CN115950439B - Bidirectional RRT path planning method and device, electronic equipment and storage medium - Google Patents
Bidirectional RRT path planning method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN115950439B CN115950439B CN202310249471.5A CN202310249471A CN115950439B CN 115950439 B CN115950439 B CN 115950439B CN 202310249471 A CN202310249471 A CN 202310249471A CN 115950439 B CN115950439 B CN 115950439B
- Authority
- CN
- China
- Prior art keywords
- path
- node
- point
- obstacle
- blank
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Landscapes
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The application belongs to the technical field of path planning, and discloses a bidirectional RRT path planning method, a device, electronic equipment and a storage medium, wherein the method comprises the following steps: dividing the map into an obstacle region and a plurality of blank regions according to the outline of the obstacle; respectively taking a starting point and a target point as first nodes of two path trees, determining a blank area where a sampling point is located according to the outline of the obstacle area, sampling in the determined blank area, and alternately expanding nodes of the two path trees until the two path trees intersect to obtain an initial path; smoothing the initial path to obtain a final path; thus, the path planning efficiency can be improved.
Description
Technical Field
The present invention relates to the field of path planning technologies, and in particular, to a bidirectional RRT path planning method, device, electronic apparatus, and storage medium.
Background
The purpose of path planning is to find an optimal collision-free path of motion from the origin to the target point in an obstacle-filled environment, so that the mobile device (e.g. mobile robot) can safely pass through with minimal time.
The RRT algorithm is a commonly used path planning algorithm, aims at generating a path tree, randomly generating a sampling point in a map, finding a tree node closest to the sampling point on the path tree, connecting the sampling point with the tree node by using a connecting line, and obtaining a new tree node on the connecting line by setting step length. However, the RRT algorithm generates sampling points in a random mode, and lacks of path guidance, so that the problem of blind expansion occurs, and further, the path planning efficiency is low, and rapid convergence is not realized.
Disclosure of Invention
The invention aims to provide a bidirectional RRT path planning method, a bidirectional RRT path planning device, electronic equipment and a storage medium, which can improve path planning efficiency.
In a first aspect, the present application provides a bidirectional RRT path planning method, including the steps of:
A1. dividing the map into an obstacle region and a plurality of blank regions according to the outline of the obstacle;
A2. respectively taking a starting point and a target point as first nodes of two path trees, determining a blank area where a sampling point is located according to the outline of the obstacle area, sampling in the determined blank area, and alternately expanding nodes of the two path trees until the two path trees intersect to obtain an initial path;
A3. And carrying out smoothing treatment on the initial path to obtain a final path.
The method has the advantages that the sampling blank area (namely, the blank area where the sampling point is) is firstly determined by utilizing the outline information of the obstacle, then sampling is carried out in the selected sampling blank area to expand the nodes, the expansion process has path guidance, the blind expansion problem is avoided, and therefore, the rapid convergence is realized, and the path planning efficiency is improved.
Preferably, step A1 comprises:
taking the area occupied by the obstacle as the obstacle area;
establishing a plane coordinate system by taking a straight line passing through the starting point and the target point as an X axis and taking a straight line perpendicular to the X axis as a Y axis;
dividing a region other than the obstacle regions into a plurality of single communication regions by using an circumscribed line of each of the obstacle regions and an outline of each of the obstacle regions, and taking each of the single communication regions as one of the blank regions; an circumscribed line of the obstacle region passes through an X-coordinate extreme point of the obstacle region and is parallel to a Y-axis.
Therefore, the blank areas and the obstacle areas are independent of each other and have no surrounding relation, so that the guiding function of the blank areas is enhanced, and the obstacle avoidance path is regulated more quickly.
Preferably, step A2 comprises:
A201. taking the starting point and the target point as the first nodes of two path trees respectively;
A202. alternately taking one of the two path trees as a first path tree and the other path tree as a second path tree, so as to execute the following steps until the two path trees intersect:
B1. taking the latest node of the first path tree as a first node, and taking the node closest to the first node on the second path tree as a second node, and acquiring a connecting line of the first node and the second node as a first line segment;
B2. acquiring a connecting line between a Y-coordinate maximum point and a Y-coordinate minimum point of each barrier zone as a second line segment of the barrier zone;
B3. acquiring two endpoints of the second line segment closest to the second node from the intersection point of the first line segment in the second line segment intersected with the first line segment, and taking the two endpoints as two candidate endpoints;
B4. selecting one of the two candidate endpoints as a selected endpoint, and minimizing the sum of the distance from the first node to the selected endpoint and the distance from the selected endpoint to the second node;
B5. determining one of said blank areas between said first node and said selected endpoint as a sampling blank area;
B6. Determining an expansion point in the sampling blank area as a new node of the first path tree;
A203. and sequentially connecting the nodes of the two path trees to obtain the initial path.
The selected endpoint is searched in the mode, so that a guiding direction from the first node to the selected endpoint is provided for guiding the selection of the sampling blank area, and the obstacle avoidance path with shorter length is obtained.
Preferably, step B5 comprises:
B501. acquiring a set of the blank areas, through which connecting lines of the first node and the selected endpoint pass, as a first blank area set;
B502. acquiring a set of the blank areas adjacent to the blank area where the first node is located as a second blank area set;
B503. and acquiring an intersection of the first blank region set and the second blank region set as the sampling blank region.
In fact, the moving route from the first node to the selected endpoint is an optimal path in the moving process from the first node to the second node, and the sampling blank area is selected from the blank areas passed by the connecting line of the first node and the selected endpoint, so that the path between the first node and the node obtained by expansion is beneficial to being close to the ideal path, and the shorter obstacle avoidance path is beneficial to being finally obtained.
Preferably, step B6 comprises:
B601. randomly generating a plurality of sampling points in the sampling blank area;
B602. selecting the sampling point closest to a connecting line of the first node and the selected endpoint as a reference point, and obtaining a point which is obtained after the first node moves by a preset step length along the direction pointing to the reference point as a candidate expansion point;
B603. performing collision detection on the candidate expansion points;
B604. if the collision detection is qualified, the candidate expansion points are taken as effective expansion points, and the effective expansion points are taken as new nodes of the first path tree; if the collision detection is not acceptable, repeating the steps B601-B604.
According to the method, on one hand, the obtained path can be ensured to be reliably prevented from being blocked, and on the other hand, the path between the first node and the expansion point is more close to an ideal path due to the fact that the sampling point closest to the connecting line of the first node and the selected end point is taken as the reference point, so that the shorter obstacle avoidance path is more favorable to be finally obtained.
Preferably, the intersection of the two path trees means that the distance between the closest two nodes on the two path trees is smaller than a preset distance threshold.
Preferably, step A3 comprises:
And performing B spline smoothing on the initial path to obtain a final path.
In a second aspect, the present application provides a bidirectional RRT path planning apparatus, including:
the dividing module is used for dividing the map into an obstacle area and a plurality of blank areas according to the outline of the obstacle;
the planning module is used for determining a blank area where a sampling point is located according to the outline of the obstacle area by taking a starting point and a target point as first nodes of two path trees respectively, and sampling in the determined blank area so as to alternately expand the nodes of the two path trees until the two path trees intersect, so that an initial path is obtained;
and the smoothing processing module is used for carrying out smoothing processing on the initial path to obtain a final path.
The method has the advantages that the sampling blank area (namely, the blank area where the sampling point is) is firstly determined by utilizing the outline information of the obstacle, then sampling is carried out in the selected sampling blank area to expand the nodes, the expansion process has path guidance, the blind expansion problem is avoided, and therefore, the rapid convergence is realized, and the path planning efficiency is improved.
In a third aspect, the present application provides an electronic device comprising a processor and a memory, the memory storing a computer program executable by the processor, when executing the computer program, running steps in a bi-directional RRT path planning method as described hereinbefore.
In a fourth aspect, a storage medium has stored thereon a computer program which, when executed by a processor, performs the steps of the bi-directional RRT path planning method as described hereinbefore.
The beneficial effects are that: according to the bidirectional RRT path planning method, device, electronic equipment and storage medium, the sampling blank area is determined firstly by utilizing the profile information of the obstacle, and then sampling is carried out in the selected sampling blank area to expand nodes.
Drawings
Fig. 1 is a flowchart of a bidirectional RRT path planning method according to an embodiment of the present application.
Fig. 2 is a schematic structural diagram of a bidirectional RRT path planning apparatus according to an embodiment of the present application.
Fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Fig. 4 is a schematic diagram of an exemplary blank zone division.
Fig. 5 is a schematic diagram of an exemplary select sample blank area.
Detailed Description
The following description of the embodiments of the present application will be made clearly and completely with reference to the drawings in the embodiments of the present application, and it is apparent that the described embodiments are only some embodiments of the present application, not all embodiments. The components of the embodiments of the present application, which are generally described and illustrated in the figures herein, may be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the present application, as provided in the accompanying drawings, is not intended to limit the scope of the application, as claimed, but is merely representative of selected embodiments of the application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present application without making any inventive effort, are intended to be within the scope of the present application.
It should be noted that: like reference numerals and letters denote like items in the following figures, and thus once an item is defined in one figure, no further definition or explanation thereof is necessary in the following figures. Meanwhile, in the description of the present application, the terms "first", "second", and the like are used only to distinguish the description, and are not to be construed as indicating or implying relative importance.
Referring to fig. 1, fig. 1 is a bidirectional RRT path planning method according to some embodiments of the present application, including the steps of:
A1. dividing the map into an obstacle region and a plurality of blank regions according to the outline of the obstacle;
A2. the method comprises the steps that a starting point and a target point are respectively taken as first nodes of two path trees, a blank area where a sampling point is located is determined according to the outline of an obstacle area, sampling is carried out in the determined blank area, and nodes of the two path trees are alternately expanded until the two path trees intersect, so that an initial path is obtained;
A3. and smoothing the initial path to obtain a final path.
The method has the advantages that the sampling blank area (namely, the blank area where the sampling point is) is firstly determined by utilizing the outline information of the obstacle, then sampling is carried out in the selected sampling blank area to expand the nodes, the expansion process has path guidance, the blind expansion problem is avoided, and therefore, the rapid convergence is realized, and the path planning efficiency is improved.
In this embodiment, step A1 includes:
A101. taking the area occupied by the barrier (namely, the area surrounded by the barrier contour line) as a barrier area;
A102. establishing a plane coordinate system by taking a straight line passing through the starting point and the target point as an X axis and taking a straight line perpendicular to the X axis as a Y axis;
A103. dividing the area except the barrier areas into a plurality of single communication areas (namely, communication areas without holes inside) by using the circumscribed line of each barrier area and the contour line of each barrier area, and taking each single communication area as a blank area; the circumscribed line of the obstacle region passes through the X-coordinate extreme point of the obstacle region and is parallel to the Y-axis.
Therefore, the blank areas and the obstacle areas are independent of each other and have no surrounding relation, so that the guiding function of the blank areas is enhanced, and the obstacle avoidance path is regulated more quickly.
The X-coordinate extreme points of the obstacle region include an X-coordinate maximum point and an X-coordinate minimum point, wherein the X-coordinate maximum point refers to a point with a maximum X-coordinate value among points of the obstacle region, and the X-coordinate minimum point refers to a point with a minimum X-coordinate value among points of the obstacle region, and the X-coordinate extreme points are generally points on a contour line of the obstacle region.
For example, in fig. 4, the black areas are barrier areas, and two sides of each barrier area have a dashed line parallel to the Y axis, where the dashed line is an circumscribed line, so that the circumscribed line and the contour line of each barrier area divide the map area into 7 blank areas respectively: s1, S2, S3, S4, S5, S6 and S7.
Specifically, step A2 includes:
A201. taking a starting point and a target point as the first nodes of two path trees respectively;
A202. alternately taking one of the two path trees as a first path tree and the other path tree as a second path tree, so as to execute the following steps until the two path trees intersect:
B1. taking the latest node of the first path tree as a first node, and taking the node closest to the first node on the second path tree as a second node, and acquiring a connecting line of the first node and the second node as a first line segment;
B2. acquiring a connecting line between a Y-coordinate maximum point and a Y-coordinate minimum point of each obstacle region as a second line segment of the obstacle region;
B3. acquiring two endpoints of a second line segment closest to a second node from a second line segment intersected with the first line segment, and taking the two endpoints as two candidate endpoints;
B4. selecting one of the two candidate endpoints as a selected endpoint, and minimizing the sum of the distance from the first node to the selected endpoint and the distance from the selected endpoint to the second node;
B5. determining a blank region between the first node and the selected endpoint as a sampling blank region;
B6. determining an expansion point in the sampling blank area as a new node of the first path tree;
A203. And sequentially connecting the nodes of the two path trees to obtain an initial path.
The selected endpoint is searched in the mode, so that a guiding direction from the first node to the selected endpoint is provided for guiding the selection of the sampling blank area, and the obstacle avoidance path with shorter length is obtained.
The starting point and the target point are preset points, and are respectively the starting point and the end point of the path to be planned.
For convenience of explanation, a path tree having a start point as a first node is referred to as a left path tree, and a path tree having a target point as a first node is referred to as a right path tree. In step a202, for example, a starting point is first taken as a first node, a second node at this time is a target point, the first path tree is a left path tree, the second path tree is a right path tree, a new node obtained by new expansion in the first cycle is a node P1, and the node P1 is the latest node of the left path tree; in the second cycle, the first node is the target point, the second node is the closest node to the target point in the left path tree, so that the new node obtained by the new expansion is the node P2, and the node P2 is the latest node of the right path tree; in the third cycle, the first node is node P1, the second node is the node closest to node P1 on the right path tree, so that the new node obtained by new expansion is node P3, and the node P3 is the latest node of the left path tree; in the fourth cycle, the first node is node P2, and the second node is the node closest to node P2 on the left path tree, so that the new node obtained by new expansion is node P4, and node P4 is the latest node of the right path tree; this loops until the two path trees intersect.
The maximum point of the Y coordinate in the obstacle region is the point with the maximum Y coordinate value among the points in the obstacle region, the minimum point of the Y coordinate is the point with the minimum Y coordinate value among the points in the obstacle region, and the maximum point of the Y coordinate and the minimum point of the Y coordinate are points on the contour line of the obstacle region in general. In step B2, if there are a plurality of Y-coordinate maximum points in one obstacle region, one of the Y-coordinate maximum points may be selected randomly as the effective Y-coordinate maximum point, or one of the Y-coordinate maximum points may be selected so that the sum of the distance from the first node to the effective Y-coordinate maximum point and the distance from the effective Y-coordinate maximum point to the second node is the smallest (for example, if three Y-coordinate maximum points are respectively the point X1, the point X2 and the point X3, the point P0 is the point P, the point Pz is the point P0X1 and the line segment X1P is the point P0X1The total length of z is L1, the total length of the line segment P0X2 and the line segment X2Pz is L2, the total length of the line segment P0X3 and the line segment X3Pz is L3, and
the point X1 is taken as the effective Y coordinate maximum point, so that a shorter path can be planned more conveniently; similarly, if there are multiple Y-coordinate minimum points in one obstacle region, one of the Y-coordinate minimum points may be selected randomly as an effective Y-coordinate minimum point, or one of the Y-coordinate minimum points may be selected as an effective Y-coordinate minimum point so that the sum of the distance from the first node to the effective Y-coordinate minimum point and the distance from the effective Y-coordinate minimum point to the second node is minimized, thereby being more beneficial to planning a shorter path.
For example, in fig. 5, two candidate end points determined in step B3 are shown for the first cycle, wherein only the second line segment of the diamond-shaped obstacle region (the line between the upper corner M1 and the lower corner M2 thereof) intersects with the first line segment (the line between the start point P0 and the target point Pz), i.e., the second line segment closest to the intersection point of the first line segment from the second node is also the second line segment of the diamond-shaped obstacle region, so that the two candidate end points are the upper corner M1 and the lower corner M2.
In fig. 5, the total length of the line segment P0M1 and the line segment M1Pz is smaller than the total length of the line segment P0M2 and the line segment M2Pz, and therefore, the upper corner point M1 is selected as the selected end point in step B4.
In some preferred embodiments, step B5 comprises:
B501. acquiring a set of blank areas passed by connecting lines of a first node and a selected endpoint as a first blank area set;
B502. acquiring a set of blank areas adjacent to the blank area where the first node is located as a second blank area set;
B503. an intersection of the first set of white spaces and the second set of white spaces is obtained as a sampling white space.
In fact, the moving route from the first node to the selected endpoint is an optimal path in the moving process from the first node to the second node, and the sampling blank area is selected from the blank areas passed by the connecting line of the first node and the selected endpoint, so that the path between the first node and the node obtained by expansion is beneficial to being close to the ideal path, and a shorter obstacle avoidance path is beneficial to being finally obtained.
Continuing with the example of FIG. 5, the blank space traversed by the connection line (i.e., segment P0M 1) of the first node and the selected endpoint includes S1, S3, S4, and S5, thus a first set of blank spaces
Is->
The blank area where the first node is located is S1, and the blank area adjacent to S1 comprises S2 and S3, so the second blank area set +.>
Is that
Intersection of the first set of blank areas and the second set of blank areas +.>
Is that
Thus, the sample blank area is S3. It should be noted that intersection->
There is one and only one blank area, not the special case of fig. 5.
In some preferred embodiments, step B6 comprises:
B601. randomly generating a plurality of sampling points in a sampling blank area;
B602. selecting a sampling point closest to a connecting line of the first node and the selected endpoint as a reference point, and acquiring a point which is obtained by moving the first node by a preset step length along the direction pointing to the reference point as a candidate expansion point;
B603. performing collision detection on the candidate expansion points;
B604. if the collision detection is qualified, taking the candidate expansion points as effective expansion points, and taking the effective expansion points as new nodes of the first path tree; if the collision detection is not acceptable, repeating the steps B601-B604.
According to the method, on one hand, the obtained path can be ensured to be reliably prevented from being blocked, and on the other hand, the path between the first node and the expansion point is more close to an ideal path due to the fact that the sampling point closest to the connecting line of the first node and the selected end point is taken as the reference point, so that the shorter obstacle avoidance path is more favorable to be finally obtained.
In step B601, a preset number of sampling points may be randomly generated, where the preset number may be set according to actual needs, for example, but not limited to, 5.
The preset step size in step B602 may be set according to actual needs.
Taking fig. 5 as an example, in step B602, assuming that the sampling point closest to the connecting line P0M1 between the first node and the selected endpoint is the point M3, the point M3 is taken as a reference point, the point obtained after the first node moves by a preset step length along the direction of p0→m3 is the point P1, and the point P1 is a candidate expansion point.
In some embodiments, step B603 comprises: setting the center of a circular area with the collision radius of the mobile device (preset according to the size of the mobile device) as the radius at a candidate expansion point, detecting whether the circular area has an intersection point with at least one obstacle area, if so, judging that the collision detection is unqualified, and if not, judging that the collision detection is qualified.
In other embodiments, step B603 includes: the geometric center of a collision area obtained after the outline of the mobile equipment is outwards expanded by a preset collision distance (which can be set according to actual needs) is arranged at a candidate expansion point, whether the collision area has an intersection point with at least one obstacle area or not is detected, if yes, the collision detection is judged to be unqualified, and if not, the collision detection is judged to be qualified.
In practical applications, there may not be a second line segment intersecting the first line segment, which means that the first line segment does not intersect all obstacle regions, and at this time, the second node may be directly used as the selected endpoint. Thus, in some embodiments, after step B2 and before step B3, further comprising:
B7. judging whether the first line segment intersects with at least one second line segment, if yes, turning to step B3 (i.e. sequentially executing steps B1, B2, B7, B3, B4, B5 and B6), and if not, taking the second node as a selected endpoint, turning to step B5 (i.e. sequentially executing steps B1, B2, B7, B5 and B6).
Preferably, the two path trees intersect, which means that the distance between the closest two nodes on the two path trees is smaller than a preset distance threshold. That is, as long as the distance between two nodes that are close on the two path trees is smaller than a preset distance threshold, it is determined that the two path trees intersect, and expansion of the nodes is stopped.
In step A3, the initial path may be smoothed by any conventional smoothing method, which is not limited herein. For example, in some embodiments, step A3 comprises:
and performing B spline smoothing on the initial path to obtain a final path.
As can be seen from the above, the two-way RRT path planning method divides the map into an obstacle region and a plurality of blank regions according to the outline of the obstacle; the method comprises the steps that a starting point and a target point are respectively taken as first nodes of two path trees, a blank area where a sampling point is located is determined according to the outline of an obstacle area, sampling is carried out in the determined blank area, and nodes of the two path trees are alternately expanded until the two path trees intersect, so that an initial path is obtained; smoothing the initial path to obtain a final path; thus, the path planning efficiency can be improved. In particular, the following advantages are achieved:
1. the automation degree is high, and the planning process does not need human intervention;
2. the sampling is carried out in the selected blank area, so that the blind expansion problem caused by the random sampling (full-image random sampling) of the traditional RRT algorithm is solved, the sampling efficiency is improved, and the planning speed is increased;
3. the sampling blank area is selected by utilizing the profile information of the obstacle, so that the calculation is simple, the operation efficiency is high, and the instantaneity of the method is improved;
4. aiming at different scenes, the searching efficiency can be accelerated by adjusting the size of the preset step length, and the application range is wide;
5. b spline smoothing is carried out on the obtained initial path, so that a smooth overall path is obtained, and movement of the mobile equipment is facilitated.
Referring to fig. 2, the present application provides a bidirectional RRT path planning apparatus, including:
a dividing module 1 for dividing the map into an obstacle region and a plurality of blank regions according to the outline of the obstacle;
a planning module 2, configured to determine, according to the outline of the obstacle region, a blank region where the sampling point is located, using the starting point and the target point as first nodes of two path trees, and sample in the determined blank region, so as to alternately expand the nodes of the two path trees until the two path trees intersect, thereby obtaining an initial path;
and the smoothing module 3 is used for smoothing the initial path to obtain a final path.
The method has the advantages that the sampling blank area (namely, the blank area where the sampling point is) is firstly determined by utilizing the outline information of the obstacle, then sampling is carried out in the selected sampling blank area to expand the nodes, the expansion process has path guidance, the blind expansion problem is avoided, and therefore, the rapid convergence is realized, and the path planning efficiency is improved.
In the present embodiment, the dividing module 1 performs, when dividing a map into an obstacle region and a plurality of blank regions according to the outline of the obstacle:
taking the area occupied by the barrier (namely, the area surrounded by the barrier contour line) as a barrier area;
Establishing a plane coordinate system by taking a straight line passing through the starting point and the target point as an X axis and taking a straight line perpendicular to the X axis as a Y axis;
dividing the area except the barrier areas into a plurality of single communication areas (namely, communication areas without holes inside) by using the circumscribed line of each barrier area and the contour line of each barrier area, and taking each single communication area as a blank area; the circumscribed line of the obstacle region passes through the X-coordinate extreme point of the obstacle region and is parallel to the Y-axis.
Therefore, the blank areas and the obstacle areas are independent of each other and have no surrounding relation, so that the guiding function of the blank areas is enhanced, and the obstacle avoidance path is regulated more quickly.
The X-coordinate extreme points of the obstacle region include an X-coordinate maximum point and an X-coordinate minimum point, wherein the X-coordinate maximum point refers to a point with a maximum X-coordinate value among points of the obstacle region, and the X-coordinate minimum point refers to a point with a minimum X-coordinate value among points of the obstacle region, and the X-coordinate extreme points are generally points on a contour line of the obstacle region.
For example, in fig. 4, the black areas are barrier areas, and two sides of each barrier area have a dashed line parallel to the Y axis, where the dashed line is an circumscribed line, so that the circumscribed line and the contour line of each barrier area divide the map area into 7 blank areas respectively: s1, S2, S3, S4, S5, S6 and S7.
Specifically, the planning module 2 determines, at the first nodes of the two path trees taking the starting point and the target point as the first nodes of the two path trees respectively, a blank area where the sampling point is located according to the outline of the obstacle area, and samples in the determined blank area, so as to alternately expand the nodes of the two path trees until the two path trees intersect, thereby obtaining an initial path, and executes:
taking a starting point and a target point as the first nodes of two path trees respectively;
alternately taking one of the two path trees as a first path tree and the other path tree as a second path tree, so as to execute the following steps until the two path trees intersect:
B1. taking the latest node of the first path tree as a first node, and taking the node closest to the first node on the second path tree as a second node, and acquiring a connecting line of the first node and the second node as a first line segment;
B2. acquiring a connecting line between a Y-coordinate maximum point and a Y-coordinate minimum point of each obstacle region as a second line segment of the obstacle region;
B3. acquiring two endpoints of a second line segment closest to a second node from a second line segment intersected with the first line segment, and taking the two endpoints as two candidate endpoints;
B4. selecting one of the two candidate endpoints as a selected endpoint, and minimizing the sum of the distance from the first node to the selected endpoint and the distance from the selected endpoint to the second node;
B5. Determining a blank region between the first node and the selected endpoint as a sampling blank region;
B6. determining an expansion point in the sampling blank area as a new node of the first path tree;
and sequentially connecting the nodes of the two path trees to obtain an initial path.
The selected endpoint is searched in the mode, so that a guiding direction from the first node to the selected endpoint is provided for guiding the selection of the sampling blank area, and the obstacle avoidance path with shorter length is obtained.
The starting point and the target point are preset points, and are respectively the starting point and the end point of the path to be planned.
For convenience of explanation, a path tree having a start point as a first node is referred to as a left path tree, and a path tree having a target point as a first node is referred to as a right path tree. For example, a starting point is first used as a first node, a second node at the moment is used as a target point, the first path tree is a left path tree, the second path tree is a right path tree, a new node obtained by new expansion in the first cycle is a node P1, and the node P1 is the latest node of the left path tree; in the second cycle, the first node is the target point, the second node is the closest node to the target point in the left path tree, so that the new node obtained by the new expansion is the node P2, and the node P2 is the latest node of the right path tree; in the third cycle, the first node is node P1, the second node is the node closest to node P1 on the right path tree, so that the new node obtained by new expansion is node P3, and the node P3 is the latest node of the left path tree; in the fourth cycle, the first node is node P2, and the second node is the node closest to node P2 on the left path tree, so that the new node obtained by new expansion is node P4, and node P4 is the latest node of the right path tree; this loops until the two path trees intersect.
Wherein the Y-coordinate maximum point of the obstacle region refers toAmong the points in the obstacle region, the point having the largest Y coordinate value is the point having the smallest Y coordinate value, and the Y coordinate maximum point and the Y coordinate minimum point are points on the contour line of the obstacle region in general. In step B2, if there are a plurality of Y-coordinate maximum points in one obstacle region, one of the Y-coordinate maximum points may be randomly selected as an effective Y-coordinate maximum point, or one of the Y-coordinate maximum points may be selected so that the sum of the distance from the first node to the effective Y-coordinate maximum point and the distance from the effective Y-coordinate maximum point to the second node is minimum (for example, assuming that three Y-coordinate maximum points are respectively the point X1, the point X2 and the point X3, the starting point is the point P0, the target point is the point Pz, if the total length of the line segment P0X1 and the line segment X1Pz is L1, the total length of the line segment P0X2 and the line segment X2Pz is L2, the total length of the line segment P0X3 and the line segment X3Pz is L3, and
the point X1 is taken as the effective Y coordinate maximum point, so that a shorter path can be planned more conveniently; similarly, if there are multiple Y-coordinate minimum points in one obstacle region, one of the Y-coordinate minimum points may be selected randomly as an effective Y-coordinate minimum point, or one of the Y-coordinate minimum points may be selected as an effective Y-coordinate minimum point so that the sum of the distance from the first node to the effective Y-coordinate minimum point and the distance from the effective Y-coordinate minimum point to the second node is minimized, thereby being more beneficial to planning a shorter path.
For example, in fig. 5, two candidate end points determined in step B3 are shown for the first cycle, wherein only the second line segment of the diamond-shaped obstacle region (the line between the upper corner M1 and the lower corner M2 thereof) intersects with the first line segment (the line between the start point P0 and the target point Pz), i.e., the second line segment closest to the intersection point of the first line segment from the second node is also the second line segment of the diamond-shaped obstacle region, so that the two candidate end points are the upper corner M1 and the lower corner M2.
In fig. 5, the total length of the line segment P0M1 and the line segment M1Pz is smaller than the total length of the line segment P0M2 and the line segment M2Pz, and therefore, the upper corner point M1 is selected as the selected end point in step B4.
In some preferred embodiments, step B5 comprises:
B501. acquiring a set of blank areas passed by connecting lines of a first node and a selected endpoint as a first blank area set;
B502. acquiring a set of blank areas adjacent to the blank area where the first node is located as a second blank area set;
B503. an intersection of the first set of white spaces and the second set of white spaces is obtained as a sampling white space.
In fact, the moving route from the first node to the selected endpoint is an optimal path in the moving process from the first node to the second node, and the sampling blank area is selected from the blank areas passed by the connecting line of the first node and the selected endpoint, so that the path between the first node and the node obtained by expansion is beneficial to being close to the ideal path, and a shorter obstacle avoidance path is beneficial to being finally obtained.
Continuing with the example of FIG. 5, the blank space traversed by the connection line (i.e., segment P0M 1) of the first node and the selected endpoint includes S1, S3, S4, and S5, thus a first set of blank spaces
Is->
The blank area where the first node is located is S1, and the blank area adjacent to S1 comprises S2 and S3, so the second blank area set +.>
Is that
Intersection of the first set of blank areas and the second set of blank areas +.>
Is that
Thus, the sample blank area is S3. It should be noted that intersection->
There is one and only one blank area, not the special case of fig. 5.
In some preferred embodiments, step B6 comprises:
B601. randomly generating a plurality of sampling points in a sampling blank area;
B602. selecting a sampling point closest to a connecting line of the first node and the selected endpoint as a reference point, and acquiring a point which is obtained by moving the first node by a preset step length along the direction pointing to the reference point as a candidate expansion point;
B603. performing collision detection on the candidate expansion points;
B604. if the collision detection is qualified, taking the candidate expansion points as effective expansion points, and taking the effective expansion points as new nodes of the first path tree; if the collision detection is not acceptable, repeating the steps B601-B604.
According to the method, on one hand, the obtained path can be ensured to be reliably prevented from being blocked, and on the other hand, the path between the first node and the expansion point is more close to an ideal path due to the fact that the sampling point closest to the connecting line of the first node and the selected end point is taken as the reference point, so that the shorter obstacle avoidance path is more favorable to be finally obtained.
In step B601, a preset number of sampling points may be randomly generated, where the preset number may be set according to actual needs, for example, but not limited to, 5.
The preset step size in step B602 may be set according to actual needs.
Taking fig. 5 as an example, in step B602, assuming that the sampling point closest to the connecting line P0M1 between the first node and the selected endpoint is the point M3, the point M3 is taken as a reference point, the point obtained after the first node moves by a preset step length along the direction of p0→m3 is the point P1, and the point P1 is a candidate expansion point.
In some embodiments, step B603 comprises: setting the center of a circular area with the collision radius of the mobile device (preset according to the size of the mobile device) as the radius at a candidate expansion point, detecting whether the circular area has an intersection point with at least one obstacle area, if so, judging that the collision detection is unqualified, and if not, judging that the collision detection is qualified.
In other embodiments, step B603 includes: the geometric center of a collision area obtained after the outline of the mobile equipment is outwards expanded by a preset collision distance (which can be set according to actual needs) is arranged at a candidate expansion point, whether the collision area has an intersection point with at least one obstacle area or not is detected, if yes, the collision detection is judged to be unqualified, and if not, the collision detection is judged to be qualified.
In practical applications, there may not be a second line segment intersecting the first line segment, which means that the first line segment does not intersect all obstacle regions, and at this time, the second node may be directly used as the selected endpoint. Thus, in some embodiments, after step B2 and before step B3, further comprising:
B7. judging whether the first line segment intersects with at least one second line segment, if yes, turning to step B3 (i.e. sequentially executing steps B1, B2, B7, B3, B4, B5 and B6), and if not, taking the second node as a selected endpoint, turning to step B5 (i.e. sequentially executing steps B1, B2, B7, B5 and B6).
Preferably, the two path trees intersect, which means that the distance between the closest two nodes on the two path trees is smaller than a preset distance threshold. That is, as long as the distance between two nodes that are close on the two path trees is smaller than a preset distance threshold, it is determined that the two path trees intersect, and expansion of the nodes is stopped.
The initial path may be smoothed by any conventional smoothing method, and is not limited herein. For example, in some embodiments, the smoothing module 3 performs, when smoothing the initial path to obtain a final path:
And performing B spline smoothing on the initial path to obtain a final path.
As can be seen from the above, the bidirectional RRT path planning apparatus divides the map into an obstacle region and a plurality of blank regions according to the outline of the obstacle; the method comprises the steps that a starting point and a target point are respectively taken as first nodes of two path trees, a blank area where a sampling point is located is determined according to the outline of an obstacle area, sampling is carried out in the determined blank area, and nodes of the two path trees are alternately expanded until the two path trees intersect, so that an initial path is obtained; smoothing the initial path to obtain a final path; thus, the path planning efficiency can be improved. In particular, the following advantages are achieved:
1. the automation degree is high, and the planning process does not need human intervention;
2. the sampling is carried out in the selected blank area, so that the blind expansion problem caused by the random sampling (full-image random sampling) of the traditional RRT algorithm is solved, the sampling efficiency is improved, and the planning speed is increased;
3. the sampling blank area is selected by utilizing the profile information of the obstacle, so that the calculation is simple, the operation efficiency is high, and the instantaneity of the method is improved;
4. aiming at different scenes, the searching efficiency can be accelerated by adjusting the size of the preset step length, and the application range is wide;
5. B spline smoothing is carried out on the obtained initial path, so that a smooth overall path is obtained, and movement of the mobile equipment is facilitated.
Referring to fig. 3, fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the present application, where the electronic device includes: processor 301 and memory 302, the processor 301 and memory 302 being interconnected and in communication with each other by a communication bus 303 and/or other form of connection mechanism (not shown), the memory 302 storing a computer program executable by the processor 301, the processor 301 executing the computer program when the electronic device is running to perform the bi-directional RRT path planning method in any of the alternative implementations of the above embodiments to implement the following functions: dividing the map into an obstacle region and a plurality of blank regions according to the outline of the obstacle; the starting point and the target point are respectively taken as the first nodes of the two path trees, a blank area where the sampling point is located is determined according to the outline of the obstacle area, and sampling is carried out in the determined blank area, so that the nodes of the two path trees are alternately expanded until the two path trees intersect, and an initial path is obtained.
The embodiment of the present application provides a storage medium having a computer program stored thereon, which when executed by a processor, performs the bidirectional RRT path planning method in any of the alternative implementations of the foregoing embodiments, to implement the following functions: dividing the map into an obstacle region and a plurality of blank regions according to the outline of the obstacle; the starting point and the target point are respectively taken as the first nodes of the two path trees, a blank area where the sampling point is located is determined according to the outline of the obstacle area, and sampling is carried out in the determined blank area, so that the nodes of the two path trees are alternately expanded until the two path trees intersect, and an initial path is obtained. The storage medium may be implemented by any type of volatile or nonvolatile Memory device or combination thereof, such as static random access Memory (Static Random Access Memory, SRAM), electrically erasable Programmable Read-Only Memory (Electrically Erasable Programmable Read-Only Memory, EEPROM), erasable Programmable Read-Only Memory (Erasable Programmable Read Only Memory, EPROM), programmable Read-Only Memory (PROM), read-Only Memory (ROM), magnetic Memory, flash Memory, magnetic disk, or optical disk.
In the embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other manners. The above-described apparatus embodiments are merely illustrative, for example, the division of the units is merely a logical function division, and there may be other manners of division in actual implementation, and for example, multiple units or components may be combined or integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be through some communication interface, device or unit indirect coupling or communication connection, which may be in electrical, mechanical or other form.
Further, the units described as separate components may or may not be physically separate, and components shown as units may or may not be physical units, may be located in one place, or may be distributed over a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
Furthermore, functional modules in various embodiments of the present application may be integrated together to form a single portion, or each module may exist alone, or two or more modules may be integrated to form a single portion.
In this document, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions.
The foregoing is merely exemplary embodiments of the present application and is not intended to limit the scope of the present application, and various modifications and variations may be suggested to one skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.
Claims (8)
1. The bidirectional RRT path planning method is characterized by comprising the following steps:
A1. dividing the map into an obstacle region and a plurality of blank regions according to the outline of the obstacle;
A2. respectively taking a starting point and a target point as first nodes of two path trees, determining a blank area where a sampling point is located according to the outline of the obstacle area, sampling in the determined blank area, and alternately expanding nodes of the two path trees until the two path trees intersect to obtain an initial path;
A3. smoothing the initial path to obtain a final path;
The step A1 comprises the following steps:
taking the area occupied by the obstacle as the obstacle area;
establishing a plane coordinate system by taking a straight line passing through the starting point and the target point as an X axis and taking a straight line perpendicular to the X axis as a Y axis;
dividing a region other than the obstacle regions into a plurality of single communication regions by using an circumscribed line of each of the obstacle regions and an outline of each of the obstacle regions, and taking each of the single communication regions as one of the blank regions; the circumscribed line of the obstacle region passes through the X coordinate extreme point of the obstacle region and is parallel to the Y axis;
the step A2 comprises the following steps:
A201. taking the starting point and the target point as the first nodes of two path trees respectively;
A202. alternately taking one of the two path trees as a first path tree and the other path tree as a second path tree, so as to execute the following steps until the two path trees intersect:
B1. taking the latest node of the first path tree as a first node, and taking the node closest to the first node on the second path tree as a second node, and acquiring a connecting line of the first node and the second node as a first line segment;
B2. acquiring a connecting line between a Y-coordinate maximum point and a Y-coordinate minimum point of each barrier zone as a second line segment of the barrier zone;
B3. Acquiring two endpoints of the second line segment closest to the second node from the intersection point of the first line segment in the second line segment intersected with the first line segment, and taking the two endpoints as two candidate endpoints;
B4. selecting one of the two candidate endpoints as a selected endpoint, and minimizing the sum of the distance from the first node to the selected endpoint and the distance from the selected endpoint to the second node;
B5. determining one of said blank areas between said first node and said selected endpoint as a sampling blank area;
B6. determining an expansion point in the sampling blank area as a new node of the first path tree;
A203. and sequentially connecting the nodes of the two path trees to obtain the initial path.
2. The bi-directional RRT path planning method according to claim 1, wherein step B5 comprises:
B501. acquiring a set of the blank areas, through which connecting lines of the first node and the selected endpoint pass, as a first blank area set;
B502. acquiring a set of the blank areas adjacent to the blank area where the first node is located as a second blank area set;
B503. and acquiring an intersection of the first blank region set and the second blank region set as the sampling blank region.
3. The bi-directional RRT path planning method according to claim 1, wherein step B6 comprises:
B601. randomly generating a plurality of sampling points in the sampling blank area;
B602. selecting the sampling point closest to a connecting line of the first node and the selected endpoint as a reference point, and obtaining a point which is obtained after the first node moves by a preset step length along the direction pointing to the reference point as a candidate expansion point;
B603. performing collision detection on the candidate expansion points;
B604. if the collision detection is qualified, the candidate expansion points are taken as effective expansion points, and the effective expansion points are taken as new nodes of the first path tree; if the collision detection is not acceptable, repeating the steps B601-B604.
4. The bi-directional RRT path planning method of claim 1, wherein the intersection of two of said path trees means that the distance between the closest two nodes on both of said path trees is less than a predetermined distance threshold.
5. The bi-directional RRT path planning method according to claim 1, wherein step A3 comprises:
and performing B spline smoothing on the initial path to obtain a final path.
6. A bi-directional RRT path planning apparatus, comprising:
The dividing module is used for dividing the map into an obstacle area and a plurality of blank areas according to the outline of the obstacle;
the planning module is used for determining a blank area where a sampling point is located according to the outline of the obstacle area by taking a starting point and a target point as first nodes of two path trees respectively, and sampling in the determined blank area so as to alternately expand the nodes of the two path trees until the two path trees intersect, so that an initial path is obtained;
the smoothing processing module is used for carrying out smoothing processing on the initial path to obtain a final path;
the division module performs, when dividing the map into an obstacle region and a plurality of blank regions according to the outline of the obstacle:
taking the area occupied by the obstacle as the obstacle area;
establishing a plane coordinate system by taking a straight line passing through the starting point and the target point as an X axis and taking a straight line perpendicular to the X axis as a Y axis;
dividing a region other than the obstacle regions into a plurality of single communication regions by using an circumscribed line of each of the obstacle regions and an outline of each of the obstacle regions, and taking each of the single communication regions as one of the blank regions; the circumscribed line of the obstacle region passes through the X coordinate extreme point of the obstacle region and is parallel to the Y axis;
The planning module determines a blank area where a sampling point is located according to the outline of the obstacle area when the starting point and the target point are respectively taken as the first nodes of two path trees, and samples the blank area so as to alternately expand the nodes of the two path trees until the two path trees intersect, thereby obtaining an initial path, and executes the following steps:
taking the starting point and the target point as the first nodes of two path trees respectively;
alternately taking one of the two path trees as a first path tree and the other path tree as a second path tree, so as to execute the following steps until the two path trees intersect:
B1. taking the latest node of the first path tree as a first node, and taking the node closest to the first node on the second path tree as a second node, and acquiring a connecting line of the first node and the second node as a first line segment;
B2. acquiring a connecting line between a Y-coordinate maximum point and a Y-coordinate minimum point of each barrier zone as a second line segment of the barrier zone;
B3. acquiring two endpoints of the second line segment closest to the second node from the intersection point of the first line segment in the second line segment intersected with the first line segment, and taking the two endpoints as two candidate endpoints;
B4. Selecting one of the two candidate endpoints as a selected endpoint, and minimizing the sum of the distance from the first node to the selected endpoint and the distance from the selected endpoint to the second node;
B5. determining one of said blank areas between said first node and said selected endpoint as a sampling blank area;
B6. determining an expansion point in the sampling blank area as a new node of the first path tree;
and sequentially connecting the nodes of the two path trees to obtain the initial path.
7. An electronic device comprising a processor and a memory, the memory storing a computer program executable by the processor, when executing the computer program, running the steps of the bi-directional RRT path planning method of any one of claims 1-5.
8. A storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the bi-directional RRT path planning method of any of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310249471.5A CN115950439B (en) | 2023-03-15 | 2023-03-15 | Bidirectional RRT path planning method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310249471.5A CN115950439B (en) | 2023-03-15 | 2023-03-15 | Bidirectional RRT path planning method and device, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115950439A CN115950439A (en) | 2023-04-11 |
| CN115950439B true CN115950439B (en) | 2023-06-02 |
Family
ID=85891450
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310249471.5A Active CN115950439B (en) | 2023-03-15 | 2023-03-15 | Bidirectional RRT path planning method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115950439B (en) |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109990796A (en) * | 2019-04-23 | 2019-07-09 | 成都信息工程大学 | Intelligent vehicle paths planning method based on two-way extension random tree |
| CN110262473A (en) * | 2019-04-29 | 2019-09-20 | 上海交通大学 | A kind of unmanned boat automatic Collision Avoidance method based on improvement Bi-RRT algorithm |
| CN110275528A (en) * | 2019-06-04 | 2019-09-24 | 合肥工业大学 | For the method for optimizing route of RRT algorithm improvement |
| CN110497403A (en) * | 2019-08-05 | 2019-11-26 | 上海大学 | A kind of manipulator motion planning method improving two-way RRT algorithm |
| CN112393739A (en) * | 2020-10-29 | 2021-02-23 | 国网安徽省电力有限公司检修分公司 | Improved rapid search random tree path planning method in large-area environment |
| CN113064426A (en) * | 2021-03-17 | 2021-07-02 | 安徽工程大学 | Intelligent vehicle path planning method for improving bidirectional fast search random tree algorithm |
| WO2021143505A1 (en) * | 2020-01-17 | 2021-07-22 | 北京市商汤科技开发有限公司 | Path planning method and apparatus, and storage medium |
| CN113341984A (en) * | 2021-06-15 | 2021-09-03 | 桂林电子科技大学 | Robot path planning method and device based on improved RRT algorithm |
| CN113359746A (en) * | 2021-06-21 | 2021-09-07 | 桂林电子科技大学 | Path planning method and device based on improved bidirectional RRT and Dijkstra fusion algorithm |
| CN113485367A (en) * | 2021-08-06 | 2021-10-08 | 浙江工业大学 | Path planning method of multifunctional stage mobile robot |
| WO2021242215A1 (en) * | 2020-05-26 | 2021-12-02 | Edda Technology, Inc. | A robot path planning method with static and dynamic collision avoidance in an uncertain environment |
| CN114577217A (en) * | 2022-05-05 | 2022-06-03 | 季华实验室 | Route planning method, device, equipment and storage medium based on Von Lonouh graph |
| CN114593743A (en) * | 2022-03-02 | 2022-06-07 | 杭州华鲲云起信息技术有限公司 | Path planning method and device based on improved bidirectional RRT algorithm |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR102165437B1 (en) * | 2014-05-02 | 2020-10-14 | 한화디펜스 주식회사 | Path planning apparatus of mobile robot |
-
2023
- 2023-03-15 CN CN202310249471.5A patent/CN115950439B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109990796A (en) * | 2019-04-23 | 2019-07-09 | 成都信息工程大学 | Intelligent vehicle paths planning method based on two-way extension random tree |
| CN110262473A (en) * | 2019-04-29 | 2019-09-20 | 上海交通大学 | A kind of unmanned boat automatic Collision Avoidance method based on improvement Bi-RRT algorithm |
| CN110275528A (en) * | 2019-06-04 | 2019-09-24 | 合肥工业大学 | For the method for optimizing route of RRT algorithm improvement |
| CN110497403A (en) * | 2019-08-05 | 2019-11-26 | 上海大学 | A kind of manipulator motion planning method improving two-way RRT algorithm |
| WO2021143505A1 (en) * | 2020-01-17 | 2021-07-22 | 北京市商汤科技开发有限公司 | Path planning method and apparatus, and storage medium |
| WO2021242215A1 (en) * | 2020-05-26 | 2021-12-02 | Edda Technology, Inc. | A robot path planning method with static and dynamic collision avoidance in an uncertain environment |
| CN112393739A (en) * | 2020-10-29 | 2021-02-23 | 国网安徽省电力有限公司检修分公司 | Improved rapid search random tree path planning method in large-area environment |
| CN113064426A (en) * | 2021-03-17 | 2021-07-02 | 安徽工程大学 | Intelligent vehicle path planning method for improving bidirectional fast search random tree algorithm |
| CN113341984A (en) * | 2021-06-15 | 2021-09-03 | 桂林电子科技大学 | Robot path planning method and device based on improved RRT algorithm |
| CN113359746A (en) * | 2021-06-21 | 2021-09-07 | 桂林电子科技大学 | Path planning method and device based on improved bidirectional RRT and Dijkstra fusion algorithm |
| CN113485367A (en) * | 2021-08-06 | 2021-10-08 | 浙江工业大学 | Path planning method of multifunctional stage mobile robot |
| CN114593743A (en) * | 2022-03-02 | 2022-06-07 | 杭州华鲲云起信息技术有限公司 | Path planning method and device based on improved bidirectional RRT algorithm |
| CN114577217A (en) * | 2022-05-05 | 2022-06-03 | 季华实验室 | Route planning method, device, equipment and storage medium based on Von Lonouh graph |
Non-Patent Citations (3)
| Title |
|---|
| A_Path_Planning_Algorithm_based_on_Leading_Rapidly-exploring_Random_Trees;Yuan-Ting Fu等;2019 Internationl Automatic Cnontrol Conferenc3(CACS);1-6 * |
| 一种改进RRT算法在路径规划中的应用研究;成怡等;控制工程(第03期);161-165 * |
| 基于子目标搜索的机器人目标导向RRT路径规划算法;阮晓钢;周静;张晶晶;朱晓庆;;控制与决策(第10期);242-247 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115950439A (en) | 2023-04-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107898393B (en) | Block adjusting method and device for cleaning robot and robot | |
| Kallmann | Dynamic and robust local clearance triangulations | |
| CN108444490B (en) | Robot path planning method based on depth fusion of visible view and A-x algorithm | |
| CN101650189A (en) | Method for planning walking path and navigation method for avoiding dynamic barrier | |
| CN114266800B (en) | Method and system for generating multiple rectangular bounding boxes of plane graph | |
| CN112306067A (en) | Global path planning method and system | |
| CN113147739B (en) | Heuristic automatic parking method and device for unmanned vehicle | |
| CN113119115A (en) | Mechanical arm motion planning method and device, readable storage medium and mechanical arm | |
| CN114593743A (en) | Path planning method and device based on improved bidirectional RRT algorithm | |
| Hechenberger et al. | Online computation of euclidean shortest paths in two dimensions | |
| CN115950439B (en) | Bidirectional RRT path planning method and device, electronic equipment and storage medium | |
| CN113034515A (en) | Bounding box tree-based polygon clipping method, electronic device and storage medium | |
| CN112462403A (en) | Positioning method, positioning device, storage medium and electronic equipment | |
| CN116518977A (en) | Unmanned aerial vehicle path planning method, system and equipment | |
| CN113867371B (en) | Path planning method and electronic equipment | |
| CN115981311A (en) | Path planning method and system for complex pipeline maintenance robot | |
| CN115481268A (en) | Parallel line wall data identification method, device, equipment and storage medium | |
| CN112393739B (en) | Improved rapid search random tree path planning method in large-area environment | |
| CN112506203B (en) | Robot motion dynamic feedback method and system | |
| CN116135159A (en) | Three-dimensional path planning method, device, equipment and storage medium | |
| FI129592B (en) | Computer-aided modeling | |
| CN112237400B (en) | Method for area division, self-moving robot and computer storage medium | |
| CN117727023A (en) | Voxel block detection method, voxel block detection device, electronic equipment and storage medium | |
| CN113066148B (en) | Map data processing method, device, equipment and storage medium | |
| CN113221202B (en) | Method, system and equipment for determining small-line-segment knife compensation interference selfing point |
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 |