CN112836681A - Obstacle marking method and device and readable non-transitory storage medium - Google Patents
Obstacle marking method and device and readable non-transitory storage medium Download PDFInfo
- Publication number
- CN112836681A CN112836681A CN202110237014.5A CN202110237014A CN112836681A CN 112836681 A CN112836681 A CN 112836681A CN 202110237014 A CN202110237014 A CN 202110237014A CN 112836681 A CN112836681 A CN 112836681A
- Authority
- CN
- China
- Prior art keywords
- obstacle
- characteristic data
- thin rod
- fitting
- radius
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 96
- 230000004888 barrier function Effects 0.000 claims abstract description 36
- 238000002372 labelling Methods 0.000 claims abstract description 6
- 238000010276 construction Methods 0.000 claims description 5
- 230000008569 process Effects 0.000 description 36
- 230000006870 function Effects 0.000 description 6
- 238000013480 data collection Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 239000003550 marker Substances 0.000 description 4
- 238000005259 measurement Methods 0.000 description 4
- 230000003068 static effect Effects 0.000 description 4
- 238000007726 management method Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 238000007790 scraping Methods 0.000 description 2
- 230000001131 transforming effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000007599 discharging Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000006748 scratching Methods 0.000 description 1
- 230000002393 scratching effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The application relates to the field of automation operation and provides an obstacle marking method, an obstacle marking device and a readable non-transitory storage medium. Specifically, provided is an obstacle labeling method including the steps of: acquiring first characteristic data of an obstacle, and acquiring a first fitting radius of the obstacle according to the first characteristic data; judging whether the first fitting radius is smaller than a first preset value or not; if the first characteristic data is smaller than the second characteristic data, second characteristic data of the obstacle is obtained, a second fitting radius of the obstacle is obtained according to the second characteristic data, and the second characteristic data is obtained after the acquisition position is changed; judging whether the second fitting radius is smaller than a second preset value or not; and if the distance is smaller than the preset distance, marking the obstacle as a thin rod obstacle. By adopting the technical scheme, whether the detected barrier is a thin rod barrier or not is verified by acquiring the second characteristic data, the situation of thin rod identification errors can be obviously reduced, and the barrier marking efficiency is improved.
Description
Technical Field
The present invention relates to the field of automated operations, and more particularly, to a method and apparatus for marking an obstacle, and a readable non-transitory storage medium.
Background
Movable electronic devices, such as automatic operation robots, need to sense the surrounding environment in real time, detect obstacles, and perform path planning and obstacle avoidance efficiently. In the environments of malls, supermarkets, transportation hubs and the like, slender rod type obstacles such as one-meter hurdle, guide cards and the like usually exist.
The thin rod part of the thin rod type obstacle can be identified through laser or a camera, and the thin rod part is marked on a map. However, since the height of the tray for the thin rod type obstacle is low, the tray is easily in the dead zone of the sensor, and effective detection cannot be realized. The robot keeps a preset safety distance with the obstacles during path planning or operation, but the safety distance is not enough to cover the tray area when facing the thin rod type obstacles. Therefore, even if the thin rod is marked, the robot may scratch the tray at the bottom of the thin rod, thereby risking collision.
Therefore, it is an urgent technical problem to provide a method and a device for marking obstacles and a readable non-transitory storage medium in the field of automation operation in a targeted manner.
Content of application
The present application is directed to providing an obstacle marking method, apparatus, and readable non-transitory storage medium to solve at least one of the problems described in the background.
In a first aspect of the present application, there is provided an obstacle marking method, comprising the steps of,
acquiring first characteristic data of an obstacle, and acquiring a first fitting radius of the obstacle according to the first characteristic data;
judging whether the first fitting radius is smaller than a first preset value or not;
if the first characteristic data is smaller than the second characteristic data, second characteristic data of the obstacle is obtained, a second fitting radius of the obstacle is obtained according to the second characteristic data, and the second characteristic data is obtained after the acquisition position is changed;
judging whether the second fitting radius is smaller than a second preset value or not;
and if the distance is smaller than the preset distance, marking the obstacle as a thin rod obstacle.
By adopting the technical scheme, whether the detected barrier is a thin rod barrier or not is verified by acquiring the second characteristic data, the situation of thin rod identification errors can be obviously reduced, and the barrier marking efficiency is improved.
Preferably, the method for labeling an obstacle further comprises the steps of:
if the obstacle is a thin rod type obstacle, an expansion area corresponding to the thin rod type obstacle is generated.
Preferably, the method for obtaining the first fitting radius includes the steps of:
obtaining a fitting circle corresponding to the obstacle according to the first characteristic data;
and obtaining the radius of the fitting circle.
Preferably, the first predetermined value is 0.05 m.
Preferably, the method for generating the expansion region comprises the steps of:
generating an expansion region center point from the first feature data or the second feature data,
forming a circular area by taking the central point as a circle center and a fourth preset value as a radius;
the expansion region center point is the center of a fitting circle generated according to the first characteristic data or the second characteristic data,
the fourth predetermined value is not less than the first predetermined value.
Preferably, the step of acquiring second characteristic data of the obstacle is,
and acquiring a plurality of second characteristic data of the obstacle, wherein the plurality of second characteristic data are acquired after a plurality of acquisition positions are changed.
Preferably, the acquiring second characteristic data of the obstacle includes:
acquiring a group of second characteristic data of the obstacle, and acquiring a second fitting radius of the obstacle according to the second characteristic data, wherein the second characteristic data is acquired after the acquisition position is changed;
the number of acquisition groups of the second characteristic data is judged,
if the number of the acquired groups is greater than or equal to a third preset value, judging whether the second fitting radius is smaller than a second preset value;
if the number of the acquired groups is smaller than a third preset value, judging whether the second fitting radius is smaller than a second preset value; if yes, continuously acquiring a group of second characteristic data of the obstacle, wherein the group of second characteristic data is acquired after the acquisition position is changed; if not, marking that the obstacle does not belong to the thin rod type obstacle.
Preferably, the first predetermined value is equal to the second predetermined value.
In a second aspect of the present application, there is provided a method for navigating a movable electronic device, comprising the steps of,
constructing a working area map;
marking obstacles in a workspace map using a method as in the first aspect of the application;
planning a running path of the movable electronic equipment according to the marked working area map, wherein the running path is not overlapped with an expansion area of the thin rod type barrier;
and controlling the movable electronic equipment to run in the working area according to the planned running path.
By adopting the technical scheme, the operation path of the movable electronic equipment can be more accurately planned by marking the obstacles in the working area map, and the risk of rubbing the obstacles when the movable electronic equipment operates is effectively reduced.
In a third aspect of the present application, there is provided an obstacle marking device including:
the first acquisition module is used for acquiring first characteristic data of an obstacle and acquiring a first fitting radius of the obstacle according to the first characteristic data;
the first judging module is used for judging whether the first fitting radius is smaller than a first preset value or not;
the second acquisition module is used for acquiring second characteristic data of the obstacle and acquiring a second fitting radius of the obstacle according to the second characteristic data, wherein the second characteristic data is acquired after the acquisition position is changed;
the second judging module is used for judging whether the second fitting radius is smaller than a second preset value or not;
the first marking module is used for marking the obstacles as thin rod type obstacles.
In a fourth aspect of the present application, there is provided a movable electronic device navigation apparatus, comprising,
the first construction module is used for constructing a working area map;
an obstacle marking device as provided in the third aspect of the present application;
the first planning module is used for planning a running path of the movable electronic equipment according to a working area map and the obstacles in the working area, and the running path is not overlapped with an expansion area of the thin rod type obstacles;
and the first control module is used for controlling the movable electronic equipment to operate in the working area according to the planned operation path.
In a fifth aspect of the present application, there is provided an electronic device comprising a processor, a memory and a program or instructions stored on the memory and executable on the processor, the program or instructions, when executed by the processor, implementing the steps of the method for obstacle marking or navigation of a mobile electronic device as in the first or second aspect of the present application.
In a sixth aspect of the present application, there is provided a readable non-transitory storage medium having stored thereon a program or instructions which, when executed by a processor, performs the steps of the method for obstacle marking or mobile electronic device navigation according to the first or second aspect of the present application.
In summary, the present application has the following beneficial effects:
1. according to the obstacle marking method, the characteristic data are obtained for multiple times, whether the detected obstacle is a thin rod obstacle or not is verified, the situation of thin rod recognition errors can be obviously reduced, and the obstacle marking efficiency is improved;
2. according to the obstacle marking method, the expansion area corresponding to the thin rod type obstacle is generated, so that the thin rod type obstacle can represent the chassis area of the thin rod type obstacle, and the expansion area can be avoided during path planning of the electronic equipment;
3. according to the movable electronic equipment navigation method, the barriers are marked in the working area map, the running path of the movable electronic equipment can be planned more accurately, and the risk of scraping and rubbing the thin rod type barriers during running of the movable electronic equipment is effectively reduced.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a schematic view of a thin rod-like barrier according to an embodiment of the present application;
FIG. 2 is a flow chart of one of the steps of an obstacle marking method in an embodiment of the present application;
FIG. 3 is a schematic diagram of a fitted circle of an embodiment of the present application;
FIG. 4 is a schematic view of an expansion zone of an embodiment of the present application;
FIG. 5 is a schematic illustration of an exemplary set of embodiments of the present application;
FIG. 6 is a schematic diagram of a method for generating an expanded region according to an embodiment of the present disclosure;
FIG. 7 is a flowchart illustrating steps of a method for navigating a mobile electronic device according to an embodiment of the present application;
FIG. 8 is a schematic view of one of the obstacle marking devices according to an embodiment of the present application;
FIG. 9 is one of the schematic diagrams of a mobile electronic device navigation apparatus of an embodiment of the present application;
fig. 10 is one of schematic diagrams of an electronic device according to an embodiment of the present application.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be further noted that, for the convenience of description, only some of the structures related to the present invention are shown in the drawings, not all of the structures. In addition, the embodiments and features of the embodiments in the present invention may be combined with each other without conflict.
Before discussing exemplary embodiments in more detail, it should be noted that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although a flowchart may describe the operations (or steps) as a sequential process, many of the operations can be performed in parallel, concurrently or simultaneously. In addition, the order of the operations may be re-arranged. The process may be terminated when its operations are completed, but may have additional steps not included in the figure. The processes may correspond to methods, functions, procedures, subroutines, and the like. In addition, the embodiments and features of the embodiments in the present invention may be combined with each other without conflict.
The term "include" and variations thereof as used herein are intended to be open-ended, i.e., "including but not limited to". The term "based on" is "based, at least in part, on". The term "one embodiment" means "at least one embodiment".
It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict. The method for marking an obstacle, the method for navigating by using a mobile electronic device, the apparatus for marking an obstacle, the apparatus for navigating by using a mobile electronic device, an electronic device and a readable non-transitory storage medium according to the embodiments of the present application are described in detail below with reference to the accompanying drawings.
The thin rod type obstacle in the present application generally includes a base portion 1, and a thin rod portion 2 connected to the base portion and extending in a vertical direction, wherein a cross-sectional area of the base portion 1 is larger than a cross-sectional area of the thin rod portion 2, as shown in fig. 1. Specifically, the base 1 of the slender rod type obstacle is usually a base with a small height (usually 0.03m or less), and a slender straight and long rod, such as a slender rod type object like a fence, a display board, a guide board and the like, extends upwards from the base and is the slender rod type obstacle described in the present application.
Fig. 2 is a flowchart of steps of an obstacle marking method according to an embodiment of the present application, where the present embodiment is applicable to a case where a mobile electronic device effectively avoids an obstacle during a movement process, and the method may be executed by an obstacle avoidance device, which may be implemented in a hardware and/or software manner and may be integrated in the electronic device, where the mobile electronic device may be an intelligent mobile device having a data processing function, such as an intelligent robot and an intelligent shopping cart, and may be applied to public places such as hotels, shopping malls, restaurants, airports, and stations. Referring to fig. 2, an embodiment of the present application provides an obstacle marking method, including:
step S102, first characteristic data of the obstacle are obtained, and a first fitting radius of the obstacle is obtained according to the first characteristic data.
The obstacle is schematically an object which influences the movement path of the electronic device during movement, and may be static, such as a table, a chair, or the like, or dynamic, such as a person, other movable electronic devices, or the like. The obstacle may be determined based on point cloud data acquired by the electronic device. The point cloud data can be obtained instantly by a 2D laser or a 3D laser, and can also be obtained by reading historical acquisition data. Each acquisition can obtain a set of point cloud data corresponding to the acquisition position, which is also called a frame of point cloud data. After the point cloud data is obtained, equipment with computing capability, such as a server, can cluster the point cloud data, and the point cloud data belonging to the same cluster indicate that the point cloud data belong to the same object. At least one target object, namely an obstacle, can be obtained through clustering of the point cloud data, and the point cloud data corresponding to each obstacle is the first characteristic data of the obstacle.
In some embodiments, the clustering of point clouds may employ the followingThe method comprises the following steps: for example, for a frame of point cloud data, the coordinates of the P point is P (x)1,y1) The coordinate of the point Q is Q (x)2,y2) The Euclidean distance between two points isAnd searching whether a point with the Euclidean distance smaller than a threshold exists nearby by taking the point P as a starting point, wherein the threshold can be adjusted according to a specific scene, and can be set to be 0.05m, 0.1m, 0.2m and the like. For example, when the threshold is 0.1M, the euclidean distance between the point Q and the point P is found to be less than 0.1M, and the two points are divided into the same cluster set M; otherwise, the method is divided into 2 clusters. And repeating the above operations by taking the point Q as a starting point until the number of points in the clustering set M is not increased any more, and considering that the clustering of the point cloud data under the frame is finished.
In a specific implementation process, the point cloud data of the obstacles obtained after clustering may be arranged in a certain order, for example, from right to left, and the point cloud index values increase sequentially. Therefore, the fitting radius can be calculated by calculating the euclidean distance between the leading and trailing points of the point cloud data of the obstacle. As shown in fig. 3, the euclidean distance between the starting point pi and the end point pj is calculated, and the distance is equal to the diameter of the fitting circle, so that the fitting radius R of the obstacle can be obtained. The fitted radius may characterize the footprint of the obstacle.
And step S104, judging whether the first fitting radius is smaller than a first preset value.
In a specific implementation, the first predetermined value may be a limit on the size of the obstacle, and the first predetermined value may be a maximum radius of a thin rod-like obstacle in a specific use environment, and if the first fitting radius is not smaller than the first predetermined value, it indicates that the size of the obstacle exceeds the size of a general thin rod-like obstacle, and the obstacle should not be marked as a thin rod-like obstacle. The first predetermined value may be 0.05m, 0.1m, 0.2m, etc., and may be adaptively set according to a specific usage scenario.
And S106, if the first characteristic data is smaller than the second characteristic data, second characteristic data of the obstacle is obtained, a second fitting radius of the obstacle is obtained according to the second characteristic data, and the second characteristic data is obtained after the acquisition position is changed.
In a specific implementation process, if it is determined in step S104 that the first fitting radius of the obstacle is smaller than the first predetermined value, it cannot be immediately determined that the obstacle is a thin rod type obstacle. Because the electronic device may be in a moving state during the point cloud data collection process, the collection position of the electronic device may also change, and the number of the returned laser point clouds for the same object may be different, for example, for a larger object, the electronic device collects the point cloud data on the side of the electronic device at a certain time, the fitting radius of the point cloud data is small, and the fitting radius of the point cloud data on the front of the electronic device collected at the next time is large. In addition, due to environmental influences, the laser may occasionally generate noise points, and the clustering radius of the noise points is small. Therefore, the acquisition position can be changed, the second characteristic data of the obstacle can be acquired, the second fitting radius can be obtained according to the second characteristic data, the obstacle can be verified again, and the error identification of the thin rod type obstacle can be obviously reduced. The acquisition positions can be changed for multiple times, each acquisition position obtains one frame of point cloud data, and each frame of point cloud data corresponds to one second fitting radius. From the second characteristic data, a second fitting radius may be calculated.
And S108, judging whether the second fitting radius is smaller than a second preset value or not, and if so, marking the barrier as a thin rod type barrier.
In a specific implementation, the second predetermined value may also be a limit on the size of the obstacle, for example, the second predetermined value may also be a radius limit of a general slender rod-type obstacle. If the second fitting radius is changed from the first fitting radius and is not less than the second predetermined value, it indicates that the measurement of the first fitting radius may generate an error, and the actual size of the obstacle exceeds the parameters of the general thin rod type obstacle and should not be marked as a thin rod type obstacle. The second predetermined value may be 0.05m, 0.1m, 0.2m, etc., and may be adaptively set according to a specific usage scenario. In some embodiments, the second predetermined value may be equal to the first predetermined value, which facilitates setting of parameters and may ensure consistency of evaluation of the thin stick obstacle criteria.
In the implementation process, if the second fitting radii are all smaller than the second predetermined value, the obstacle is characterized by a thin rod type obstacle at a plurality of acquisition positions and can be identified as the thin rod type obstacle. In some embodiments, since at least two fitting circles are generated according to the first characteristic data and the second characteristic data when the thin rod type obstacle is determined, if the object is not the thin rod type obstacle, any one fitting circle can be used as a mark point for representing the position of the object. In some embodiments, the circle fitted with the largest obstacle is used as the marker point for characterizing its position.
The thin rod type obstacles are small in size, and are generally in a static state, and the clustering radius of the thin rod type obstacles is smaller than a radius threshold value at different acquisition positions. Therefore, by adopting the technical scheme, whether the detected barrier is a thin rod type barrier or not is verified by collecting the characteristic data for multiple times, the situation of thin rod identification errors can be obviously reduced, the barrier marking efficiency is improved, and the collision risk is reduced in the path planning of the electronic equipment.
In some preferred embodiments, as shown in fig. 4, the method for labeling an obstacle further includes the steps of:
in step S110, if the obstacle is a thin rod obstacle, an expansion area corresponding to the thin rod obstacle is generated.
In a specific implementation process, the expansion area is a marking area corresponding to the thin rod type obstacle, so that the thin rod type obstacle can represent a chassis area of the thin rod type obstacle, the area can be considered to have a collision risk, and the expansion area can be avoided in the path planning of the electronic equipment.
Illustratively, the method of generating the expanded region comprises the steps of: and generating a central point of the expansion area according to the first characteristic data or the second characteristic data, and forming a circular area by taking the central point as a circle center and a fourth preset value as a radius. Wherein the expansion region center point may be a center of a fitted circle generated from the first characteristic data or the second characteristic data. In some embodiments, the fourth predetermined value is not less than the first predetermined value. . Referring to fig. 6, schematically, the expansion region may be generated in the following manner: first, the central point position po (xo, yo) of the thin-rod type obstacle point cloud data is calculated, as shown in fig. 6A, where xo is the average of the x coordinates of all points in the obstacle cluster, and yo is the average of the y coordinates of all points in the cluster. Then, the expansion point is plotted with a radius of 0.1m with the calculated center point as the center, and the area surrounded by the expansion point is the expansion area, as shown in fig. 6B. The central point and the expansion point of the thin rod are marked on the map, so that the effective identification and marking of the thin rod objects are realized.
When the thin rod type barrier is judged, at least two fitting circles can be generated according to the first characteristic data and the second characteristic data, the area of the expansion area is larger than the area of the largest fitting circle, and all the fitting circles fall into the expansion area, so that the marking range of the thin rod type barrier is expanded by the expansion area. The marking range is expanded because the mark of the barrier is avoided during path planning, and the safety of the movable electronic equipment such as a robot traveling along the path can be improved. In some embodiments, the expansion zone is circular and has a radius greater than a first predetermined value, ensuring that the expansion zone is always wider than the assumed condition for a thin rod-like obstacle. In some embodiments, the radius of the expansion area is significantly larger than the first predetermined value, or the radius thereof is larger than a first safety value, which is the sum of the first predetermined value and a safety distance, such as the first predetermined value is 0.05m, the pin tray radius is typically larger than the pin radius by 0.1m, which is the safety distance, and the first safety value is 0.05+0.1 — 0.15 m. The inflated area may be presented on an electronic map as a marker for thin rod-like obstacles in such a way that manual or manual routing is possible. In some implementations, the expansion region is concentric with the fitting circle having the largest area, further reducing the risk of collision when the electronic device is in operation.
By adopting the technical scheme, after the thin rod type obstacles are detected, the expansion area is generated to mark the tray or the chassis of the thin rod type obstacles, so that the scratch or collision between the movable electronic equipment and the tray when the movable electronic equipment runs along a planned path can be effectively avoided, and the running safety of the movable electronic equipment is improved.
In some preferred embodiments, the step of acquiring second characteristic data of the obstacle is,
and acquiring a plurality of second characteristic data of the obstacle, wherein the plurality of second characteristic data are acquired after a plurality of acquisition positions are changed.
In a specific implementation process, the electronic device changes a plurality of acquisition positions and obtains second feature data, namely multi-frame point cloud data, corresponding to each acquisition position. And acquiring the acquired second characteristic data by the equipment with computing power, such as a server, and acquiring a second fitting radius corresponding to each group of second characteristic data according to the plurality of groups of second characteristic data. In some optional embodiments, in the subsequent step 108, it is determined whether the plurality of acquired second fitting radii are all smaller than a second predetermined value. If the second fitting radiuses are all smaller than a second preset value, marking the barrier as a thin rod type barrier; and if at least one second fitting radius in the plurality of second fitting radii is larger than or equal to a second preset value, the obstacle cannot be defined as a thin rod type obstacle.
And transforming a plurality of acquisition positions, acquiring a plurality of second characteristic data, performing radius fitting on the point cloud data of the plurality of frames, and when the radii of the fitting circles are smaller than a first preset value, the possibility that the obstacle is a thin rod obstacle is extremely high. Therefore, by adopting the technical scheme, the situation of fine rod identification errors can be further reduced, and the obstacle marking efficiency is improved.
In some preferred embodiments, the acquiring second characteristic data of the obstacle includes:
s1062, acquiring a group of second characteristic data of the obstacle, and acquiring a second fitting radius of the obstacle according to the second characteristic data, wherein the second characteristic data is acquired after the acquisition position is changed.
In a specific implementation process, the electronic device changes one acquisition position at first and obtains second characteristic data corresponding to the acquisition position. A corresponding second fitting radius is obtained according to the set of second feature data.
S1064, judging the number of the acquisition groups of the second characteristic data,
if the number of the acquired groups is greater than or equal to a third preset value, executing S108, and judging whether the second fitting radius is smaller than a second preset value;
if the number of the acquired groups is smaller than a third preset value, executing S1066;
in a specific implementation process, the third predetermined value is a limit on the number of the second characteristic data acquisition groups, and if the number of the second characteristic data acquisition groups is smaller than the third predetermined value, it is indicated that the currently acquired second characteristic data is used for estimating whether the obstacle is a thin rod type obstacle, so that a risk of error exists. When the number of the second characteristic data collection sets is greater than or equal to the third predetermined value, it is described that the accuracy is extremely high when the currently collected second characteristic data is used to presume whether the obstacle is a thin rod type obstacle, and step S108 may be further performed to determine whether the second fitting radius corresponding to the group of the second characteristic data collected most recently is smaller than the second predetermined value. The second characteristic data are limited, and the identification accuracy of the thin rod type obstacles can be further ensured. In some embodiments, the third predetermined value is a positive integer and may be 1, 2, 3 … n, etc.
S1066, judging whether the second fitting radius is smaller than a second preset value;
if yes, changing the acquisition position, and continuing to execute S1062;
if not, executing S108, and marking that the obstacle does not belong to the thin rod type obstacle.
In a specific implementation process, whether the second fitting radius obtained in step S1062 is smaller than a second predetermined value is determined, and if the second fitting radius is changed from the first fitting radius and is not smaller than the second predetermined value, it is indicated that an error may be generated in the measurement of the first fitting radius, and the actual size of the obstacle exceeds the parameters of a common slender rod type obstacle, and cannot be defined as a slender rod type obstacle. By adopting the judging mode, the judgment can be carried out after each group of second characteristic data is obtained, the processing speed can be increased, and the judging efficiency can be improved.
If the second fitting radius is smaller than the second preset value, it is indicated that the feature of the obstacle still conforms to the parameter of the common thin rod type obstacle at this time, in order to ensure the accuracy of the identification of the thin rod type obstacle, the acquisition position needs to be continuously changed, a new group of second feature data is acquired, and whether the second fitting radius obtained according to the group of second feature data is smaller than the second preset value or not is judged, that is, the steps of S1062-S0164 are repeated until the number of the acquired groups of second feature data reaches the third preset value. When the number of the collected groups of the second characteristic data reaches a third predetermined value and the second fitting radii corresponding to the multiple groups of the second characteristic data are all smaller than the second predetermined value, step S108 is executed to determine whether the second fitting radii corresponding to the group of the second characteristic data collected most recently are smaller than the second predetermined value.
In some preferred embodiments, the method for obtaining the first fitting radius includes the steps of:
obtaining a fitting circle corresponding to the obstacle according to the first characteristic data;
and obtaining the radius of the fitting circle.
In a specific implementation process, the first feature data, that is, the point cloud data, may be arranged in a certain order, for example, from right to left, and the point cloud index values increase sequentially. Therefore, the fitting radius can be calculated by clustering the euclidean distances of the head and end points, and the obstacle can be fitted to a circle. As shown in fig. 3, the euclidean distance between the start point pi and the end point pj of the cluster is calculated, and the distance is equal to the diameter of the fitting circle, so as to obtain the radius R of the cluster.
By adopting the technical scheme, the misjudgment risk of the thin rod type obstacles caused by inaccurate fitting shape of the obstacles is reduced by fitting the first characteristic data into the circle, the diameter of the fitting circle is obtained by clustering the Euclidean distances of the head and tail points, and the characteristics of the fitting circle are obtained more efficiently.
In some preferred embodiments, the expansion region is circular and has a radius not less than a fourth predetermined value, the fourth predetermined value not less than the first predetermined value.
Exemplarily, fig. 5 shows a labeling process of 4 obstacles, and after first feature data is obtained, a plurality of cluster sets are obtained by point cloud clustering or euclidean clustering of the point cloud data, different clusters belong to different obstacles, the point cloud in the same cluster, that is, the first feature data, belongs to the same obstacle, the plane where the point cloud is located can be regarded as a first plane, and the point cloud can be displayed on a planar electronic map. In fig. 5 there are 4 clusters, i.e. divided into 4 obstacles, which are numbered 1-4. And judging the first fitting radius of each obstacle, wherein the fitting radius of the No. 2 and No. 3 obstacles is smaller than a radius threshold value, namely smaller than a first preset value, such as 0.05m, extracting the obstacles as candidate thin rod type obstacles, and further verifying the obstacles. The fitting radius of the No. 1 and No. 4 obstacles is larger than or equal to a first preset value, and the obstacles are not extracted as candidate thin rod type obstacles. Further, second feature data is collected for the obstacle No. 2 and No. 3, and three groups of second feature data are collected in this embodiment, which may also be referred to as collecting three frames of second feature data. The No. 2 obstacle is larger than or equal to the first preset value in the second group of data, and is not detected in the third group of data, namely, the fitting radius and the position are changed, so that the No. 2 obstacle possibly comes from detection errors, and is not detected as a thin rod type obstacle. No. 3 barrier, first group, second group and third group second characteristic data have all detected the radius and have been less than first predetermined value in the same position, consequently judge that No. 3 barrier is thin rod class barrier. The detected No. 3 obstacle is expanded, and the generation method can adopt the following steps: the center point position po (xo, yo) of obstacle No. 3 is first calculated, where xo is the average of the x coordinates of all points in the cluster and yo is the average of the y coordinates of all points in the cluster. Then, the expansion point is drawn by a preset fourth preset value, such as a radius of 0.1m, with the calculated center point of the thin rod as the center of the circle, and an expansion area is formed. In some embodiments, the center point and/or the expansion point of the thin rod type obstacle can be marked on the map, so that the effective identification and marking of the thin rod type obstacle are realized.
In other embodiments of the present application, a method for navigating a mobile electronic device is provided, as shown in fig. 7, including:
step S202, a working area map is constructed.
In a specific implementation process, the construction of the workspace map may be implemented in a user terminal, where the user terminal may be a mobile phone, a tablet computer, an intelligent display, a notebook computer, a palm computer, a vehicle-mounted electronic device, a wearable device, an ultra-mobile personal computer (UMPC), a netbook or a Personal Digital Assistant (PDA), and the non-mobile electronic device may be a server, a Network Attached Storage (NAS), a Personal Computer (PC), a television (television, TV), a teller machine, or a self-service machine. The map data can be from data collected on site and historical data of a working area, and the map can mark a runnable path, a non-movable object and the movable electronic equipment in a running or standby state of the working area so as to provide visibility of the running of the movable electronic equipment and provide basic data for path planning.
In step S204, the method described in the above embodiment is used to mark obstacles in the workspace map.
In a specific implementation process, the obstacle marking method described in the above embodiment is used to identify a thin rod obstacle and a non-thin rod obstacle. In some embodiments, an expansion zone is generated for a thin rod-like obstacle, marking its location; and for the non-slender rod type obstacle, the first characteristic data is used as a mark point for representing the position of the obstacle.
And S206, planning a running path of the movable electronic equipment according to the marked working area map, wherein the running path is not overlapped with the expansion area of the thin rod type barrier.
In a specific implementation process, the operation path of the movable electronic equipment is planned according to the target position of the movable electronic equipment and an object to be avoided, and the path is not overlapped with the expansion area of the thin-rod type barrier. After receiving the planned path, the movable electronic equipment runs and works in the working area along the route so as to ensure the running safety of the movable electronic equipment.
And step S208, controlling the movable electronic equipment to operate in the working area according to the planned operation path.
In the specific implementation process, the control of the operation of the movable electronic equipment can be realized through a controller arranged in the movable electronic equipment, and the controller is in communication connection with a back-end server; or by sending instructions to the removable electronic device in real time by a controller external to the removable electronic device. In some embodiments, a battery is disposed inside the removable electronic device to maintain the normal operation of the removable electronic device.
By adopting the technical scheme, the operation path of the movable electronic equipment can be more accurately planned by marking the obstacles in the working area map, the risk of scratching the obstacles when the movable electronic equipment operates is effectively reduced, and meanwhile, the operation efficiency of the movable electronic equipment cannot be reduced.
Other embodiments of the present application, as shown in fig. 8, provide an obstacle marking device, including:
the first obtaining module 102 is configured to obtain first feature data of an obstacle, and obtain a first fitting radius of the obstacle according to the first feature data.
The obstacle is schematically an object which influences the movement path of the electronic device during movement, and may be static, such as a table, a chair, or the like, or dynamic, such as a person, other movable electronic devices, or the like. The obstacle may be determined based on point cloud data acquired by the electronic device. The point cloud data can be obtained instantly by a 2D laser or a 3D laser, and can also be obtained by reading historical acquisition data. Each acquisition can obtain a set of point cloud data corresponding to the acquisition position, which is also called a frame of point cloud data. After the point cloud data is obtained, equipment with computing capability, such as a server, can cluster the point cloud data, and the point cloud data belonging to the same cluster indicate that the point cloud data belong to the same object. At least one target object, namely an obstacle, can be obtained through clustering of the point cloud data, and the point cloud data corresponding to each obstacle is the first characteristic data of the obstacle.
In some embodiments, theThe point cloud clustering can adopt the following method: for example, for a frame of point cloud data, the coordinates of the P point is P (x)1,y1) The coordinate of the point Q is Q (x)2,y2) The Euclidean distance between two points isAnd searching whether a point with the Euclidean distance smaller than a threshold exists nearby by taking the point P as a starting point, wherein the threshold can be adjusted according to a specific scene, and can be set to be 0.05m, 0.1m, 0.2m and the like. For example, when the threshold is 0.1M, the euclidean distance between the point Q and the point P is found to be less than 0.1M, and the two points are divided into the same cluster set M; otherwise, the method is divided into 2 clusters. And repeating the above operations by taking the point Q as a starting point until the number of points in the clustering set M is not increased any more, and considering that the clustering of the point cloud data under the frame is finished.
In a specific implementation process, the point cloud data of the obstacles obtained after clustering may be arranged in a certain order, for example, from right to left, and the point cloud index values increase sequentially. Therefore, the fitting radius can be calculated by calculating the euclidean distance between the leading and trailing points of the point cloud data of the obstacle. As shown in fig. 3, the euclidean distance between the starting point pi and the end point pj is calculated, and the distance is equal to the diameter of the fitting circle, so that the fitting radius R of the obstacle can be obtained.
The fitted radius may characterize the footprint of the obstacle.
A first determining module 104, configured to determine whether the first fitting radius is smaller than a first predetermined value.
In a specific implementation, the first predetermined value may be a limit on the size of the obstacle, and the first predetermined value may be a maximum radius of a thin rod-like obstacle in a specific use environment, and if the first fitting radius is not smaller than the first predetermined value, it indicates that the size of the obstacle exceeds the size of a general thin rod-like obstacle, and the obstacle should not be marked as a thin rod-like obstacle. The first predetermined value may be 0.05m, 0.1m, 0.2m, etc., and may be adaptively set according to a specific usage scenario.
A second obtaining module 106, configured to obtain second feature data of the obstacle, and obtain a second fitting radius of the obstacle according to the second feature data, where the second feature data is obtained after the acquisition position is changed.
In a specific implementation process, if the first fitting radius of the obstacle is smaller than the first predetermined value in the step performed by the first determining module 104, it cannot be determined immediately that the obstacle is a rod-type obstacle. Because the electronic device may be in a moving state during the point cloud data collection process, the collection position of the electronic device may also change, and the number of the returned laser point clouds for the same object may be different, for example, for a larger object, the electronic device collects the point cloud data on the side of the electronic device at a certain time, the fitting radius of the point cloud data is small, and the fitting radius of the point cloud data on the front of the electronic device collected at the next time is large. In addition, due to environmental influences, the laser may occasionally generate noise points, and the clustering radius of the noise points is small. Therefore, the acquisition position can be changed, the second characteristic data of the obstacle can be acquired, the second fitting radius can be obtained according to the second characteristic data, the obstacle can be verified again, and the error identification of the thin rod type obstacle can be obviously reduced. The acquisition positions can be changed for multiple times, each acquisition position obtains one frame of point cloud data, and each frame of point cloud data corresponds to one second fitting radius. From the second characteristic data, a second fitting radius may be calculated.
A second determining module 108, configured to determine whether the second fitting radius is smaller than a second predetermined value;
the first marking module 109 is used for marking the obstacles as thin rod type obstacles.
In a specific implementation, the second predetermined value may also be a limit on the size of the obstacle, for example, the second predetermined value may also be a radius limit of a general slender rod-type obstacle. If the second fitting radius is changed from the first fitting radius and is not less than the second predetermined value, it indicates that the measurement of the first fitting radius may generate an error, and the actual size of the obstacle exceeds the parameters of the general thin rod type obstacle and should not be marked as a thin rod type obstacle. The second predetermined value may be 0.05m, 0.1m, 0.2m, etc., and may be adaptively set according to a specific usage scenario. In some embodiments, the second predetermined value may be equal to the first predetermined value, which facilitates setting of parameters and may ensure consistency of evaluation of the thin stick obstacle criteria.
In the implementation process, if the second fitting radii are all smaller than the second predetermined value, the obstacle is characterized by a thin rod type obstacle at a plurality of acquisition positions and can be identified as the thin rod type obstacle. In some embodiments, since at least two fitting circles are generated according to the first characteristic data and the second characteristic data when the thin rod type obstacle is determined, if the object is not the thin rod type obstacle, any one fitting circle can be used as a mark point for representing the position of the object. In some embodiments, the circle fitted with the largest obstacle is used as the marker point for characterizing its position.
The thin rod type obstacles are small in size, and are generally in a static state, and the clustering radius of the thin rod type obstacles is smaller than a radius threshold value at different acquisition positions. Therefore, by adopting the technical scheme, whether the detected barrier is a thin rod type barrier or not is verified by collecting the characteristic data for multiple times, the situation of thin rod identification errors can be obviously reduced, the barrier marking efficiency is improved, and the collision risk is reduced in the path planning of the electronic equipment.
In some preferred embodiments, the obstacle marking device further comprises:
the first generating module 110 is configured to generate an expansion area corresponding to the thin rod-like obstacle.
In a specific implementation process, the expansion area is a marking area corresponding to the thin rod type obstacle, so that the thin rod type obstacle can represent a chassis area of the thin rod type obstacle, the area can be considered to have a collision risk, and the expansion area can be avoided in the path planning of the electronic equipment.
Illustratively, the method of generating the expanded region comprises the steps of: and generating a central point of the expansion area according to the first characteristic data or the second characteristic data, and forming a circular area by taking the central point as a circle center and a fourth preset value as a radius. Wherein the expansion region center point may be a center of a fitted circle generated from the first characteristic data or the second characteristic data. In some embodiments, the fourth predetermined value is not less than the first predetermined value. Referring to fig. 6, schematically, the expansion region may be generated in the following manner: first, the central point position po (xo, yo) of the slender rod-like obstacle point cloud data is calculated, where xo is the average of the x coordinates of all points in the obstacle cluster, and yo is the average of the y coordinates of all points in the cluster, as shown in fig. 6A. Then, the expansion point is plotted with a radius of 0.1m with the calculated center point as the center, and the area surrounded by the expansion point is the expansion area, as shown in fig. 6B. The central point and the expansion point of the thin rod are marked on the map, so that the effective identification and marking of the thin rod objects are realized.
When the thin rod type barrier is judged, at least two fitting circles can be generated according to the first characteristic data and the second characteristic data, the area of the expansion region is larger than the area of the largest fitting circle, and all the fitting circles fall into the expansion region, so that the expansion region expands the marking range of the thin rod type barrier; the marking range is expanded because the mark of the barrier is avoided during path planning, and the safety of the movable electronic equipment such as a robot traveling along the path can be improved. In some embodiments, the expansion zone is circular and has a radius greater than a first predetermined value, ensuring that the expansion zone is always wider than the assumed condition for a thin rod-like obstacle. In some embodiments, the radius of the expansion area is significantly greater than a first predetermined value, or the radius is greater than a first safety value, which is the sum of the first predetermined value and a safety distance, such as the first predetermined value is 0.05m, the pin tray radius is typically greater than the pin radius by 0.1m, where 0.1m is the safety distance, and the first safety value is 0.05+0.1 ═ 0.15 m; the inflated area may be presented on an electronic map as a marker for thin rod-like obstacles in such a way that manual or manual routing is possible. In some implementations, the expansion region is concentric with the fitting circle having the largest area, further reducing the risk of collision when the electronic device is in operation.
By adopting the technical scheme, after the thin rod type obstacles are detected, the expansion area is generated to mark the tray or the chassis of the thin rod type obstacles, so that the scratch or collision between the movable electronic equipment and the tray when the movable electronic equipment runs along a planned path can be effectively avoided, and the running safety of the movable electronic equipment is improved.
In some preferred embodiments, the method of acquiring the second characteristic data of the obstacle is,
and acquiring a plurality of second characteristic data of the obstacle, wherein the plurality of second characteristic data are acquired after a plurality of acquisition positions are changed.
In a specific implementation process, the electronic device changes a plurality of acquisition positions and obtains second feature data, namely multi-frame point cloud data, corresponding to each acquisition position. And acquiring the acquired second characteristic data by the equipment with computing power, such as a server, and acquiring a second fitting radius corresponding to each group of second characteristic data according to the plurality of groups of second characteristic data. In some optional embodiments, the second determining module 108 performs the step of determining whether the collected second fitting radii are all smaller than a second predetermined value. If the second fitting radiuses are all smaller than a second preset value, marking the barrier as a thin rod type barrier; and if at least one second fitting radius in the plurality of second fitting radii is larger than or equal to a second preset value, the obstacle cannot be defined as a thin rod type obstacle.
And transforming a plurality of acquisition positions, acquiring a plurality of second characteristic data, performing radius fitting on the point cloud data of the plurality of frames, and when the radii of the fitting circles are smaller than a first preset value, the possibility that the obstacle is a thin rod obstacle is extremely high. Therefore, by adopting the technical scheme, the situation of fine rod identification errors can be further reduced, and the obstacle marking efficiency is improved.
In some preferred embodiments, the second obtaining module 106 includes:
the first obtaining sub-module 1062 is configured to obtain a set of second feature data of the obstacle, and obtain a second fitting radius of the obstacle according to the second feature data, where the second feature data is obtained after the acquisition position is changed.
In a specific implementation process, the electronic device changes one acquisition position at first and obtains second characteristic data corresponding to the acquisition position. A corresponding second fitting radius is obtained according to the set of second feature data.
A first judging sub-module 1064 for judging the number of the acquired sets of the second characteristic data,
if the number of the acquired groups is greater than or equal to a third predetermined value, executing a step executed by a second judging module 108, and judging whether the second fitting radius is smaller than a second predetermined value;
if the number of the acquired groups is smaller than the third predetermined value, the step executed by the second judgment sub-module 1066 is executed;
in a specific implementation process, the third predetermined value is a limit on the number of the second characteristic data acquisition groups, and if the number of the second characteristic data acquisition groups is smaller than the third predetermined value, it is indicated that the currently acquired second characteristic data is used for estimating whether the obstacle is a thin rod type obstacle, so that a risk of error exists. When the number of the second characteristic data collection sets is greater than or equal to the third predetermined value, it is described that the accuracy is extremely high when the currently collected second characteristic data is used to presume whether the obstacle is a thin rod type obstacle, and the step executed by the second determination module 108 may be further executed to determine whether the second fitting radius corresponding to the group of the second characteristic data collected most recently is smaller than the second predetermined value. The second characteristic data are limited, and the identification accuracy of the thin rod type obstacles can be further ensured. In some embodiments, the third predetermined value is a positive integer and may be 1, 2, 3 … n, etc.
A second determination sub-module 1066, configured to determine whether the second fitting radius is smaller than a second predetermined value;
if yes, changing the acquisition position, and continuing to execute the steps executed by the first acquisition sub-module 1062;
if not, executing the steps executed by the second judging module 108, and marking that the obstacle does not belong to the thin rod type obstacle.
In a specific implementation process, it is determined whether the second fitting radius obtained in the step executed by the first obtaining sub-module 1062 is smaller than a second predetermined value, and if the second fitting radius is changed from the first fitting radius and is not smaller than the second predetermined value, it indicates that an error may be generated in the measurement of the first fitting radius, and the actual size of the obstacle exceeds the parameters of a common thin-rod obstacle, and cannot be defined as a thin-rod obstacle. By adopting the judging mode, the judgment can be carried out after each group of second characteristic data is obtained, the processing speed can be increased, and the judging efficiency can be improved.
If the second fitting radius is smaller than the second predetermined value, it indicates that the feature of the obstacle still conforms to the parameter of the general pin-type obstacle, and in order to ensure the accuracy of the pin-type obstacle identification, the acquisition position needs to be continuously changed, a new set of second feature data is acquired, and it is determined whether the second fitting radius obtained according to the set of second feature data is smaller than the second predetermined value, that is, the steps performed by the first obtaining sub-module 1062 and the first determining sub-module 1064 are repeated until the number of the acquired sets of second feature data reaches the third predetermined value. When the number of the collected groups of the second feature data reaches a third predetermined value and the second fitting radii corresponding to the multiple groups of the second feature data are all smaller than the second predetermined value, the step executed by the second determining module 108 is executed to determine whether the second fitting radii corresponding to the group of the second feature data collected most recently are smaller than the second predetermined value.
In some preferred embodiments, the method for obtaining the first fitting radius includes the steps of:
obtaining a fitting circle corresponding to the obstacle according to the first characteristic data;
and obtaining the radius of the fitting circle.
In a specific implementation process, the first feature data, that is, the point cloud data, may be arranged in a certain order, for example, from right to left, and the point cloud index values increase sequentially. Therefore, the fitting radius can be calculated by clustering the euclidean distances of the head and end points, and the obstacle can be fitted to a circle. As shown in fig. 3, the euclidean distance between the start point pi and the end point pj of the cluster is calculated, and the distance is equal to the diameter of the fitting circle, so that the radius R of the cluster can be obtained.
By adopting the technical scheme, the misjudgment risk of the thin rod type obstacles caused by inaccurate fitting shape of the obstacles is reduced by fitting the first characteristic data into the circle, the diameter of the fitting circle is obtained by clustering the Euclidean distances of the head and tail points, and the characteristics of the fitting circle are obtained more efficiently.
In some preferred embodiments, the expansion region is circular and has a radius not less than a fourth predetermined value, the fourth predetermined value not less than the first predetermined value.
Further embodiments of the present application, as shown in fig. 9, provide a mobile electronic device navigation apparatus, comprising,
a first construction module 202 for constructing a workspace map.
In a specific implementation process, the construction of the workspace map may be implemented in a user terminal, where the user terminal may be a mobile phone, a tablet computer, an intelligent display, a notebook computer, a palm computer, a vehicle-mounted electronic device, a wearable device, an ultra-mobile personal computer (UMPC), a netbook or a Personal Digital Assistant (PDA), and the non-mobile electronic device may be a server, a Network Attached Storage (NAS), a Personal Computer (PC), a television (television, TV), a teller machine, or a self-service machine. The map data can be from data collected on site and historical data of a working area, and the map can mark a runnable path, a non-movable object and the movable electronic equipment in a running or standby state of the working area so as to provide visibility of the running of the movable electronic equipment and provide basic data for path planning.
An obstacle marking device 204 as provided in the embodiments of the present application.
In a specific implementation, the steps performed by the obstacle marking device 204 according to the above-described embodiment are used to identify thin-rod obstacles and non-thin-rod obstacles. In some embodiments, an expansion zone is generated for a thin rod-like obstacle, marking its location; and for the non-slender rod type obstacle, the first characteristic data is used as a mark point for representing the position of the obstacle.
The first planning module 206 is configured to plan a movement path of the mobile electronic device according to the work area map and the obstacles in the work area, where the movement path is not overlapped with the expansion area of the thin rod type obstacle.
In a specific implementation process, the operation path of the movable electronic equipment is planned according to the target position of the movable electronic equipment and an object to be avoided, and the path is not overlapped with the expansion area of the thin-rod type barrier. After receiving the planned path, the movable electronic equipment runs and works in the working area along the route so as to ensure the running safety of the movable electronic equipment.
And the first control module 208 is used for controlling the movable electronic equipment to operate in the working area according to the planned operation path.
In the specific implementation process, the control of the operation of the movable electronic equipment can be realized through a controller arranged in the movable electronic equipment, and the controller is in communication connection with a back-end server; or by sending instructions to the removable electronic device in real time by a controller external to the removable electronic device. In some embodiments, a battery is disposed inside the removable electronic device to maintain the normal operation of the removable electronic device.
By adopting the technical scheme, the operation path of the robot can be more accurately planned by marking the obstacles in the working area map, the risk of scraping and rubbing the obstacles when the robot operates is effectively reduced, and meanwhile, the reduction of the operation efficiency of the robot is avoided.
The device for obstacle marking or mobile electronic device navigation in the embodiment of the present application may be a device, or may be a component, an integrated circuit, or a chip in a terminal. The device can be mobile electronic equipment or non-mobile electronic equipment. By way of example, the mobile electronic device may be a mobile phone, a tablet computer, a smart display, a notebook computer, a palm top computer, an in-vehicle electronic device, a wearable device, an ultra-mobile personal computer (UMPC), a netbook or a Personal Digital Assistant (PDA), and the like, and the non-mobile electronic device may be a server, a Network Attached Storage (NAS), a Personal Computer (PC), a television (television), a teller machine, a self-service machine, and the like, and the embodiments of the present application are not particularly limited.
The device for obstacle marking or navigation of the mobile electronic device in the embodiment of the application may be a device with an operating system. The operating system may be an Android (Android) operating system, an ios operating system, or other possible operating systems, and embodiments of the present application are not limited specifically.
In further embodiments of the present application, an electronic device is provided, such as the electronic device 300 shown in fig. 10, comprising a processor 301, a readable non-transitory storage medium 302, an input device 303, an output device 304, the readable non-transitory storage medium 302 comprising computer program instructions executable by the processor 301 to perform steps for obstacle marking or navigation of a mobile electronic device according to any of the embodiments of the present application.
Those skilled in the art will appreciate that the electronic device may further include a power source (e.g., a battery) for supplying power to the various components, and the power source may be logically connected to the processor via a power management system, so as to manage charging, discharging, and power consumption management functions via the power management system.
The processor is the processor in the electronic device in the above embodiment. Readable non-transitory storage media include computer-readable non-transitory storage media such as a computer-Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic or optical disk, and the like.
In other embodiments of the present application, which may be referred to in fig. 10, embodiments of the present application provide a readable non-transitory storage medium having stored thereon a program or instructions, which when executed by a processor, perform steps for obstacle marking or navigation of a mobile electronic device according to any of the embodiments of the present application.
Readable non-transitory storage media include computer-readable non-transitory storage media such as a computer-Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic or optical disk, and the like.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element. Further, it should be noted that the scope of the methods and apparatus of the embodiments of the present application is not limited to performing the functions in the order illustrated or discussed, but may include performing the functions in a substantially simultaneous manner or in a reverse order based on the functions involved, e.g., the methods described may be performed in an order different than that described, and various steps may be added, omitted, or combined. In addition, features described with reference to certain examples may be combined in other examples.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solutions of the present application may be embodied in the form of a software product, which is stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk) and includes instructions for enabling a terminal (such as a mobile phone, a computer, a server, an air conditioner, or a network device) to execute the methods of the embodiments of the present application.
While the present embodiments have been described with reference to the accompanying drawings, it is to be understood that the invention is not limited to the precise embodiments described above, which are meant to be illustrative and not restrictive, and that various changes may be made therein by those skilled in the art without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (10)
1. A method for marking an obstacle, comprising the steps of,
acquiring first characteristic data of an obstacle, and acquiring a first fitting radius of the obstacle according to the first characteristic data;
judging whether the first fitting radius is smaller than a first preset value or not;
if the first characteristic data is smaller than the second characteristic data, second characteristic data of the obstacle is obtained, a second fitting radius of the obstacle is obtained according to the second characteristic data, and the second characteristic data is obtained after the acquisition position is changed;
judging whether the second fitting radius is smaller than a second preset value or not;
and if the distance is smaller than the preset distance, marking the obstacle as a thin rod obstacle.
2. The method for labeling an obstacle according to claim 1, characterized in that: the method for labeling a disorder, further comprising the steps of:
if the obstacle is a thin rod type obstacle, an expansion area corresponding to the thin rod type obstacle is generated.
3. The method of claim 2, wherein: the method for generating the expansion area comprises the following steps:
generating an expansion region center point from the first feature data or the second feature data,
forming a circular area by taking the central point as a circle center and a fourth preset value as a radius;
the expansion region center point is the center of a fitting circle generated according to the first characteristic data or the second characteristic data,
the fourth predetermined value is not less than the first predetermined value.
4. The method of any one of claims 1 to 3, wherein: the step of acquiring second characteristic data of the obstacle is,
and acquiring a plurality of second characteristic data of the obstacle, wherein the plurality of second characteristic data are acquired after a plurality of acquisition positions are changed.
5. The method of claim 4, wherein: the acquiring of the second characteristic data of the obstacle comprises the following steps:
acquiring a group of second characteristic data of the obstacle, and acquiring a second fitting radius of the obstacle according to the second characteristic data, wherein the second characteristic data is acquired after the acquisition position is changed;
the number of acquisition groups of the second characteristic data is judged,
if the number of the acquired groups is greater than or equal to a third preset value, judging whether the second fitting radius is smaller than a second preset value;
if the number of the acquired groups is smaller than a third preset value, judging whether the second fitting radius is smaller than a second preset value; if yes, continuously acquiring a group of second characteristic data of the obstacle, wherein the group of second characteristic data is acquired after the acquisition position is changed; if not, marking that the obstacle does not belong to the thin rod type obstacle.
6. The method of claim 5, wherein: the first predetermined value is equal to the second predetermined value.
7. A method for navigating a movable electronic device, comprising the steps of,
constructing a working area map;
marking obstacles in a map of a work area using an obstacle marking method according to any one of claims 1 to 6;
planning a running path of the movable electronic equipment according to the marked working area map, wherein the running path is not overlapped with an expansion area of the thin rod type barrier;
and controlling the movable electronic equipment to run in the working area according to the planned running path.
8. An obstacle marking device comprising:
the first acquisition module is used for acquiring first characteristic data of an obstacle and acquiring a first fitting radius of the obstacle according to the first characteristic data;
the first judging module is used for judging whether the first fitting radius is smaller than a first preset value or not;
the second acquisition module is used for acquiring second characteristic data of the obstacle and acquiring a second fitting radius of the obstacle according to the second characteristic data, wherein the second characteristic data is acquired after the acquisition position is changed;
the second judging module is used for judging whether the second fitting radius is smaller than a second preset value or not;
the first marking module is used for marking the obstacles as thin rod type obstacles.
9. A movable electronic equipment navigation device comprises a navigation device,
the first construction module is used for constructing a working area map;
the obstacle marking device of claim 8;
the first planning module is used for planning the operation path of the movable electronic equipment according to the marked work area map, and the operation path is not overlapped with the expansion area of the thin rod type barrier;
and the first control module is used for controlling the movable electronic equipment to operate in the working area according to the planned operation path.
10. A readable non-transitory storage medium storing a program or instructions thereon, which when executed by a processor, implement the steps of the obstacle marking method according to any one of claims 1 to 6.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110237014.5A CN112836681B (en) | 2021-03-03 | 2021-03-03 | Obstacle marking method and device and readable non-transitory storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110237014.5A CN112836681B (en) | 2021-03-03 | 2021-03-03 | Obstacle marking method and device and readable non-transitory storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112836681A true CN112836681A (en) | 2021-05-25 |
CN112836681B CN112836681B (en) | 2024-01-26 |
Family
ID=75934463
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110237014.5A Active CN112836681B (en) | 2021-03-03 | 2021-03-03 | Obstacle marking method and device and readable non-transitory storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112836681B (en) |
Citations (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104816306A (en) * | 2014-02-04 | 2015-08-05 | 精工爱普生株式会社 | Robot, robot system, control device and control method |
CN106204547A (en) * | 2016-06-29 | 2016-12-07 | 山东科技大学 | The method automatically extracting shaft-like atural object locus from Vehicle-borne Laser Scanning point cloud |
CN107305380A (en) * | 2016-04-20 | 2017-10-31 | 上海慧流云计算科技有限公司 | A kind of automatic obstacle-avoiding method and apparatus |
CN108764012A (en) * | 2018-03-27 | 2018-11-06 | 国网辽宁省电力有限公司电力科学研究院 | The urban road shaft recognizer of mobile lidar data based on multi-frame joint |
US20190005667A1 (en) * | 2017-07-24 | 2019-01-03 | Muhammad Zain Khawaja | Ground Surface Estimation |
CN109579854A (en) * | 2019-02-01 | 2019-04-05 | 禾多科技(北京)有限公司 | Unmanned vehicle barrier-avoiding method based on Quick Extended random tree |
CN109709945A (en) * | 2017-10-26 | 2019-05-03 | 深圳市优必选科技有限公司 | Path planning method and device based on obstacle classification and robot |
CN109919237A (en) * | 2019-03-13 | 2019-06-21 | 武汉海达数云技术有限公司 | Points cloud processing method and device |
JP2020030466A (en) * | 2018-08-20 | 2020-02-27 | 株式会社Soken | Object detection device |
CN110989631A (en) * | 2019-12-30 | 2020-04-10 | 科沃斯机器人股份有限公司 | Self-moving robot control method, device, self-moving robot and storage medium |
CN111291697A (en) * | 2020-02-19 | 2020-06-16 | 北京百度网讯科技有限公司 | Method and device for recognizing obstacle |
US20200202107A1 (en) * | 2018-12-20 | 2020-06-25 | Here Global B.V. | Automatic detection and positioning of pole-like objects in 3d |
CN112001287A (en) * | 2020-08-17 | 2020-11-27 | 禾多科技(北京)有限公司 | Method and device for generating point cloud information of obstacle, electronic device and medium |
CN112015181A (en) * | 2020-08-28 | 2020-12-01 | 上海高仙自动化科技发展有限公司 | Obstacle avoidance method, device, equipment and computer readable storage medium |
CN112327878A (en) * | 2020-11-25 | 2021-02-05 | 珠海市一微半导体有限公司 | Obstacle classification and obstacle avoidance control method based on TOF camera |
CN112380942A (en) * | 2020-11-06 | 2021-02-19 | 北京石头世纪科技股份有限公司 | Method, device, medium and electronic equipment for identifying obstacle |
-
2021
- 2021-03-03 CN CN202110237014.5A patent/CN112836681B/en active Active
Patent Citations (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104816306A (en) * | 2014-02-04 | 2015-08-05 | 精工爱普生株式会社 | Robot, robot system, control device and control method |
CN107305380A (en) * | 2016-04-20 | 2017-10-31 | 上海慧流云计算科技有限公司 | A kind of automatic obstacle-avoiding method and apparatus |
CN106204547A (en) * | 2016-06-29 | 2016-12-07 | 山东科技大学 | The method automatically extracting shaft-like atural object locus from Vehicle-borne Laser Scanning point cloud |
US20190005667A1 (en) * | 2017-07-24 | 2019-01-03 | Muhammad Zain Khawaja | Ground Surface Estimation |
CN109709945A (en) * | 2017-10-26 | 2019-05-03 | 深圳市优必选科技有限公司 | Path planning method and device based on obstacle classification and robot |
CN108764012A (en) * | 2018-03-27 | 2018-11-06 | 国网辽宁省电力有限公司电力科学研究院 | The urban road shaft recognizer of mobile lidar data based on multi-frame joint |
JP2020030466A (en) * | 2018-08-20 | 2020-02-27 | 株式会社Soken | Object detection device |
US20200202107A1 (en) * | 2018-12-20 | 2020-06-25 | Here Global B.V. | Automatic detection and positioning of pole-like objects in 3d |
CN109579854A (en) * | 2019-02-01 | 2019-04-05 | 禾多科技(北京)有限公司 | Unmanned vehicle barrier-avoiding method based on Quick Extended random tree |
CN109919237A (en) * | 2019-03-13 | 2019-06-21 | 武汉海达数云技术有限公司 | Points cloud processing method and device |
CN110989631A (en) * | 2019-12-30 | 2020-04-10 | 科沃斯机器人股份有限公司 | Self-moving robot control method, device, self-moving robot and storage medium |
CN111291697A (en) * | 2020-02-19 | 2020-06-16 | 北京百度网讯科技有限公司 | Method and device for recognizing obstacle |
CN112001287A (en) * | 2020-08-17 | 2020-11-27 | 禾多科技(北京)有限公司 | Method and device for generating point cloud information of obstacle, electronic device and medium |
CN112015181A (en) * | 2020-08-28 | 2020-12-01 | 上海高仙自动化科技发展有限公司 | Obstacle avoidance method, device, equipment and computer readable storage medium |
CN112380942A (en) * | 2020-11-06 | 2021-02-19 | 北京石头世纪科技股份有限公司 | Method, device, medium and electronic equipment for identifying obstacle |
CN112327878A (en) * | 2020-11-25 | 2021-02-05 | 珠海市一微半导体有限公司 | Obstacle classification and obstacle avoidance control method based on TOF camera |
Non-Patent Citations (6)
Title |
---|
LI YAN ET AL: "Detection and classification of pole-like road objects from mobile LiDAR data in motorway environment", 《OPTICS AND LASER TECHNOLOGY》, 31 December 2017 (2017-12-31), pages 272 * |
朱德海 等: "《点云库PCL学习教程》", 北京航空航天大学出版社, pages: 338 - 339 * |
李永强 等: "车载激光扫描数据中杆状地物提取", 《测绘科学》 * |
李永强 等: "车载激光扫描数据中杆状地物提取", 《测绘科学》, vol. 40, no. 8, 31 August 2015 (2015-08-31), pages 42 - 46 * |
王鹏 等: "一种车载激光点云中杆目标自动提取方法", 《武汉大学学报信息科学版》 * |
王鹏 等: "一种车载激光点云中杆目标自动提取方法", 《武汉大学学报信息科学版》, vol. 45, no. 7, 31 July 2020 (2020-07-31), pages 1036 - 1037 * |
Also Published As
Publication number | Publication date |
---|---|
CN112836681B (en) | 2024-01-26 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11709058B2 (en) | Path planning method and device and mobile device | |
US11877716B2 (en) | Determining region attribute | |
US20210063159A1 (en) | Positioning Method, Positioning Server and Positioning System | |
CN107610176A (en) | A kind of pallet Dynamic Recognition based on Kinect and localization method, system and medium | |
CN113378760A (en) | Training target detection model and method and device for detecting target | |
CN107218927B (en) | A kind of cargo pallet detection system and method based on TOF camera | |
US11438886B2 (en) | System for establishing positioning map data and method for the same | |
CN110135278B (en) | Obstacle detection method and device and electronic equipment | |
CN110470308B (en) | Obstacle avoidance system and method | |
CN113095184B (en) | Positioning method, driving control method, device, computer equipment and storage medium | |
CN110000793B (en) | Robot motion control method and device, storage medium and robot | |
CN110263713A (en) | Method for detecting lane lines, device, electronic equipment and storage medium | |
CN110705385B (en) | Method, device, equipment and medium for detecting angle of obstacle | |
CN111295666A (en) | Lane line detection method, device, control equipment and storage medium | |
CN114322799B (en) | Vehicle driving method and device, electronic equipment and storage medium | |
CN113674355A (en) | Target identification and positioning method based on camera and laser radar | |
CN115139303A (en) | Grid well lid detection method, device, equipment and storage medium | |
CN112445215A (en) | Automatic guided vehicle driving control method, device and computer system | |
CN114200472A (en) | Real-time detection method and device for passable area, terminal and storage medium | |
CN112836681B (en) | Obstacle marking method and device and readable non-transitory storage medium | |
CN115147791A (en) | Vehicle lane change detection method and device, vehicle and storage medium | |
CN112784175B (en) | Method, device, equipment and storage medium for processing interest point data | |
CN112036268B (en) | Component identification method and related device | |
CN114489050A (en) | Obstacle avoidance route control method, device, equipment and storage medium for straight line driving | |
CN115035425B (en) | Target recognition method, system, electronic equipment and storage medium based on deep learning |
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 |