CN117516513A - Intelligent mower path planning method, device, equipment and storage medium - Google Patents
Intelligent mower path planning method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN117516513A CN117516513A CN202410022946.1A CN202410022946A CN117516513A CN 117516513 A CN117516513 A CN 117516513A CN 202410022946 A CN202410022946 A CN 202410022946A CN 117516513 A CN117516513 A CN 117516513A
- Authority
- CN
- China
- Prior art keywords
- intelligent mower
- path
- information
- position information
- camera
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 49
- 238000013136 deep learning model Methods 0.000 claims description 15
- 238000012549 training Methods 0.000 claims description 9
- 238000013135 deep learning Methods 0.000 claims description 4
- 238000010276 construction Methods 0.000 abstract description 11
- 238000013473 artificial intelligence Methods 0.000 abstract description 2
- 238000004891 communication Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 5
- 230000003287 optical effect Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 241000251468 Actinopterygii Species 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
Abstract
The application discloses an intelligent mower path planning method, device, equipment and storage medium, and relates to the technical field of artificial intelligence, wherein the method comprises the following steps: acquiring position information of a boundary line, wherein the boundary line refers to a boundary line between a mowed area and an unharked area; and planning a mowing path of the intelligent mower based on the position information. In the method, the situation of planning path deviation caused by inaccurate global map construction is avoided, and therefore accuracy of mowing path planning is improved.
Description
Technical Field
The application relates to the technical field of artificial intelligence, in particular to an intelligent mower path planning method, device, equipment and storage medium.
Background
Compared with the traditional mower, the automatic mower can automatically complete the mowing task, has the advantages of simple operation, low labor cost and the like, and has become a main development direction of the mower industry.
At present, an automatic mower mainly performs global map construction of a lawn area through Real-time kinematic (RTK) so as to plan a mowing path based on the global map. However, because the RTK technology constructs the global map through satellite positioning, under the condition that satellite positioning is interfered, the situation that the planned path is offset caused by inaccurate global map construction often occurs, so that the accuracy of the planning of the mowing path is low.
Disclosure of Invention
The utility model provides a main aim at provides an intelligent mower path planning method, device, equipment and storage medium, aims at solving because RTK technique passes through satellite positioning and builds global map, under the circumstances that satellite positioning receives the interference, often appears because of global map builds inaccurate circumstances that lead to planning route skew to lead to the problem that the planning of mowing route's rate of accuracy is low.
In order to achieve the above object, the present application provides an intelligent mower path planning method, which includes the following steps:
acquiring position information of a boundary line, wherein the boundary line refers to a boundary line between a mowed area and an unharked area;
and planning a mowing path of the intelligent mower based on the position information.
Optionally, the step of acquiring the position information of the dividing line includes:
after the target camera identifies the dividing line and collects the position information of the dividing line, the position information is obtained from the target camera, wherein the target camera comprises one or more of a depth camera, an RGB camera and a fish-eye camera.
Optionally, in the case that the target camera is a depth camera, the step of acquiring the position information of the dividing line further includes:
the method comprises the steps that after a depth camera takes a boundary line of a lawn area with a height difference larger than a preset value as a boundary line through height information and collects position information of the boundary line, the position information is obtained from the depth camera; the height information refers to information of the height of the lawn area acquired by the depth camera.
Optionally, in the case that the target camera is an RGB camera and a depth camera, the step of acquiring the position information of the dividing line further includes:
after an RGB camera identifies a boundary through a deep learning model and sends an image of the boundary to a depth camera, acquiring position information of the boundary in the image from the depth camera; the deep learning model is obtained by performing iterative training on a model to be trained through a deep learning algorithm, and the deep learning model can identify an object based on color information acquired by an RGB camera.
Optionally, the step of planning a mowing path of the intelligent mower based on the position information includes:
and taking the dividing line as a mowing path of the intelligent mower based on the position information, so that the intelligent mower can mow at the position corresponding to the position information.
Optionally, before the step of planning a mowing path of the intelligent mower based on the position information, the method comprises:
after an RGB camera recognizes an obstacle through a deep learning model and sends an image of the obstacle to the depth camera, acquiring distance information of the obstacle in the image from the depth camera, wherein the distance information comprises information of distances from a plurality of points on the edge of the obstacle to the intelligent mower;
the step of planning a mowing path of the intelligent mower based on the position information further comprises the following steps:
based on the position information, taking the dividing line as an initial path of the intelligent mower;
calculating the central position and the safety radius of the obstacle through a preset algorithm based on the distance information, wherein the safety radius is larger than the maximum radius of the obstacle;
and taking a section of arc curve path intersecting with the initial path as an avoidance path based on the central position and the safety radius, wherein the arc curve path takes the central position as a circle center and takes the safety radius as a radius.
Optionally, before the step of planning a mowing path of the intelligent mower based on the position information, the method further includes:
obtaining boundary information of a lawn area from an RGB camera, wherein the boundary information refers to information of a boundary line of the lawn area;
the step of planning a mowing path of the intelligent mower based on the position information further comprises the following steps:
and taking the boundary line in the lawn area as a mowing path of the intelligent mower based on the position information and the boundary information.
In addition, in order to achieve the above-mentioned purpose, the present application also provides an intelligent mower path planning device, the intelligent mower path planning device includes:
the device comprises an acquisition module, a control module and a control module, wherein the acquisition module is used for acquiring position information of a boundary line, wherein the boundary line refers to a boundary line of a mowed area and an unharked area;
and the planning module is used for planning a mowing path of the intelligent mower based on the position information.
In addition, in order to achieve the above object, the present application further provides an intelligent mower path planning apparatus, which is characterized in that the apparatus includes: the intelligent mower path planning system comprises a memory, a processor and an intelligent mower path planning program which is stored in the memory and can run on the processor, wherein the intelligent mower path planning program is configured to realize the steps of the intelligent mower path planning method.
In addition, in order to achieve the above object, the present application further provides a storage medium, wherein the storage medium stores an intelligent mower path planning program, and the intelligent mower path planning program implements the steps of the intelligent mower path planning method when executed by a processor.
Compared with the situation that in the related art, global map is built through satellite positioning due to RTK technology, and under the condition that satellite positioning is interfered, planned path deviation caused by inaccurate global map building often occurs, so that the accuracy of the planned mowing path is low, in the method, the position information of a dividing line is obtained, wherein the dividing line refers to the dividing line of a mowed area and an unharked area; and planning a mowing path of the intelligent mower based on the position information. It can be understood that in the application, by acquiring the position information of the boundary between the mowed area and the unharked area, the mowing path of the intelligent mower is planned, and only the information of the local map is required to be acquired, so that the situation that the planned path is deviated due to inaccurate global map construction is avoided, and the accuracy of mowing path planning is improved.
Drawings
FIG. 1 is a first flow chart of a first embodiment of a method for path planning for a smart mower of the present application;
FIG. 2 is a first schematic view of a first embodiment of a path planning method for an intelligent mower of the present application;
FIG. 3 is a second flow diagram of a second embodiment of a method of intelligent mower path planning according to the present application;
FIG. 4 is a second scenario schematic diagram of a second embodiment of a path planning method for an intelligent mower of the present application;
FIG. 5 is a third flow diagram of a third embodiment of a method of path planning for a smart mower of the present application;
FIG. 6 is a block diagram of a path planning apparatus for an intelligent mower of the present application;
fig. 7 is a schematic structural diagram of a hardware running environment according to an embodiment of the present application.
The realization, functional characteristics and advantages of the present application will be further described with reference to the embodiments, referring to the attached drawings.
Detailed Description
It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application.
Referring to fig. 1, fig. 1 is a first flow chart of a first embodiment of a path planning method for a smart mower of the present application.
In a first embodiment, the intelligent mower path planning method comprises the following steps:
step S10, acquiring position information of a boundary line, wherein the boundary line refers to a boundary line of a mowed area and an unharked area;
and step S20, planning a mowing path of the intelligent mower based on the position information.
The present embodiment aims at: by distinguishing the boundary between the mowed area and the unharked area, the mowing path of the intelligent mower is planned, only the information of the local map is required to be acquired, and the situation of deviation of the planned path caused by inaccurate global map construction is avoided, so that the accuracy of mowing path planning is improved.
The specific steps are set forth below:
step S10, acquiring position information of a boundary line, wherein the boundary line refers to a boundary line of a mowed area and an unharked area;
it should be noted that, the execution body of the embodiment is an intelligent mower path planning device, and the intelligent mower path planning device may be a device subordinate to the intelligent mower path planning device.
It is understood that the location information refers to position information and distance information of the parting line relative to the intelligent mower path planning apparatus, and the intelligent mower path planning apparatus obtains visual information (i.e., location information of the parting line) from a measuring apparatus, which can identify the parting line and collect location information of the parting line, and the measuring apparatus includes one or more of a depth camera, an RGB camera, and a fisheye camera.
For example, in the case where the measuring device is a depth camera and an RGB camera, the RGB camera acquires the color of the lawn area, and recognizes the boundary line of the lawn area where the color difference exists, taking the boundary line as a boundary line; the structured light depth camera (comprising a projector and a camera) actively emits infrared light invisible to naked eyes to the surface of the dividing line through the projector, then captures images of the surface of the dividing line through one or more cameras to acquire structured light images, sends the acquired data to the computing unit, and then calculates and acquires depth (distance) information of the dividing line through a triangulation principle to determine the position information of the dividing line.
In particular, with reference to fig. 2, the dividing line is located at the intersection of a cut lawn area and an uncut lawn area.
And step S20, planning a mowing path of the intelligent mower based on the position information.
It should be noted that, the intelligent mower path planning device performs visual navigation on the intelligent mower, that is, the intelligent mower path planning device can use the boundary between the mowed area and the unharred area as navigation through measurement devices (such as an RGB camera and a depth camera) based on the position information of the boundary, so as to guide the intelligent mower to mow on the path where the boundary is located.
In an implementation, the intelligent mower path planning apparatus plans a path for the intelligent mower to reach the parting line in the event that the intelligent mower is not on a path along the parting line.
For example, in the case that the intelligent mower is not on a path along the boundary line, the measuring device collects a target point on the boundary line closest to the intelligent mower, and the intelligent mower path planning device plans a straight path for reaching the boundary line with the current position as a starting point and the target point as an ending point.
It will be appreciated that the measuring device (e.g. RGB camera) may collect boundary information of a lawn area, the boundary information being information of boundary lines of the lawn area, and the intelligent mower path planning device plans a mowing path of the intelligent mower within the lawn area.
In a specific implementation, referring to fig. 2, the intelligent mower path planning apparatus plans a mowing path of the intelligent mower within an area surrounded by a boundary line of a lawn area.
It will be appreciated that in the event that no demarcation line is detected, the intelligent mower path planning apparatus feeds back to the user notification of completion of mowing.
In this embodiment, compared with the situation that in the related art, because the RTK technology constructs the global map through satellite positioning, when satellite positioning is interfered, the planned path is often deviated due to inaccurate global map construction, so that the accuracy of the planned mowing path is low, in this embodiment, the position information of a dividing line is obtained, where the dividing line refers to the dividing line of a mowed area and an unharked area; and planning a mowing path of the intelligent mower based on the position information. In this embodiment, by acquiring the position information of the boundary between the mowed area and the unharked area, the mowing path of the intelligent mower is planned, and only the information of the local map is required to be acquired, so that the situation that the planned path is deviated due to inaccurate global map construction is avoided, and the accuracy of mowing path planning is improved.
Further, referring to fig. 3, based on the above embodiment, a second embodiment of the present application is provided, in this embodiment, the intelligent mower path planning method further includes the following steps:
and step A1, after the target camera identifies the dividing line and acquires the position information of the dividing line, acquiring the position information from the target camera, wherein the target camera comprises one or more of a depth camera, an RGB camera and a fish-eye camera.
The object camera has the capability of identifying the dividing line and acquiring the position information of the dividing line, the depth camera can acquire the depth (distance) information from the dividing line to the camera, the RGB camera can acquire the color information of the lawn area by acquiring the colors of three color channels of red (R), green (G) and blue (B) which are overlapped with each other, and the fisheye camera can acquire the image of the lawn area in a wide viewing angle range (generally up to 220 degrees or 230 degrees).
It will be appreciated that in the case where the target camera is a depth camera, the depth camera may collect height information of different lawn areas and identify a boundary line by the collected height information, i.e. the boundary line of two lawn areas where there is a height difference is taken as the boundary line of a mowed area and an unharked area.
For example, when one of the lawn areas has a height h and the other lawn area has a height 2h, the depth camera recognizes the boundary between the two lawn areas as a parting line.
In an implementation, the depth camera may also collect location information of the demarcation line.
For example, referring to fig. 4, a binocular stereoscopic depth camera acquires left and right image information through left and right cameras and is based on left coordinates of a selected point on a boundary line in a left imageRight coordinates of selected point on boundary line in right image +.>Determining coordinates of a selected point on the demarcation line relative to the binocular stereoscopic depth camera, the base line distance B and the optical axes of the left and right cameras。
It can be appreciated that in the case where the target camera is an RGB camera, the RGB camera can recognize the boundary line through a deep learning model obtained by iteratively training a model to be trained through a deep learning algorithm.
For example, before recognizing the boundary, the user stores a training sample in the RGB camera or guides the RGB camera to collect the training sample (a sample of the boundary/obstacle/boundary line), the RGB camera acquires a state (i.e., a set of information of the recognized boundary/obstacle/boundary line) in the training sample through a preset model training device, selects an action (i.e., information of the recognized boundary/obstacle/boundary line, and compares the information of the recognized boundary/obstacle/boundary line with the information of the actual boundary/obstacle/boundary line), receives an enhancement signal (i.e., a comparison result) sent by the environment, wherein the enhancement signal is the overlapping degree of the information of the recognized boundary/obstacle/boundary line and the information of the actual boundary/obstacle/boundary line, and the RGB camera trains the model to be trained through the preset model training device so as to iterate the model to be trained in a direction with the overlapping degree of the boundary, and obtains the deep learning model when the overlapping degree of the boundary, the obstacle and the boundary line reach the preset value.
It will be appreciated that the target camera may also include multiple cameras of different types that share acquired information through an image.
For example, the RGB camera recognizes a boundary line, acquires an image including the boundary line, and transmits the image to the depth camera, which acquires position information of the boundary line based on the pattern.
In an implementation, two or more RGB cameras and/or fish eye cameras may generate depth (distance) information of the dividing line through a preset algorithm.
In this embodiment, compared to the situation that in the related art, because the RTK technology constructs the global map through satellite positioning, when satellite positioning is interfered, the planned path is often deviated due to inaccurate global map construction, so that the accuracy of the planned mowing path is low, in this embodiment, after the target camera identifies the dividing line and collects the position information of the dividing line, the position information is obtained from the target camera, where the target camera includes one or more of a depth camera, an RGB camera, and a fisheye camera, and the target camera has the capability of identifying the dividing line and collecting the position information of the dividing line. In this embodiment, the boundary line is identified by one or more of the depth camera, the RGB camera and the fisheye camera, and the position information of the boundary line is collected, so that the boundary line is accurately positioned, the situation that the planned path deviates is avoided, and the accuracy of the planning of the mowing path is improved.
Further, referring to fig. 5, based on the above embodiment, a third embodiment of the present application is provided, in this embodiment, the intelligent mower path planning method further includes the following steps:
step B1, taking the dividing line as an initial path of the intelligent mower based on the position information;
after taking the boundary line as an initial path of the intelligent mower, the intelligent mower path planning device informs an RGB camera to identify whether an obstacle exists on the initial path, the RGB camera identifies the obstacle through a deep learning model, the RGB camera sends an image of the obstacle to the depth camera when the obstacle exists, and the depth camera acquires distance information of the obstacle in the image, wherein the distance information comprises information of distances from a plurality of points on the edge of the obstacle to the intelligent mower.
For example, when the RGB camera recognizes an obstacle tree, the image of the tree is sent to a time-of-flight depth camera, the time-of-flight depth camera transmits continuous light pulses to each point on the edge of the tree corresponding to the image, the light reflected by the tree is received by a sensor, the time of flight is recorded, and the distance to the tree is calculated by the time of flight.
Step B2, calculating the central position and the safety radius of the obstacle through a preset algorithm based on the distance information, wherein the safety radius is larger than the maximum radius of the obstacle;
the intelligent mower path planning device calculates distances from a plurality of points on the edge of the obstacle to the intelligent mower through a preset algorithm to obtain the center position of the obstacle and a safety radius, wherein the safety radius is the sum of the maximum radius of the obstacle and a preset adding radius.
It can be appreciated that, in the case that an obstacle is identified as a person, the intelligent mower path planning device sends an alarm notification to the obstacle to notify the obstacle to avoid the intelligent mower, when the obstacle leaves the initial path, the path avoidance is not planned, the initial path is taken as a mowing path, and when the obstacle does not leave the mowing path, the path avoidance is continuously planned.
And B3, taking a section of arc curve path intersecting with the initial path as an avoidance path based on the central position and the safety radius, wherein the arc curve path takes the central position as a circle center and takes the safety radius as a radius.
The intelligent mower path planning device plans a section of arc curve path by taking the calculated center position of the obstacle as the center of a circle and taking the safety radius as the radius, and overlaps the arc curve path with the initial path to obtain a section of avoidance path connected with the initial path.
In this embodiment, compared to the case that in the related art, because the RTK technology constructs the global map through satellite positioning, in the case that satellite positioning is interfered, the situation that the planned path is offset due to inaccurate global map construction often occurs, so that the accuracy of the planned mowing path is low, in this embodiment, the boundary is used as the initial path of the intelligent mower based on the position information; calculating the central position and the safety radius of the obstacle through a preset algorithm based on the distance information, wherein the safety radius is larger than the maximum radius of the obstacle; and taking a section of arc curve path intersecting with the initial path as an avoidance path based on the central position and the safety radius, wherein the arc curve path takes the central position as a circle center and takes the safety radius as a radius. In this embodiment, an initial path is planned first, then information of an obstacle is acquired from a camera, and planning of an avoidance path is performed on the obstacle, so that the situation that a planned path is deviated due to inaccurate global map construction is avoided through local path planning, and the accuracy of the mowing path planning is improved.
In addition, the embodiment of the application also provides an intelligent mower path planning device, referring to fig. 6, the intelligent mower path planning device includes:
an acquisition module 10, configured to acquire location information of a boundary line, where the boundary line refers to a boundary line between a mowed area and an unharked area;
a planning module 20, configured to plan a mowing path of the intelligent mower based on the location information.
Optionally, the intelligent mower path planning device further includes:
and the target acquisition module is used for acquiring the position information from the target camera after the target camera recognizes the dividing line and acquires the position information of the dividing line, wherein the target camera comprises one or more of a depth camera, an RGB camera and a fish-eye camera.
Optionally, the intelligent mower path planning device further includes:
the depth acquisition module is used for acquiring the position information from the depth camera after the depth camera takes the boundary line of the lawn area with the height difference larger than a preset value as a boundary line through the height information and acquires the position information of the boundary line; the height information refers to information of the height of the lawn area acquired by the depth camera.
Optionally, the intelligent mower path planning device further includes:
the position acquisition module is used for acquiring the position information of the boundary in the image from the depth camera after the RGB camera recognizes the boundary through the deep learning model and sends the image of the boundary to the depth camera; the deep learning model is obtained by performing iterative training on a model to be trained through a deep learning algorithm, and the deep learning model can identify an object based on color information acquired by an RGB camera.
Optionally, the intelligent mower path planning device further includes:
and the path planning module is used for taking the dividing line as a mowing path of the intelligent mower based on the position information so that the intelligent mower can mow at the position corresponding to the position information.
Optionally, the intelligent mower path planning device further includes:
the obstacle recognition module is used for recognizing an obstacle through a deep learning model by the RGB camera, sending an image of the obstacle to the depth camera, and acquiring distance information of the obstacle in the image from the depth camera, wherein the distance information comprises information of distances from a plurality of points on the edge of the obstacle to the intelligent mower;
optionally, the intelligent mower path planning device further includes:
the initial path planning module is used for taking the dividing line as an initial path of the intelligent mower based on the position information;
the obstacle determining module is used for calculating the central position and the safety radius of the obstacle through a preset algorithm based on the distance information, wherein the safety radius is larger than the maximum radius of the obstacle;
the avoidance planning module is configured to take a section of arc curve path intersecting the initial path as a avoidance path based on the center position and the safety radius, where the arc curve path uses the center position as a center and uses the safety radius as a radius.
Optionally, the intelligent mower path planning device further includes:
the boundary acquisition module is used for acquiring boundary information of the lawn area from the RGB camera, wherein the boundary information refers to information of a boundary line of the lawn area;
optionally, the intelligent mower path planning device further includes:
and the mowing path planning module is used for taking the dividing line in the lawn area as a mowing path of the intelligent mower based on the position information and the boundary information.
In this embodiment, position information of a boundary line is acquired, wherein the boundary line refers to a boundary line between a mowed area and an unharked area; and planning a mowing path of the intelligent mower based on the position information. In this embodiment, by acquiring the position information of the boundary between the mowed area and the unharked area, the mowing path of the intelligent mower is planned, and only the information of the local map is required to be acquired, so that the situation that the planned path is deviated due to inaccurate global map construction is avoided, and the accuracy of mowing path planning is improved.
The specific implementation manner of the intelligent mower path planning device is basically the same as the above-mentioned embodiments of the intelligent mower path planning method, and is not repeated here.
Referring to fig. 7, fig. 7 is a schematic structural diagram of an intelligent mower path planning apparatus in a hardware running environment according to an embodiment of the present application.
As shown in fig. 7, the intelligent mower path planning apparatus may include: a processor 1001, such as a central processing unit (Central Processing Unit, CPU), a communication bus 1002, a user interface 1003, a network interface 1004, a memory 1005. Wherein the communication bus 1002 is used to enable connected communication between these components. The user interface 1003 may include a Display, an input unit such as a Keyboard (Keyboard), and the optional user interface 1003 may further include a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a WIreless interface (e.g., a WIreless-FIdelity (WI-FI) interface). The Memory 1005 may be a high-speed random access Memory (Random Access Memory, RAM) Memory or a stable nonvolatile Memory (NVM), such as a disk Memory. The memory 1005 may also optionally be a storage device separate from the processor 1001 described above.
It will be appreciated by those skilled in the art that the configuration shown in fig. 7 does not constitute a limitation of the intelligent mower path planning apparatus and may include more or fewer components than illustrated, or may combine certain components, or a different arrangement of components.
As shown in fig. 7, an operating system, a network communication module, a user interface module, and a smart mower path planning program may be included in a memory 1005, which is a type of computer storage medium.
The operating system is a program for managing and controlling the intelligent mower path planning device and software resources, and supports the operation of a network communication module, a user interface module, the intelligent mower path planning program and other programs or software, wherein the network communication module is used for managing and controlling the network interface 1002; the user interface module is used to manage and control the user interface 1003.
In the intelligent mower path planning apparatus shown in fig. 7, the intelligent mower path planning apparatus invokes the intelligent mower path planning program stored in the memory 1005 through the processor 1001, to implement the steps of the intelligent mower path planning method described in any one of the above.
The specific implementation manner of the intelligent mower path planning device is basically the same as the above-mentioned embodiments of the intelligent mower path planning method, and will not be repeated here.
In addition, the embodiment of the invention also provides a storage medium, and the storage medium stores one or more programs, and the one or more programs can be further executed by one or more processors to implement the steps of the intelligent mower path planning method according to any one of the above.
The specific implementation manner of the storage medium is basically the same as the above embodiments of the intelligent mower path planning method, and will not be repeated here.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.
The foregoing embodiment numbers of the present application are merely for describing, and do not represent advantages or disadvantages of the embodiments.
From the above description of embodiments, it will be clear to a person skilled in the art that the above embodiment method may be implemented by means of software plus a necessary general hardware platform, but may of course also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk) as described above, including several instructions for causing a terminal device (which may be a mobile phone, a computer, a server, or a network device, etc.) to perform the method described in the embodiments of the present application.
The foregoing description is only of the preferred embodiments of the present application, and is not intended to limit the scope of the claims, and all equivalent structures or equivalent processes using the descriptions and drawings of the present application, or direct or indirect application in other related technical fields are included in the scope of the claims of the present application.
Claims (10)
1. The intelligent mower path planning method is characterized by comprising the following steps of:
acquiring position information of a boundary line, wherein the boundary line refers to a boundary line between a mowed area and an unharked area;
and planning a mowing path of the intelligent mower based on the position information.
2. The intelligent mower path planning method according to claim 1, wherein said step of acquiring the positional information of the dividing line comprises:
after the target camera identifies the dividing line and collects the position information of the dividing line, the position information is obtained from the target camera, wherein the target camera comprises one or more of a depth camera, an RGB camera and a fish-eye camera.
3. The intelligent mower path planning method according to claim 2, wherein in the case where the target camera is a depth camera, the step of acquiring the positional information of the dividing line further comprises:
the method comprises the steps that after a depth camera takes a boundary line of a lawn area with a height difference larger than a preset value as a boundary line through height information and collects position information of the boundary line, the position information is obtained from the depth camera; the height information refers to information of the height of the lawn area acquired by the depth camera.
4. The intelligent mower path planning method according to claim 2, wherein in the case where the target camera is an RGB camera and a depth camera, the step of acquiring the positional information of the dividing line further comprises:
after an RGB camera identifies a boundary through a deep learning model and sends an image of the boundary to a depth camera, acquiring position information of the boundary in the image from the depth camera; the deep learning model is obtained by performing iterative training on a model to be trained through a deep learning algorithm, and the deep learning model can identify an object based on color information acquired by an RGB camera.
5. The intelligent mower path planning method according to any one of claims 1 to 4, wherein the step of planning a mowing path of the intelligent mower based on the position information comprises:
and taking the dividing line as a mowing path of the intelligent mower based on the position information, so that the intelligent mower can mow at the position corresponding to the position information.
6. The intelligent mower path planning method according to any one of claims 1 to 4, wherein before the step of planning a mowing path of the intelligent mower based on the position information, the method comprises:
after an RGB camera recognizes an obstacle through a deep learning model and sends an image of the obstacle to the depth camera, acquiring distance information of the obstacle in the image from the depth camera, wherein the distance information comprises information of distances from a plurality of points on the edge of the obstacle to the intelligent mower;
the step of planning a mowing path of the intelligent mower based on the position information further comprises the following steps:
based on the position information, taking the dividing line as an initial path of the intelligent mower;
calculating the central position and the safety radius of the obstacle through a preset algorithm based on the distance information, wherein the safety radius is larger than the maximum radius of the obstacle;
and taking a section of arc curve path intersecting with the initial path as an avoidance path based on the central position and the safety radius, wherein the arc curve path takes the central position as a circle center and takes the safety radius as a radius.
7. The intelligent mower path planning method according to any one of claims 1 to 4, wherein before the step of planning a mowing path of the intelligent mower based on the position information, further comprising:
obtaining boundary information of a lawn area from an RGB camera, wherein the boundary information refers to information of a boundary line of the lawn area;
the step of planning a mowing path of the intelligent mower based on the position information further comprises the following steps:
and taking the boundary line in the lawn area as a mowing path of the intelligent mower based on the position information and the boundary information.
8. An intelligent mower path planning apparatus, characterized in that the intelligent mower path planning apparatus comprises:
the device comprises an acquisition module, a control module and a control module, wherein the acquisition module is used for acquiring position information of a boundary line, wherein the boundary line refers to a boundary line of a mowed area and an unharked area;
and the planning module is used for planning a mowing path of the intelligent mower based on the position information.
9. An intelligent mower path planning apparatus, the apparatus comprising: a memory, a processor, and an intelligent mower path planning program stored on the memory and operable on the processor, the intelligent mower path planning program configured to implement the steps of the intelligent mower path planning method of any one of claims 1 to 7.
10. A storage medium having stored thereon an intelligent mower path planning program which when executed by a processor performs the steps of the intelligent mower path planning method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410022946.1A CN117516513A (en) | 2024-01-08 | 2024-01-08 | Intelligent mower path planning method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410022946.1A CN117516513A (en) | 2024-01-08 | 2024-01-08 | Intelligent mower path planning method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117516513A true CN117516513A (en) | 2024-02-06 |
Family
ID=89746171
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410022946.1A Pending CN117516513A (en) | 2024-01-08 | 2024-01-08 | Intelligent mower path planning method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117516513A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102081752A (en) * | 2011-01-27 | 2011-06-01 | 西北工业大学 | Dynamic flight path planning method based on adaptive mutation genetic algorithm |
| CN110481543A (en) * | 2019-08-22 | 2019-11-22 | 宝能汽车有限公司 | A kind of method and device for coping with vehicle running collision |
| CN114440908A (en) * | 2020-10-31 | 2022-05-06 | 华为技术有限公司 | Method and device for planning vehicle driving path, intelligent vehicle and storage medium |
| CN114863381A (en) * | 2021-01-20 | 2022-08-05 | 未岚大陆(北京)科技有限公司 | Recognition method and device for mowing area, electronic equipment and storage medium |
| CN115053689A (en) * | 2022-06-29 | 2022-09-16 | 松灵机器人(深圳)有限公司 | Intelligent obstacle avoidance method and device, mowing robot and storage medium |
| CN117115774A (en) * | 2023-10-23 | 2023-11-24 | 锐驰激光(深圳)有限公司 | Lawn boundary identification method, device, equipment and storage medium |
-
2024
- 2024-01-08 CN CN202410022946.1A patent/CN117516513A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102081752A (en) * | 2011-01-27 | 2011-06-01 | 西北工业大学 | Dynamic flight path planning method based on adaptive mutation genetic algorithm |
| CN110481543A (en) * | 2019-08-22 | 2019-11-22 | 宝能汽车有限公司 | A kind of method and device for coping with vehicle running collision |
| CN114440908A (en) * | 2020-10-31 | 2022-05-06 | 华为技术有限公司 | Method and device for planning vehicle driving path, intelligent vehicle and storage medium |
| CN114863381A (en) * | 2021-01-20 | 2022-08-05 | 未岚大陆(北京)科技有限公司 | Recognition method and device for mowing area, electronic equipment and storage medium |
| CN115053689A (en) * | 2022-06-29 | 2022-09-16 | 松灵机器人(深圳)有限公司 | Intelligent obstacle avoidance method and device, mowing robot and storage medium |
| CN117115774A (en) * | 2023-10-23 | 2023-11-24 | 锐驰激光(深圳)有限公司 | Lawn boundary identification method, device, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9639960B1 (en) | Systems and methods for UAV property assessment, data capture and reporting | |
| EP3805981A1 (en) | Method and apparatus for planning operation in target region, storage medium, and processor | |
| EP3186685B1 (en) | Three-dimensional elevation modeling for use in operating agricultural vehicles | |
| CN102103663B (en) | Ward visit service robot system and target searching method thereof | |
| US9429945B2 (en) | Surveying areas using a radar system and an unmanned aerial vehicle | |
| CN107561547B (en) | Method, device and system for measuring distance from power transmission line to target object | |
| CN106662452A (en) | Robot lawnmower mapping | |
| CN109443345B (en) | Positioning method and system for monitoring navigation | |
| CN107972027B (en) | Robot positioning method and device and robot | |
| CN106647738A (en) | Method and system for determining docking path of automated guided vehicle, and automated guided vehicle | |
| CN115597659B (en) | Intelligent safety management and control method for transformer substation | |
| CN113296495A (en) | Path forming method and device for self-moving equipment and automatic working system | |
| WO2023005384A1 (en) | Repositioning method and device for mobile equipment | |
| CN115659452B (en) | Intelligent patrol method, intelligent patrol system and computer readable storage medium | |
| CN110291480A (en) | A kind of unmanned plane test method, equipment and storage medium | |
| CN108521809A (en) | Obstacle information reminding method, system, unit and recording medium | |
| CN202010257U (en) | Ward round robot system based on Bayesian theory | |
| CN112686951A (en) | Method, device, terminal and storage medium for determining robot position | |
| CN112033390A (en) | Robot navigation deviation rectifying method, device, equipment and computer readable storage medium | |
| CN113454558A (en) | Obstacle detection method and device, unmanned aerial vehicle and storage medium | |
| CN117516513A (en) | Intelligent mower path planning method, device, equipment and storage medium | |
| KR102133898B1 (en) | Autonomous flight system for agricultural disease control and method thereof | |
| EP4206849A1 (en) | Autonomous mobile device and method for controlling same | |
| CN114637332A (en) | Pesticide spraying method and system for unmanned aerial vehicle and readable storage medium | |
| CN116164776A (en) | Quality evaluation method, electronic equipment and system for robot navigation data |
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 |