CN117073688B - Coverage path planning method based on multi-layer cost map - Google Patents
Coverage path planning method based on multi-layer cost map Download PDFInfo
- Publication number
- CN117073688B CN117073688B CN202311330268.7A CN202311330268A CN117073688B CN 117073688 B CN117073688 B CN 117073688B CN 202311330268 A CN202311330268 A CN 202311330268A CN 117073688 B CN117073688 B CN 117073688B
- Authority
- CN
- China
- Prior art keywords
- map
- gradient
- robot
- layer
- cost map
- 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 29
- 238000005457 optimization Methods 0.000 claims abstract description 10
- 238000010845 search algorithm Methods 0.000 claims abstract description 5
- 238000007781 pre-processing Methods 0.000 claims abstract description 4
- 238000006243 chemical reaction Methods 0.000 claims description 6
- 238000012876 topography Methods 0.000 claims description 4
- 239000006185 dispersion Substances 0.000 claims description 3
- 230000003746 surface roughness Effects 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 6
- 239000000463 material Substances 0.000 description 4
- 230000008569 process Effects 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000003796 beauty Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 230000008635 plant growth Effects 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
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
- G01C21/20—Instruments for performing navigational calculations
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 relates to the technical field of application of mowing robots, in particular to a coverage path planning method based on a multi-layer cost map. A coverage path planning method based on a multi-layer cost map comprises the following steps of S1, generating the multi-layer cost map: the multi-layer map comprises a roughness cost map and a gradient cost map; s2, generating a traversable cost map; s3, establishing a boundary; s4, preprocessing a multi-layer cost map; s5, path planning. According to the invention, a cost map with related roughness and gradient is built according to the point cloud map data acquired by the robot, namely a multi-layer cost map, the maximum running roughness and gradient of the robot are combined to obtain an area which the robot cannot pass through, a traversable cost map is built, a traversable cost map is taken as a basic layer planning path, an optimization function which aims at gradient and turning angle is found by utilizing a heuristic search algorithm, and an optimal path is found, so that the mowing robot can run efficiently and safe running is ensured.
Description
Technical Field
The invention relates to the technical field of application of mowing robots, in particular to a coverage path planning method based on a multi-layer cost map.
Background
In the agricultural and horticultural fields, mowing is a key element in maintaining the beauty of the landscape and plant growth. Autonomous navigation lawn mowing robots have been widely used in recent years for efficiency and reduced labor costs. However, path planning for a lawnmower robot still faces a series of challenges in complex three-dimensional environments, such as gradients, undulations, irregular terrain, and the presence of obstacles.
Current path planning methods for mowing robots are mainly based on traditional grid map and obstacle avoidance algorithms, and generally adopt a single cost function to evaluate the path, and neglect various information of the terrain. Thus, under complex terrain, these methods tend to be difficult to create efficient and safe mowing paths. Furthermore, existing approaches are not sufficiently balanced in terms of multiple objectives, such as maximum coverage, minimum energy consumption, minimum number of turns, etc., resulting in a failure to obtain an overall optimized path.
Disclosure of Invention
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention may be realized and attained by the structure particularly pointed out in the written description and the appended drawings.
The invention aims to overcome the defects, and provides a coverage path planning method based on a multi-layer cost map, which is characterized in that a cost map related to roughness and gradient is built according to point cloud map data acquired by laser of a mowing robot, namely the multi-layer cost map, and a region which cannot be traversed by the robot is obtained by combining the maximum running roughness and gradient of the robot, a traversable cost map is built, a traversable cost map is taken as a basic layer planning path, an optimization function which aims at gradient and turning angle is found by utilizing a heuristic search algorithm, and an optimal path is found, so that the mowing robot can efficiently run and simultaneously safe running is ensured.
The invention provides a coverage path planning method based on a multi-layer cost map, which comprises the following steps:
s1, generating a multi-layer cost map: generating a roughness cost map and a gradient cost map based on point cloud map data related to grasslands acquired by the mowing robot, and constructing a conversion function between the point cloud map data and the multi-layer cost map;
s2, generating a traversable cost map: based on the roughness cost map and the gradient cost map, establishing a cost function, generating a traversable cost map, and planning a path by taking the traversable cost map layer as a basic layer;
s3, establishing a boundary: the mowing robot walks around the boundary of the grassland for one circle, the pose of the mowing robot is tracked in real time, the inside of a polygon formed by the track of the mowing robot is set as a passable area, the outside of the polygon is set as a forbidden area, a virtual boundary map layer is created, a boundary is established, and the boundary is fitted into a passable cost map;
s4, preprocessing a multi-layer cost map: the resolution ratio in the original multi-layer cost map is the unit grid size, and the resolution ratio of the grid map is adjusted according to the actual size of the mowing robot so that the grid size of the multi-layer cost map is adapted to the size of the mowing robot;
s5, path planning: and (3) path planning is carried out on the traversable layer map with the boundary, meanwhile, information in the roughness cost map and the gradient cost map is called, a multi-objective optimization function with the gradient and the turning angle as targets is constructed, and an optimal coverage path is obtained.
In some embodiments, in step S1, the topographical features of the lawn are represented by roughness and slope, which are converted from point cloud map data acquired by the lawn mowing robot;
roughness, i.e., the degree of surface roughness of the terrain, is represented by the degree of dispersion in the point cloud map unit and calculated by the least square method; the gradient layer fits the height information in the point cloud map data into a plane to represent the specific transfer function of roughness and gradient as follows:
a i ,b i ,c i ＝LSM({x i ,y i ,z i )∈B r (π i )})
wherein S is slope (pi) represents the gradient of a place in the map, S rough (pi) represents roughness, a gradient is calculated by fitting height information in the point cloud map data to a plane ax+by+c=z by a least square method, a i ,b i ,c i To fit coefficients of a plane, x, y, z are information of each axis in the point cloud map, LSM (x i ,y i ,z i ) Namely, the least square method is simplified formula, B r (π i ) Substituting each axis data of point cloud information in the point cloud map into a specific conversion function of roughness and gradient to calculate a for the point cloud information set around a certain place in the map i ,b i ,c i Is a value of (2); sigma (sigma) i For estimating the height deviation of the ground from the fitted plane, and thus calculating the roughness.
In some embodiments, in step S2, the traversable map is generated by analyzing the lawn topography and the robot kinematic model, finding the maximum gradient and the maximum roughness that the mowing robot can walk, setting the part of the map that the mowing robot cannot traverse as an obstacle, and setting the rest as a traversable area.
In some embodiments, in step S2, the specific cost function is as follows:
wherein alpha is 1 And alpha 2 Is a weight of sum 1, s max And r max Representing the maximum gradient and maximum roughness that the mowing robot can traverse, i.e., the threshold that causes the robot to tip over, s and r represent some local area in the mapSlope and roughness of (2);
tra represents the traversability of the robot at a certain place in the map, the range of the Tra value is [0,1], and when the Tra value at the certain place in the terrain does not belong to [0,1], the terrain is marked as an obstacle, namely the traversable object is not obtained.
In some embodiments, in step S4, assuming that the original map size is mx×my and the robot size is model_size, the adjusted resolution should be:
row＝mx/model_size
col＝my/model_size
where row represents the resolution in the x-axis direction of the adjusted map, and col represents the resolution in the y-axis direction.
In some embodiments, in step S5, a cost function of full coverage path planning loss of the mowing robot is defined first, and then a heuristic search algorithm is used to calculate a mode of minimizing the cost of the cost to mow, which relates to a multi-objective optimization function with the objective of gradient and turning angle as follows:
E(p,n)＝d r (p,n)+N(n)+E slope
E slope ＝max(mg(μcosω+sinα)·‖d r ‖,0)
wherein p= (x, y, θ) represents the current attitude of the robot, θ represents the current attitude angle of the robot, n represents the position to be reached next, and the rotation distance d r Measured in pi/4 units; the function N (N) represents 8 neighbors Nb around N 8 (n) the number of locations not yet accessed, which function produces tracking behavior; k represents Nb 8 The members in (N), L is the set of visited locations, |kL| represents whether N surrounding neighbors have been visited, ω is the gradient tilt angle, mg is the robot weight, moveThe coefficient of friction μ between the surface and the all-terrain surface is set to 0.2, α being the slope angle there in the map.
In some embodiments, if there are unvisited neighbors in the 8 neighbors of p, then one of them is selected as the next robot pose; if all neighbors around p have been visited, then the potential next pose n is extracted from the set of unvisited grid cells.
By adopting the technical scheme, the invention has the beneficial effects that:
according to the invention, a multi-layer cost grid map is built through point cloud map data, targets such as gradient and turning angle are combined, a multi-target optimization function is built, so that a collision-free coverage type path with the largest coverage area is obtained, and meanwhile, the energy loss and turning times are minimized, so that the mowing robot can perform efficient and safe mowing operation in an unstructured environment of a complex obstacle, and meanwhile, relatively optimal path planning is obtained under the condition of taking topography fluctuation into consideration.
Compared with a single cost function, the multi-layer cost map established by the invention can more accurately depict the terrain features, improves the accuracy and feasibility of path planning, introduces a multi-objective optimization function, and ensures that the path planning is more comprehensive and comprehensive, so that the multi-layer cost map is weighted among different targets to obtain a better path, is suitable for complex obstacles and uneven terrains, and provides strong support for autonomous planning of the mowing robot in various environments.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.
It is apparent that these and other objects of the present invention will become more apparent from the following detailed description of the preferred embodiments, which is to be read in connection with the accompanying drawings and figures.
The foregoing and other objects, features and advantages of the invention will be apparent from the following more particular description of the preferred embodiments, as illustrated in the accompanying drawings.
Drawings
The accompanying drawings are included to provide a further understanding of the invention, and are incorporated in and constitute a part of this specification, illustrate the invention and together with the embodiments of the invention, serve to explain the invention, without limitation to the invention.
In the drawings, like parts are designated with like reference numerals and are illustrated schematically and are not necessarily drawn to scale.
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are only one or several embodiments of the invention, and that other drawings can be obtained according to such drawings without inventive effort to a person skilled in the art.
FIG. 1 is a schematic overall flow diagram of path planning for a robot lawnmower according to some embodiments of the invention;
FIG. 2 is a schematic diagram of a multi-layer cost map structure in some embodiments of the invention;
fig. 3 is a schematic diagram illustrating boundary establishment of a mowing robot according to some embodiments of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be further described in detail with reference to the following detailed description. It should be understood that the detailed description is presented merely to illustrate the invention, and is not intended to limit the invention.
In addition, in the description of the present invention, it should be understood that the terms "center", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", "axial", "radial", "circumferential", etc. indicate orientations or positional relationships based on the drawings, are merely for convenience in describing the present invention and simplifying the description, and do not indicate or imply that the devices or elements referred to must have a specific orientation, be configured and operated in a specific orientation, and thus should not be construed as limiting the present invention.
In the present invention, unless explicitly specified and limited otherwise, the terms "mounted," "connected," "secured," and the like are to be construed broadly, and may be, for example, fixedly connected, detachably connected, or integrally formed; can be directly connected or indirectly connected through an intermediate medium, and can be communicated with the inside of two elements or the interaction relationship of the two elements. However, it is noted that direct connection indicates that the two bodies connected together do not form a connection relationship through a transition structure, but are connected together to form a whole through a connection structure. The specific meaning of the above terms in the present invention can be understood by those of ordinary skill in the art according to the specific circumstances.
In the present invention, unless expressly stated or limited otherwise, a first feature "up" or "down" a second feature may be the first and second features in direct contact, or the first and second features in indirect contact via an intervening medium. In the description of the present specification, a description referring to terms "one embodiment," "some embodiments," "examples," "specific examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms are not necessarily directed to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
Referring to fig. 1-3, fig. 1 is a schematic overall flow diagram of path planning for a robot lawnmower according to some embodiments of the invention; FIG. 2 is a schematic diagram of a multi-layer cost map structure in some embodiments of the invention; fig. 3 is a schematic diagram illustrating boundary establishment of a mowing robot according to some embodiments of the present invention.
According to some embodiments of the present invention, the present invention provides a coverage path planning method based on a multi-layer cost map, including:
s1, generating a multi-layer cost map: generating a roughness cost map and a gradient cost map based on point cloud map data related to grasslands acquired by the mowing robot, and constructing a conversion function between the point cloud map data and the multi-layer cost map;
in the S1 step, the terrain features of the grasslands are represented by roughness and gradient, the roughness and the gradient are converted from point cloud map data acquired by the mowing robot, a roughness cost map reflects the unevenness of the earth surface, a gradient cost map reveals the gradient change of the terrain, and the complexity of the terrain and the passing difficulty of the robot can be obtained by integrating the information; the acquisition of the point cloud map data can refer to the prior art, and in the prior art, a laser radar or a camera is usually arranged on a robot to acquire the point cloud information of the terrain;
roughness, i.e., the degree of surface roughness of the terrain, is represented by the degree of dispersion in the point cloud map unit and calculated by the least square method; the gradient layer fits the height information in the point cloud map data into a plane to represent the specific transfer function of roughness and gradient as follows:
a i ,b i ,c i ＝LSM({x i ,y i ,z i )∈B r (π i )})
wherein S is slope (pi) represents the gradient of a place in the map, S rough (pi) represents roughness, a gradient is calculated by fitting height information in the point cloud map data to a plane ax+by+c=z by a least square method, a i ,b i ,c i To fit coefficients of a plane, x, y, z are information of each axis in the point cloud map, LSM (x i ,y i ,z i ) Namely, isThe least square method simplifies the formula, B r (π i ) Substituting each axis data of point cloud information in the point cloud map into a specific conversion function of roughness and gradient to calculate a for the point cloud information set around a certain place in the map i ,b i ,c i Is a value of (2); sigma (sigma) i For estimating the height deviation of the ground from the fitted plane, and thus calculating the roughness.
S2, generating a traversable cost map: based on the roughness cost map and the gradient cost map, establishing a cost function, generating a traversable cost map, and planning a path by taking the traversable cost map layer as a basic layer;
in the step S2, as shown in fig. 2, the grassland topography and the robot kinematic model are analyzed to find the maximum gradient and the maximum roughness that the mowing robot can walk, the part of the map that the mowing robot cannot pass through is set as an obstacle, the rest part is set as a passable area, and a passable map is generated;
specifically, the robot kinematic model is in the prior art, and in the actual application process, the forms and the traversing capacities of different types of mowing robots are different, so that the obtained maximum walkable gradient and the maximum roughness are also different, and the robot kinematic model is combined with the actual robot structure, and is not described in detail herein;
the specific cost function is as follows:
wherein alpha is 1 And alpha 2 Is a weight of sum 1, s max And r max The maximum gradient and the maximum roughness that the mowing robot can traverse are represented, namely, the critical value causing the robot to tip over, and s and r represent the gradient and the roughness of a certain local area in the map;
tra represents the traversability of a robot at a certain position in a map, the range of the Tra value is [0,1], when the Tra value at a certain position in the terrain does not belong to [0,1], the terrain is marked as an obstacle, namely the traversability is impossible, when the Tra value is smaller, the terrain is flat, the Tra value represents the terrain is rough, in the actual application process, the Tra value is specifically set according to a specific robot, and the Tra value is provided with a parameter file reference and can be set according to the maximum gradient and flatness that different robots can climb over.
S3, establishing a boundary: the mowing robot walks around the boundary of the grassland for one circle, the pose of the mowing robot is tracked in real time, as shown in fig. 3, the inside of a polygon formed by the track of the mowing robot is set as a passable area, the outside of the polygon is set as a forbidden area, a virtual boundary map layer is created, a boundary is established, and the boundary is fitted into a passable cost map;
specifically, the pose tracking of the mowing robot is realized through the IMU, and acceleration, angular speed, direction and the like can be obtained by the IMU, so that support is provided for the operation of the mowing robot.
S4, preprocessing a multi-layer cost map: the resolution ratio in the original multi-layer cost map is the unit grid size, and the resolution ratio of the grid map is adjusted according to the actual size of the mowing robot so that the grid size of the multi-layer cost map is adapted to the size of the mowing robot;
in step S4, assuming that the original map size is mx×my and the robot size is model_size, the adjusted resolution should be:
row＝mx/model_size
col＝my/model_size
the row represents the resolution of the adjusted map in the x-axis direction, the col represents the resolution of the adjusted map in the y-axis direction, and the resolution of the grid map is adjusted according to the size of the mowing robot, so that a path can be planned more accurately.
S5, path planning: path planning is carried out on the traversable layer map with the boundary, meanwhile, information in the roughness cost map and the gradient cost map is called, a multi-objective optimization function taking gradient and turning angle as targets is constructed, and an optimal coverage path is obtained;
in step S5, firstly, defining a cost function of the full coverage path planning loss of the mowing robot, and then, calculating a mode of minimizing the cost by using a heuristic search algorithm to mow, wherein the multi-objective optimization function aiming at the gradient and the turning angle is specifically as follows:
E(p,n)＝d r (p,n)+N(n)+E slope
E slope ＝max(mg(μcosω+sinα)·‖d r ‖,0)
wherein p= (x, y, θ) represents the current attitude of the robot, θ represents the current attitude angle of the robot, n represents the position to be reached next, and the rotation distance d r Measured in pi/4 units; the function N (N) represents 8 neighbors Nb around N 8 (n) the number of locations not yet accessed, which function produces tracking behavior; k represents Nb 8 The member of (N), L is the set of visited locations, |k N l| represents whether the neighbor around N has been visited, ω is the inclination of the gradient, mg is the weight of the robot, the coefficient of friction μ between the moving surface and the all-terrain surface is set to 0.2, α is the gradient angle there in the map;
if the 8 neighbors of the p have unviewed neighbors, selecting one of the neighbors as the next robot gesture; if all neighbors around p have been visited, then the potential next pose n is extracted from the set of unvisited grid cells.
It is to be understood that the disclosed embodiments are not limited to the specific process steps or materials disclosed herein, but are intended to extend to equivalents of such features as would be understood by one of ordinary skill in the relevant arts. It is also to be understood that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting.
Reference in the specification to "an embodiment" means that a particular feature, or characteristic, described in connection with the embodiment is included in at least one embodiment of the invention. Thus, appearances of the phrase or "an embodiment" in various places throughout this specification are not necessarily all referring to the same embodiment.
Furthermore, the described features or characteristics may be combined in any other suitable manner in one or more embodiments. In the above description, certain specific details are provided, such as thicknesses, numbers, etc., to provide a thorough understanding of embodiments of the invention. One skilled in the relevant art will recognize, however, that the invention can be practiced without one or more of the specific details, or with other methods, components, materials, etc.
Claims (5)
1. A coverage path planning method based on a multi-layer cost map is characterized by comprising the following steps of
S1, generating a multi-layer cost map: generating a roughness cost map and a gradient cost map based on point cloud map data related to grasslands acquired by the mowing robot, and constructing a conversion function between the point cloud map data and the multi-layer cost map;
the terrain features of the grasslands are represented by roughness and gradient, and the roughness and the gradient are converted from point cloud map data acquired by the mowing robot;
roughness, i.e., the degree of surface roughness of the terrain, is represented by the degree of dispersion in the point cloud map unit and calculated by the least square method; the gradient layer fits the height information in the point cloud map data into a plane to represent the specific transfer function of roughness and gradient as follows:
a i ,b i ,c i ＝LSM({x i ,y i ,z i )∈B r (π i )})
wherein S is slope (pi) represents the gradient of a place in the map, S rough (pi) represents roughness, a gradient is calculated by fitting height information in the point cloud map data to a plane ax+by+c=z by a least square method, a i ,b i ,c i To fit coefficients of a plane, x, y, z are information of each axis in the point cloud map, LSM (x i ,y i ,z i ) Namely, the least square method is simplified formula, B r (π i ) Substituting each axis data of point cloud information in the point cloud map into a specific conversion function of roughness and gradient to calculate a for the point cloud information set around a certain place in the map i ,b i ,c i Is a value of (2); sigma (sigma) i The method comprises the steps of estimating the height deviation of the ground and a fitting plane, so as to calculate roughness;
s2, generating a traversable cost map: based on the roughness cost map and the gradient cost map, establishing a cost function, generating a traversable cost map, and planning a path by taking the traversable cost map layer as a basic layer;
s3, establishing a boundary: the mowing robot walks around the boundary of the grassland for one circle, the pose of the mowing robot is tracked in real time, the inside of a polygon formed by the track of the mowing robot is set as a passable area, the outside of the polygon is set as a forbidden area, a virtual boundary map layer is created, a boundary is established, and the boundary is fitted into a passable cost map;
s4, preprocessing a multi-layer cost map: the resolution ratio in the original multi-layer cost map is the unit grid size, and the resolution ratio of the grid map is adjusted according to the actual size of the mowing robot so that the grid size of the multi-layer cost map is adapted to the size of the mowing robot;
s5, path planning: path planning is carried out on the traversable layer map with the boundary, meanwhile, information in the roughness cost map and the gradient cost map is called, a multi-objective optimization function taking gradient and turning angle as targets is constructed, and an optimal coverage path is obtained;
firstly, defining a full-coverage path planning loss cost function of a mowing robot, and then calculating a mode of minimizing the cost of the mowing robot by utilizing a heuristic search algorithm, wherein a multi-objective optimization function aiming at a gradient and a turning angle is specifically as follows:
E(p,n)＝d r (p,n)+N(n)+E slope
E slope ＝max(mg(μcosω+sinα)·‖d r ‖,0)
wherein p= (x, y, θ) represents the current attitude of the robot, θ represents the current attitude angle of the robot, n represents the position to be reached next, and the rotation distance d r Measured in pi/4 units; the function N (N) represents 8 neighbors Nb around N 8 (n) the number of locations not yet accessed, which function produces tracking behavior; k represents Nb 8 The member in (N), L is the set of visited locations, |k N l| indicates whether the neighbor around N has been visited, ω is the inclination of the gradient, mg is the weight of the robot, and the coefficient of friction μ between the moving surface and the all-terrain surface is set to 0.2, α is the gradient angle there in the map.
2. The coverage path planning method based on the multi-layer cost map according to claim 1, wherein in the step S2, the traversable map is generated by analyzing the grassland topography and the robot kinematics model, searching the maximum gradient and the maximum roughness that the mowing robot can walk, setting the part of the map that the mowing robot cannot traverse as an obstacle, and the rest as a traversable area.
3. The coverage path planning method based on a multi-layer cost map according to claim 2, wherein in step S2, a specific cost function is as follows:
wherein alpha is 1 And alpha 2 Is a weight of sum 1, s max And r max The maximum gradient and the maximum roughness that the mowing robot can traverse are represented, namely, the critical value causing the robot to tip over, and s and r represent the gradient and the roughness of a certain local area in the map;
tra represents the traversability of the robot at a certain place in the map, the range of the Tra value is [0,1], and when the Tra value at the certain place in the terrain does not belong to [0,1], the terrain is marked as an obstacle, namely the traversable object is not obtained.
4. The coverage path planning method based on the multi-layer cost map according to claim 1, wherein in step S4, assuming that the original map size is mx_my and the robot size is model_size, the adjusted resolution shall be:
row＝mx/model_size
col＝my/model_size
where row represents the resolution in the x-axis direction of the adjusted map, and col represents the resolution in the y-axis direction.
5. The multi-layer cost map-based coverage path planning method of claim 1, wherein if there are unvisited neighbors in the 8 neighbors of p, one of them is selected as the next robot pose; if all neighbors around p have been visited, then the potential next pose n is extracted from the set of unvisited grid cells.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311330268.7A CN117073688B (en) | 2023-10-16 | 2023-10-16 | Coverage path planning method based on multi-layer cost map |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311330268.7A CN117073688B (en) | 2023-10-16 | 2023-10-16 | Coverage path planning method based on multi-layer cost map |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117073688A CN117073688A (en) | 2023-11-17 |
| CN117073688B true CN117073688B (en) | 2024-03-29 |
Family
ID=88717474
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311330268.7A Active CN117073688B (en) | 2023-10-16 | 2023-10-16 | Coverage path planning method based on multi-layer cost map |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117073688B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117593900B (en) * | 2024-01-16 | 2024-05-14 | 浙江爱特电子技术股份有限公司 | Pre-hospital first-aid scheduling method and system |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108444488A (en) * | 2018-02-05 | 2018-08-24 | 天津大学 | Based on etc. steps sample A* algorithms unmanned local paths planning method |
| CN110398964A (en) * | 2019-07-16 | 2019-11-01 | 浙江大学 | A kind of low energy loss robot complete coverage path planning method and system |
| CN111046846A (en) * | 2019-12-27 | 2020-04-21 | 长安大学 | Method for judging passing ability of obstacle in front of robot |
| CN111096138A (en) * | 2019-12-30 | 2020-05-05 | 中电海康集团有限公司 | UWB-based mowing robot working boundary establishing and identifying system and method |
| CN111982129A (en) * | 2020-08-24 | 2020-11-24 | 哈尔滨工业大学 | Comprehensive global path planning method based on lunar surface digital elevation map |
| CN112015183A (en) * | 2020-09-08 | 2020-12-01 | 安徽工程大学 | Obstacle avoidance method for mobile robot in terrain with concave-convex features under constraint of energy consumption |
| CN112113573A (en) * | 2020-09-18 | 2020-12-22 | 武汉理工大学 | Planning method for coverage path of single unmanned measurement boat |
| CN113126613A (en) * | 2019-12-30 | 2021-07-16 | 南京德朔实业有限公司 | Intelligent mowing system and autonomous mapping method thereof |
| CN113821025A (en) * | 2021-08-24 | 2021-12-21 | 贵州电网有限责任公司 | Mobile robot path planning method for optimizing heuristic function through neural network |
| CN115185266A (en) * | 2022-06-14 | 2022-10-14 | 重庆大学 | Robot control method and system based on terrain trafficability |
| CN115562265A (en) * | 2022-09-29 | 2023-01-03 | 哈尔滨理工大学 | Mobile robot path planning method based on improved A-x algorithm |
| CN115628748A (en) * | 2022-10-23 | 2023-01-20 | 东南大学 | Improved Q-learning path planning method based on hierarchical mixed cost map |
| WO2023125512A1 (en) * | 2021-12-31 | 2023-07-06 | 丰疆智能(深圳)有限公司 | Navigation path planning method and apparatus, and storage medium |
-
2023
- 2023-10-16 CN CN202311330268.7A patent/CN117073688B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108444488A (en) * | 2018-02-05 | 2018-08-24 | 天津大学 | Based on etc. steps sample A* algorithms unmanned local paths planning method |
| CN110398964A (en) * | 2019-07-16 | 2019-11-01 | 浙江大学 | A kind of low energy loss robot complete coverage path planning method and system |
| CN111046846A (en) * | 2019-12-27 | 2020-04-21 | 长安大学 | Method for judging passing ability of obstacle in front of robot |
| CN113126613A (en) * | 2019-12-30 | 2021-07-16 | 南京德朔实业有限公司 | Intelligent mowing system and autonomous mapping method thereof |
| CN111096138A (en) * | 2019-12-30 | 2020-05-05 | 中电海康集团有限公司 | UWB-based mowing robot working boundary establishing and identifying system and method |
| CN111982129A (en) * | 2020-08-24 | 2020-11-24 | 哈尔滨工业大学 | Comprehensive global path planning method based on lunar surface digital elevation map |
| CN112015183A (en) * | 2020-09-08 | 2020-12-01 | 安徽工程大学 | Obstacle avoidance method for mobile robot in terrain with concave-convex features under constraint of energy consumption |
| CN112113573A (en) * | 2020-09-18 | 2020-12-22 | 武汉理工大学 | Planning method for coverage path of single unmanned measurement boat |
| CN113821025A (en) * | 2021-08-24 | 2021-12-21 | 贵州电网有限责任公司 | Mobile robot path planning method for optimizing heuristic function through neural network |
| WO2023125512A1 (en) * | 2021-12-31 | 2023-07-06 | 丰疆智能(深圳)有限公司 | Navigation path planning method and apparatus, and storage medium |
| CN115185266A (en) * | 2022-06-14 | 2022-10-14 | 重庆大学 | Robot control method and system based on terrain trafficability |
| CN115562265A (en) * | 2022-09-29 | 2023-01-03 | 哈尔滨理工大学 | Mobile robot path planning method based on improved A-x algorithm |
| CN115628748A (en) * | 2022-10-23 | 2023-01-20 | 东南大学 | Improved Q-learning path planning method based on hierarchical mixed cost map |
Non-Patent Citations (2)
| Title |
|---|
| Traversability-Based RRT* for Planetary Rover Path Planning in Rough Terrain with LIDAR Point Cloud Data;Reiya Takemura等;《Journal of Robotics and Mechatronics》;第29卷(第5期);第838-846页 * |
| 非结构化场景下地面无人平台环境感知及三维路径规划研究;张旋;《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》(第1期);第C032-399页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117073688A (en) | 2023-11-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117073688B (en) | Coverage path planning method based on multi-layer cost map | |
| Vidal et al. | Pursuit-evasion games with unmanned ground and aerial vehicles | |
| US7272474B1 (en) | Method and system for estimating navigability of terrain | |
| US11579618B2 (en) | Coverage planner | |
| CN114442621A (en) | Autonomous exploration and mapping system based on quadruped robot | |
| Usher et al. | Visual servoing of a car-like vehicle-an application of omnidirectional vision | |
| Zhang et al. | Fast active aerial exploration for traversable path finding of ground robots in unknown environments | |
| Gangadharan et al. | Ant colony optimization and firefly algorithms for robotic motion planning in dynamic environments | |
| Li et al. | Hybrid filtering framework based robust localization for industrial vehicles | |
| Höffmann et al. | Coverage path planning and precise localization for autonomous lawn mowers | |
| Liu et al. | 3D path planning in threat environment based on fuzzy logic | |
| Okada et al. | Exploration and observation planning for 3D indoor mapping | |
| Singh et al. | Autonomous cross-country navigation using stereo vision | |
| CN117289301A (en) | Air-ground unmanned platform collaborative path planning method under unknown off-road scene | |
| Wei et al. | Energy-efficient path planning for ground robots by and combining air and ground measurements | |
| CN115808933A (en) | Unmanned aerial vehicle path planning method based on quantum seagull algorithm | |
| Selkäinaho | Adaptive autonomous navigation of mobile robots in unknown environments | |
| EP4175455B1 (en) | Autonomous machine having vision system for navigation and method of using same | |
| Fong et al. | Representing a 3-d environment with a 2 1/2-d map structure | |
| Liang et al. | An Accurate Visual Navigation Method for Wheeled Robot in Unstructured Outdoor Environment Based on Virtual Navigation Line | |
| Bao et al. | Research on trajectory planning and control system of general mobile platform for Mountain Orchard | |
| Yao et al. | Autonomous navigation and adaptive path planning in dynamic greenhouse environments utilizing improved LeGO‐LOAM and OpenPlanner algorithms | |
| Zhang et al. | Vision-based leader vehicle trajectory tracking for multiple agricultural vehicles | |
| Dou et al. | SLAM Algorithm Based on Heterogeneous Sensor Data Fusion | |
| CN117896672A (en) | Cross-domain multi-unmanned platform relative positioning and navigation system and method |
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 |