CN110823241B - Robot path planning method and system based on passable area skeleton extraction - Google Patents
Robot path planning method and system based on passable area skeleton extraction Download PDFInfo
- Publication number
- CN110823241B CN110823241B CN201911135786.7A CN201911135786A CN110823241B CN 110823241 B CN110823241 B CN 110823241B CN 201911135786 A CN201911135786 A CN 201911135786A CN 110823241 B CN110823241 B CN 110823241B
- Authority
- CN
- China
- Prior art keywords
- grid
- path
- point
- starting point
- robot
- 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 44
- 238000000605 extraction Methods 0.000 title claims abstract description 42
- 230000008569 process Effects 0.000 claims abstract description 10
- 238000007670 refining Methods 0.000 claims abstract description 7
- 238000010845 search algorithm Methods 0.000 claims abstract description 7
- 238000005457 optimization Methods 0.000 claims description 10
- 230000004888 barrier function Effects 0.000 claims description 8
- 230000000717 retained effect Effects 0.000 claims description 5
- 238000010586 diagram Methods 0.000 description 19
- 230000008859 change Effects 0.000 description 3
- 230000007613 environmental effect Effects 0.000 description 3
- 230000007547 defect Effects 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/34—Route searching; Route guidance
- G01C21/3407—Route searching; Route guidance specially adapted for specific applications
- G01C21/343—Calculating itineraries, i.e. routes leading from a starting point to a series of categorical destinations using a global route restraint, round trips, touristic trips
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/34—Route searching; Route guidance
- G01C21/3446—Details of route searching algorithms, e.g. Dijkstra, A*, arc-flags, using precalculated routes
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Automation & Control Theory (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The invention provides a robot path planning method and system based on passable area skeleton extraction, wherein an environment grid map is constructed, and an initial position, an obstacle and a target position of a robot are projected into the grid map; determining a passable area of the robot in the grid map, and then adopting a Zhang-Suen algorithm to perform skeleton extraction on the passable area; positioning a path starting point and a path ending point to a grid map, and designing eight-neighborhood grid states of the grid map, so that grids where the path starting point and the path ending point are positioned can be reserved as framework points in the process of refining a passable area; searching the shortest communicated framework connecting the starting point and the end point of the path by using a breadth-first search algorithm to obtain the shortest path which can be passed by the robot; the path track obtained by the method is approximately in the middle position of the passable area, the safety requirement of robot path planning can be better met, and the skeleton extraction algorithm is improved, so that the information of the starting point and the ending point of the path is reserved in the skeleton extraction result.
Description
Technical Field
The disclosure relates to the technical field of robot path planning, in particular to a robot path planning method and system based on passable region skeleton extraction.
Background
The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art.
The mobile robot path planning technology is that a robot plans a safe operation route according to the sensing information of a sensor of the robot on the environment, and simultaneously, the operation task is efficiently completed. According to the map construction principle, path planning is generally divided into a road marking method and a grid method. The road marking method is to construct a feasible path diagram of the robot, which is composed of mark points and connecting edges, such as a visual diagram method, a tangent diagram method, a Voronoi diagram method, a probability diagram expansion method and the like. The grid method decomposes the space around the robot into mutually connected and non-overlapping space grids, a connected graph is formed by the grids, and an optimal path without collision from a starting grid to a target grid is searched on the graph according to the occupancy condition of an obstacle, such as an A-algorithm and the like.
The visual graph method, the A-algorithm and the like in the above algorithms all belong to shortest path planning algorithms, namely, the robot must almost approach to the obstacle to walk, but if a position error is generated in the control process, the possibility of collision between the mobile robot and the environment is high. The Voronoi diagram is composed of a series of straight line segments and parabolic segments, the algorithm first obtains a circumscribed circle of the obstacle and "grows" the circumscribed circle, and at this time, the robot can be treated as a single point. However, the voronoi diagram is generated by the center of the circumscribed circle regardless of the radius of the circumscribed circle, so that the edges of the voronoi diagram may still intersect the obstacle circle and there is still a possibility of collision.
The inventors of the present disclosure have found that for mobile robots, in many applications it is not really necessary to get the shortest path, and it is sufficient to just ensure near-optimal. And for an obstructed area on the map, the shortest path may not be very important, but the safety of the robot is the most important. If a path with high safety is obtained by the path planning algorithm, the path planning algorithm needs to be realized by expanding the barrier, namely, a passable area close to the barrier is regarded as a non-passable area, so that the aim that the path of the robot is far away from the barrier is fulfilled. However, the method has the obvious defect that a narrow passage is easy to block, so that the path planning fails, and therefore, the safety problem in the path planning of the robot cannot be well solved by the existing method.
Disclosure of Invention
In order to solve the defects of the prior art, the robot path planning method and system based on passable area skeleton extraction are provided, the path track is approximately located in the middle of the passable area instead of being close to an obstacle, and the safety requirement of robot path planning can be better met.
In order to achieve the purpose, the following technical scheme is adopted in the disclosure:
the first aspect of the disclosure provides a robot path planning method based on passable region skeleton extraction.
A robot path planning method based on passable area skeleton extraction comprises the following steps:
constructing an environment grid map, and then projecting the initial position, the obstacle and the target position of the robot into the grid map according to the environment information;
determining a passable area of the robot in the grid map, and then adopting a Zhang-Suen algorithm to perform skeleton extraction on the passable area;
positioning a path starting point and a path ending point to a grid map, and designing eight-neighborhood grid states of the grid map, so that grids where the path starting point and the path ending point are positioned can be reserved as framework points in the process of refining a passable area;
and searching the shortest communicated framework connecting the starting point and the end point of the path by using a breadth-first search algorithm to obtain the shortest path which can be passed by the robot.
As some possible implementations, if the grid where the starting point or the ending point is located at the vertex position of the grid map at the upper left, upper right, lower left, or lower right, and the diagonal grid where the triangle is located is set as the impassable grid, the grid where the starting point or the ending point is located is reserved as the skeleton point.
As some possible implementations, if the starting point or the ending point is located at the edge positions of the grid map, which are above, below, left, or right, and the grid opposite to the edge where the triangle is located is set as the impassable grid, the grid where the starting point or the ending point is located is retained as the skeleton point.
As some possible implementation manners, if the position of the start point or the end point has a complete eight-neighborhood grid, at this time, the start point or the end point is located inside the passable region, a grid located in a diagonal direction of the eight-neighborhood grid, which traverses the grid first, is set as an impassable grid, and the grid where the start point or the end point is located is reserved as a skeleton point.
As some possible implementation manners, connectable frameworks of the starting point and the end point of the path are searched, if the connectable frameworks exist, it is indicated that a passable path exists between the starting point and the end point, and otherwise, the path planning fails.
As a further limitation, when the connectable skeleton exists, node information contained in the connectable skeleton is extracted, path lengths among all nodes are calculated, an undirected graph containing a path starting point, a path ending point and nodes is constructed, and then a shortest line segment combination connecting the path starting point and the path ending point is searched as an optimal passable path by adopting a Dijkstra algorithm.
The second aspect of the disclosure provides a robot path planning system based on passable region skeleton extraction.
A robot path planning system based on passable region skeleton extraction comprises:
a grid map building module configured to: constructing an environment grid map, and then projecting the initial position, the obstacle and the target position of the robot into the grid map according to the environment information;
a skeleton extraction module configured to: determining a passable area of the robot in the grid map, and then adopting a Zhang-Suen algorithm to perform skeleton extraction on the passable area;
a skeletal optimization module configured to: positioning a path starting point and a path ending point to a grid map, and designing eight-neighborhood grid states of the grid map, so that grids where the path starting point and the path ending point are positioned can be reserved as framework points in the process of refining a passable area;
a shortest path acquisition module configured to: and searching the shortest communicated framework connecting the starting point and the end point of the path by using a breadth-first search algorithm to obtain the shortest path which can be passed by the robot.
As some possible implementation manners, the framework optimization module optimizes the framework, specifically: if the grid where the starting point or the end point is located at the top left, top right, bottom left or bottom right vertex position of the grid map, the diagonal grid where the triangle is located is set as an impassable grid, and the grid where the starting point or the end point is located is reserved as a framework point;
the framework optimization module optimizes the framework, and specifically comprises the following steps: if the starting point or the end point is located at the upper edge position, the lower edge position, the left edge position or the right edge position of the grid map, and the grid opposite to the edge where the triangle is located is set as an impassable grid, the grid where the starting point or the end point is located is reserved as a framework point;
the framework optimization module optimizes the framework, and specifically comprises the following steps: if the starting point or the end point has a complete eight-neighborhood grid, the starting point or the end point is located in the passable area, the grid located in the diagonal direction of the grid traversed firstly in the eight-neighborhood grid is set as the impassable grid, and the grid located at the starting point or the end point is reserved as the framework point.
A third aspect of the present disclosure provides a medium on which a program is stored, which when executed by a processor implements the steps in the passable region skeleton extraction-based robot path planning method according to the first aspect of the present disclosure.
A fourth aspect of the present disclosure provides an electronic device, including a memory, a processor, and a program stored in the memory and executable on the processor, where the processor executes the program to implement the steps in the robot path planning method based on navigable area skeleton extraction according to the first aspect of the present disclosure.
Compared with the prior art, the beneficial effect of this disclosure is:
1. the path trajectory planned by the method and the system disclosed by the disclosure is approximately in the middle of the passable area, but not close to the barrier, so that the safety requirement of robot path planning can be better met.
2. According to the method, the framework extraction algorithm in the image processing field is introduced to the aspect of robot path planning based on the grid map, and is improved according to the special requirement of the path planning, so that the information of a path starting point and a path ending point is reserved in the framework extraction result, and the accuracy of the path planning is greatly improved.
Drawings
Fig. 1 is a schematic flow chart of a robot path planning method based on passable region skeleton extraction according to embodiment 1 of the present disclosure.
Fig. 2 is a schematic diagram of a 3 × 3 grid map provided in embodiment 1 of the present disclosure.
Fig. 3(a) is an original environment grid map provided in embodiment 1 of the present disclosure.
Fig. 3(b) is a schematic diagram of a skeleton extraction result provided in embodiment 1 of the present disclosure.
Fig. 4(a) is a schematic diagram of a vertex primitive grid state provided in embodiment 1 of the present disclosure.
Fig. 4(b) is a schematic diagram of a modified vertex grid state provided in embodiment 1 of the present disclosure.
Fig. 5(a) is a schematic diagram of an original grid state of edge points provided in embodiment 1 of the present disclosure.
Fig. 5(b) is a schematic diagram of a state of the modified edge point grid provided in embodiment 1 of the present disclosure.
Fig. 6(a) is a schematic diagram of an original grid state of an internal point provided in embodiment 1 of the present disclosure.
Fig. 6(b) is a schematic diagram of a modified internal point grid state provided in embodiment 1 of the present disclosure.
Fig. 7 is a schematic diagram of an optimized passable skeleton extraction result provided in embodiment 1 of the present disclosure.
Fig. 8 is a schematic diagram of an extraction result of a passable skeleton labeled with nodes according to embodiment 1 of the present disclosure.
Fig. 9 is a path undirected graph provided by embodiment 1 of the present disclosure.
Fig. 10 is a schematic diagram of a selected shortest passable path provided in embodiment 1 of the present disclosure.
Detailed Description
It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the disclosure. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments according to the present disclosure. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, and it should be understood that when the terms "comprises" and/or "comprising" are used in this specification, they specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof, unless the context clearly indicates otherwise.
The embodiments and features of the embodiments in the present disclosure may be combined with each other without conflict.
Example 1:
as shown in fig. 1, an embodiment 1 of the present disclosure provides a robot path planning method based on passable region skeleton extraction, which includes the following steps:
constructing an environment grid map, and then projecting the initial position, the obstacle and the target position of the robot into the grid map according to the environment information;
determining a passable area of the robot in the grid map, and then adopting a Zhang-Suen algorithm to perform skeleton extraction on the passable area;
positioning a path starting point and a path ending point to a grid map, and designing eight-neighborhood grid states of the grid map, so that grids where the path starting point and the path ending point are positioned can be reserved as framework points in the process of refining a passable area;
and searching the shortest communicated framework connecting the starting point and the end point of the path by using a breadth-first search algorithm to obtain the shortest path which can be passed by the robot.
The specific scheme is as follows:
the robot senses environmental information by means of a sensor of the robot, and a grid map is built according to the environmental information.
Determining a passable area of the robot in the grid map, and then extracting a skeleton of the passable area by adopting the conventional Zhang-Suen algorithm, wherein the principle and the method are as follows:
an environmental map block with known 3 x 3 grids is shown in fig. 2, in which the mesh grid represents an obstacle and the blank grid represents a passable area. For convenience of description, the passable grid is labeled as 1 and the obstacle point is labeled as 0.
(1) Let the center grid be P1, and 8 points in its neighborhood are denoted as P2, P3, …, and P9 clockwise around the center point, respectively, where P2 is directly above P1.
First, a grid is marked which simultaneously satisfies the following conditions:
（a）2≤B(P1)≤6；
（b）A(P1)=1；
（c）P2×P4×P6=0；
（d）P4×P6×P8=0；
where A (P1) is the number of times the values of these points change from 0 to 1 in the order of P2, P3, …, P9, and B (P1) is the number of non-zero neighbors of P1. When all the boundary points are checked, all the marked points are removed.
(2) Just like the step (1), the previous condition (c) is changed to (e) P2 × P4 × P8= 0; the condition (d) is changed to the condition (f) P2 × P6 × P8= 0. Similarly, when all boundary points have been examined, all marked points are removed.
The above two operations constitute one iteration. Until no more points satisfy the marking condition, the remaining points constitute the skeleton of the passable area.
The black lines in fig. 3(b) are the results obtained by the traversable region skeleton extraction algorithm acting on the grid map shown in fig. 3(a), and it is clear from fig. 3(b) that the connected skeleton of the traversable region can be extracted by the Zhang-Suen algorithm, and the skeleton is approximately in the middle of the obstacle rather than being close to the obstacle, so that the safety requirement of robot path planning can be met.
However, fig. 3(b) only makes skeleton connection to the passable area by means of the Zhang-Suen algorithm, but does not include information of a starting point and an end point of the path, and the skeleton includes multiple branches, so that the mobile robot cannot obtain an optimal passable path connecting the starting point and the end point from the skeleton. Therefore, the algorithm is further perfected by combining the special requirements of path planning, and the operation is as follows:
and positioning the starting point and the final point of the path to a grid map, and designing the grid state of eight neighborhoods of the grid map to ensure that the grid can be reserved as a framework point in the process of thinning the passable area.
As known from the Zhang-Suen algorithm operation process, when any grid simultaneously satisfies the above 4 conditions, the grid is eliminated. Therefore, the grid in which the start point and the end point of the route are located can be retained as the skeleton point as long as it does not satisfy any of the 4 conditions. Therefore, the eight neighborhood grid states of the starting point and the end point are modified according to the following steps:
the first step is as follows: positioning the starting point and the terminal point to a grid map, and arranging eight neighborhoods of the grid map to be grids which can pass through;
the second step is that: if the grid where the starting point or the ending point is located (as shown by the triangle in fig. 4 (a)) is located at the vertex (upper left, upper right, lower left, and lower right) of the grid map, 5 of the eight neighborhood grids are located outside the map range, as shown by the dotted line, and for this reason, the 5 neighborhood grids are regarded as the impassable grids. Therefore, the formula (b) will not be satisfied if only the diagonal grid where the triangle is located is set as the impassable grid, and at this time, the triangle grid can be retained as the skeleton point, as shown in fig. 4 (b).
If the start point or the end point is located at the edge (up, down, left, and right) of the grid map, 3 of the eight neighboring grids are located outside the map range (as shown by the triangle in fig. 5(a), which is located at the right edge of the grid map), and these 3 grids are regarded as the non-accessible grids. Therefore, the lattice opposite to the edge where the triangle is located is only required to be the impassable lattice, and the formula (b) will not be satisfied, and at this time, the triangle lattice can be retained as the skeleton point, as shown in fig. 5 (b).
If the start or end position has a complete eight neighborhood grid, as shown by the triangle in FIG. 6(a), it is now inside the passable region. Although the grid does not satisfy the requirement of deleting points, the state of the grid in the neighborhood can change along with the traversal effect of the algorithm on the grid in the framework extraction process. In order to ensure that the point is still reserved as a skeleton point, after the traversal order of the grids is fixed by the skeleton extraction algorithm, the grid located in the diagonal direction of the first traversed grid in the eight-neighborhood grids is set as the impassable grid (if the algorithm starts from the upper left corner of the grid map, the lower right corner grid of the triangular grid is set as the impassable grid), then the formula (b) will not be satisfied, and at this time, the triangular grid can be reserved as the skeleton point, as shown in fig. 6 (b).
With the above change, the passable region skeleton of the start point and the end point of the communication path obtained in fig. 3(b) is shown in fig. 7, in which a circle is the start point of the path and a pentagon is the end point of the path.
Based on fig. 7, a connectable skeleton of the starting point and the ending point of the path is found, which is denoted as L. If L exists, the passable path exists between the starting point and the end point, otherwise, the path planning fails. When L exists, node information contained in L is extracted, as shown in fig. 8, where asterisks indicate path nodes, and the path length D = { D } between nodes is calculated1，d2…diAnd constructing an undirected graph comprising a path starting point, a path ending point and a path node corresponding to the undirected graph, as shown in fig. 9.
Then, a Dijkstra algorithm is adopted to find the shortest line segment combination connecting the starting point and the ending point of the path, so that a passable path is found, and the planning is finished, wherein the result is shown in fig. 10.
Example 2:
the embodiment 2 of the present disclosure provides a robot path planning system based on passable region skeleton extraction, including:
a grid map building module configured to: constructing an environment grid map, and then projecting the initial position, the obstacle and the target position of the robot into the grid map according to the environment information;
a skeleton extraction module configured to: determining a passable area of the robot in the grid map, and then adopting a Zhang-Suen algorithm to perform skeleton extraction on the passable area;
a skeletal optimization module configured to: positioning a path starting point and a path ending point to a grid map, and designing eight-neighborhood grid states of the grid map, so that grids where the path starting point and the path ending point are positioned can be reserved as framework points in the process of refining a passable area;
a shortest path acquisition module configured to: and searching the shortest communicated framework connecting the starting point and the end point of the path by using a breadth-first search algorithm to obtain the shortest path which can be passed by the robot.
The framework optimization module optimizes the framework, and specifically comprises the following steps: if the grid where the starting point or the end point is located at the top left, top right, bottom left or bottom right vertex position of the grid map, the diagonal grid where the triangle is located is set as an impassable grid, and the grid where the starting point or the end point is located is reserved as a framework point;
the framework optimization module optimizes the framework, and specifically comprises the following steps: if the starting point or the end point is located at the upper edge position, the lower edge position, the left edge position or the right edge position of the grid map, and the grid opposite to the edge where the triangle is located is set as an impassable grid, the grid where the starting point or the end point is located is reserved as a framework point;
the framework optimization module optimizes the framework, and specifically comprises the following steps: if the starting point or the end point has a complete eight-neighborhood grid, the starting point or the end point is located in the passable area, the grid located in the diagonal direction of the grid traversed firstly in the eight-neighborhood grid is set as the impassable grid, and the grid located at the starting point or the end point is reserved as the framework point.
Example 3:
the embodiment 3 of the present disclosure provides a computer-readable storage medium, on which a program is stored, where the program, when executed by a processor, implements the steps in the robot path planning method based on navigable area skeleton extraction according to embodiment 1 of the present disclosure.
Example 4:
the embodiment 4 of the present disclosure provides an electronic device, which includes a memory, a processor, and a program stored in the memory and executable on the processor, where the processor executes the program to implement the steps in the robot path planning method based on navigable area skeleton extraction according to embodiment 1 of the present disclosure.
The above description is only a preferred embodiment of the present disclosure and is not intended to limit the present disclosure, and various modifications and changes may be made to the present disclosure by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present disclosure should be included in the protection scope of the present disclosure.
Claims (8)
1. A robot path planning method based on passable area skeleton extraction is characterized by comprising the following steps:
constructing an environment grid map, and projecting the initial position, the obstacle and the target position of the robot into the grid map according to the environment information;
determining a passable area of the robot in the grid map, and extracting a skeleton of the passable area by adopting a Zhang-Suen algorithm, wherein the skeleton is positioned in the middle of the barrier instead of being close to the barrier;
positioning a path starting point and a path ending point to a grid map, and designing eight-neighborhood grid states of the grid map, so that grids where the path starting point and the path ending point are positioned can be reserved as framework points in the process of refining a passable area;
searching the shortest communicated framework connecting the starting point and the end point of the path by using a breadth-first search algorithm to obtain the shortest path which can be passed by the robot;
if the grid where the starting point or the end point is located at the top left, top right, bottom left or bottom right vertex position of the grid map, the diagonal grid of the grid where the starting point or the end point is located is set as an impassable grid, and the grid where the starting point or the end point is located is reserved as a skeleton point; and if the starting point or the end point is positioned at the upper, lower, left or right edge position of the grid map, and the grid opposite to the edge of the grid where the starting point or the end point is positioned is set as the impassable grid, the grid where the starting point or the end point is positioned is reserved as the framework point.
2. The method for planning a robot path based on navigable area skeleton extraction according to claim 1, wherein if the position of the start point or the end point has a complete eight-neighborhood grid, and the start point or the end point is located inside the navigable area at this time, the grid located in the diagonal direction of the first traversed grid in the eight-neighborhood grid is set as an unviable grid, and the grid located at the start point or the end point is retained as a skeleton point.
3. The method for planning the robot path based on the passable area skeleton extraction of claim 1, wherein a passable skeleton of the starting point and the end point of the path is found, if the passable skeleton exists, the passable path exists between the starting point and the end point, and if not, the path planning fails.
4. The accessible area skeleton extraction-based robot path planning method according to claim 3, wherein when the accessible skeleton exists, node information contained in the accessible skeleton is extracted, path lengths among all nodes are calculated, an undirected graph containing a path starting point, a path ending point and nodes is constructed, and then a shortest line segment combination connecting the path starting point and the path ending point is found as an optimal accessible path by adopting a Dijkstra algorithm.
5. A robot path planning system based on passable region skeleton extraction is characterized by comprising:
a grid map building module configured to: constructing an environment grid map, and then projecting the initial position, the obstacle and the target position of the robot into the grid map according to the environment information;
a skeleton extraction module configured to: determining a passable area of the robot in the grid map, and then extracting a framework of the passable area by adopting a Zhang-Suen algorithm, wherein the framework is positioned in the middle of the barrier instead of being close to the barrier;
a skeletal optimization module configured to: positioning a path starting point and a path ending point to a grid map, and designing eight-neighborhood grid states of the grid map, so that grids where the path starting point and the path ending point are positioned can be reserved as framework points in the process of refining a passable area;
a shortest path acquisition module configured to: searching the shortest communicated framework connecting the starting point and the end point of the path by using a breadth-first search algorithm to obtain the shortest path which can be passed by the robot;
if the grid where the starting point or the end point is located at the top left, top right, bottom left or bottom right vertex position of the grid map, the diagonal grid of the grid where the starting point or the end point is located is set as an impassable grid, and the grid where the starting point or the end point is located is reserved as a skeleton point; and if the starting point or the end point is positioned at the upper, lower, left or right edge position of the grid map, and the grid opposite to the edge of the grid where the starting point or the end point is positioned is set as the impassable grid, the grid where the starting point or the end point is positioned is reserved as the framework point.
6. The navigable area skeleton extraction-based robot path planning system of claim 5,
the framework optimization module optimizes the framework, and specifically comprises the following steps: if the starting point or the end point has a complete eight-neighborhood grid, the starting point or the end point is located in the passable area, the grid located in the diagonal direction of the grid traversed firstly in the eight-neighborhood grid is set as the impassable grid, and the grid located at the starting point or the end point is reserved as the framework point.
7. A computer-readable storage medium, on which a program is stored, which program, when being executed by a processor, carries out the steps of the method for robot path planning based on navigable area skeleton extraction according to any one of claims 1 to 4.
8. An electronic device comprising a memory, a processor and a program stored on the memory and executable on the processor, wherein the processor when executing the program implements the steps of the navigable area skeleton extraction based robot path planning method according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911135786.7A CN110823241B (en) | 2019-11-19 | 2019-11-19 | Robot path planning method and system based on passable area skeleton extraction |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911135786.7A CN110823241B (en) | 2019-11-19 | 2019-11-19 | Robot path planning method and system based on passable area skeleton extraction |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110823241A CN110823241A (en) | 2020-02-21 |
| CN110823241B true CN110823241B (en) | 2021-05-28 |
Family
ID=69556893
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911135786.7A Active CN110823241B (en) | 2019-11-19 | 2019-11-19 | Robot path planning method and system based on passable area skeleton extraction |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110823241B (en) |
Families Citing this family (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111323037B (en) * | 2020-02-28 | 2022-07-05 | 海博(苏州)机器人科技有限公司 | Voronoi path planning algorithm for novel framework extraction of mobile robot |
| CN111426328B (en) * | 2020-03-03 | 2023-03-28 | 青岛联合创智科技有限公司 | Robot path planning method for static scene |
| CN112164020B (en) * | 2020-03-31 | 2024-01-23 | 苏州润迈德医疗科技有限公司 | Method, device, analysis system and storage medium for accurately extracting blood vessel center line |
| CN111649748A (en) * | 2020-06-16 | 2020-09-11 | 湖北友系互联科技有限公司 | Indoor navigation method and system |
| CN111998859B (en) * | 2020-09-16 | 2022-08-05 | 杭州海康消防科技有限公司 | Path planning method and device, electronic equipment and path indicating system |
| CN112444263B (en) * | 2020-09-22 | 2023-05-23 | 北京智行者科技股份有限公司 | Global path planning method and device |
| CN112923942B (en) * | 2021-01-22 | 2022-11-25 | 北京中交兴路信息科技有限公司 | Method and device for vehicle reference driving route between starting point and end point |
| CN112936288B (en) * | 2021-03-19 | 2022-09-27 | 之江实验室 | Robot action safety detection method and device, electronic equipment and storage medium |
| CN112950782A (en) * | 2021-03-29 | 2021-06-11 | 北京布科思科技有限公司 | Autonomous roaming method, device and equipment for robot |
| CN113189988B (en) * | 2021-04-21 | 2022-04-15 | 合肥工业大学 | Autonomous path planning method based on Harris algorithm and RRT algorithm composition |
| CN113156956B (en) * | 2021-04-26 | 2023-08-11 | 珠海一微半导体股份有限公司 | Navigation method and chip of robot and robot |
| CN113358129B (en) * | 2021-05-25 | 2023-11-21 | 南京邮电大学 | Obstacle avoidance shortest path planning method based on Voronoi diagram |
| CN113720344B (en) * | 2021-08-30 | 2024-06-04 | 深圳银星智能集团股份有限公司 | Path searching method, path searching device, intelligent equipment and storage medium |
| CN116700230A (en) * | 2022-02-24 | 2023-09-05 | 苏州科瓴精密机械科技有限公司 | Robot path finding method and device based on grid map, robot and storage medium |
| CN118031975B (en) * | 2024-04-15 | 2024-06-11 | 山东省科霖检测有限公司 | Large-scale environmental humidity monitoring method and system |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102314609A (en) * | 2011-09-13 | 2012-01-11 | 中国科学院地理科学与资源研究所 | Skeleton extraction method and device for polygonal image |
| CN105716613A (en) * | 2016-04-07 | 2016-06-29 | 北京进化者机器人科技有限公司 | Method for planning shortest path in robot obstacle avoidance |
| CN106840163A (en) * | 2016-12-29 | 2017-06-13 | 上海斐讯数据通信技术有限公司 | A kind of indoor orientation method and system |
| CN108958238A (en) * | 2018-06-01 | 2018-12-07 | 哈尔滨理工大学 | A kind of robot area Dian Dao paths planning method based on covariant cost function |
-
2019
- 2019-11-19 CN CN201911135786.7A patent/CN110823241B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102314609A (en) * | 2011-09-13 | 2012-01-11 | 中国科学院地理科学与资源研究所 | Skeleton extraction method and device for polygonal image |
| CN105716613A (en) * | 2016-04-07 | 2016-06-29 | 北京进化者机器人科技有限公司 | Method for planning shortest path in robot obstacle avoidance |
| CN106840163A (en) * | 2016-12-29 | 2017-06-13 | 上海斐讯数据通信技术有限公司 | A kind of indoor orientation method and system |
| CN108958238A (en) * | 2018-06-01 | 2018-12-07 | 哈尔滨理工大学 | A kind of robot area Dian Dao paths planning method based on covariant cost function |
Non-Patent Citations (2)
| Title |
|---|
| DEM 数据中路径搜索与地貌自动划分方法研究;万晨;《中国优秀硕士学位论文全文数据库 基础科学辑》;20180215(第2期);第3.1-3.2节 * |
| 城市轨道交通接运公交线网规划与运营方案优化方法研究;张思林;《中国博士学位论文全文数据库 工程科技II辑》;20180115(第1期);第12页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110823241A (en) | 2020-02-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110823241B (en) | Robot path planning method and system based on passable area skeleton extraction | |
| CN110823240B (en) | Following robot path planning method and system with course constraint | |
| CN109059924B (en) | Accompanying robot incremental path planning method and system based on A-x algorithm | |
| CN109947100B (en) | Path planning method and system and terminal equipment | |
| WO2018121448A1 (en) | Topology map creation method and navigation method for mobile robot, programmable device, and computer readable medium | |
| CN111811514B (en) | Path planning method based on regular hexagon grid jump point search algorithm | |
| CN108444490B (en) | Robot path planning method based on depth fusion of visible view and A-x algorithm | |
| WO2023155371A1 (en) | Stable movement global path planning method for indoor mobile robot | |
| CN110220521B (en) | High-precision map generation method and device | |
| CN107990903A (en) | A kind of indoor AGV paths planning methods based on improvement A* algorithms | |
| CN107389079B (en) | High-precision path planning method and system | |
| CN110006430B (en) | Optimization method of track planning algorithm | |
| CN111399543B (en) | Same-region multi-collision-free air route planning method based on A-star algorithm | |
| CN111080786A (en) | BIM-based indoor map model construction method and device | |
| CN115164907A (en) | Forest operation robot path planning method based on A-x algorithm of dynamic weight | |
| CN113741539B (en) | Unmanned aerial vehicle plant protection operation route planning method | |
| CN117419738A (en) | Based on visual view and D * Path planning method and system of Lite algorithm | |
| CN115562356A (en) | Flight vehicle graph search path planning method, terminal device and medium | |
| CN116772846A (en) | Unmanned aerial vehicle track planning method, unmanned aerial vehicle track planning device, unmanned aerial vehicle track planning equipment and unmanned aerial vehicle track planning medium | |
| CN116560360A (en) | Method and system for planning real-time dynamic path of medical care robot facing complex dynamic scene | |
| WO2022213519A1 (en) | Path planning method and apparatus, and cleaning robot and storage medium | |
| CN114442642B (en) | Path planning method, path planning device, computer equipment and storage medium | |
| CN115143980A (en) | Incremental topological map construction method based on pruning Voronoi diagram | |
| CN115205823A (en) | Method and system for determining travelable area and automatic driving vehicle | |
| CN115238525B (en) | Feasible path searching method for pedestrian simulation passenger flow organization |
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 | ||
| CB03 | Change of inventor or designer information | ||
| CB03 | Change of inventor or designer information |
Inventor after: Yan Zhiguo Inventor after: Zhang Hui Inventor after: Ma Fengying Inventor after: Liu Haiying Inventor after: Zhao Yongguo Inventor before: Zhang Hui Inventor before: Ma Fengying Inventor before: Liu Haiying Inventor before: Zhao Yongguo Inventor before: Zhang Youpan |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20220620 Address after: Room 409, Yimeng cloud Valley, No.19 Chang'an Road, Zhimadun street, economic development zone, Linyi City, Shandong Province 276000 Patentee after: SHANDONG TONGQI INTELLIGENT TECHNOLOGY CO.,LTD. Address before: 250353 University Road, Changqing District, Ji'nan, Shandong Province, No. 3501 Patentee before: Qilu University of Technology |
|
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20230804 Address after: Room 713, 7th Floor, Unit 1, Building S1, Rongchang Lvyuan Phase 1, Intersection of Wuhan Road and Xiaohe Road, Liuqing Street, Lanshan District, Linyi City, Shandong Province, 276000 Patentee after: Shandong Junce Standardization Service Co.,Ltd. Address before: Room 409, Yimeng cloud Valley, No.19 Chang'an Road, Zhimadun street, economic development zone, Linyi City, Shandong Province 276000 Patentee before: SHANDONG TONGQI INTELLIGENT TECHNOLOGY CO.,LTD. |
|
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20240129 Address after: Room 714, Building 1, Rongchang Green Garden, Intersection of Wuhan Road and Xiaohe Road, Liuqing Street, Lanshan District, Linyi City, Shandong Province, 276000 Patentee after: Shandong Shouyin Cultural Media Co.,Ltd. Country or region after: China Address before: Room 713, 7th Floor, Unit 1, Building S1, Rongchang Lvyuan Phase 1, Intersection of Wuhan Road and Xiaohe Road, Liuqing Street, Lanshan District, Linyi City, Shandong Province, 276000 Patentee before: Shandong Junce Standardization Service Co.,Ltd. Country or region before: China |