CN111562787B - Method, device, medium and equipment for dividing planning area of full-coverage path of robot - Google Patents
Method, device, medium and equipment for dividing planning area of full-coverage path of robot Download PDFInfo
- Publication number
- CN111562787B CN111562787B CN202010465917.4A CN202010465917A CN111562787B CN 111562787 B CN111562787 B CN 111562787B CN 202010465917 A CN202010465917 A CN 202010465917A CN 111562787 B CN111562787 B CN 111562787B
- Authority
- CN
- China
- Prior art keywords
- convex
- polygon
- polygons
- robot
- area
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 45
- 230000003068 static effect Effects 0.000 claims description 19
- 230000001174 ascending effect Effects 0.000 claims description 11
- 238000004140 cleaning Methods 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 claims description 6
- 230000004888 barrier function Effects 0.000 claims description 5
- 230000002708 enhancing effect Effects 0.000 claims description 4
- 238000004590 computer program Methods 0.000 claims description 3
- 238000005260 corrosion Methods 0.000 claims description 3
- 230000007797 corrosion Effects 0.000 claims description 3
- 238000001514 detection method Methods 0.000 claims description 3
- 238000000638 solvent extraction Methods 0.000 claims description 3
- 238000000354 decomposition reaction Methods 0.000 abstract description 42
- 238000004364 calculation method Methods 0.000 abstract description 6
- 230000009286 beneficial effect Effects 0.000 abstract description 2
- 238000004422 calculation algorithm Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 241000283690 Bos taurus Species 0.000 description 1
- 230000001133 acceleration Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000009313 farming Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000013101 initial test Methods 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000033764 rhythmic process Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0231—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means
- G05D1/0246—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using a video camera in combination with image processing means
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
- G05D1/0221—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory involving a learning process
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0276—Control of position or course in two dimensions specially adapted to land vehicles using signals provided by a source external to the vehicle
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Aviation & Aerospace Engineering (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Electromagnetism (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The invention discloses a method, a device, a medium and equipment for dividing a planning area of a full-coverage path of a robot, wherein the method comprises the following steps: obtaining an obstacle polygon and a region boundary polygon according to the map; detecting the vertex with the inner angle larger than 180 degrees in the obstacle polygon, wherein the inner angle is an angle which is formed by two intersecting sides in the obstacle polygon and faces to the idle area; extending two sides of each vertex of the obstacle polygon towards the idle area at the vertex until the two sides intersect with the area boundary polygon, so that the idle area where the robot can walk is divided into n initial sub-convex polygons; and merging the obtained initial sub-convex polygons into a plurality of convex polygons to obtain a final region convex decomposition result with the minimum total width of the sub-polygons. The invention improves the decomposition performance of the concave polygon area with the linear shape, can ensure the minimum total width of the sub-polygons, reduces the calculation complexity, and is beneficial to the robot to find high-quality coverage paths.
Description
Technical Field
The invention relates to the field of unmanned aerial vehicle, in particular to a method, a device, a medium and equipment for dividing a robot full-coverage path planning area.
Background
With the rapid development of economic construction and the acceleration of the life rhythm of modern people, more and more people hope to be released from heavy household work, and the intelligent cleaning robot meets the requirement. The cleaning robot moves in an indoor environment to realize the functions of cleaning, obstacle avoidance, path planning and the like, and particularly relates to a key technology, namely a full-coverage path planning algorithm, which is deeply researched along with the development of an artificial intelligent control technology and the wide application of an intelligent robot.
Dividing the area to be traversed by the robot into a plurality of subareas according to obstacles or other methods in the environment, and traversing the whole area by traversing each subarea. This idea reduces the difficulty of global overlay implementation to a great extent, so research on this regional decomposition approach is the main trend in recent years. The regional decomposition method mainly researches the contents of three aspects: decomposition of the target region, splicing of the sub-regions and traversing methods in the sub-regions after the region decomposition. Decomposing the target region is the first step of the region decomposition method, and the result of the decomposition directly affects the linkage between the sub-regions and the traversal within the sub-regions. The regional decomposition algorithm mainly comprises a trapezoid decomposition method and a cattle cultivation decomposition algorithm.
The trapezoid decomposition method is to scan the whole environment map by a vertical line, and the vertical line intersects with the fixed point of the obstacle to generate different subareas. Niu Geng decomposition combines the scanning vertical lines with sub-regions of vertex decomposition at both ends of the removed obstacle, with only one sub-region above and below the obstacle. The Niu Geng decomposition method reduces the number of decomposed subregions, but some subregions are irregular in shape, and covering the subregions causes a problem that some regions cannot be covered.
Both trapezoidal decomposition and bovine-farming decomposition are convex decomposition methods based on swept lines, which have significant limitations, such as the inability of decomposition to handle more than one vertex intersecting one scan line. Therefore, given a sweep line and its direction, all vertices in the polygon must be unique with respect to the sweep line, which means that the decomposition performance of a concave polygon with a straight shape is poor. In addition, as the target polygon becomes complex, it is more difficult to determine the optimal scanning direction, thereby further increasing the difficulty of region decomposition.
Disclosure of Invention
The invention provides a method for dividing a planning area of a full-coverage path of a robot, which aims to solve the problems that the existing robot is poor in area decomposition performance and difficult to meet the complex polygonal target area decomposition during full-coverage path planning.
The technical scheme adopted by the invention is as follows:
a method for dividing a planning area of a full-coverage path of a robot comprises the following steps:
obtaining an obstacle polygon and a region boundary polygon according to a map, and obtaining an idle region where a robot can walk;
detecting the vertex with the inner angle larger than 180 degrees in the obstacle polygon, wherein the inner angle is an angle which is formed by two intersecting sides in the obstacle polygon and faces to the idle area;
extending two sides of each vertex of the obstacle polygon towards the idle area at the vertex until the two sides intersect with the area boundary polygon, so that the idle area where the robot can walk is divided into n initial sub-convex polygons;
and merging the obtained initial sub-convex polygons into a plurality of convex polygons to obtain a final region convex decomposition result with the minimum total width of the sub-polygons.
Further, the step of obtaining the obstacle polygon and the region boundary polygon according to the map, and the step of obtaining the free region where the robot can walk specifically includes:
reading a static map acquired by a sensor;
preprocessing the static map to highlight obstacle information;
and extracting obstacle polygons and region boundary polygons of the static map according to the preprocessed static map to obtain an idle region where the cleaning robot can walk.
Further, preprocessing the static map to highlight obstacle information, wherein the method specifically comprises the steps;
performing binarization treatment, expansion and corrosion treatment on the static map;
and enhancing the image by using a frequency domain method, removing noise points, and highlighting barrier information.
Further, the merging the obtained initial sub-convex polygons into a plurality of convex polygons to obtain a final region convex decomposition result with the minimum total width of the sub-polygons specifically includes the steps of:
all combinations of n initial sub-convex polygons which can be combined into a convex polygon are calculated and used as a convex combining option set;
searching and selecting a plurality of corresponding convex merging options in the convex merging option set to obtain a plurality of sub-polygons, wherein the sub-polygons fully cover the idle area and have the minimum total width.
Further, the calculating to obtain all combinations of n initial sub-convex polygons which can be combined into a convex polygon as a convex combining option set specifically includes the steps of:
and (3) solving possible combinations of convex merging options formed by n initial sub-convex polygons according to the ascending order of n to obtain a convex merging option set.
Further, the step of obtaining possible combinations of the convex merging options consisting of n initial sub-convex polygons in the convex merging option set in ascending order of n as the convex merging option set includes the steps of:
and (3) obtaining a convex merging option set of possible combinations of convex merging options formed by a set number of initial sub-convex polygons in an ascending order, wherein the set number < n.
Further, the step of stopping the search when the set number of the convex merging options consisting of the initial sub-convex polygons are searched, and taking the search result as the search result of the convex merging options consisting of the n initial sub-convex polygons specifically comprises:
obtaining
Possible combinations of convex merging options consisting of the initial sub-convex polygons,/->
Convex merging options consisting of initial sub-convex polygonsPossibly in combination, wherein->
Representing a round up->
Representing a downward rounding;
and combining the obtained possible combinations to obtain possible combinations of convex combining options consisting of n initial sub-convex polygons.
According to another aspect of the present invention, there is also provided a robot full-coverage path planning area dividing apparatus, including:
the polygon obtaining module is used for obtaining an obstacle polygon and a region boundary polygon according to the map and obtaining an idle region where the robot can walk;
the vertex detection module is used for detecting a vertex with an inner angle larger than 180 degrees in the obstacle polygon, wherein the inner angle is an angle which is formed by two intersecting sides in the obstacle polygon and faces to an idle area;
the initial sub-convex polygon dividing module is used for extending two sides at each vertex of the obstacle polygon towards the idle area at the vertex to intersect with the area boundary polygon, so that the idle area where the robot can walk is divided into n initial sub-convex polygons;
and the convex polygon merging module is used for merging the obtained initial sub-convex polygons into a plurality of convex polygons to obtain a final region convex decomposition result with the minimum total width of the sub-polygons.
According to another aspect of the present invention, there is also provided a storage medium including a stored program, which when executed controls a device in which the storage medium is located to perform the robot full coverage path planning area division method as described.
According to another aspect of the present invention, there is also provided an electronic device including a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing the robot full coverage path planning area division method as described when executing the program.
The invention has the following beneficial effects:
according to the method, an obstacle polygon and a region boundary polygon are obtained according to a map, then vertices with inner angles larger than 180 degrees in the obstacle polygon are detected, edge expansion is carried out on two sides of the vertices of the obstacle polygon to obtain an initial sub-convex polygon, and finally a final region convex decomposition result with the minimum total width of the sub-polygon is obtained through combination of the initial sub-convex polygons. The convex decomposition method improves the decomposition performance of the concave polygonal area with the linear shape, and meanwhile, for the complex target polygon, the optimal scanning direction is not required to be considered, so that the decomposition effect can be better, the decomposition difficulty is simplified, the method has the advantages in the aspects of minimizing the total width of the sub-polygon and reducing the calculation complexity, the robot can find a high-quality coverage path, and the operation efficiency of the robot is improved.
In addition to the objects, features and advantages described above, the present invention has other objects, features and advantages. The invention will be described in further detail with reference to the accompanying drawings.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the invention. In the drawings:
fig. 1 is a flow chart of a method for dividing a planning area of a full coverage path of a robot according to a preferred embodiment of the present invention;
FIG. 2 is a schematic illustration of the internal continuation of the edge of the preferred embodiment of the present invention.
FIG. 3 is a schematic diagram of an initial set of sub-convex polygons with identifiers in accordance with a preferred embodiment of the present invention.
Fig. 4 is a schematic diagram of the merging result of the initial sub-convex polygons according to the preferred embodiment of the present invention.
Fig. 5 is a schematic diagram of a robot full coverage path planning area dividing apparatus according to a preferred embodiment of the present invention.
Detailed Description
It should be noted that, in the case of no conflict, the embodiments and features in the embodiments may be combined with each other. The invention will be described in detail below with reference to the drawings in connection with embodiments.
Referring to fig. 1, a preferred embodiment of the present invention provides a method for dividing a planning area of a full coverage path of a robot, comprising the steps of:
s1, obtaining an obstacle polygon and an area boundary polygon according to a map, and obtaining an idle area where a robot can walk;
s2, detecting the vertex with the inner angle larger than 180 degrees in the obstacle polygon, wherein the inner angle is an angle which is formed by two intersecting sides in the obstacle polygon and faces the idle area;
s3, extending two sides of each vertex of the obstacle polygon towards the idle area at the vertex to intersect with the area boundary polygon, so that the idle area where the robot can walk is divided into n initial sub-convex polygons;
s4, combining the obtained initial sub-convex polygons into a plurality of convex polygons to obtain a final region convex decomposition result with the minimum total width of the sub-polygons.
In this embodiment, the dividing process of the initial sub-convex polygon is designed based on the following ideas:
convex decomposition mainly occurs at points where the internal angle between two edges of the target polygon (the angle towards the area to be covered) exceeds 180 degrees, following this idea we first expand the edges of the edges forming the internal angle greater than 180 degrees until they hit the boundary of the target polygon or an obstacle inside the polygon. Thus, all sub-polygons generated by the expansion are convex, and this concept is illustrated in FIG. 2, where the interior angle of five points is greater than 180 degrees in FIG. 2. Ten corresponding sides of the five points are extended, the extended sides being indicated by dashed lines in fig. 2 until they touch the boundary of the target area, thereby producing ten initial sub-convex polygons.
And these initial sub-convex polygons found by edge extension may be further merged with neighboring initial sub-convex polygons, as long as the merged polygons are convex. Importantly, this polygon merging requires a reduction in the number of final sub-polygons and the sum of sub-polygon widths, which is the main goal of convex decomposition.
Given a set of initial sub-convex polygons found by edge extension, we first need to find all combinations of initial sub-convex polygons that can be merged into a convex polygon, called convex merging options. For example, given ten initial sub-convex polygons with index numbers 1-10 as shown in FIG. 3, there are 25 convex merging options for the initial sub-convex polygon: the single sub-polygon is 10 cases, the two initial sub-convex polygons are 10 cases, and the three initial sub-convex polygons are 5 cases. After all the convex merging options are calculated, we then select a particular convex merging option to have the sub-polygon generated by the selected convex merging option cover the original region of interest, i.e. the free region where the robot can walk, and to minimize the total width of the sub-polygon. In order to cover the free area that the robot can walk, all initial sub-convex polygons must be included in one of the convex merging options selected.
The choice of convex merging option is a set partitioning problem. Formally, let S denote the initial set of sub-convex polygons indexed by i. The set of merging options, denoted Ω, is indexed by j. Coefficient w j Is the width of the convex polygon generated by the convex merging option j e omega. If merge option j is selected, integer decision variable λ j Then equal to 1, otherwise zero, the choice of convex merging option may be expressed as an integer programming model as follows:
if merge option j contains an initial sub-convex polygon i, then a ij 1, otherwise zero, a ij Also integer decision variables. Objective function
The total width of the sub-polygons is minimized. Constraint->
Ensure that all initial sub-convex polygons are included in a selected one of the convex merging options. Constraint->
Is an integrity constraint on the decision variables. As an illustrative example of this embodiment, fig. 4 shows the best results of the combination of this embodiment.
According to the method for dividing the fully covered path planning area of the robot, the obstacle polygon and the area boundary polygon are obtained according to the map, then the vertices with the inner angles larger than 180 degrees in the obstacle polygon are detected, then the edges of the vertices of the obstacle polygon are expanded to obtain initial sub-convex polygons, and finally the final area convex decomposition result with the minimum total width of the sub-polygons is obtained through combination of the initial sub-convex polygons, namely the combined convex edge shape can be used for subsequent spiral or reciprocating path planning.
The convex decomposition method improves the decomposition performance of the concave polygonal area with the linear shape, and meanwhile, for the complex target polygon, the optimal scanning direction is not required to be considered, so that the decomposition effect can be better, the decomposition difficulty is simplified, the method has the advantages in the aspects of minimizing the total width of the sub-polygon and reducing the calculation complexity, the robot can find a high-quality coverage path, and the operation efficiency of the robot is improved.
In a preferred embodiment of the present invention, the step of obtaining the obstacle polygon and the region boundary polygon according to the map, and the step of obtaining the free region where the robot can walk specifically includes:
s11, reading a static map acquired by a sensor;
s12, preprocessing the static map to highlight obstacle information;
s13, extracting obstacle polygons and region boundary polygons of the static map according to the preprocessed static map, and obtaining an idle region where the cleaning robot can walk.
In a preferred embodiment of the present invention, preprocessing the static map to highlight obstacle information specifically includes the steps of;
s121, performing binarization treatment, expansion and corrosion treatment on the static map;
s122, enhancing the image by using a frequency domain method, removing noise points, and highlighting barrier information.
The process of expanding and then corroding the image is called a closed operation in this embodiment, and the closed operation has the function of filling the tiny holes in the object and connecting the adjacent objects and the smooth boundary. And then, enhancing the image by using a frequency domain method, removing noise points, and further highlighting barrier information, thereby facilitating the subsequent extraction of barrier polygons and region boundary polygons of the static map.
In a preferred embodiment of the present invention, the merging the obtained initial sub-convex polygons into a plurality of convex polygons to obtain a final region convex decomposition result with a minimum total width of the sub-polygons specifically includes the steps of:
all combinations of n initial sub-convex polygons which can be combined into a convex polygon are calculated and used as a convex combining option set;
searching and selecting a plurality of corresponding convex merging options in the convex merging option set to obtain a plurality of sub-polygons, wherein the sub-polygons fully cover the idle area and have the minimum total width.
In a preferred embodiment of the present invention, the calculating to obtain all combinations of n initial sub-convex polygons to be combined into a convex polygon as a convex combining option set specifically includes the steps of:
and (3) solving possible combinations of convex merging options formed by n initial sub-convex polygons according to the ascending order of n to obtain a convex merging option set.
In this embodiment, the possible combinations of the n initial sub-convex polygon components are sequentially calculated according to the ascending order of n as the convex merging option set, for example, for the case of ten initial sub-convex polygons with index numbers 1-10 shown in fig. 3, the possible combinations of the 1 initial sub-convex polygon components are sequentially calculated, the possible combinations of the 2 initial sub-convex polygon components are calculated …, and the possible combinations of the 10 initial sub-convex polygon components are calculated until the possible combinations of the 10 initial sub-convex polygon components are obtained as the convex merging option set. Finally, a final region convex decomposition result with a minimum total width of sub-polygons is obtained by selecting a convex merging option from the set of convex merging options, the selection of which can be represented as an integer programming model as described above.
In a preferred embodiment of the present invention, the step of finding possible combinations of convex merging options consisting of n initial sub-convex polygons in the convex merging option set in ascending order of n as a convex merging option set comprises the steps of:
and (3) obtaining a convex merging option set of possible combinations of convex merging options formed by a set number of initial sub-convex polygons according to an ascending order, wherein the set number < n.
The first step in the choice of convex merging option is to seek all the possibilities of merging the initial sub-convex polygons into convex polygons, but it takes a long time as the number of initial sub-convex polygons increases. Given n initial sub-convex polygons, all combinations should be examined when calculating their width, including convex polygons and non-convex polygons, the initial sub-convex polygons as described above having 25 convex polygons, and some non-convex polygons, such as the combination numbered (4, 5, 6) in fig. 2, being not convex polygons, in order to be able to find whether the combination returns a convex polygon. From the initial test, we know that this is difficult to accomplish quickly when the number of initial sub-convex polygons is large. To overcome this difficulty we have found an approximation scheme to limit the resolution of the convex merging option. In the case of fig. 2 above, when it is necessary to check the convex merging option including 10 initial sub-convex polygons, it is replaced by checking the convex merging option of 5 initial sub-convex polygons, such as checking whether the numbers (1, 2,3,4, 5), the numbers (2, 3,4,5, 6) and the like in fig. 2 are convex polygons. It is apparent that a convex polygon comprising ten (i.e. all) initial sub-convex polygons is necessarily absent, nor is a convex polygon comprising nine initial sub-convex polygons present for fig. 2, indeed, none of the convex polygons comprising four initial sub-convex polygons present for fig. 3, at most only a convex polygon comprising 3 initial sub-convex polygons. Therefore, the present embodiment can simplify the calculation by sequentially obtaining the set of possible combinations of the convex merging options composed of the set number of initial sub-convex polygons in ascending order, representing the set of possible combinations of the 10 initial sub-convex polygons, wherein the set number <10, such as 5,6, 7, 8, etc., can reduce the time for obtaining the possible combinations of the convex merging options to some extent.
Further, in a preferred embodiment of the present invention, the stopping the search when the set number of convex merging options consisting of the initial sub-convex polygons are searched, and using the search result as the search result of the convex merging options consisting of the n initial sub-convex polygons specifically includes:
obtaining
Possible combinations of convex merging options consisting of the initial sub-convex polygons,/->
Possible combinations of convex merging options consisting of the initial sub-convex polygons, wherein +_>
Representing a round up->
Representing a downward rounding;
and combining the obtained possible combinations to obtain possible combinations of convex combining options consisting of n initial sub-convex polygons.
In the present embodiment, as an approximation, in order to further simplify the calculation, the calculation is performed by checking only
And->
Possible combinations of convex merging options for the n initial sub-convex polygons are found. Based on the number of internal obstacles and the uncertainty of the shape, only check +.>
And->
It is sufficient and does not affect much of the accuracy. For example, to find a convex merging option with six initial sub-convex polygons, only consider combinations among the convex merging options with three initial sub-convex polygons, and not check all the possibilities, thereby greatly reducing the time for finding possible combinations of the convex merging options, reducing the computational complexity, and the main steps for checking the possible combinations of the convex merging options consisting of the initial sub-convex polygons by approximation are as follows:
step 1: order the
L 1 ＝S，/>
Wherein 2.ltoreq.i.ltoreq. |S|, S represents an initial convex polygon set indexed by i, Ω represents a convex merging option set indexed by j;
step 2: order the
Step 3: order the
Step 4: let k be from 1 to
Circulation check->
And->
Whether it is a convex polygon, if so, will { S } j ∪S k Adding to the sets Ω and L i In (a) and (b);
step 5: go to step 3 and continue to execute downwards until the cycle
Next, omega and L are obtained i ；/>
Step 6: let i=i+1, then go to step 2 and continue to execute downward.
The method for dividing the planning area of the full coverage path of the robot has obvious technical advantages in the aspects of minimizing the total width of the sub-polygons and reducing the computational complexity of the solution, and can play a key role in searching high-quality coverage paths and successfully performing the operations.
As shown in fig. 5, another embodiment of the present invention further provides a robot full coverage path planning area dividing apparatus, including:
the polygon obtaining module is used for obtaining an obstacle polygon and a region boundary polygon according to the map and obtaining an idle region where the robot can walk;
the vertex detection module is used for detecting a vertex with an inner angle larger than 180 degrees in the obstacle polygon, wherein the inner angle is an angle which is formed by two intersecting sides in the obstacle polygon and faces to an idle area;
the initial sub-convex polygon dividing module is used for extending two sides at each vertex of the obstacle polygon towards the idle area at the vertex to intersect with the area boundary polygon, so that the idle area where the robot can walk is divided into n initial sub-convex polygons;
and the convex polygon merging module is used for merging the obtained initial sub-convex polygons into a plurality of convex polygons to obtain a final region convex decomposition result with the minimum total width of the sub-polygons.
Another embodiment of the present invention provides a storage medium including a stored program, where the program, when executed, controls a device in which the storage medium is located to perform a method of planning an area division by a path entirely covered by the robot, for example.
Another embodiment of the present invention provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor implements the method for dividing a full coverage path planning area of the robot when executing the program.
It should be noted that the steps illustrated in the flowcharts 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 flowcharts, in some cases the steps illustrated or described may be performed in an order other than that illustrated herein.
The functions described in the methods of this embodiment, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in one or more computing device readable storage media. Based on such understanding, a part of the present invention that contributes to the prior art or a part of the technical solution may be embodied in the form of a software product stored in a storage medium, comprising several instructions for causing a computing device (which may be a personal computer, a server, a mobile computing device or a network device, etc.) to execute all or part of the steps of the method described in the embodiments of the present invention. And the aforementioned storage medium includes: a usb disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk or an optical disk, or other various media capable of storing program codes.
In this specification, each embodiment is described in a progressive manner, and each embodiment is mainly described in a different point from other embodiments, so that the same or similar parts between the embodiments are referred to each other.
The above description is only of the preferred embodiments of the present invention and is not intended to limit the present invention, but various modifications and variations can be made to the present invention by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (9)
1. The method for dividing the planning area of the full-coverage path of the robot is characterized by comprising the following steps:
obtaining an obstacle polygon and a region boundary polygon according to a map, and obtaining an idle region where a robot can walk;
detecting the vertex with the inner angle larger than 180 degrees in the obstacle polygon, wherein the inner angle is an angle which is formed by two intersecting sides in the obstacle polygon and faces to the idle area;
extending two sides of each vertex of the obstacle polygon towards the idle area at the vertex until the two sides intersect with the area boundary polygon, so that the idle area where the robot can walk is divided into n initial sub-convex polygons;
all combinations of n initial sub-convex polygons which can be combined into a convex polygon are calculated and used as a convex combining option set; searching and selecting a plurality of corresponding convex merging options in the convex merging option set to obtain a plurality of sub-polygons, wherein the sub-polygons fully cover the idle area and have the minimum total width.
2. The method for dividing the planning area of the full coverage path of the robot according to claim 1, wherein the step of obtaining the obstacle polygon and the area boundary polygon according to the map, and obtaining the free area where the robot can walk, specifically comprises the steps of:
reading a static map acquired by a sensor;
preprocessing the static map to highlight obstacle information;
and extracting obstacle polygons and region boundary polygons of the static map according to the preprocessed static map to obtain an idle region where the cleaning robot can walk.
3. The robot full-coverage path planning area division method according to claim 2, wherein preprocessing the static map to highlight obstacle information specifically comprises the steps of;
performing binarization treatment, expansion and corrosion treatment on the static map;
and enhancing the image by using a frequency domain method, removing noise points, and highlighting barrier information.
4. The method for dividing the planning area of the full coverage path of the robot according to claim 1, wherein the calculating to obtain all combinations of n initial sub-convex polygons which can be combined into a convex polygon as the convex combining option set specifically comprises the steps of:
and (3) solving possible combinations of convex merging options formed by n initial sub-convex polygons according to the ascending order of n to obtain a convex merging option set.
5. The method for partitioning a fully covered path planning area of a robot according to claim 4, wherein the step of obtaining possible combinations of convex merging options consisting of n initial sub-convex polygons in the convex merging option set in ascending order of n as the convex merging option set comprises the steps of:
and (3) obtaining a convex merging option set of possible combinations of convex merging options formed by a set number of initial sub-convex polygons according to an ascending order, wherein the set number < n.
6. The method for dividing a planning area of a fully covered path of a robot according to claim 5, wherein stopping the search when the set number of convex merging options consisting of the initial sub-convex polygons is searched, and using the search result as the search result of the convex merging options consisting of the n initial sub-convex polygons, comprises:
respectively calculate
Possible combinations of convex merging options consisting of the initial sub-convex polygons,/->
Possible combinations of convex merging options consisting of the initial sub-convex polygons, wherein +_>
Representing a round up->
Representing a downward rounding;
and combining the obtained possible combinations to obtain possible combinations of convex combining options consisting of n initial sub-convex polygons.
7. The utility model provides a robot full coverage route planning area division device which characterized in that includes:
the polygon obtaining module is used for obtaining an obstacle polygon and a region boundary polygon according to the map and obtaining an idle region where the robot can walk;
the vertex detection module is used for detecting a vertex with an inner angle larger than 180 degrees in the obstacle polygon, wherein the inner angle is an angle which is formed by two intersecting sides in the obstacle polygon and faces to an idle area;
the initial sub-convex polygon dividing module is used for extending two sides at each vertex of the obstacle polygon towards the idle area at the vertex to intersect with the area boundary polygon, so that the idle area where the robot can walk is divided into n initial sub-convex polygons;
the convex polygon merging module is used for calculating all combinations of n initial sub-convex polygons which can be merged into a convex polygon as a convex merging option set; searching and selecting a plurality of corresponding convex merging options in the convex merging option set to obtain a plurality of sub-polygons, wherein the sub-polygons fully cover the idle area and have the minimum total width.
8. A storage medium including a stored program, characterized in that an apparatus in which the storage medium is controlled to execute the robot full coverage path planning area division method according to any one of claims 1 to 6 when the program is run.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the robot full coverage path planning zone partitioning method of any one of claims 1 to 6 when the program is executed by the processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010465917.4A CN111562787B (en) | 2020-05-28 | 2020-05-28 | Method, device, medium and equipment for dividing planning area of full-coverage path of robot |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010465917.4A CN111562787B (en) | 2020-05-28 | 2020-05-28 | Method, device, medium and equipment for dividing planning area of full-coverage path of robot |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111562787A CN111562787A (en) | 2020-08-21 |
| CN111562787B true CN111562787B (en) | 2023-05-30 |
Family
ID=72070081
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010465917.4A Active CN111562787B (en) | 2020-05-28 | 2020-05-28 | Method, device, medium and equipment for dividing planning area of full-coverage path of robot |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111562787B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113741414A (en) * | 2021-06-08 | 2021-12-03 | 北京理工大学 | Safe motion planning method and device based on mobile robot contour |
| CN113703455B (en) * | 2021-08-27 | 2024-05-28 | 广州文远知行科技有限公司 | Semantic information labeling method of laser point cloud and related equipment |
| CN114323047A (en) * | 2021-12-31 | 2022-04-12 | 北京工业大学 | Full-coverage path planning algorithm based on polygon decomposition |
| CN116048069B (en) * | 2022-12-19 | 2023-12-26 | 香港中文大学（深圳） | Outdoor full-coverage path planning method based on GPS positioning and robot |
| CN116380082B (en) * | 2023-06-07 | 2023-08-08 | 北京理工大学 | Quick path planning method and system for unmanned vehicle in unknown environment |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106643719A (en) * | 2016-09-23 | 2017-05-10 | 江西洪都航空工业集团有限责任公司 | Route planning algorithm of intelligent lawn mower |
| CN110986955A (en) * | 2019-12-19 | 2020-04-10 | 拉扎斯网络科技（上海）有限公司 | Robot path planning method and device, electronic equipment and storage medium |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8306659B2 (en) * | 2006-12-06 | 2012-11-06 | F Robotics Acquisitions Ltd. | Autonomous robot |
| US8498788B2 (en) * | 2010-10-26 | 2013-07-30 | Deere & Company | Method and system for determining a planned path of a vehicle |
| CN107807644A (en) * | 2017-10-30 | 2018-03-16 | 洛阳中科龙网创新科技有限公司 | A kind of farm machinery consumption minimization trajectory path planning method |
| CN108955695B (en) * | 2018-08-22 | 2021-04-02 | 洛阳中科龙网创新科技有限公司 | Global path planning method for farmland robot |
-
2020
- 2020-05-28 CN CN202010465917.4A patent/CN111562787B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106643719A (en) * | 2016-09-23 | 2017-05-10 | 江西洪都航空工业集团有限责任公司 | Route planning algorithm of intelligent lawn mower |
| CN110986955A (en) * | 2019-12-19 | 2020-04-10 | 拉扎斯网络科技（上海）有限公司 | Robot path planning method and device, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111562787A (en) | 2020-08-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111562787B (en) | Method, device, medium and equipment for dividing planning area of full-coverage path of robot | |
| Keidar et al. | Efficient frontier detection for robot exploration | |
| Keidar et al. | Robot exploration with fast frontier detection: Theory and experiments | |
| CN109163722B (en) | Humanoid robot path planning method and device | |
| US6985810B2 (en) | Real-time route and sensor planning system with variable mission objectives | |
| Ström et al. | Predictive exploration considering previously mapped environments | |
| Lee et al. | Perceptual organization of 3D surface points | |
| Stekovic et al. | Montefloor: Extending mcts for reconstructing accurate large-scale floor plans | |
| Gudmundsson et al. | Algorithms for hotspot computation on trajectory data | |
| CN111433780A (en) | Lane line detection method, lane line detection apparatus, and computer-readable storage medium | |
| CN105956994A (en) | Graph processing method and device based on rasterized superposition analysis | |
| CN111966097A (en) | Map building method, system and terminal based on grid map regionalization exploration | |
| CN113221403A (en) | Finite element mesh optimization method, device and medium based on deep reinforcement learning | |
| CN114779779A (en) | Path planning method, path planning device, computer equipment and storage medium | |
| Tanase et al. | Polygon decomposition based on the straight line skeleton | |
| CN113110507A (en) | Path planning method for autonomous obstacle avoidance | |
| Boysen et al. | A journey from IFC files to indoor navigation | |
| Zhang et al. | C-space tunnel discovery for puzzle path planning | |
| CN114343490B (en) | Robot cleaning method, robot, and storage medium | |
| Li et al. | Improving autonomous exploration using reduced approximated generalized voronoi graphs | |
| KR20190080331A (en) | Extended BSA Coverage Path Searching Device, Method and Recording Medium thereof | |
| CN111666361A (en) | Quad-tree construction method and indexing method for storing polygon inclusion relation | |
| CN113034515A (en) | Bounding box tree-based polygon clipping method, electronic device and storage medium | |
| CN111027606B (en) | Multi-mode time series anomaly detection method, storage medium and equipment | |
| CN109977455B (en) | Ant colony optimization path construction method suitable for three-dimensional space with terrain obstacles |
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 |