CN117873054A - Unmanned method and system for intelligent harvester - Google Patents
Unmanned method and system for intelligent harvester Download PDFInfo
- Publication number
- CN117873054A CN117873054A CN202311611219.0A CN202311611219A CN117873054A CN 117873054 A CN117873054 A CN 117873054A CN 202311611219 A CN202311611219 A CN 202311611219A CN 117873054 A CN117873054 A CN 117873054A
- Authority
- CN
- China
- Prior art keywords
- harvester
- rice
- intelligent
- land
- intelligent harvester
- 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 22
- 241000209094 Oryza Species 0.000 claims abstract description 131
- 235000007164 Oryza sativa Nutrition 0.000 claims abstract description 131
- 235000009566 rice Nutrition 0.000 claims abstract description 131
- 238000005520 cutting process Methods 0.000 claims abstract description 33
- 238000005096 rolling process Methods 0.000 claims abstract description 26
- 230000008569 process Effects 0.000 claims abstract description 4
- 238000003306 harvesting Methods 0.000 claims description 25
- 230000000007 visual effect Effects 0.000 claims description 19
- 238000007726 management method Methods 0.000 claims description 18
- 238000009434 installation Methods 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 8
- 238000005259 measurement Methods 0.000 claims description 7
- 238000013459 approach Methods 0.000 claims description 6
- 238000007373 indentation Methods 0.000 claims description 5
- 230000003993 interaction Effects 0.000 claims description 4
- 238000012544 monitoring process Methods 0.000 claims description 4
- 230000002093 peripheral effect Effects 0.000 claims description 4
- 238000013519 translation Methods 0.000 claims description 3
- 230000004888 barrier function Effects 0.000 claims description 2
- 230000001172 regenerating effect Effects 0.000 description 13
- 238000004590 computer program Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 6
- 238000011160 research Methods 0.000 description 4
- 238000003860 storage Methods 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012271 agricultural production Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 230000005674 electromagnetic induction Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 244000037666 field crops Species 0.000 description 1
- 230000006698 induction Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- A—HUMAN NECESSITIES
- A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
- A01D—HARVESTING; MOWING
- A01D45/00—Harvesting of standing crops
- A01D45/04—Harvesting of standing crops of rice
Landscapes
- Life Sciences & Earth Sciences (AREA)
- Environmental Sciences (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
- Guiding Agricultural Machines (AREA)
Abstract
The invention provides an unmanned method and system of an intelligent harvester, which execute an operation instruction, identify crops to be harvested and stubble cutting surfaces according to an acquired operation front image, and control the transverse deviation and heading deviation of the intelligent harvester relative to the stubble cutting surfaces so that one side of a header is always aligned with the stubble cutting surfaces; identifying the height of the rice piles, the spacing between the rice piles and the rolling rate of the rice piles in the operated area according to the acquired operation rear image, controlling the height of a header according to feedback of the height of the rice piles, and controlling the transverse deviation and the heading deviation of the intelligent harvester according to the spacing between the rice piles and the rolling rate of the rice piles; in the operation process, RTK-GNSS positioning information and machine vision positioning information are acquired, and the RTK-GNSS positioning information and the machine vision positioning information are fused, and the fused positioning information is used as the positioning information of the intelligent harvester. The invention combines the machine vision positioning system and the RTK-GNSS positioning system, can improve the accuracy of positioning information, can realize obstacle avoidance of the harvester and reduce the rolling rate of rice piles.
Description
Technical Field
The invention belongs to the technical field of unmanned operation, and particularly relates to an unmanned operation method and system of an intelligent harvester.
Background
The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art.
Related research of unmanned agricultural machinery is earlier, and one scheme is to lay induction cable in advance in the farmland, detects the relative position of agricultural machinery relative to the cable that has been laid in advance based on the electromagnetic induction sensor on the agricultural machinery to this is feedback control vehicle steering to realize the agricultural machinery autopilot. This kind of mode needs to reform transform the farmland, and the cost is higher, is difficult to popularize. In another scheme, marks are arranged on the ground boundary, the transverse distance between the agricultural machine and the ground boundary is measured through a mechanical structure, so that deviation of the agricultural machine relative to a working path is obtained, and steering of the vehicle is controlled through feedback. The method needs to install marks on the boundaries of the agricultural machinery in advance, has complex measuring mechanism and higher cost, and is inconvenient to popularize. The two schemes have good precision when the agricultural machinery runs at a lower speed, and the path tracking precision can be reduced when the agricultural machinery runs at a higher speed.
With the development of global positioning navigation technology, the research of automatic driving agricultural machinery based on satellite positioning navigation has also made a certain progress.
The harvester is used as an important machine for harvesting operation and widely applied to agricultural production, so that the production efficiency is improved, and the labor intensity of farmers is greatly reduced. The intelligent driving of the harvester has become a research hotspot of general concern in all communities, and the accurate identification of unmanned paths of the harvester is a key for realizing autonomous navigation and positioning of the harvester. For a harvester, not only is the problem of autonomous walking solved to realize intelligent driving, but also the requirement of harvesting operation must be met, and not only accurate positioning signals are needed, but also the intelligent driving is closely related to the characteristics of field crops. Therefore, the purely satellite unmanned means cannot meet the requirement of autonomous navigation of the harvester, and the research on unmanned problems based on crop information feedback is significant.
Disclosure of Invention
In order to solve the problems, the invention provides an unmanned method and system for an intelligent harvester, and the unmanned method and system for the intelligent harvester are combined with a machine vision positioning system and a high-precision RTK-GNSS positioning system, so that the accuracy of positioning information can be improved, obstacle avoidance of the harvester can be realized, the rolling rate of rice piles can be reduced, and the height of the rice piles can be accurately controlled.
According to some embodiments, the present invention employs the following technical solutions:
an intelligent unmanned method of a harvester, comprising the following steps:
controlling the intelligent harvester to travel to an initial position of a working path, and enabling one side of a header of the intelligent harvester to be aligned with a stubble cutting surface;
executing an operation instruction, wherein the operation instruction comprises a planned operation path of a whole harvesting land and a land turning and steering path based on the harvesting land parameter information and the harvester operation parameter information;
according to the acquired operation front image, identifying crops to be harvested and stubble cutting surfaces, and controlling the transverse deviation and heading deviation of the intelligent harvester relative to the stubble cutting surfaces so that one side of the header is always aligned with the stubble cutting surfaces;
identifying the height of the rice piles, the spacing between the rice piles and the rolling rate of the rice piles in the operated area according to the acquired operation rear image, controlling the height of a header according to feedback of the height of the rice piles, and controlling the transverse deviation and the heading deviation of the intelligent harvester according to the spacing between the rice piles and the rolling rate of the rice piles;
in the operation process, RTK-GNSS positioning information and machine vision positioning information are acquired, the RTK-GNSS positioning information and the machine vision positioning information are fused, and the fused positioning information is used as the positioning information of the intelligent harvester;
when the cutting machine advances to the boundary of the land, the cutting table is controlled to ascend, the harvesting operation is stopped, and the turning and steering operation is carried out according to the turning and steering path of the land;
repeating the operation steps until the operation instruction is completed.
As an alternative embodiment, during the operation, when the header of the intelligent harvester approaches the crop to be harvested by a preset distance, the header is controlled to descend to a preset height, the harvesting operation is started, and otherwise, the header is controlled to ascend to a preset height, and the harvesting operation is stopped.
As an alternative implementation mode, when the turning operation is carried out, the peripheral visual image of the intelligent harvester is obtained, the peripheral environment and the obstacle avoidance object are identified according to the visual image, and the obstacle avoidance object is ensured to be avoided when the intelligent harvester turns.
Alternatively, the machine vision positioning information is the main if the RTK-GNSS positioning information is not available during the operation.
Alternatively, the post-job image is acquired at set time period intervals.
As an alternative implementation mode, after the rice pile targets in the operated area are identified, measuring the row spacing of rice piles between two adjacent rice piles and the number and width of the rice piles in the width of a header, combining the identified rice pile targets in the operated area with the width of the travelling indentation of the intelligent harvester, calculating the rolling rate of the rice piles, controlling the transverse deviation and the heading deviation of the intelligent harvester when the rolling rate of the rice piles exceeds a preset threshold value, enabling the travelling indentation width of the intelligent harvester to be smaller, and controlling the intelligent harvester to travel in the row spacing of the rice piles when the width of the travelling part of the intelligent harvester is smaller than the row spacing of the rice piles.
An intelligent unmanned system of a harvester, comprising:
the operation management terminal system is used for managing land block information and intelligent harvester parameter information, generating an operation instruction comprising an operation path of harvesting land block and a land turning and steering path, monitoring and tracking the intelligent harvester, and carrying out information interaction between the intelligent harvester and the main controller;
the RTK-GNSS positioning system is used for providing RTK-GNSS positioning information;
the machine vision system is used for providing machine vision positioning information, acquiring an operation front image, an operation rear image and an intelligent harvester surrounding image, identifying crops to be harvested and stubble cutting surfaces, identifying the height of rice piles, the row spacing of the rice piles and the rolling rate of the rice piles in an operated area, and identifying surrounding environment and barrier information;
and the main controller is in information interaction with each system and is used for controlling the running and operation states of the intelligent harvester according to the operation instructions, the positioning information and the identification results.
As an alternative embodiment, the machine vision positioning system includes a lift platform mounted on top of the intelligent harvester, a rotatable pan-tilt mounted on the lift platform, and a depth of sense camera mounted on the pan-tilt.
As a further embodiment, the depth-of-sense camera includes a camera unit, an inertial measurement unit for detecting rotation and translation of three axes, and a processing unit;
the camera unit is used for acquiring visual images;
the processing unit is used for identifying a land area and obstacle avoidance objects, an unworked area, an operated area and a boundary area in the visual image according to the visual image and combining land parameter information, and identifying crops to be harvested and stubble cutting surfaces in the unworked area.
As an alternative embodiment, the job management terminal system includes a job parameter management module, a land parcel information management module, a job path planning module, and a remote control module, wherein:
the operation parameter management module is used for managing the size parameter, the header height parameter and the width parameter of the intelligent harvester, and the machine track width parameter, the antenna installation position parameter, the actual depth camera installation position parameter, the running speed parameter and the steering angle parameter;
the land information management module is used for managing land parameters, including key point coordinates of land boundaries, obstacle region calibration, land crop types and crop height calibration;
the operation path planning module is used for planning an operation path and a land turning and steering path of the whole harvesting land based on the harvesting land parameter information and the harvester operation parameter information;
the remote control module is used for being connected with the main controller to realize remote control of machine running and operation.
As an alternative embodiment, the RTK-GNSS positioning system includes a reference station and a mobile station, the reference station is disposed at a fixed point of the plot, the mobile station includes antennas disposed on the left and right sides of the intelligent harvester, and the mobile station is disposed on the intelligent harvester, so that the position coordinates of the midpoint of the two antennas are used as the position of the intelligent harvester.
Compared with the prior art, the invention has the beneficial effects that:
the invention is based on real-time tracking control of a machine vision positioning system and a high-precision RTK-GNSS positioning system. Because the data frequency of the RTK-GNSS positioning system is often not high, the machine vision positioning system is used as the main positioning information source at present in the time interval when the RTK-GNSS positioning system does not output positioning information until the RTK-GNSS positioning system outputs new positioning data. And when the RTK-GNSS positioning system outputs positioning information, the positioning information provided by the machine vision positioning system is fused with the positioning information provided by the RTK-GNSS positioning system, so that the accuracy of the positioning information is improved.
The invention can rotate 360 degrees by using a sense depth camera, adjust a pitch angle, acquire clear visual images around a harvester, identify a paddy field area and obstacle avoidance objects in the visual images by combining paddy field parameter information, identify an unworked area, an operated area and a boundary area based on the paddy field area, identify crops to be harvested and stubble cutting surfaces in the unworked area, and identify information such as a height of a rice pile, a line spacing of the rice pile, a rolling rate of the rice pile and the like in the operated area. And the height of the header is controlled by the feedback according to the height feedback of the rice piles in the identified working area, and the transverse deviation and the course deviation of the harvester are controlled by the feedback according to the line spacing of the rice piles and the rolling rate of the rice piles, so that the obstacle avoidance of the intelligent rice harvester and the precise control of the rolling rate of the rice piles and the height of the rice piles are realized.
In order to make the above objects, features and advantages of the present invention more comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the invention.
FIG. 1 is a system installation schematic of one embodiment;
FIG. 2 is a system installation schematic of another embodiment;
FIG. 3 is an identification height schematic of another embodiment;
the harvester comprises a harvester body, a header body, a turntable, a third-dimension depth camera, an antenna, a lifting platform and a second third-dimension depth camera, wherein the harvester body comprises the harvester body, the header body, the turntable, the camera body, the third-dimension depth camera, the antenna, the lifting platform and the second third-dimension depth camera.
Detailed Description
The invention will be further described with reference to the drawings and examples.
It should be noted that the following detailed description is illustrative and is intended to provide further explanation of the invention. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of exemplary embodiments according to the present invention. As used herein, the singular is also intended to include the plural unless the context clearly indicates otherwise, and furthermore, it is to be understood that the terms "comprises" and/or "comprising" when used in this specification are taken to specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof.
Example 1
As shown in fig. 1, in this embodiment, a rice harvester is used as an application object, and a detailed description will be made. But not representative, the solution of the invention can be used only in the context of a ratoon harvester.
An intelligent ratoon harvester unmanned system comprises a user operation management terminal system, a main controller, an RTK-GNSS positioning system and a machine vision positioning system. The user operation management terminal system comprises a rice harvester 1, an operation parameter management module, a paddy field land parcel information management module, an operation path planning module, a monitoring and track display realization module and a remote control module.
The function of each system or module is described below.
The operation parameter management module of the regenerative rice harvester comprises a length, width, height and wheelbase size parameter of the machine, a ground clearance height parameter of the header 2, a width parameter of the header 2, a crawler width parameter of the machine, an installation position parameter of the antenna 5, an installation position parameter of the depth camera 4, a running speed parameter, a steering angle parameter and the like.
The paddy field land information management module is used for managing paddy field land parameters, including key point coordinates of paddy field land boundaries, obstacle area calibration, paddy field land crop types and crop height calibration. In addition, the paddy field land parcel parameter information can be permanently used after being calibrated once, so that the uploading and downloading functions of land parcel information are realized, the land parcel information can be directly used by downloading the pre-calibrated land parcel information through a cloud server without calibrating the land parcel information on a plurality of terminals.
The operation path planning module plans the operation path and the edge turning and steering path of the whole paddy field based on the paddy field parameter information and the operation parameter information of the regenerative rice harvester, transmits the operation path and the edge turning and steering path to the main controller to execute automatic driving, and utilizes the machine vision positioning system and the high-precision RTK-GNSS positioning system to track and control in real time.
The monitoring and track display module is used for displaying the running state of the machine, the data of each sensor, the real-time track, images and the like on the user terminal.
The remote control module is used for enabling a user to remotely control the machine to run and work through the user terminal.
The RTK-GNSS positioning system is used for providing RTK-GNSS positioning information of the rice harvester. The R30/R60 Beidou GNSS high-precision differential positioning (RTK-GNSS) equipment is selected. Wherein R30 is a single-antenna high-precision positioning receiver which is used as a reference station for differential positioning and is arranged at a fixed point near a working site. R60 is a dual antenna 5 positioning directional receiver, which is a differentially positioned mobile station, mounted with two antennas 5 and a radio station on a rice harvester to be positioned.
In the present embodiment, two antennas 5 of the mobile station are installed on the upper roof of the middle of the left and right sides of the rice harvester, and the position coordinates of the midpoints of the installation positions of the two antennas 5 of the mobile station are measured as the positions of the rice harvester 1. The reference station communicates with the mobile station via a radio station.
In the embodiment, the plane positioning precision of the RTK-GNSS positioning system is 2.5cm, the heading angle precision is 0.1 degrees, and the speed measuring precision is 0.01m/s. The measurement data output by the RTK-GNSS positioning system comprises position coordinates, running speed and course angle of the rice harvester.
The machine vision positioning system comprises a lifting platform 6 arranged at the top of the rice harvester, a turntable 3 which is arranged on the lifting platform 6 and can rotate by 360 degrees, and a sense depth camera 4 arranged on the turntable 3.
The turntable 3 not only can control the horizontal plane of the depth camera 4 to rotate 360 degrees, but also can control and adjust the pitch angle of the depth camera 4. In some embodiments, the turntable may be a cradle head.
The depth of sense camera 4, in this embodiment, may be a depth of sense camera D435i, including a completely new Inertial Measurement Unit (IMU), based on which six degrees of freedom data are added. The built-in inertial measurement unit combines various linear accelerometers with gyroscopes to detect rotation and translation of the three axes. For advanced scanning, the IMU provides an additional set of data that can support dense reconstruction and provide more references, preventing the sensor from losing track. Not only can visual information be provided, but also location data will be provided, more advanced depth perception and tracking capabilities can be built.
The depth camera 4 can rotate 360 degrees to obtain a visual image around the harvester, a paddy field area and obstacle avoidance objects in the visual image are identified based on paddy field parameter information, an unworked area, an operated area and a boundary area are identified based on the paddy field area, and crops to be harvested and stubble cutting surfaces are identified in the unworked area.
The above identification algorithm may be a prior art.
According to the identification of the crop to be harvested and the stubble cutting surface, the transverse deviation and the heading deviation of the header 2 of the ratoon rice harvester 1 relative to the stubble cutting surface are controlled to align one side of the header 2 of the ratoon rice harvester 1 with the stubble cutting surface.
When the header 2 of the rice harvester 1 approaches to the crops to be harvested for a preset distance, the header 2 of the rice harvester 1 is controlled to descend to a preset height, the harvesting operation is started, otherwise, the header 2 of the rice harvester 1 is controlled to ascend to the preset height, and the harvesting operation is stopped.
When the header 2 of the rice harvester 1 approaches the boundary of the paddy field land, the header 2 of the rice harvester 1 is controlled to rise to a preset height, and the harvesting operation is stopped. And controlling the turning and steering operation of the rice harvester 1 according to the turning and steering path of the ground.
When the turning operation is performed, the sense depth camera 4 is controlled to rotate 360 degrees to obtain a visual image around the harvester, and the surrounding environment and obstacle avoidance objects are identified. After the turning operation of the rice harvester 1 is completed, the transverse deviation and the course deviation of the header 2 of the rice harvester 1 relative to the stubble cutting surface are controlled according to the identification of the crop to be cut and the stubble cutting surface, so that one side of the header 2 of the rice harvester 1 is aligned with the stubble cutting surface.
When the regenerative rice harvester 1 operates in a straight line, the real-sense depth camera 4 is controlled to face forward, and crops to be harvested and stubble cutting surfaces are collected and identified in real time.
In this embodiment, the depth cameras 4 are controlled to face backward at intervals, and information such as the height of the rice piles, the line spacing between the rice piles, the rolling rate of the rice piles, etc. in the area where the operation has been performed is collected and identified in real time. The height of the header 2 is feedback-controlled according to the recognized height of the rice piles in the operated area, and the lateral deviation and heading deviation of the regenerative rice harvester 1 are feedback-controlled according to the recognized row spacing of the rice piles and the rolling rate of the rice piles.
The operation path planning module plans the operation path and the edge turning and steering path of the whole paddy field based on the paddy field parameter information and the operation parameter information of the regenerative rice harvester 1, transmits the operation path and the edge turning and steering path to the main controller to execute automatic driving, and utilizes the machine vision positioning system and the high-precision RTK-GNSS positioning system to track and control in real time.
Because the data frequency of the RTK-GNSS positioning system is often not high, the machine vision positioning system is used as the main positioning information source at present in the time interval when the RTK-GNSS positioning system does not output positioning information until the RTK-GNSS positioning system outputs new positioning data. And when the RTK-GNSS positioning system outputs positioning information, the positioning information provided by the machine vision positioning system is fused with the positioning information provided by the RTK-GNSS positioning system, so that the accuracy of the positioning information is improved.
Example two
On the basis of the first embodiment, the operation method of the unmanned system of the intelligent regenerative rice harvester comprises the following steps:
step one: the user remotely controls the machine to travel to the initial position of the working path through the user terminal, so that one side of the header 2 of the rice harvester 1 is aligned with the stubble cutting surface, and an unmanned working mode is started.
Step two: the operation path planning module plans the operation path and the edge turning and steering path of the whole paddy field based on the paddy field parameter information and the operation parameter information of the regenerative rice harvester 1, transmits the operation path and the edge turning and steering path to the main controller to execute automatic driving, and utilizes the machine vision positioning system and the high-precision RTK-GNSS positioning system to track and control in real time.
In the time interval when the RTK-GNSS positioning system does not output the positioning information, the machine vision positioning system is used as the current main positioning information source until the RTK-GNSS positioning system outputs new positioning data. And when the RTK-GNSS positioning system outputs positioning information, the positioning information provided by the machine vision positioning system is fused with the positioning information provided by the RTK-GNSS positioning system.
The depth camera 4 can rotate 360 degrees to obtain a visual image around the harvester, a paddy field area and obstacle avoidance objects in the visual image are identified based on paddy field parameter information, an unworked area, an operated area and a boundary area are identified based on the paddy field area, crops to be harvested and stubble cutting surfaces are identified in the unworked area, and information such as a height of a rice pile, a line spacing of the rice pile, a rolling rate of the rice pile and the like is identified in the operated area.
Step three: when the regenerative rice harvester 1 performs linear operation according to the operation path, the real-sense depth camera 4 is controlled to face forward, crops to be harvested and stubble cutting surfaces are collected and identified in real time, and the transverse deviation and heading deviation of the header 2 of the regenerative rice harvester 1 relative to the stubble cutting surfaces are controlled to enable one side of the header 2 of the regenerative rice harvester 1 to be aligned with the stubble cutting surfaces. And the interval control sense depth camera 4 is used for collecting and identifying the information such as the height of the rice piles, the line spacing of the rice piles, the rolling rate of the rice piles and the like of the operated area in real time towards the rear.
The height of the header 2 is feedback-controlled according to the recognized height of the rice piles in the operated area, and the lateral deviation and heading deviation of the regenerative rice harvester 1 are feedback-controlled according to the recognized row spacing of the rice piles and the rolling rate of the rice piles. When the header 2 of the rice harvester 1 approaches to the crops to be harvested for a preset distance, the header 2 of the rice harvester 1 is controlled to descend to a set height, harvesting operation is started, otherwise, the header 2 of the rice harvester 1 is controlled to ascend to the preset height, and harvesting operation is stopped.
As shown in the figure 3 of the drawings,
step four: when the header 2 of the rice harvester 1 approaches the boundary of the paddy field land, the header 2 of the rice harvester 1 is controlled to rise to a preset height, and the harvesting operation is stopped. And controlling the turning and steering operation of the rice harvester 1 according to the turning and steering path of the ground. And during turning operation, controlling the sense depth camera to rotate 4360 degrees to acquire a visual image around the harvester, and identifying the surrounding environment and obstacle avoidance objects. After the turning operation of the rice harvester 1 is completed, returning to the third step, and reciprocating the steps until the harvesting operation of the rice harvester 1 is completed.
Example III
A difference from the embodiment is that a second depth of sense camera 7 is added, the second depth of sense camera 7 being mounted below the tail of the machine and at the machine centre line position. The second depth of sense camera 7 is used for gathering and discern the information such as the stake height, stake line spacing of the regional rice of having already worked.
In this embodiment, the second depth camera 7 collects information such as the height of the rice piles and the line spacing of the rice piles in the identified operation area in real time, and as shown in fig. 3, the height scheme of the rice piles in the identified operation area is identified, and after the target objects of the rice piles in the identified operation area are identified, the vertical heights of the target objects of the rice piles are measured. The measurement formula is:
in the formula, H is the vertical height of the rice pile object, x and y are distance values of the highest point and the lowest point of the observed rice pile object respectively, and a is the relative view angle of the observed rice pile object in the vertical direction.
Identifying the row spacing of the rice piles in the operated area and the rolling rate scheme of the rice piles: after identifying the objects of the rice piles in the worked area, the distance L between the rice piles row between two adjacent rice piles and the number E and the width R of the rice piles within the width of the header 2 are measured. The width P of the tracked impression of the rice stake target object in the worked area is recognized, and the rice stake rolling ratio k=e×r≡p. When the rice pile rolling rate K exceeds a preset threshold value, controlling the transverse deviation and the heading deviation of the regenerative rice harvester 1 to enable the width P of the track travelling indentation to be smaller, and when the width of the track is smaller than the rice pile line spacing L, controlling the track of the regenerative rice harvester 1 to travel in the rice pile line spacing, so that the rice pile rolling rate K is reduced.
Of course, the above procedure is also applicable to the identification procedure in the first embodiment.
In the above embodiments, the model selection, the size, etc. of each system may be adjusted or replaced in other embodiments.
It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may employ one or more computer-usable storage media (including, but not limited to, disk storage, memory,CD-ROMOptical storage, etc.).
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The above description is only of the preferred embodiments of the present invention and is not intended to limit the present invention, but various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc. which do not require the inventive effort by those skilled in the art, are intended to be included within the scope of the present invention.
Claims (10)
1. An unmanned method of an intelligent harvester is characterized by comprising the following steps:
controlling the intelligent harvester to travel to an initial position of a working path, and enabling one side of a header of the intelligent harvester to be aligned with a stubble cutting surface;
executing an operation instruction, wherein the operation instruction comprises a planned operation path of a whole harvesting land and a land turning and steering path based on the harvesting land parameter information and the harvester operation parameter information;
according to the acquired operation front image, identifying crops to be harvested and stubble cutting surfaces, and controlling the transverse deviation and heading deviation of the intelligent harvester relative to the stubble cutting surfaces so that one side of the header is always aligned with the stubble cutting surfaces;
identifying the height of the rice piles, the spacing between the rice piles and the rolling rate of the rice piles in the operated area according to the acquired operation rear image, controlling the height of a header according to feedback of the height of the rice piles, and controlling the transverse deviation and the heading deviation of the intelligent harvester according to the spacing between the rice piles and the rolling rate of the rice piles;
in the operation process, RTK-GNSS positioning information and machine vision positioning information are acquired, the RTK-GNSS positioning information and the machine vision positioning information are fused, and the fused positioning information is used as the positioning information of the intelligent harvester;
when the cutting machine advances to the boundary of the land, the cutting table is controlled to ascend, the harvesting operation is stopped, and the turning and steering operation is carried out according to the turning and steering path of the land;
repeating the operation steps until the operation instruction is completed.
2. The unmanned method of claim 1, wherein during operation, when the header of the intelligent harvester approaches a predetermined distance from the crop to be harvested, the header is controlled to descend to a predetermined height to start harvesting, and otherwise, the header is controlled to ascend to a set height to stop harvesting.
3. The unmanned method of the intelligent harvester according to claim 1, wherein the peripheral visual image of the intelligent harvester is obtained when the intelligent harvester turns around, the peripheral environment and the obstacle avoidance object are identified according to the visual image, and the obstacle avoidance object is ensured when the intelligent harvester turns around.
4. The unmanned method of claim 1, wherein the machine vision positioning information is the main if the RTK-GNSS positioning information is not available during the operation.
5. The unmanned method of an intelligent harvester according to claim 1, wherein after identifying the rice stake targets in the operated area, measuring the row spacing of rice stakes between two adjacent rice stakes and the number and width of the rice stakes within the width of the header, calculating the rolling rate of the rice stake by combining the identified walking indentation width of the rice stake targets in the operated area with the intelligent harvester, and controlling the lateral deviation and heading deviation of the intelligent harvester to make the walking indentation width of the intelligent harvester smaller when the rolling rate of the rice stake exceeds a predetermined threshold value and controlling the intelligent harvester to travel within the row spacing of the rice stake when the width of the walking part of the intelligent harvester is smaller than the row spacing of the rice stake.
6. An intelligent unmanned system of harvester, characterized by comprising:
the operation management terminal system is used for managing land block information and intelligent harvester parameter information, generating an operation instruction comprising an operation path of harvesting land block and a land turning and steering path, monitoring and tracking the intelligent harvester, and carrying out information interaction between the intelligent harvester and the main controller;
the RTK-GNSS positioning system is used for providing RTK-GNSS positioning information;
the machine vision system is used for providing machine vision positioning information, acquiring an operation front image, an operation rear image and an intelligent harvester surrounding image, identifying crops to be harvested and stubble cutting surfaces, identifying the height of rice piles, the row spacing of the rice piles and the rolling rate of the rice piles in an operated area, and identifying surrounding environment and barrier information;
and the main controller is in information interaction with each system and is used for controlling the running and operation states of the intelligent harvester according to the operation instructions, the positioning information and the identification results.
7. The intelligent harvester unmanned system of claim 6, wherein the machine vision positioning system comprises a lift platform mounted on top of the intelligent harvester, a rotatable pan-tilt mounted on the lift platform, and a depth-of-sense camera mounted on the pan-tilt.
8. The intelligent harvester unmanned system of claim 7, wherein the depth of sense camera comprises a camera unit, an inertial measurement unit, and a processing unit, the inertial measurement unit configured to detect rotation and translation of the three axes;
the camera unit is used for acquiring visual images;
the processing unit is used for identifying a land area and obstacle avoidance objects, an unworked area, an operated area and a boundary area in the visual image according to the visual image and combining land parameter information, and identifying crops to be harvested and stubble cutting surfaces in the unworked area.
9. The intelligent unmanned system of claim 6, wherein the job management terminal system comprises a job parameter management module, a plot information management module, a job path planning module, and a remote control module, wherein:
the operation parameter management module is used for managing the size parameter, the header height parameter and the width parameter of the intelligent harvester, and the machine track width parameter, the antenna installation position parameter, the actual depth camera installation position parameter, the running speed parameter and the steering angle parameter;
the land information management module is used for managing land parameters, including key point coordinates of land boundaries, obstacle region calibration, land crop types and crop height calibration;
the operation path planning module is used for planning an operation path and a land turning and steering path of the whole harvesting land based on the harvesting land parameter information and the harvester operation parameter information;
the remote control module is used for being connected with the main controller to realize remote control of machine running and operation.
10. The unmanned system of claim 6, wherein the RTK-GNSS positioning system comprises a reference station and a mobile station, the reference station being disposed at a fixed point of the plot, the mobile station comprising antennas disposed on the left and right sides of the intelligent harvester, respectively, and a mobile station disposed on the intelligent harvester, the position coordinates of the midpoint of the two antennas being the position of the intelligent harvester.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311611219.0A CN117873054A (en) | 2023-11-29 | 2023-11-29 | Unmanned method and system for intelligent harvester |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311611219.0A CN117873054A (en) | 2023-11-29 | 2023-11-29 | Unmanned method and system for intelligent harvester |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117873054A true CN117873054A (en) | 2024-04-12 |
Family
ID=90587343
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311611219.0A Pending CN117873054A (en) | 2023-11-29 | 2023-11-29 | Unmanned method and system for intelligent harvester |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117873054A (en) |
-
2023
- 2023-11-29 CN CN202311611219.0A patent/CN117873054A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3698618B1 (en) | Smart lawn mowing system | |
| EP3529556B1 (en) | Land mapping and guidance system | |
| US11960295B2 (en) | 3-D image system for vehicle control | |
| US20200278680A1 (en) | Method and Device for Operating a Mobile System | |
| US9603300B2 (en) | Autonomous gardening vehicle with camera | |
| EP3794919B1 (en) | Method and system for planning a path of a vehicle | |
| CN102368158B (en) | Navigation positioning method of orchard machine | |
| KR101879247B1 (en) | The Working Path Setting Method for Automatic Driving Agricultural Machine | |
| US20210364632A1 (en) | Methods and Systems for Map Creation and Calibration of Localization Equipment in an Outdoor Environment | |
| CN113126613B (en) | Intelligent mowing system and autonomous image building method thereof | |
| CN105607635A (en) | Panoramic optic visual navigation control system of automatic guided vehicle and omnidirectional automatic guided vehicle | |
| WO2009100463A1 (en) | Visual, gnss and gyro autosteering control | |
| CN108801269A (en) | A kind of interior cloud Algorithms of Robots Navigation System and method | |
| CN112965481A (en) | Orchard operation robot unmanned driving method based on point cloud map | |
| Wang et al. | Autonomous maneuvers of a robotic tractor for farming | |
| JP7365103B2 (en) | Farming support system, location information generation method, computer program and processing device | |
| CN111578942A (en) | Navigation method and system of land leveler | |
| CN108669046B (en) | Plant protection unmanned vehicle integrating visual navigation and Beidou positioning and control method | |
| TWI752366B (en) | Method and module for displacement processing and mower device | |
| Post et al. | Autonomous navigation with open software platform for field robots | |
| CN109634277B (en) | Unmanned operation system and operation method for grain harvester | |
| CN117873054A (en) | Unmanned method and system for intelligent harvester | |
| CN104898551B (en) | The double vision of full-automatic grass-removing robot feels self aligning system | |
| CN114234983B (en) | Walking type farmland mobile platform robot navigation method | |
| WO2024022204A1 (en) | Gardening tool, control method therefor, and system |
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 |