes: and if the number of the laser clusters matched with the electronic map exceeds a fourth preset threshold value, the matching result is that the positioning result is accurate.
Optionally, the lidar data comprises: distance information and direction information of an obstacle located within the sensing range.
According to another aspect of the embodiments of the present application, there is provided another lidar-based positioning method, including: acquiring laser radar data collected by a laser radar, wherein the laser radar data comprises: relative distance information and relative direction information of the laser radar and the obstacle; clustering laser radar data to obtain a plurality of laser clusters; in the process of positioning the barrier corresponding to the moving robot, matching each laser cluster with an electronic map respectively; and determining whether the positioning result is accurate or not based on the matching result of each laser cluster and the electronic map.
Optionally, in the process of positioning an obstacle corresponding to the moving robot, matching each laser cluster with the electronic map respectively includes: obtaining a positioning result of the barrier; mapping each laser cluster into an electronic map based on the positioning result; and matching each laser cluster with the corresponding area respectively mapped in the electronic map to obtain a matching result.
Optionally, determining whether the positioning result of the robot is accurate based on the matching result of each laser cluster and the electronic map includes: and if the number of the laser clusters matched with the electronic map exceeds a preset threshold value, the positioning result of the robot is accurate.
According to still another aspect of an embodiment of the present application, there is provided a robot including: the laser radar is used for collecting laser radar data; the processor is connected with the laser radar and used for determining the positioning result of the obstacle based on the laser radar data; and matching each laser cluster obtained by clustering the laser radar data with the electronic map, and determining whether the positioning result is accurate or not based on the matching result.
Optionally, the lidar data comprises: relative distance information and relative direction information between the robot and the obstacle.
Alternatively, if the number of laser clusters matching the electronic map exceeds a predetermined threshold, the positioning result is determined to be accurate.
According to another aspect of the embodiments of the present application, there is provided a positioning apparatus based on a lidar, including: the acquisition module is used for acquiring laser radar data of the laser radar; the clustering module is used for clustering the laser radar data to obtain a plurality of laser clusters; the matching module is used for matching each laser cluster with the electronic map respectively in the process of positioning the target object; and the positioning module is used for determining whether the positioning result of the target object is accurate or not based on the matching result of each laser cluster and the electronic map.
According to still another aspect of the embodiments of the present application, there is provided a storage medium including a stored program, wherein when the program is executed, the apparatus on which the storage medium is located is controlled to execute the laser radar-based positioning method described above.
According to yet another aspect of the embodiments of the present application, there is provided a processor for executing a program stored in a memory, wherein the program is executed to perform the lidar-based positioning method described above.
In the embodiment of the application, the laser radar data are clustered, each cluster obtained through clustering is matched with the electronic map, whether the positioning result of the target object is accurate or not is determined according to the matching result, and each cluster can be matched with the map based on the clustering mode, so that the matching can be performed by taking the class as a unit, whether the positioning result is reliable or not can be judged even if the environment changes, and the technical problem that whether the positioning result is reliable or not cannot be judged in a dynamic scene in the related technology is solved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the application and together with the description serve to explain the application and not to limit the application. In the drawings:
FIG. 1 is a schematic diagram of a robot according to an embodiment of the present application;
fig. 2 is a schematic flow chart of a positioning method of a laser radar according to an embodiment of the present application;
FIG. 3 is a schematic diagram of a distribution of obstacle points according to an embodiment of the present application;
FIG. 4 is a diagram illustrating a distribution of clustered obstacle points according to an embodiment of the present disclosure;
fig. 5 is a schematic diagram of a map after determining whether a positioning result of a robot moving area is reliable according to an embodiment of the present application;
FIG. 6 is a schematic flow chart diagram illustrating an alternative lidar positioning method according to an embodiment of the present disclosure;
FIG. 7 is a schematic structural diagram of a positioning apparatus of a lidar according to an embodiment of the present disclosure;
fig. 8 is a schematic flowchart of another lidar positioning method according to an embodiment of the present disclosure.
Detailed Description
In order to make the technical solutions better understood by those skilled in the art, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only partial embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
It should be noted that the terms "first," "second," and the like in the description and claims of this application and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the application described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
For a better understanding of the embodiments of the present application, the terms referred to in the embodiments of the present application are explained below:
laser radar: the radar system for detecting the position of an obstacle by emitting a laser beam has the working principle that a detection signal (laser beam) is emitted, then a signal reflected by the obstacle in the environment is received and compared with a sending signal, and after appropriate processing is carried out, relevant information of a target, such as parameters of target distance, direction, height, speed, posture, even shape and the like, can be obtained, so that the target is detected, tracked and identified. The laser radar may include a laser transmitter, an optical receiver, a turntable, an information processing system, and the like.
Map: the map constructed based on the 2D lidar SLAM may be a grid map in the embodiment of the present application, and the value in each grid point represents the probability that the point is occupied by an obstacle.
In the related technology, after the robot obtains the positioning result, the laser radar data is directly projected onto a map, and then whether the current positioning is reliable or not is judged according to the matching condition of all the laser radar data and the map. However, when the environment where the robot is located changes greatly, the measurement data obtained by the laser radar has a large difference from the map, and even if the positioning is completely correct, the matching degree of the laser radar data and the map is not high. Therefore, the method is not suitable for dynamic scenes with large environmental changes
In order to solve the technical problem, in the embodiment of the application, the laser radar data are clustered, and the laser radar data falling on different objects are classified into different classes. And after the positioning result is generated, projecting the laser radar data onto a map according to the positioning result, and calculating the matching condition of each laser cluster and the map so as to judge whether the positioning result is reliable. The following detailed description is given with reference to specific examples.
Fig. 1 is a schematic structural diagram of a robot according to an embodiment of the present application. As shown in fig. 1, the robot 1 includes: lidar 10 and a processor 12, wherein:
and the laser radar 10 is used for collecting laser radar data.
In some embodiments of the present disclosure, the laser radar 10 may be disposed in the robot 10, the robot 10 may be a small-sized mobile robot such as a carrying logistics robot or a floor sweeping robot, and the laser radar may be integrated inside a robot body for positioning a position of the robot in a map in real time during operation. For example, when the robot is used for cleaning, a laser radar emits light signals at regular intervals, and after receiving the return light of the light signals, the laser radar data are sent to the positioning equipment, and after the positioning equipment receives the laser radar data of the robot, the laser radar data are mapped to an electronic map, so that the position of the obstacle can be judged.
The robot 10 may move in a target area when moving, the target area may be an active area of the robot 10, and may also be represented as a sensing area of a laser radar in some application scenarios, where radar sensing is a wireless sensing technology, and by analyzing received echo features of a target, the position, shape, motion characteristics, and motion trajectory of the target are extracted and found, and features of the target and an environment may be further inferred. The target echo is characterized by the process that when a beam of wireless optical signal hits a forward object, the reflected beam is received again. The distance between the laser radar and the object (namely the distance between the robot and the object) can be calculated according to the time from the transmitting time to the time of turning back when the laser radar touches the object and the time of receiving the echo, and the size, the shape and the moving speed of the object can be judged according to the size or the signal intensity of the received echo. The sensing area refers to a range that can be covered by a laser radar signal, and in some embodiments of the present application, the sensing area is a sensing range of a laser radar, and may be a circular plane or a sector plane, for example, a central angle of a sector is 90 degrees or 50 degrees, and a radius is r. In general, the value of r may be related to the measurement parameters of the lidar or set according to the requirements of the user within the measurement parameters.
For another example, a rectangular coordinate system is established with the acquisition point of the lidar as the center, and the sensing range of the lidar may be the first quadrant, the second quadrant, the third quadrant, the fourth quadrant, or any combination between two adjacent quadrants, for example, the range formed by the first quadrant and the second quadrant serves as the sensing range of the lidar.
The lidar data may include, but is not limited to: a set of multiple laser points with range information and direction information collected in real time, for example, lidar data includes: relative distance information and relative direction information between the laser radar and the obstacle.
Alternatively, the lidar 10 may be a combination of multiple lidar arranged at different positions of the robot such that the different lidar have mutually overlapping detection ranges to cover as many obstacles as possible in the active area of the robot.
For example, when the laser radar 10 emits a laser with a fixed wavelength, the timer in the laser radar 10 obtains distance information of the laser radar 10 from different obstacles by calculating the feedback time of the feedback wave, the feedback time of the obstacle with a long distance is inevitably longer than the feedback time of the obstacle with a short distance, and the laser radar 10 calculates the position of the source of the feedback wave, i.e., the direction of the source of the feedback wave, according to the vertical angle fed back by the feedback wave to obtain the position data of the peripheral environment such as the obstacle, so that the position information of the laser radar (i.e., the position of the robot where the laser radar is located) is determined, for example, the relative position information of the robot and the obstacle can be determined.
A processor 12 connected to the lidar 10 for determining a result of the location of the obstacle based on the lidar data; and matching each laser cluster obtained by clustering the laser radar data with the electronic map, and determining whether the positioning result is accurate or not based on the matching result.
When the position or direction information of the target object (e.g., an obstacle) in the laser radar data matches the position or direction information of the obstacle in the map, the current positioning result for the robot is considered to be accurate. When the position or direction information of the target object (e.g., an obstacle) in the lidar data matches the position or direction information of the obstacle in the map, the positioning result of the robot obtained at this time may be considered to be authentic, i.e., the positioning result is accurate.
In some embodiments of the present application, the laser cluster may be determined by: and clustering the laser radar data, and classifying point cloud data with the same position into one class to obtain a laser cluster.
Specifically, there are various ways to determine whether the positioning result of the obstacle is accurate based on the matching positioning result, for example, to determine whether all the laser clusters are matched with the data in the electronic map, and if the number of the matched laser clusters is greater than the first threshold, it is determined that the positioning result is accurate, otherwise, it is determined that the positioning result is inaccurate. The first threshold may be a predetermined quantity value, or may be determined according to a predetermined ratio, where the ratio is a ratio of the preset matched laser clusters to all laser clusters, for example, when the preset ratio is 70% and the number of all laser clusters is 10, the first threshold is 10 ═ 70% — 7.
In some embodiments of the present application, in order to further ensure the accuracy of the positioning result, before determining whether all the laser clusters are matched with the data in the electronic map, each laser cluster may be further screened to reject laser clusters that do not meet the requirements, for example: and counting the laser points in each laser cluster, and when the distance d between the laser point and the nearest barrier is smaller than a second threshold Dt, considering that the laser point is matched with the map. Where Dt is typically determined by the inherent error magnitude of the lidar. For each laser cluster, when the number of laser points in the cluster matched with the map exceeds a third threshold (for example, the number of matched laser points exceeds 90% of the number of laser points in the cluster), the laser cluster is considered to be matched with the map; otherwise there is no match.
In the above operating environment, the embodiments of the present application provide a method embodiment of a positioning method for lidar to note that the steps illustrated in the flowchart of the figures may be performed in a computer system such as a set of computer-executable instructions, and that although a logical order is illustrated in the flowchart, in some cases the steps illustrated or described may be performed in an order different than here.
Fig. 2 is a schematic flowchart of a positioning method of a lidar according to an embodiment of the present disclosure, where as shown in fig. 2, the method includes the following steps:
step S202, laser radar data collected by a laser radar is obtained;
in particular, the lidar may be a combination of a plurality of lidars, which are distributed at different positions of the robot, such that mutually overlapping detection ranges are formed between different lidars to cover as many obstacles as possible.
For example, when the laser radar emits laser with a fixed wavelength, the timer in the laser radar obtains distance information of the laser radar from different obstacles by calculating feedback time of the feedback wave, the feedback time of the obstacle with a long distance is inevitably longer than the feedback time of the obstacle with a short distance, and meanwhile, the laser radar calculates the source position of the feedback wave according to the vertical angle fed back by the feedback wave, namely the direction of the source of the feedback wave, so as to obtain position data of the peripheral environment such as the obstacle, so that the self position (namely the position of the robot where the laser radar is located) information of the laser radar can be determined, for example, the relative position information of the robot and the obstacle can be determined.
Step S204, clustering the laser radar data to obtain a plurality of laser clusters;
the clustering method may be various, for example, clustering may be performed by using a clustering algorithm, where the clustering algorithm includes but is not limited to: a K-means clustering algorithm, a Mean-Shift clustering algorithm, and the like.
In some embodiments of the present application, if the number of laser clusters matching the electronic map exceeds a predetermined threshold, the positioning result of the robot is accurate.
Fig. 3 is a visual representation of lidar output data where each point is an obstacle point location in the environment. As can be seen from fig. 3, it is not possible to distinguish from the raw data which objects these point cloud data belong to.
The laser data is clustered before fusion with vision. The point clouds with the same position can be clustered into a cluster by clustering. The clustering method is realized by using an RBNN (radial basis function neural network) algorithm, wherein the RBNN algorithm is an improved algorithm based on a KNN clustering method, and whether the data and the adjacent points belong to one class or not is determined by using the distance between the data and the adjacent points. After clustering, the point cloud image with the cluster label is shown in fig. 4.
It should be noted that, the RBNN algorithm is a normalization algorithm, and is generally used for lattice classification calculation, and specifically, in the embodiment of the present application, in order to classify laser clusters of the same position point into a class of laser clusters, the RBNN algorithm may be used to "round" the laser clusters of the similar position to obtain an accurate and single laser cluster position, which is used in the subsequent matching step.
At this time, according to the clustering process, it can be determined which laser points belong to the same object. And the laser data can be denoised through clustering, and some irregular environmental information can be removed. The specific method for removing the environmental information is to remove redundant laser cluster dot matrix coordinates by using an RBNN algorithm, so that the technical effect of removing noise is achieved.
Step S206, in the process of positioning the target object, matching each laser cluster with an electronic map respectively;
specifically, in some embodiments of the present application, the matching process can be represented in the following two ways:
the first mode is as follows:
a, obtaining a positioning result of an obstacle in a target area;
for example, when the robot moves in a target area, the position of an obstacle in a map during the operation of the robot is located in real time by using a laser radar integrated in the interior of the robot body. For example, when a robot based on the ARM smart chip carries goods by using a mechanical ARM, laser radar data (namely data obtained after the laser radar transmits a laser signal to an obstacle and receives an echo signal) is sent to a server by the laser radar every 0.5s, and after the server receives the laser radar signal of the robot, the position of the obstacle can be judged according to a map of a sensing area. In some optional embodiments of the present application, the position of the robot in the map may also be determined based on the position of the obstacle, and at this time, a GPS positioning device may also be disposed in the robot, so that the positioning information of the robot may be determined based on the GPS positioning device and the lidar data together. For example, a GPS positioning device is used to perform coarse-grained positioning, and laser radar data is used to perform fine-grained positioning, specifically: acquiring GPS positioning data to obtain a first positioning result, wherein the precision of satellite positioning is limited, so that the satellite positioning method is not suitable for large-area indoor scenes or outdoor scenes, and fine-grained positioning of radar data is needed; acquiring laser radar data to obtain a second positioning result; acquiring a first position of the robot by using the first positioning result; and correcting the first position diameter by using a second positioning result.
b, mapping each laser cluster into an electronic map based on a positioning result; wherein each laser cluster can be mapped into an electronic map by: reading a positioning coordinate in a positioning result; and projecting the laser point of each laser cluster into the electronic map based on the positioning coordinates, and determining the position of the laser point of each laser cluster mapped in the electronic map.
Specifically, each laser cluster is mapped into the electronic map, and mapping is performed according to a positioning result, that is, a positioning coordinate in a coordinate system where the obstacle is located is obtained, for example, the positioning coordinate is (a, b), and then the positioning coordinate is converted into a coordinate in a coordinate system corresponding to the electronic map.
And c, matching each laser cluster with the corresponding area respectively mapped in the electronic map to obtain a matching result.
Specifically, a plurality of laser points in any one laser cluster are obtained; calculating the position point of the obstacle closest to each laser point on the electronic map and the closest distance value between each laser point and the corresponding position point; counting the number of laser points with the closest distance value smaller than a first preset threshold value; and if the statistical quantity exceeds a second preset threshold value, determining that the laser cluster is matched with the electronic map.
In some embodiments of the present application, after calculating a position point of an obstacle on the electronic map that is closest to each laser point, a cache map is established based on the position point corresponding to each laser point, wherein each coordinate point on the cache map represents a closest distance value.
The second mode is as follows:
step 1) taking each laser cluster as a center, and acquiring coordinates of an obstacle closest to each laser cluster on the electronic map;
specifically, the position of each laser cluster on the electronic map is a positioning coordinate, and different obstacles exist around the positioning coordinate, so that the position information of the obstacles can be determined according to the coordinates of the obstacles detected by the laser radar on the electronic map, the position coordinates of the obstacles in the map can also be preset on the electronic map, and then the coordinate values are directly obtained from the electronic map. The latter means can shorten the execution period and save system resources.
Step 2) obtaining the distance between each laser cluster and the nearest barrier to obtain a plurality of distance values;
specifically, the distance between the obstacle and the laser cluster is obtained through the method of step 1), however, the selected obstacle is determined according to the obstacle whose distance value between the surrounding obstacle and the laser cluster is the closest, for example, the distance between the laser cluster and the first obstacle is a, the distance between the laser cluster and the first obstacle is b, the distance between the laser cluster and the first obstacle is c, when a > b > c, the obstacle c is selected as the obstacle closest to the laser cluster, and the value of c is obtained as the output value.
And 3) if the distance value is smaller than or equal to a third preset threshold value, determining that the corresponding laser cluster is matched with the electronic map.
In some embodiments of the present application, at least one obstacle in a corresponding area on an electronic map is acquired with a mapping point of any one laser cluster on the electronic map as a center; calculating the distance between the laser cluster and each obstacle in the corresponding area, and acquiring the obstacle closest to the laser cluster; and traversing each laser cluster to obtain the coordinates of the obstacle closest to each laser cluster on the electronic map.
As shown in fig. 5, wherein the black part represents the grid points occupied by the obstacles, the white part represents the grid points occupied by the obstacles, the robot can freely move in these areas, and the gray part represents the unknown area; and after the clustering result is obtained, matching each cluster with the map.
And step S208, determining whether the positioning result of the target object is accurate or not based on the matching result of each laser cluster and the electronic map.
In some embodiments of the present application, if the number of laser clusters matched with the electronic map exceeds a fourth predetermined threshold, the matching result is that the positioning result is accurate.
In some embodiments of the present application, the lidar data comprises: relative distance information and relative direction information between the obstacle and the laser radar.
Taking the map shown in fig. 5 as an example, finally, the matching conditions of all clusters are integrated to judge whether the current positioning is reliable, so as to solve the problem of determining the positioning reliability in a dynamic scene. The specific matching method comprises the following steps:
projecting the laser points in each laser cluster into a map by using the positioning information;
and finding the point occupied by the obstacle closest to the point in the map for each point in each cluster, and calculating the distance d between the laser point and the point. In actual use, after the map is read, the distance between each position on the map and the nearest barrier point is calculated to establish a buffer map, the value of each point on the map represents the distance between the point and the nearest barrier point, and the buffer map is directly inquired in actual use, so that the pressure calculated in real time can be greatly reduced.
And counting the laser points in each cluster, and when the distance d between the laser point and the nearest barrier is smaller than a preset threshold Dt, considering that the laser point is matched with the map. Dt settings are typically the inherent error magnitudes of using lidar. For each laser cluster, when the number of laser points in the cluster exceeds 90% and is matched, the laser cluster is considered to be matched with a map; otherwise, the signals are not matched; and when more than N laser clusters are matched with the map, judging that the positioning result is reliable. The positioning result is shown in fig. 6, the red line, the green line and the purple line are divided into laser clusters matched with the map, and at the moment, 3 laser clusters are matched with the map, so that the positioning can be judged to be reliable.
Compared with the condition that the original laser data and the map are not clustered to directly calculate the matching condition, the method and the device for positioning the laser cluster match the map directly by using the original laser data and the map, when the environment changes greatly, the matching degree of the laser and the map is not high, whether positioning is unreliable can not be judged, and the laser cluster using the object as a unit is used for matching, so that positioning can be judged to be reliable as long as some static objects can be successfully matched even if the environment changes greatly.
The embodiment of the present application provides a positioning apparatus based on a laser radar, and the apparatus is used for implementing the method shown in fig. 2, as shown in fig. 7, the apparatus includes: an obtaining module 70, configured to obtain lidar data collected by a lidar; a clustering module 72, configured to cluster the laser radar data to obtain a plurality of laser clusters; the matching module 74 is configured to match each laser cluster with an electronic map respectively in the process of positioning the target object; and a positioning module 76, configured to determine whether the positioning result of the target object is accurate based on the matching result of each laser cluster and the electronic map.
Specifically, the clustering module 72 is configured to cluster the laser radar data to obtain a plurality of laser clusters, generate a laser cluster according to the laser radar measurement data, and match the laser cluster with positioning data in an electronic map, where the laser cluster is laser radar position data, and after determining the positioning of the subject, the laser radar can position the subject device according to the surrounding environment.
In some embodiments of the present application, if the number of laser clusters matching the electronic map exceeds a predetermined threshold, the positioning result of the robot is accurate.
The laser data is clustered before fusion with vision. The point clouds with the same position can be clustered into a cluster by clustering. The clustering method is realized by using an RBNN algorithm, the RBNN algorithm is an improvement of a KNN-based clustering method, and whether the data and the neighboring points belong to one class or not is determined by using the distance between each data and the neighboring points. After clustering, the point cloud image with the cluster label is shown in fig. 4.
At this time, according to the clustering process, it can be determined which laser points belong to the same object. And we can denoise the laser data by clustering, and remove some irregular environmental information. The specific method for removing the environmental information is to remove redundant laser cluster dot matrix coordinates by using an RBNN algorithm, so that the technical effect of removing noise is achieved.
Specifically, the matching module 74 is configured to match each laser cluster with the electronic map respectively in the process of locating the target object in the sensing region, and in some embodiments of the present application, the matching process may be represented in the following two manners:
the first mode is as follows:
a, obtaining a positioning result of the moving target object;
b, mapping each laser cluster into an electronic map based on a positioning result; wherein each laser cluster can be mapped into an electronic map by: reading a positioning coordinate in a positioning result; and projecting the laser point of each laser cluster into the electronic map based on the positioning coordinates, and determining the position of the laser point of each laser cluster mapped in the electronic map.
And c, matching each laser cluster with the corresponding area respectively mapped in the electronic map to obtain a matching result.
Specifically, a plurality of laser points in any one laser cluster are obtained; calculating the occupation point of the obstacle closest to each laser point on the electronic map and the closest distance value between each laser point and the corresponding occupation point; counting the number of laser points with the closest distance value smaller than a first preset threshold value; and if the statistical quantity exceeds a second preset threshold value, determining that the laser cluster is matched with the electronic map.
The second mode is as follows:
step 1) taking each laser cluster as a center, and acquiring coordinates of an obstacle closest to each laser cluster on the electronic map;
step 2) obtaining the distance between each laser cluster and the nearest barrier to obtain a plurality of distance values;
and 3) if the distance value is smaller than or equal to a third preset threshold value, determining that the corresponding laser cluster is matched with the electronic map.
Specifically, the positioning module 76 is configured to determine whether the positioning result of the target object is accurate based on the matching result of each laser cluster and the electronic map. In some embodiments of the present application, if the number of laser clusters matched with the electronic map exceeds a fourth predetermined threshold, the matching result is that the positioning result is accurate.
Taking the map shown in fig. 5 as an example, finally, the matching conditions of all clusters are integrated to determine whether the current positioning is reliable, so as to solve the problem of determining the positioning reliability in a dynamic scene. The specific matching method comprises the following steps:
projecting the laser points in each laser cluster into a map by using the positioning information;
and finding the point occupied by the obstacle closest to the point in the map for each point in each cluster, and calculating the distance d between the laser point and the map point. In actual use, after the map is read, the distance between each position on the map and the nearest barrier point is calculated to establish a buffer map, the value of each point on the map represents the distance between the point and the nearest barrier point, and the buffer map is directly inquired in actual use, so that the pressure calculated in real time can be greatly reduced.
And counting the laser points in each cluster, and when the distance d between the laser point and the nearest barrier is smaller than a preset threshold Dt, considering that the laser point is matched with the map. Dt is typically an inherent error of the lidar. For each laser cluster, when the number of laser points in the cluster exceeds 90% and is matched, the laser cluster is considered to be matched with a map; otherwise, the signals are not matched; and when more than N laser clusters are matched with the map, judging that the positioning result is reliable. The positioning result is shown in fig. 6, the red, green and purple parts in the map are laser clusters matched with the map, and at this time, 3 laser clusters are matched with the map, so that the positioning can be judged to be reliable.
Compared with the condition that the original laser data and the map are not clustered to directly calculate the matching condition, the method and the device for positioning the laser cluster match the map directly by using the original laser data and the map, when the environment changes greatly, the matching degree of the laser and the map is not high, whether positioning is unreliable can not be judged, and the laser cluster using the object as a unit is used for matching, so that positioning can be judged to be reliable as long as some static objects can be successfully matched even if the environment changes greatly.
Fig. 8 is a schematic flowchart of another positioning method for lidar according to an embodiment of the present application, where the method includes, as shown in fig. 8:
step S802, laser radar data collected by a laser radar is obtained, wherein the laser radar data comprises: relative distance information and relative direction information of the laser radar and the obstacle;
step S804, clustering the laser radar data to obtain a plurality of laser clusters;
step S806, in the process of positioning the obstacle corresponding to the moving robot, matching each laser cluster with an electronic map respectively;
and step S808, determining whether the positioning result is accurate or not based on the matching result of each laser cluster and the electronic map.
In some embodiments of the present application, in the process of locating an obstacle corresponding to a moving robot, matching each laser cluster with an electronic map respectively includes: obtaining a positioning result of the obstacle; mapping each laser cluster into the electronic map based on the positioning result; and matching each laser cluster with the corresponding area respectively mapped in the electronic map to obtain the matching result.
Wherein: and if the number of the laser clusters matched with the electronic map exceeds a preset threshold value, the positioning result of the robot is accurate.
The embodiment of the application provides a storage medium, which includes a stored program, wherein when the program runs, the device where the storage medium is located is controlled to execute the laser radar-based positioning method. For example, the method may be: acquiring laser radar data collected by a laser radar; clustering the laser radar data to obtain a plurality of laser clusters; in the process of positioning a target object, matching each laser cluster with an electronic map respectively; and determining whether the positioning result of the target object is accurate or not based on the matching result of each laser cluster and the electronic map.
In yet another aspect of the embodiments of the present application, a processor is provided, and the processor is configured to execute a program stored in a memory, where the program executes the lidar-based positioning method described above. For example, the method may be: acquiring laser radar data collected by a laser radar; clustering the laser radar data to obtain a plurality of laser clusters; in the process of positioning a target object in the sensing area, matching each laser cluster with an electronic map respectively; and determining whether the positioning result of the target object is accurate or not based on the matching result of each laser cluster and the electronic map.
The above-mentioned serial numbers of the embodiments of the present application are merely for description and do not represent the merits of the embodiments.
In the above embodiments of the present application, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.
In the embodiments provided in the present application, it should be understood that the disclosed technology can be implemented in other ways. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units may be a logical division, and in actual implementation, there may be another division, for example, multiple units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, units or modules, and may be in an electrical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be substantially implemented or contributed to by the prior art, or all or part of the technical solution may be embodied in a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic or optical disk, and other various media capable of storing program codes.
The foregoing is only a preferred embodiment of the present application and it should be noted that those skilled in the art can make several improvements and modifications without departing from the principle of the present application, and these improvements and modifications should also be considered as the protection scope of the present application.
Claims (18)
1. A positioning method based on laser radar is characterized by comprising the following steps:
acquiring laser radar data of a laser radar;
clustering the laser radar data to obtain a plurality of laser clusters;
in the process of positioning a target object, matching each laser cluster with an electronic map respectively;
and determining whether the positioning result of the target object is accurate or not based on the matching result of each laser cluster and the electronic map.
2. The method of claim 1, wherein matching each laser cluster with an electronic map during the positioning of the target object comprises:
obtaining a positioning result of the target object;
mapping each laser cluster into the electronic map based on the positioning result;
and matching each laser cluster with the corresponding area respectively mapped in the electronic map to obtain the matching result.
3. The method of claim 2, wherein mapping each laser cluster into the electronic map based on the positioning results comprises:
reading a positioning coordinate in the positioning result;
and projecting the laser point of each laser cluster into the electronic map based on the positioning coordinates, and determining the position of the laser point mapping of each laser cluster in the electronic map.
4. The method of claim 3, wherein matching each laser cluster with a corresponding region respectively mapped in the electronic map to obtain the matching result comprises:
acquiring a plurality of laser points in any one laser cluster;
calculating the occupation point of the obstacle closest to each laser point on the electronic map and the closest distance value between each laser point and the corresponding occupation point;
counting the number of laser points with the closest distance value smaller than a first preset threshold value;
and if the statistical quantity exceeds a second preset threshold value, determining that the laser cluster is matched with the electronic map.
5. The method of claim 4, wherein after calculating the occupancy point on the electronic map of the obstacle at the closest distance from each laser point, the method further comprises:
and establishing a cache map based on the occupied point corresponding to each laser point, wherein each coordinate point on the cache map represents the closest distance value.
6. The method of claim 3, wherein matching each laser cluster with a corresponding region respectively mapped in the electronic map, and obtaining the matching result comprises:
taking each laser cluster as a center, and acquiring coordinates of an obstacle closest to each laser cluster on the electronic map;
obtaining the distance between each laser cluster and the nearest barrier to obtain a plurality of distance values;
and if the distance value is less than or equal to a third preset threshold value, determining that the corresponding laser cluster is matched with the electronic map.
7. The method of claim 6, wherein obtaining coordinates of an obstacle on the electronic map nearest to each laser cluster centered on the each laser cluster comprises:
taking a mapping point of any one laser cluster on the electronic map as a center, and acquiring at least one obstacle in a corresponding area on the electronic map;
calculating the distance between the laser cluster and each obstacle in the corresponding area, and acquiring the obstacle closest to the laser cluster;
and traversing each laser cluster to obtain the coordinates of the obstacles on the electronic map closest to each laser cluster.
8. The method according to claim 4 or 6, wherein determining whether the positioning result of the target object is accurate based on the matching result of each laser cluster and the electronic map comprises: and if the number of the laser clusters matched with the electronic map exceeds a fourth preset threshold value, the matching result is that the positioning result is accurate.
9. The method of claim 1, wherein the lidar data comprises: relative distance information and relative direction information between the laser radar and the obstacle.
10. A positioning method based on laser radar is characterized by comprising the following steps:
acquiring laser radar data collected by a laser radar, wherein the laser radar data comprises: relative distance information and relative direction information of the laser radar and the obstacle;
clustering the laser radar data to obtain a plurality of laser clusters;
in the process of positioning the barrier corresponding to the moving robot, matching each laser cluster with an electronic map respectively;
and determining whether the positioning result is accurate or not based on the matching result of each laser cluster and the electronic map.
11. The method of claim 10, wherein matching each laser cluster with an electronic map during the positioning of the obstacle corresponding to the moving robot comprises:
obtaining a positioning result of the obstacle;
mapping each laser cluster into the electronic map based on the positioning result;
and matching each laser cluster with the corresponding area respectively mapped in the electronic map to obtain the matching result.
12. The method of claim 10, wherein determining whether the positioning result of the robot is accurate based on the matching result of each laser cluster with the electronic map comprises: and if the number of the laser clusters matched with the electronic map exceeds a preset threshold value, the positioning result of the robot is accurate.
13. A robot, comprising:
the laser radar is used for collecting laser radar data;
a processor connected to the lidar for determining a location result of an obstacle based on the lidar data; and matching each laser cluster obtained by clustering the laser radar data with an electronic map, and determining whether the positioning result is accurate or not based on the matching result.
14. The robot of claim 13, wherein the lidar data comprises: relative distance information and relative direction information between the robot and the obstacle.
15. The robot of claim 13, wherein the positioning result is determined to be accurate if the number of laser clusters matching the electronic map exceeds a predetermined threshold.
16. A lidar-based positioning apparatus, comprising:
the acquisition module is used for acquiring laser radar data acquired by a laser radar;
the clustering module is used for clustering the laser radar data to obtain a plurality of laser clusters;
the matching module is used for matching each laser cluster with the electronic map respectively in the process of positioning the target object;
and the positioning module is used for determining whether the positioning result of the target object is accurate or not based on the matching result of each laser cluster and the electronic map.
17. A storage medium comprising a stored program, wherein the program, when executed, controls an apparatus in which the storage medium is located to perform the lidar-based positioning method according to any of claims 1 to 9.
18. A processor for executing a program stored in a memory, wherein,
the program is operative to perform a lidar based positioning method according to any of claims 1 to 9.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911206878.XA CN110865393A (en) | 2019-11-29 | 2019-11-29 | Positioning method and system based on laser radar, storage medium and processor |
PCT/CN2020/132457 WO2021104497A1 (en) | 2019-11-29 | 2020-11-27 | Positioning method and system based on laser radar, and storage medium and processor |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911206878.XA CN110865393A (en) | 2019-11-29 | 2019-11-29 | Positioning method and system based on laser radar, storage medium and processor |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110865393A true CN110865393A (en) | 2020-03-06 |
Family
ID=69657832
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201911206878.XA Pending CN110865393A (en) | 2019-11-29 | 2019-11-29 | Positioning method and system based on laser radar, storage medium and processor |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN110865393A (en) |
WO (1) | WO2021104497A1 (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112213738A (en) * | 2020-09-28 | 2021-01-12 | 劢微机器人科技(深圳)有限公司 | Map construction method, device and equipment for automated guided vehicle and storage medium |
WO2021104497A1 (en) * | 2019-11-29 | 2021-06-03 | 广州视源电子科技股份有限公司 | Positioning method and system based on laser radar, and storage medium and processor |
CN113390415A (en) * | 2021-06-04 | 2021-09-14 | 深圳优艾智合机器人科技有限公司 | Robot positioning method, positioning device, management system, and storage medium |
CN114252883A (en) * | 2020-09-24 | 2022-03-29 | 北京万集科技股份有限公司 | Target detection method, apparatus, computer device and medium |
WO2022116831A1 (en) * | 2020-12-03 | 2022-06-09 | 深圳市优必选科技股份有限公司 | Positioning method and apparatus, electronic device and readable storage medium |
CN115616578A (en) * | 2022-12-05 | 2023-01-17 | 成都航空职业技术学院 | Radar detection method and device for unmanned aerial vehicle |
Families Citing this family (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113432533B (en) * | 2021-06-18 | 2023-08-15 | 北京盈迪曼德科技有限公司 | Robot positioning method and device, robot and storage medium |
CN114445572B (en) * | 2021-12-29 | 2024-05-14 | 航天时代(青岛)海洋装备科技发展有限公司 | DeeplabV3+ based method for immediately positioning and constructing map of obstacle in strange sea area |
CN114440858B (en) * | 2022-01-25 | 2023-12-19 | 中国人民解放军总医院第一医学中心 | Mobile robot positioning loss detection method, system, equipment and storage medium |
CN115267796B (en) * | 2022-08-17 | 2024-04-09 | 深圳市普渡科技有限公司 | Positioning method, positioning device, robot and storage medium |
CN115685990A (en) * | 2022-09-22 | 2023-02-03 | 深圳市智绘科技有限公司 | Automatic charging method and device, electronic equipment and readable storage medium |
CN115840205B (en) * | 2023-02-16 | 2023-05-23 | 济宁市质量计量检验检测研究院(济宁半导体及显示产品质量监督检验中心、济宁市纤维质量监测中心) | Terrain area metering method and system based on laser radar technology |
CN116077186B (en) * | 2023-04-07 | 2023-06-30 | 青岛大学附属医院 | Surgical positioning system based on laser interference |
CN116840820B (en) * | 2023-08-29 | 2023-11-24 | 上海仙工智能科技有限公司 | Method and system for detecting 2D laser positioning loss and storage medium |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20160217611A1 (en) * | 2015-01-26 | 2016-07-28 | Uber Technologies, Inc. | Map-like summary visualization of street-level distance data and panorama data |
CN106323273A (en) * | 2016-08-26 | 2017-01-11 | 深圳微服机器人科技有限公司 | Robot relocation method and device |
CN107064955A (en) * | 2017-04-19 | 2017-08-18 | 北京汽车集团有限公司 | barrier clustering method and device |
CN107422730A (en) * | 2017-06-09 | 2017-12-01 | 武汉市众向科技有限公司 | The AGV transportation systems of view-based access control model guiding and its driving control method |
CN108507579A (en) * | 2018-04-08 | 2018-09-07 | 浙江大承机器人科技有限公司 | A kind of method for relocating based on localized particle filtering |
CN109284348A (en) * | 2018-10-30 | 2019-01-29 | 百度在线网络技术(北京)有限公司 | A kind of update method of electronic map, device, equipment and storage medium |
CN109917792A (en) * | 2019-04-10 | 2019-06-21 | 湖南汽车工程职业学院 | A kind of autonomous collision avoidance system based on unmanned sightseeing electric car |
CN110084272A (en) * | 2019-03-26 | 2019-08-02 | 哈尔滨工业大学(深圳) | A kind of cluster map creating method and based on cluster map and the matched method for relocating of location expression |
Family Cites Families (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2005181059A (en) * | 2003-12-18 | 2005-07-07 | Toshiba Corp | Target position evaluating method and device |
CN104931977B (en) * | 2015-06-11 | 2017-08-25 | 同济大学 | A kind of obstacle recognition method for intelligent vehicle |
CN105866790B (en) * | 2016-04-07 | 2018-08-10 | 重庆大学 | A kind of laser radar obstacle recognition method and system considering lasing intensity |
CN109840454B (en) * | 2017-11-28 | 2021-01-29 | 华为技术有限公司 | Target positioning method, device, storage medium and equipment |
CN109509256B (en) * | 2018-06-21 | 2023-07-18 | 华南理工大学 | Automatic measurement and 3D model generation method for building structure based on laser radar |
CN109829032B (en) * | 2019-03-14 | 2021-02-26 | 广州蓝胖子移动科技有限公司 | Method, equipment and storage medium for article identification |
CN110865393A (en) * | 2019-11-29 | 2020-03-06 | 广州视源电子科技股份有限公司 | Positioning method and system based on laser radar, storage medium and processor |
-
2019
- 2019-11-29 CN CN201911206878.XA patent/CN110865393A/en active Pending
-
2020
- 2020-11-27 WO PCT/CN2020/132457 patent/WO2021104497A1/en active Application Filing
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20160217611A1 (en) * | 2015-01-26 | 2016-07-28 | Uber Technologies, Inc. | Map-like summary visualization of street-level distance data and panorama data |
CN106323273A (en) * | 2016-08-26 | 2017-01-11 | 深圳微服机器人科技有限公司 | Robot relocation method and device |
CN107064955A (en) * | 2017-04-19 | 2017-08-18 | 北京汽车集团有限公司 | barrier clustering method and device |
CN107422730A (en) * | 2017-06-09 | 2017-12-01 | 武汉市众向科技有限公司 | The AGV transportation systems of view-based access control model guiding and its driving control method |
CN108507579A (en) * | 2018-04-08 | 2018-09-07 | 浙江大承机器人科技有限公司 | A kind of method for relocating based on localized particle filtering |
CN109284348A (en) * | 2018-10-30 | 2019-01-29 | 百度在线网络技术(北京)有限公司 | A kind of update method of electronic map, device, equipment and storage medium |
CN110084272A (en) * | 2019-03-26 | 2019-08-02 | 哈尔滨工业大学(深圳) | A kind of cluster map creating method and based on cluster map and the matched method for relocating of location expression |
CN109917792A (en) * | 2019-04-10 | 2019-06-21 | 湖南汽车工程职业学院 | A kind of autonomous collision avoidance system based on unmanned sightseeing electric car |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2021104497A1 (en) * | 2019-11-29 | 2021-06-03 | 广州视源电子科技股份有限公司 | Positioning method and system based on laser radar, and storage medium and processor |
CN114252883A (en) * | 2020-09-24 | 2022-03-29 | 北京万集科技股份有限公司 | Target detection method, apparatus, computer device and medium |
CN114252883B (en) * | 2020-09-24 | 2022-08-23 | 北京万集科技股份有限公司 | Target detection method, apparatus, computer device and medium |
CN112213738A (en) * | 2020-09-28 | 2021-01-12 | 劢微机器人科技(深圳)有限公司 | Map construction method, device and equipment for automated guided vehicle and storage medium |
WO2022116831A1 (en) * | 2020-12-03 | 2022-06-09 | 深圳市优必选科技股份有限公司 | Positioning method and apparatus, electronic device and readable storage medium |
CN113390415A (en) * | 2021-06-04 | 2021-09-14 | 深圳优艾智合机器人科技有限公司 | Robot positioning method, positioning device, management system, and storage medium |
CN113390415B (en) * | 2021-06-04 | 2024-03-01 | 深圳优艾智合机器人科技有限公司 | Positioning method, positioning device, management system and storage medium for robot |
CN115616578A (en) * | 2022-12-05 | 2023-01-17 | 成都航空职业技术学院 | Radar detection method and device for unmanned aerial vehicle |
Also Published As
Publication number | Publication date |
---|---|
WO2021104497A1 (en) | 2021-06-03 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110865393A (en) | Positioning method and system based on laser radar, storage medium and processor | |
KR102061522B1 (en) | Apparatus and method for detecting object based on density using lidar sensor | |
EP3812793B1 (en) | Information processing method, system and equipment, and computer storage medium | |
CN111712731B (en) | Target detection method, target detection system and movable platform | |
WO2021253430A1 (en) | Absolute pose determination method, electronic device and mobile platform | |
CN111753609B (en) | Target identification method and device and camera | |
CN109521757B (en) | Static obstacle identification method and device | |
WO2018222889A1 (en) | Collision prediction system | |
CN112513679B (en) | Target identification method and device | |
CN104732514A (en) | Apparatus, systems, and methods for processing a height map | |
CN110471086B (en) | Radar fault detection system and method | |
CN111308500B (en) | Obstacle sensing method and device based on single-line laser radar and computer terminal | |
CN113111513B (en) | Sensor configuration scheme determining method and device, computer equipment and storage medium | |
WO2022198637A1 (en) | Point cloud noise filtering method and system, and movable platform | |
US10989804B2 (en) | Method and apparatus for optical distance measurements | |
US20220108552A1 (en) | Method and Apparatus for Determining Drivable Region Information | |
WO2022083529A1 (en) | Data processing method and apparatus | |
US20230094836A1 (en) | Method for Detecting Moving Objects in the Surroundings of a Vehicle, and Motor Vehicle | |
CN114102577B (en) | Robot and positioning method applied to robot | |
CN117751301A (en) | Method, device, equipment and storage medium for processing laser radar point cloud | |
US11668799B2 (en) | Histogram based L-shape detection of target objects | |
Wang et al. | Fusion perception of vision and millimeter wave radar for autonomous driving | |
KR20220128787A (en) | Method and apparatus for tracking an object using LIDAR sensor, and recording medium for recording program performing the method | |
JP5743457B2 (en) | Object detection system and method | |
CN111723797A (en) | Method and system for determining bounding box of three-dimensional target |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200306 |
|
RJ01 | Rejection of invention patent application after publication |