CN118355792B - A continuous walking cutting and harvesting robot and its operation method - Google Patents

A continuous walking cutting and harvesting robot and its operation method

Info

Publication number
CN118355792B
CN118355792B CN202410426414.4A CN202410426414A CN118355792B CN 118355792 B CN118355792 B CN 118355792B CN 202410426414 A CN202410426414 A CN 202410426414A CN 118355792 B CN118355792 B CN 118355792B
Authority
CN
China
Prior art keywords
picking
walking
module
robot
harvesting
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202410426414.4A
Other languages
Chinese (zh)
Other versions
CN118355792A (en
Inventor
刘继展
蔡连江
金玉成
蒋厚康
王杰
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Jiangsu University
Original Assignee
Jiangsu University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Jiangsu University filed Critical Jiangsu University
Priority to CN202410426414.4A priority Critical patent/CN118355792B/en
Publication of CN118355792A publication Critical patent/CN118355792A/en
Application granted granted Critical
Publication of CN118355792B publication Critical patent/CN118355792B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • A—HUMAN NECESSITIES
    • A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
    • A01D—HARVESTING; MOWING
    • A01D46/00—Picking of fruits, vegetables, hops, or the like; Devices for shaking trees or shrubs
    • A01D46/30—Robotic devices for individually picking crops

Landscapes

  • Engineering & Computer Science (AREA)
  • Robotics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Environmental Sciences (AREA)
  • Manipulator (AREA)

Abstract

The invention discloses a continuously-walking cut-grafting harvesting robot and an operation method thereof, wherein the continuously-walking cut-grafting harvesting robot comprises a cut-grafting picking module, a floating fruit receiving module, a picking path planning control module, a depth camera, an image processor, an autonomous walking chassis module, a walking speed regulating module and a picking point walking error amount compensation module, the floating fruit receiving module, the cutting fruit receiving module and the depth camera are sequentially arranged at the front end, the middle part and the tail end of the autonomous walking chassis module along the longitudinal center line of the autonomous walking chassis module, a picking motion counter is arranged in the picking path planning control module and used for counting the parity of the action times of a mechanical arm so as to regulate the mechanical arm, the depth camera is in signal connection with the image processor, the walking speed regulating module regulates the walking speed of the autonomous walking chassis module according to the fruit distribution density, and the picking point walking error amount compensation module controls the mechanical arm to accurately position the spatial coordinates of a fruit stalk picking point in a continuous walking state of the robot. The invention is used for realizing continuous running high-speed harvesting of the trellis grape.

Description

Continuous walking cutting and harvesting robot and operation method thereof
Technical Field
The invention relates to the field of intelligent agricultural equipment and robots, in particular to a cut-grafting harvesting robot for continuous walking of a robot for trellis grapes and an operation method thereof.
Background
In recent years, the harvesting robot technology at home and abroad is rapidly developed, but the low harvesting operation efficiency becomes a bottleneck for development. The conventional harvesting robot scheme requires that the chassis can drive vision and tail end to accurately position and pick the slender fruit stalks under a static state, the vision-mechanical accurate positioning requirement, the moving and delivering box of a long round-trip path of a mechanical arm and the chassis are static and wait for harvesting to finish consume a great deal of time, and the above points determine that the conventional harvesting robot scheme cannot realize great improvement of harvesting efficiency. The robot continuous walking harvesting is applied to the mechanized harvesting of crops such as grains and vegetables, but the conditions of fluctuation of a greenhouse surface, different fruit bearing heights and different positions exist in a horizontal greenhouse cultivation mode, the vision positioning error is extremely large in the robot continuous walking state, the continuous walking harvesting of the grapes cannot be realized, and the robot in-situ waiting time is long.
Disclosure of Invention
Aiming at the defects in the prior art, the invention provides the continuous walking cutting and harvesting robot and the operation method thereof, and the continuous walking high-speed harvesting of the shed frame fresh grape by the harvesting robot is realized.
The present invention achieves the above technical object by the following means.
A continuously walking cut harvesting robot comprising:
The cutting and harvesting path planning subsystem comprises a cutting type picking module, a floating fruit receiving module and a harvesting path planning control module, wherein the floating fruit receiving module and the cutting type picking module are fixedly arranged at the front end and the middle part of the cutting type picking module along the longitudinal central line of the autonomous walking chassis module in sequence, a harvesting motion counter is arranged in the harvesting path planning control module, the parity of the action times of a mechanical arm of the cutting type picking module is counted through the harvesting motion counter, and then the motion direction of the mechanical arm is regulated;
The hand-eye movement-photographing time sequence cooperative regulation and control subsystem comprises a depth camera and an image processor, wherein the depth camera is in signal connection with the image processor;
The picking path point walking error amount compensation subsystem comprises an autonomous walking chassis module, a walking speed regulation module and a picking point walking error amount compensation module, wherein the walking speed regulation module regulates the walking speed of the autonomous walking chassis module according to the fruit distribution density, and the picking point walking error amount compensation module controls the mechanical arm to accurately position the spatial coordinates of a fruit stalk picking point in a robot continuous walking state;
The mechanical arm, the picking path planning control module, the walking speed regulation and control module and the picking point walking error amount compensation module are in bidirectional communication with the main controller, and the actions of the mechanical arm, the autonomous walking chassis module and the lifting platform are controlled by the main controller.
In the above technical scheme, the cutting type picking module comprises a mechanical arm, a cutting type circular cutter end effector and a mechanical arm base, wherein the mechanical arm base is fixed above the autonomous walking chassis module, the mechanical arm is fixed above the mechanical arm base, and the cutting type circular cutter end effector is fixed at the end wrist of the mechanical arm and the working posture is always horizontal.
In the above technical scheme, the floating fruit receiving module comprises a fruit box and a lifting platform, wherein the lifting platform is fixed above the autonomous walking chassis module, and the fruit box is detachably connected above the lifting platform.
The operation method of the continuous walking cutting and harvesting robot comprises the following steps:
The autonomous walking chassis module is static after being longitudinally aligned with the row lines of the fruit trees and waits for a walking instruction, the tail end of the mechanical arm moves to the right boundary end point A to wait for a picking action instruction, and the base of the fruit box rises to a height h 1 from the ground to wait for a floating fruit receiving harvesting instruction;
The depth camera continuously detects the three-dimensional region of interest of the hand-eye combination, automatically selects between a picking target searching working condition and a continuous walking picking working condition according to the actual distribution condition of fruits of the three-dimensional region of interest of the hand-eye combination, and then transmits the number k of the grapes in the three-dimensional region of interest of the hand-eye combination to the walking speed regulation and control module, so that the speed v k of uniform linear walking of the independent walking chassis module along the row lines of the fruit trees is regulated;
When the robot is in a continuous walking harvesting working condition, the image processor sends spatial coordinates S 1、S2、……Si……Sn of multiple strings of target grape picking points in the three-dimensional region of interest of the hand-eye combination to the main controller, the main controller controls the mechanical arm to conduct constant-width cyclic picking path planning on all the grapes identified in the three-dimensional region of interest of the hand-eye combination according to the data parity counted by the picking motion counter between A, B boundary endpoints of which the edges of the operation breadth are mirror-symmetrical relative to the axial plane of the robot;
based on the fixed width cycle picking path planning, the picking point walking error amount compensation module compensates errors of spatial coordinates S i of each picking path point during continuous walking, the compensated coordinates S i' of each picking point are transmitted to the main controller, the mechanical arm is controlled to execute the picking action of accurately positioning the picking point under the continuous walking state, meanwhile, the operation height of the fruit box is adjusted according to the height value of the picking point, and fruit harvesting is not damaged under the three-dimensional region of interest of the hand-eye combination.
Further, according to the actual distribution situation of fruits in the three-dimensional region of interest of the hand-eye combination, autonomous selection is performed between a picking target searching working condition and a continuous walking picking working condition, specifically:
When the continuously walking cut-in picking robot is in a picking target searching working condition, the depth camera moves forward along with the robot, the main controller controls the depth camera to continuously detect a three-dimensional region of interest of the hand-eye combination, when the fact that the grapes enter the three-dimensional region of interest of the hand-eye combination is recognized, the image processor acquires picking point space coordinates S i of each string of grapes in the three-dimensional region of interest of the hand-eye combination in real time, the main controller extracts a picking point space coordinate depth value y min closest to the robot in the depth direction, when the depth value y min is less than or equal to 900mm, the main controller controls the depth camera to shoot a single frame image at the current moment, and immediately closes the continuous detection function of the depth camera, and controls the mechanical arm to pick according to the picking point space coordinates S i of all the grapes of the frame image, so that the switching from the picking target searching working condition to the continuously walking picking working condition is realized;
When the continuously walking cut-grafting harvesting robot is in a continuously walking harvesting working condition, the data parity change of the harvesting motion counter triggers a photographing signal of the depth camera, when no grape is located in a three-dimensional region of interest of the hand-eye combination in the last frame of image obtained by the depth camera, the main controller triggers a continuous detection function of the depth camera, and the mechanical arm immediately resets to a right boundary endpoint A to wait for a harvesting action instruction, so that the switching from the continuously walking harvesting working condition to a harvesting target searching working condition is realized.
The method comprises the steps of determining the width of a picking object, wherein the width of the picking object is determined by a fixed-width circulation picking path planning, namely, a main controller extracts horizontal width direction components x i of space coordinates of all picking points, then performs unidirectional picking path planning from left to right or from right to left on all picking objects, and after the unidirectional picking path planning is compensated by a picking point walking error amount compensation module, the main controller controls a mechanical arm to be positioned between A, B boundary endpoints of mirror symmetry of the operation width edge of the robot relative to the axial surface of the robot, and circularly executes picking actions with fixed action width, wherein the point A is the right boundary endpoint of the picking robot, and the point B is the left boundary endpoint of the picking robot;
Counting the number of actions of the mechanical arm between A, B boundary endpoints from 0 by the picking motion counter, when the number of actions is odd, the picking action directions of the mechanical arm are all from right to left, the corresponding picking paths are A- & gtS 1→S2→……→Sm - & gtB, when the number of actions is even, the picking action directions of the mechanical arm are all from left to right, the corresponding picking paths are B- & gtS m+1→Sm+2→……→Sn-1→Sn - & gtA, wherein m represents the accumulated number of picked grapes in the process that the mechanical arm executes the picking action from the right boundary endpoint A to the left boundary endpoint B, n represents the accumulated number of picked grapes in the process that the mechanical arm returns to the right boundary endpoint A from the right boundary endpoint A to the left boundary endpoint B, and n is more than m.
Further, the spatial coordinates of the right boundary endpoint a and the left boundary endpoint B are both located in a spatial base coordinate system of the mechanical arm, and a= (x A,yA,zA)、B＝(xB,yB,zB) satisfies:
b, H, D respectively represent the operation range of the continuous walking cutting and harvesting robot, the operation height range and the operation depth range.
Further, the speed v k of the autonomous walking chassis module walking straight at a constant speed along the row line of the fruit tree meets the following conditions:
wherein v k1＞vk2＞vk3 >0.
Further, the picking point walking error amount compensation module compensates the error of the spatial coordinates S i of each picking path point during continuous walking, specifically:
The automatic walking chassis module comprises a picking point walking error amount compensation module, a main controller and a mechanical arm, wherein the picking point walking error amount compensation module calculates the displacement delta S i＝(Δxi,Δyi,Δzi of the walking mileage of the automatic walking chassis module relative to the ground absolute coordinate system, and the displacement delta S i＝(Δxi,Δyi,Δzi is used as the walking error compensation amount of each picking path point to obtain the spatial coordinate S i′(xi′,yi′,zi ' of each picking point compensated in the picking path, the S i ' is fed back to the main controller to control the mechanical arm to execute the picking action, and the spatial coordinate S i ' of each picking point compensated meets the following conditions:
Wherein t i represents the time required by the mechanical arm to reach the spatial coordinates S i of each picking point, and v kx、vky and v kz are the speed components of the autonomous walking chassis module along the operation width x, depth y and height z directions of the picking robot respectively;
The time t i required for the mechanical arm to reach the spatial coordinates S i of each picking point is as follows:
wherein M i represents the Euclidean distance between adjacent picking path points, and:
further, the hand-eye combined three-dimensional region of interest is a largest inscribed cuboid region formed by a common three-dimensional region commonly determined by a working space of the mechanical arm and a field-of-view space of the depth camera.
The beneficial effects of the invention are as follows:
(1) According to the invention, through the cooperative coordination of the cutting type picking module, the floating fruit receiving module and the autonomous walking chassis module, the continuous walking picking of the fresh grapes on the horizontal shed frame is realized, and the device is simple and reliable in structure and strong in practicability.
(2) The cut-and-pick operation method for continuous walking of the trellis grape harvesting robot adopts a constant-width cyclic picking path planning sub-method to carry out unidirectional picking path planning on picking targets with similar fruit bearing heights, effectively avoids the condition of detouring and returning in the mechanical arm picking process, coordinates the parity check of the movement times of the mechanical arm and the image photographing time sequence of a depth camera by a hand-eye movement-photographing time sequence collaborative regulation sub-method, effectively solves the two problems of interference shielding by the mechanical arm when photographing by the depth camera and overlong photographing time of the mechanical arm waiting for the camera, and effectively eliminates the positioning errors caused by inconsistent coordinates of picking points in static positioning of a single frame image by a vision system under the continuous walking state of the robot by taking the displacement of an autonomous walking chassis module from the photographing time of the depth camera as the walking error compensation quantity of each picking path point.
Drawings
FIG. 1 is a schematic view of a continuously traveling cut-and-pick robot of the present invention;
FIG. 2 is a schematic diagram of the construction of a three-dimensional region of interest of a multi-parameter constrained limited string harvest grape-hand-eye combination of the present invention;
FIG. 3 is a schematic diagram of a coordinated multi-hand-eye motion-photographing timing sub-method according to the present invention;
FIG. 4 is a schematic diagram of a multi-picking-point walking error compensation sub-method according to the present invention;
FIG. 5 is a schematic view of a multi-trellis inter-row harvest scenario of the present invention;
FIG. 6 is a schematic diagram of the communication of the main controller with other components of the present invention;
In the figure, a 1-cutting type picking module, a 2-floating fruit receiving module, a 3-autonomous walking chassis module, a 4-mechanical arm, a 5-cutting type disc cutter end effector, a 6-mechanical arm base, a 7-fruit box, an 8-lifting platform, a 9-depth camera, a 10-image processor, a 11-camera support, a 12-picking path planning control module, a 13-walking speed regulating module, a 14-picking point walking error amount compensation module, a 15-main controller, a 16-picking motion counter, a 17-hand-eye combined three-dimensional interested area, a 18-shed frame upright post, a 19-shed frame net surface, a 20-grape cluster and 21-grape fruit stalks are shown.
Detailed Description
The invention will be further described with reference to the drawings and the specific embodiments, but the scope of the invention is not limited thereto.
The invention discloses a continuously walking cut-and-pick harvesting robot which comprises a cut-and-pick harvesting path planning subsystem, a hand-eye action-photographing time sequence cooperative regulation subsystem and a picking path point walking error amount compensation subsystem.
As shown in fig. 1 and 5, the cut-and-pick harvesting path planning subsystem comprises a cut-and-pick module 1, a floating fruit receiving module 2 and a picking path planning control module 12, wherein the floating fruit receiving module 2 and the cut-and-pick module 1 are fixedly installed at the front end and the middle part of the autonomous walking chassis module 3 along the longitudinal central line of the autonomous walking chassis module 3 in sequence and are both positioned above the autonomous walking chassis module 3. The cutting type picking module 1 comprises a mechanical arm 4, a cutting type circular cutter end effector 5 and a mechanical arm base 6, wherein the mechanical arm base 6 is fixed above the autonomous walking chassis module 3, the mechanical arm 4 is fixed above the mechanical arm base 6, and the cutting type circular cutter end effector 5 is fixed at the end wrist of the mechanical arm 4 and the working posture is always horizontal.
As shown in fig. 2, the floating fruit receiving module 2 includes a fruit box 7 and a lifting platform 8, the lifting platform 8 is fixed above the autonomous walking chassis module 3, and the fruit box 7 is detachably connected above the lifting platform 8, so that the fruit box is convenient to replace after being filled with grapes.
The picking path planning control module 12 is internally provided with a picking motion counter 16, and the parity of the action times of the mechanical arm 4 is counted through the picking motion counter 16, so that the main controller 15 adjusts the movement direction of the mechanical arm 4, and the picking path planning control module has the function of quickly planning the picking action path of the cutting type picking module 1.
The hand-eye motion-photographing time sequence cooperative regulation and control subsystem comprises a depth camera 9 and an image processor 10, wherein the depth camera 9 is in signal connection with the image processor 10, the depth camera 9 outputs image signals to the image processor 10 in a unidirectional mode, the image processor 10 outputs signals to a main controller 15 in a unidirectional mode, the depth camera 9 is controlled by unidirectional signals of the main controller 15, the depth camera 9 is horizontally arranged on a camera support 11 along a longitudinal center line of the tail end of the autonomous walking chassis module 3, and the camera support 11 is fixed above the autonomous walking chassis module 3.
The picking point walking error amount compensation subsystem comprises an autonomous walking chassis module 3, a walking speed regulation module 13 and a picking point walking error amount compensation module 14, wherein the walking speed regulation module 13 has the function of regulating the walking speed of the autonomous walking chassis module 3 according to the fruit distribution density, and the picking point walking error amount compensation module 14 can control the mechanical arm 4 to accurately position the spatial coordinates of the fruit stalk picking points in the continuous walking state of the robot.
As shown in fig. 6, the mechanical arm 4, the picking path planning control module 12, the walking speed regulating module 13 and the picking point walking error amount compensating module 14 are all in bidirectional communication with the main controller 15. The actions of the mechanical arm 4, the autonomous walking chassis module 3 and the lifting platform 8 are controlled by the main controller 15.
The continuous walking cutting and harvesting robot can achieve a picking target searching working condition and a continuous walking harvesting working condition. The judging method of the picking target searching working condition comprises the steps that in the continuous walking process of a robot, the depth camera 9 does not detect the existence of the grape in the hand-eye combined three-dimensional region of interest 17 and continues to detect the existence of the grape, in the continuous walking process of the robot, the depth camera 9 detects the existence of the grape in the hand-eye combined three-dimensional region of interest 17, the depth value y min of a target grape picking point spatial coordinate closest to the robot in the depth direction is less than or equal to 900mm, and the spatial coordinate of the picking point is located in a spatial base coordinate system of the mechanical arm 4.
As shown in fig. 2, the three-dimensional region of interest 17 of the hand-eye combination is a largest inscribed cuboid region formed by a common three-dimensional region commonly determined by the working space Θ of the mechanical arm 4 and the field of view space θ of the depth camera 9, and the grapes in the three-dimensional region of interest 17 of the hand-eye combination can be correctly identified by the depth camera 9 and picked by the cut picking module 1, wherein the working space Θ of the mechanical arm 4 and the field of view space θ of the depth camera 9 satisfy:
Ψ=[B,H,D](Ψ∈Θ∩θ)
wherein, ψ represents a three-dimensional region of interest 17 of the hand-eye combination, B and H, D represent the operation range of the continuously-running cutting and harvesting robot respectively, The working height range and the working depth range, W b is the working width of the working space Θ of the mechanical arm 4, W g is the transverse width of the fruit box body, D b is the working depth range which needs to be met by the mechanical arm 4, D min is the minimum detection depth set by the vertical distance from the depth camera 9 to the rear plane M 1 of the fruit box 7, D max is the maximum detection depth set by the vertical distance from the depth camera 9 to a certain plane M 2 parallel to M 1 in the fruit box 7, H s is the mounting height of the upper surface of the mechanical arm base 6 relative to the ground, H bmax is the maximum working height reached by the mechanical arm body, H bmin is the minimum working height reached by the mechanical arm body, J is the variation of the picking height under the same grid plane, θ w is the transverse included angle of the field space θ of the depth camera 9 in the horizontal plane, θ v is the longitudinal included angle of the field space θ of the depth camera 9 in the vertical plane, H c is the mounting height of the depth camera 9 relative to the ground, W emin is the minimum detection depth D min of the corresponding to the field depth range of the depth camera 5428.
The depth camera 9 has a ground mounting height H c which is set as follows:
In the present embodiment of the present invention, 1000mm is taken by B, 1750-2000 mm is taken by H, and 2000mm is taken by D600-1000 mm, H c is 1750mm.
The operation method of the continuous walking cut-grafting harvesting robot comprises a fixed-width cyclic picking path planning sub-method, a hand-eye action-photographing time sequence cooperative regulation sub-method, a picking point walking error amount compensation sub-method and a cut-grafting harvesting operation flow of continuous walking of the trellis grape harvesting robot.
A fixed-breadth cyclic picking path planning sub-method comprises the steps that when a main controller 15 receives all picking point space coordinates S i＝(xi,yi,zi in a three-dimensional region of interest 17 of a hand-eye combination calculated by an image processor 10, the main controller 15 immediately extracts horizontal width direction components x i of all the picking point space coordinates, then performs unidirectional picking path planning from left to right or from right to left on all picking targets, after the picking point walking error amount compensation module 14 compensates, the main controller 15 controls the mechanical arm 4 to be located between A, B boundary endpoints of mirror symmetry of the working breadth edge of the robot relative to the axial surface of the robot, cyclic execution of picking actions with fixed action breadth, wherein a point A is a right boundary endpoint of the picking robot, a point B is a left boundary endpoint of the picking robot, a picking motion counter 16 counts the number of actions between two boundary endpoints of the mechanical arm 4 at A, B from 0, when the number of actions is odd, picking action directions of the mechanical arm 4 are all right to left, corresponding picking paths are A-S 1→S2→……→Sm→B(xA＞x1＞x2＞……＞xm＞xB, when the number of actions are even numbers, the action directions of the mechanical arm 4 are all picking actions from left to right B→Sm+1→Sm+2→……→Sn-1→Sn→A(xA＞xn＞xn-1＞……＞xm+2＞xm+1＞xB);, m represents the number of the boundary endpoints of the picking motion cycle of the mechanical arm 4 is accumulated, and the number of the n is calculated from the boundary endpoint A to the right boundary endpoint of the picking robot is calculated, and the number n is calculated from the boundary endpoint of the end point B of the picking edge of the picking motion 4, and the n is calculated.
The specific workflow of the coordinated control sub-method of hand-eye motion and photographing time sequence is shown in fig. 3.
When the continuously walking cut-grafting harvesting robot is under the working condition of searching a picking target, the specific working flow of the hand-eye action-photographing time sequence cooperative regulation sub-method is as follows:
The main controller 15 controls the depth camera 9 to continuously detect the three-dimensional region of interest 17 of the hand-eye combination, judges whether a grape exists in the three-dimensional region of interest 17 of the hand-eye combination, and simultaneously controls the mechanical arm 4 to reach a point A or a point B of a boundary of a field of view of the depth camera 9 in the three-dimensional region of interest 17 of the hand-eye combination to wait for picking action instructions, wherein the two spatial coordinates of A, B points are both located in a spatial base coordinate system of the mechanical arm 4, and the two boundary points A= (x A,yA,zA)、B＝(xB,yB,zB) satisfy:
In this embodiment, two boundary points a= (600,800,1850), b= (-600,800,1850).
When the continuously walking cut-grafting harvesting robot is in a continuously walking harvesting working condition, the specific working flow of the hand-eye action-photographing time sequence cooperative regulation sub-method is as follows:
When the data parity of the picking motion counter 16 changes, the main controller 15 triggers the photographing signal of the depth camera 9, the obtained single frame image is sent to the image processor 10 to refresh and cover the previous frame image, then the image processor 10 calculates the multi-string target grape picking point space coordinates S i according to the refreshed single frame image (the specific calculation method is the prior art), the multi-string target grape picking point space coordinates S i are sent to the main controller 15, the main controller 15 sequentially sends the multi-string target grape picking point space coordinates S i to the picking path planning control module 12, the walking speed regulation module 13 and the picking point walking error amount compensation module 14, and the cut type picking module 1 and the autonomous walking chassis module 3 are controlled to execute continuous walking with the coordinated action timing.
When the continuous walking cutting and harvesting robot needs to be switched between a picking target searching working condition and a continuous walking harvesting working condition, the specific working flow of the hand-eye action-photographing time sequence cooperative regulation and control sub-method is as follows:
When the continuously walking cut-and-pick robot is in a picking target searching working condition, the depth camera 9 moves forwards along with the robot, the main controller 15 controls the depth camera 9 to continuously detect the hand-eye combined three-dimensional interested region 17, when the fact that a grape enters the hand-eye combined three-dimensional interested region 17 is recognized, the image processor 10 acquires picking point space coordinates S i＝(xi,yi,zi of each string of grapes in the hand-eye combined three-dimensional interested region 17 in real time, the main controller 15 extracts a depth value y min of the closest picking point space coordinates of the depth direction from the robot, when the depth value y min is smaller than or equal to 900mm, the main controller 15 controls the depth camera 9 to shoot a single frame image at the current moment, and immediately closes the continuous detection function of the depth camera 9, and the main controller 15 controls the mechanical arm 4 to pick according to the picking point space coordinates S i of all the grapes in the frame image, so that the switching of the picking target searching working condition to the continuously walking picking working condition is realized. When the continuously walking cut-grafting harvesting robot is in a continuously walking harvesting working condition, the data parity of the harvesting motion counter 16 changes to trigger the photographing signal of the depth camera 9, when no grape is positioned in the three-dimensional region of interest 17 of the hand-eye combination in the last frame of image obtained by the depth camera 9, the main controller 15 triggers the continuous detection function of the depth camera 9, and the mechanical arm 4 immediately resets to the point A to wait for a harvesting action instruction, so that the switching from the continuously walking harvesting working condition to the harvesting target searching working condition is realized.
The picking point walking error amount compensation sub-method is shown in fig. 4, and comprises a picking point walking error amount compensation algorithm and a walking speed regulation algorithm based on the current fruit bearing density.
The picking point walking error amount compensation algorithm is only executed when the continuously walking cut-and-connect picking robot is under the continuously walking picking working condition, the picking point walking error amount compensation module 14 calculates the displacement delta S i＝(Δxi,Δyi,Δzi of the walking mileage of the autonomous walking chassis module 3 relative to the ground absolute coordinate system, and the displacement delta S i＝(Δxi,Δyi,Δzi is used as the walking error compensation amount of each picking path point to obtain the spatial coordinates S i′(xi′,yi′,zi ' of each picking point compensated in the picking path, and the S i ' is fed back to the main controller 15, the main controller 15 controls the mechanical arm 4 to execute picking actions, and the S i ' meets the following conditions:
Wherein t i represents the time required by the mechanical arm 4 to reach the spatial coordinates S i of each picking point, t i is calculated according to the Euclidean distance M i between adjacent picking path points and the tail end linear velocity v s of the mechanical arm 4, and the Euclidean distance M i between the adjacent picking path points and the time t i required by the mechanical arm 4 to reach the spatial coordinates S i of each grape are as follows:
The terminal linear velocity v s of the mechanical arm 4 can be regarded as a uniform velocity under the condition that the motion direction has no large abrupt change, v kx、vky and v kz are velocity components of the autonomous walking chassis module 3 along the operation width x, depth y and height z directions of the harvesting robot respectively, and in the embodiment, v k＝vkx、vky＝0、vkz＝0,vs =600mm/s.
The speed v k of the autonomous walking chassis module 3 is adaptively adjusted according to the number of the grapes in the three-dimensional region of interest 17 of the current hand-eye combination based on the walking speed regulation algorithm of the current fruit bearing density, so that the aims of speeding up and quickly passing the robot when fruits are sparse and slowing down and finely harvesting the robot when the fruits are dense are fulfilled, and the working efficiency of continuous walking, cutting, collecting and harvesting is improved. The main controller 15 acquires the number of the grapes in the hand-eye combined three-dimensional region of interest 17 calculated by the image processor 10 in real time, transmits the number of the grapes to the walking speed regulating and controlling module 13, and the walking speed regulating and controlling module 13 calculates the walking speed v k of the autonomous walking chassis module 3 according to the number of the grapes and transmits the walking speed v k to the main controller 15 to regulate and control the walking speed of the autonomous walking chassis module 3, wherein the walking speed v k of the autonomous walking chassis module 3 meets the following conditions:
Wherein v k1＞vk2＞vk3 >0. In this example, v k1＝200mm/s、vk2＝150mm/s、vk3 = 100mm/s.
The scene schematic diagram of the harvesting among the trellis rows is shown in fig. 5, and the cut-grafting harvesting operation flow of the continuous walking of the trellis grape harvesting robot is as follows:
the main controller 15 controls the autonomous walking chassis module 3 to longitudinally align with the row lines of the fruit trees and then to rest and wait for a walking instruction, the main controller 15 controls the tail end of the mechanical arm 4 to move to a right boundary end point A to wait for a picking action instruction, the main controller 15 controls the lifting platform 8 to lift the base of the fruit box 7 to a height h 1 from the ground to wait for a floating fruit receiving harvesting instruction, and in the embodiment, h 1 = 1250mm;
The main controller 15 controls the depth camera 9 to continuously detect the hand-eye combined three-dimensional interested region 17, and automatically selects between a picking target searching working condition and a continuous walking picking working condition according to the actual distribution condition of fruits in the hand-eye combined three-dimensional interested region 17, then the main controller 15 transmits the number k of the grapes in the hand-eye combined three-dimensional interested region 17 to the walking speed regulating module 13, and the walking speed regulating module 13 regulates and controls the speed v k of the independent walking chassis module 3 in uniform straight walking along the row lines of the fruit trees according to the number k of the grapes in the hand-eye combined three-dimensional interested region 17;
When the robot is in a continuous walking harvesting working condition, the image processor 10 sends the spatial coordinates S 1、S2、……Si……Sn of multiple strings of target grape picking points in the hand-eye combined three-dimensional interested region 17 to the main controller 15, the main controller 15 controls the mechanical arm 4 to conduct constant width cyclic picking path planning on all the grapes identified in the hand-eye combined three-dimensional interested region 17 according to the parity of the data of the picking motion counter 16 between two boundary endpoints of A, B with the operation width edge mirror symmetry relative to the axial plane of the robot;
The main controller 15 transmits the constant-width cycle picking path planning data to the picking point walking error amount compensation module 14, the picking point walking error amount compensation module 14 compensates the error of the space coordinates S i of each picking path point during continuous walking, the compensated coordinates S i' of each picking point are transmitted to the main controller 15, the mechanical arm 4 is controlled to pull the cutting type circular cutter end effector 5 with certain tolerance to execute the picking action of accurately positioning the picking point in the continuous walking state, meanwhile, the main controller 15 adjusts the operation height of the fruit box 7 according to the depth value of the space coordinates of the picking point, and no damage is caused to fruit harvesting under the three-dimensional region of interest 17 of the hand-eye combination;
So far, the harvesting robot completes continuous walking, cutting and harvesting operation of the trellis grape under the continuous walking state of the autonomous walking chassis module 3.
The examples are preferred embodiments of the present invention, but the present invention is not limited to the above-described embodiments, and any obvious modifications, substitutions or variations that can be made by one skilled in the art without departing from the spirit of the present invention are within the scope of the present invention.

Claims (9)

1.一种连续行走的切接采收机器人的作业方法，其特征在于，所述连续行走的切接采收机器人，包括：1. A method for operating a continuously walking cutting and harvesting robot, characterized in that the continuously walking cutting and harvesting robot comprises: 切接采收路径规划子系统，包括切割式采摘模块(1)、浮动接果模块(2)和采摘路径规划控制模块(12)，所述浮动接果模块(2)和切割式采摘模块(1)依次沿自主行走底盘模块(3)的纵向中心线固定安装于其前端和中部，所述采摘路径规划控制模块(12)内置采摘运动计数器(16)，通过采摘运动计数器(16)统计切割式采摘模块(1)的机械臂(4)动作次数的奇偶性，进而调节机械臂(4)的运动方向；A cutting and harvesting path planning subsystem comprises a cutting picking module (1), a floating fruit receiving module (2) and a picking path planning control module (12), wherein the floating fruit receiving module (2) and the cutting picking module (1) are fixedly mounted on the front end and the middle part of the autonomous walking chassis module (3) along the longitudinal center line thereof, and the picking path planning control module (12) has a built-in picking motion counter (16), which counts the odd and even number of motions of the mechanical arm (4) of the cutting picking module (1) through the picking motion counter (16), thereby adjusting the motion direction of the mechanical arm (4); 手眼动作-拍照时序协同调控子系统，包括深度相机(9)和图像处理器(10)，所述深度相机(9)与图像处理器(10)信号连接；深度相机(9)沿自主行走底盘模块(3)尾端的纵向中心线水平安装在相机支架(11)上；A hand-eye movement-photographing timing coordinated control subsystem includes a depth camera (9) and an image processor (10), wherein the depth camera (9) is signal-connected to the image processor (10); the depth camera (9) is horizontally mounted on a camera bracket (11) along the longitudinal centerline of the rear end of the autonomous walking chassis module (3); 采摘路径点行走误差量补偿子系统，包括自主行走底盘模块(3)、行走速度调控模块(13)和采摘点行走误差量补偿模块(14)，所述行走速度调控模块(13)根据果实分布密度调节自主行走底盘模块(3)行走速度，所述采摘点行走误差量补偿模块(14)控制机械臂(4)在机器人连续行走状态下精准定位果梗采摘点的空间坐标；A picking path point walking error compensation subsystem comprises an autonomous walking chassis module (3), a walking speed control module (13) and a picking point walking error compensation module (14), wherein the walking speed control module (13) adjusts the walking speed of the autonomous walking chassis module (3) according to the fruit distribution density, and the picking point walking error compensation module (14) controls the robot arm (4) to accurately locate the spatial coordinates of the fruit stem picking point when the robot is in a continuous walking state; 所述机械臂(4)、采摘路径规划控制模块(12)、行走速度调控模块(13)和采摘点行走误差量补偿模块(14)均与主控制器(15)双向通信；所述机械臂(4)、自主行走底盘模块(3)、升降平台(8)的动作由主控制器(15)控制；The mechanical arm (4), the picking path planning control module (12), the walking speed control module (13), and the picking point walking error compensation module (14) all communicate bidirectionally with the main controller (15); the movements of the mechanical arm (4), the autonomous walking chassis module (3), and the lifting platform (8) are controlled by the main controller (15); 所述作业方法为：The operation method is: 自主行走底盘模块(3)纵向对齐果树行线后静止并等待行走指令，机械臂(4)的末端运动至右边界端点A等待采摘动作指令，果箱(7)的底座上升至距离地面高度h1等待浮动接果收获指令；The autonomous walking chassis module (3) is aligned longitudinally with the fruit tree line and then stops and waits for a walking instruction. The end of the robotic arm (4) moves to the right boundary endpoint A and waits for a picking action instruction. The base of the fruit box (7) rises to a height h1 from the ground and waits for a floating fruit harvesting instruction. 深度相机(9)对手眼组合三维感兴趣区域(17)连续检测，并根据手眼组合三维感兴趣区域(17)果实的实际分布情况，在采摘目标搜寻工况和连续行走采收工况之间进行自主选择，然后将手眼组合三维感兴趣区域(17)内的葡萄数量k传输给行走速度调控模块(13)，进而调控自主行走底盘模块(3)沿果树行线匀速直线行走的速度vk；The depth camera (9) continuously detects the hand-eye combined three-dimensional region of interest (17), and autonomously selects between a picking target search mode and a continuous walking harvesting mode according to the actual distribution of fruits in the hand-eye combined three-dimensional region of interest (17). Then, the number k of grapes in the hand-eye combined three-dimensional region of interest (17) is transmitted to the walking speed control module (13), thereby regulating the speed vk of the autonomous walking chassis module (3) walking uniformly along the fruit tree row line. 当机器人处于连续行走采收工况，图像处理器(10)将手眼组合三维感兴趣区域(17)内多串目标葡萄采摘点空间坐标S1、S2、……Si……Sn发送给主控制器(15)，主控制器(15)控制机械臂(4)在作业幅宽边缘相对机器人中轴面镜像对称的A、B两个边界端点间，根据采摘运动计数器(16)统计的数据奇偶性对手眼组合三维感兴趣区域(17)内识别到的所有葡萄进行定幅宽循环采摘路径规划；When the robot is in a continuous walking harvesting state, the image processor (10) sends the spatial coordinates S1 , S2 , ... Si ... Sn of the picking points of multiple target grape bunches in the hand-eye combined three-dimensional interest region (17) to the main controller (15). The main controller (15) controls the robot arm (4) to perform fixed-width cyclic picking path planning for all grapes identified in the hand-eye combined three-dimensional interest region (17) between the two boundary endpoints A and B that are mirror-symmetrical relative to the robot's central axis at the edge of the working width according to the parity of the data counted by the picking motion counter (16); 基于定幅宽循环采摘路径规划，采摘点行走误差量补偿模块(14)对连续行走时各采摘路径点的空间坐标Si的误差进行补偿，将补偿的各采摘点坐标Si ′传输给主控制器(15)，控制机械臂(4)执行连续行走状态下精准定位采摘点的采摘动作，同时根据采摘点空间坐标深度值调节果箱(7)的作业高度，在手眼组合三维感兴趣区域(17)正下方无损接果收获。Based on the fixed-width cyclic picking path planning, the picking point walking error compensation module (14) compensates for the error of the spatial coordinates Si of each picking path point during continuous walking, transmits the compensated picking point coordinates Si ' to the main controller (15), controls the robot arm (4) to perform the picking action of accurately locating the picking point under the continuous walking state, and adjusts the operating height of the fruit box (7) according to the depth value of the picking point spatial coordinate, so as to harvest the fruit without damage right below the hand-eye combination three-dimensional interest area (17). 2.根据权利要求1所述的作业方法，其特征在于，所述根据手眼组合三维感兴趣区域(17)果实的实际分布情况，在采摘目标搜寻工况和连续行走采收工况之间进行自主选择，具体为：2. The operation method according to claim 1 is characterized in that the actual distribution of fruits in the hand-eye combined three-dimensional interest area (17) is used to autonomously select between the picking target search working condition and the continuous walking harvesting working condition, specifically: 连续行走的切接采收机器人处于采摘目标搜寻工况时，深度相机(9)随着机器人向前行走，主控制器(15)控制深度相机(9)对手眼组合三维感兴趣区域(17)连续检测，当识别到有葡萄进入手眼组合三维感兴趣区域(17)中，图像处理器(10)实时获取手眼组合三维感兴趣区域(17)中每串葡萄的采摘点空间坐标Si，由主控制器(15)提取深度方向距离机器人最近的采摘点空间坐标深度值ymin；当深度值ymin≤900mm，控制深度相机(9)拍摄当前时刻的单帧图像，并立即关闭深度相机(9)的连续检测功能，主控制器(15)根据该帧图像所有葡萄的采摘点空间坐标Si，控制机械臂(4)进行采摘；由此，实现了采摘目标搜寻工况到连续行走采收工况的切换；When the continuously walking splicing harvesting robot is in a picking target search mode, the depth camera (9) moves forward with the robot, and the main controller (15) controls the depth camera (9) to continuously detect the hand-eye combination three-dimensional interest region (17). When it is recognized that grapes enter the hand-eye combination three-dimensional interest region (17), the image processor (10) obtains the picking point spatial coordinates Si of each bunch of grapes in the hand-eye combination three-dimensional interest region (17) in real time, and the main controller (15) extracts the depth value ymin of the picking point spatial coordinate closest to the robot in the depth direction; when the depth value ymin ≤900mm, the depth camera (9) is controlled to capture a single frame image at the current moment, and the continuous detection function of the depth camera (9) is immediately turned off. The main controller (15) controls the robot arm (4) to pick grapes according to the picking point spatial coordinates Si of all grapes in the frame image; thereby, the switching from the picking target search mode to the continuous walking harvesting mode is realized; 连续行走的切接采收机器人处于连续行走采收工况时，采摘运动计数器(16)的数据奇偶性变化触发深度相机(9)的拍照信号，当深度相机(9)得到的最后一帧图像中没有葡萄位于手眼组合三维感兴趣区域(17)内，主控制器(15)触发深度相机(9)的连续检测功能，且机械臂(4)立即复位至右边界端点A等待采摘动作指令，实现连续行走采收工况到采摘目标搜寻工况的切换。When the continuously walking splicing harvesting robot is in a continuous walking harvesting mode, the parity change of the data of the picking motion counter (16) triggers the photo signal of the depth camera (9). When no grapes are located in the hand-eye combined three-dimensional interest area (17) in the last frame image obtained by the depth camera (9), the main controller (15) triggers the continuous detection function of the depth camera (9), and the robot arm (4) immediately resets to the right boundary endpoint A to wait for the picking action instruction, thereby realizing the switching from the continuous walking harvesting mode to the picking target search mode. 3.根据权利要求2所述的作业方法，其特征在于，所述定幅宽循环采摘路径规划具体为：主控制器(15)提取所有采摘点空间坐标的水平宽度方向分量xi，然后对所有采摘目标进行从左向右或从右向左的单向采摘路径规划，经过采摘点行走误差量补偿模块(14)补偿后，主控制器(15)控制机械臂(4)位于机器人作业幅宽边缘相对机器人中轴面镜像对称的A、B两个边界端点间，循环执行动作幅宽固定的采摘动作；其中：A点为采收机器人的右边界端点，B点为采收机器人的左边界端点；3. The operation method according to claim 2 is characterized in that the fixed-width cyclic picking path planning is specifically as follows: the main controller (15) extracts the horizontal width direction component x i of the spatial coordinates of all picking points, and then performs unidirectional picking path planning from left to right or from right to left for all picking targets. After compensation by the picking point walking error compensation module (14), the main controller (15) controls the robot arm (4) to be located between the two boundary endpoints A and B that are mirror-symmetrical relative to the robot's central axis at the edge of the robot's working width, and cyclically executes the picking action with a fixed action width; wherein: point A is the right boundary endpoint of the harvesting robot, and point B is the left boundary endpoint of the harvesting robot; 采摘运动计数器(16)从0开始统计机械臂(4)在A、B两个边界端点间的动作次数；当动作次数为奇数，机械臂(4)的采摘动作方向均为从右向左，对应的采摘路径为A→S1→S2→……→Sm→B；当动作次数为偶数，机械臂(4)的采摘动作方向均为从左向右，对应的采摘路径为B→Sm+1→Sm+2→……→Sn-1→Sn→A；其中，m表示机械臂(4)从右边界端点A向左边界端点B执行采摘动作过程中累计采摘的葡萄数量，n表示机械臂(4)从右边界端点A向左边界端点B再返回右边界端点A执行采摘动作过程中累计采摘的葡萄数量，n＞m。The picking motion counter (16) starts counting the number of actions of the robot arm (4) between the two boundary endpoints A and B from 0; when the number of actions is an odd number, the picking action direction of the robot arm (4) is from right to left, and the corresponding picking path is A→S 1 →S 2 →……→S m →B; when the number of actions is an even number, the picking action direction of the robot arm (4) is from left to right, and the corresponding picking path is B→S m+1 →S m+2 →……→S n-1 →S n →A; wherein, m represents the cumulative number of grapes picked by the robot arm (4) during the picking action from the right boundary endpoint A to the left boundary endpoint B, and n represents the cumulative number of grapes picked by the robot arm (4) during the picking action from the right boundary endpoint A to the left boundary endpoint B and then back to the right boundary endpoint A, and n＞m. 4.根据权利要求3所述的作业方法，其特征在于，所述右边界端点A、左边界端点B的空间坐标均位于机械臂(4)的空间基坐标系，A＝(xA，yA，zA)、B＝(xB，yB，zB)满足：4. The operation method according to claim 3, characterized in that the spatial coordinates of the right boundary endpoint A and the left boundary endpoint B are both located in the spatial base coordinate system of the robot arm (4), A = ( xA , yA , zA ) and B = ( xB , yB , zB ) satisfying: 其中：B、H、D分别表示连续行走的切接采收机器人的作业幅宽范围、作业高度范围和作业深度范围。Wherein: B, H, and D represent the operating width range, operating height range, and operating depth range of the continuously walking cutting and harvesting robot, respectively. 5.根据权利要求1所述的作业方法，其特征在于，所述自主行走底盘模块(3)沿果树行线匀速直线行走的速度vk满足：5. The operation method according to claim 1, characterized in that the speed vk of the autonomous walking chassis module (3) walking uniformly and straight along the row of fruit trees satisfies: 其中：vk1＞vk2＞vk3＞0。Among them: v k1 ＞v k2 ＞v k3 ＞0. 6.根据权利要求1所述的作业方法，其特征在于，所述采摘点行走误差量补偿模块(14)对连续行走时各采摘路径点的空间坐标Si的误差进行补偿，具体为：6. The operation method according to claim 1, characterized in that the picking point walking error compensation module (14) compensates for the error of the spatial coordinates Si of each picking path point during continuous walking, specifically: 采摘点行走误差量补偿模块(14)计算自主行走底盘模块(3)行走里程相对于地面绝对坐标系的位移量ΔSi＝(Δxi，Δyi，Δzi)，作为各采摘路径点的行走误差补偿量，得到采摘路径中补偿的各采摘点空间坐标Si ′(xi ′，yi ′，zi ′)，将Si ′反馈至主控制器(15)，控制机械臂(4)执行采摘动作；所述补偿的各采摘点空间坐标Si ′满足：The picking point walking error compensation module (14) calculates the displacement of the autonomous walking chassis module (3) walking mileage relative to the ground absolute coordinate system ΔS i = ( Δxi , Δyi , Δzi ) as the walking error compensation of each picking path point, obtains the compensated picking point spatial coordinates S i ′ (xi ′ , yi ′ , zi ′ ) in the picking path , feeds S i ′ back to the main controller (15), and controls the robot arm (4) to perform the picking action; the compensated picking point spatial coordinates S i ′ satisfy: 其中：ti表示机械臂(4)到达各采摘点空间坐标Si所需的时间，vkx、vky和vkz分别为自主行走底盘模块(3)沿采收机器人作业宽度x、深度y和高度z方向的速度分量；Where: ti represents the time required for the robotic arm (4) to reach the spatial coordinates Si of each picking point, vkx , vky and vkz are the velocity components of the autonomous walking chassis module (3) along the working width x, depth y and height z directions of the harvesting robot respectively; 所述机械臂(4)到达各采摘点空间坐标Si所需的时间ti满足：The time ti required for the robotic arm (4) to reach the spatial coordinates Si of each picking point satisfies: 其中：Mi表示相邻采摘路径点之间的欧式距离，且：Where: Mi represents the Euclidean distance between adjacent picking path points, and: 7.根据权利要求4所述的作业方法，其特征在于，所述手眼组合三维感兴趣区域(17)是机械臂(4)的工作空间和深度相机(9)的视场空间共同确定的公共三维区域所形成的最大内接长方体区域。7. The operating method according to claim 4 is characterized in that the hand-eye combined three-dimensional area of interest (17) is the largest inscribed rectangular parallelepiped area formed by the common three-dimensional area jointly determined by the working space of the robotic arm (4) and the field of view space of the depth camera (9). 8.根据权利要求4所述的作业方法，其特征在于，所述切割式采摘模块(1)包括机械臂(4)、切割式圆盘刀末端执行器(5)和机械臂基座(6)，所述机械臂基座(6)固定在自主行走底盘模块(3)上方，所述机械臂(4)固定在机械臂基座(6)上方，所述切割式圆盘刀末端执行器(5)固定在机械臂(4)的末端腕部且工作姿态始终水平。8. The operating method according to claim 4 is characterized in that the cutting picking module (1) includes a robotic arm (4), a cutting disc knife end effector (5) and a robotic arm base (6), the robotic arm base (6) is fixed above the autonomous walking chassis module (3), the robotic arm (4) is fixed above the robotic arm base (6), the cutting disc knife end effector (5) is fixed at the end wrist of the robotic arm (4) and the working posture is always horizontal. 9.根据权利要求4所述的作业方法，其特征在于，所述浮动接果模块(2)包括果箱(7)和升降平台(8)，所述升降平台(8)固定在自主行走底盘模块(3)上方，所述果箱(7)可拆卸连接在升降平台(8)上方。9. The operating method according to claim 4 is characterized in that the floating fruit receiving module (2) includes a fruit box (7) and a lifting platform (8), the lifting platform (8) is fixed above the autonomous walking chassis module (3), and the fruit box (7) is detachably connected above the lifting platform (8).
CN202410426414.4A 2024-04-10 2024-04-10 A continuous walking cutting and harvesting robot and its operation method Active CN118355792B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202410426414.4A CN118355792B (en) 2024-04-10 2024-04-10 A continuous walking cutting and harvesting robot and its operation method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202410426414.4A CN118355792B (en) 2024-04-10 2024-04-10 A continuous walking cutting and harvesting robot and its operation method

Publications (2)

Publication Number Publication Date
CN118355792A CN118355792A (en) 2024-07-19
CN118355792B true CN118355792B (en) 2025-10-03

Family

ID=91883357

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202410426414.4A Active CN118355792B (en) 2024-04-10 2024-04-10 A continuous walking cutting and harvesting robot and its operation method

Country Status (1)

Country Link
CN (1) CN118355792B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN119302091A (en) * 2024-09-29 2025-01-14 西北农林科技大学 A film-following guidance control system and method based on OpenCV

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110249793A (en) * 2019-05-09 2019-09-20 江苏大学 A robot end-depth camera configuration method and servo control method for trellis grape harvesting
CN111602517A (en) * 2020-05-28 2020-09-01 华南农业大学 A distributed visual active perception method for string fruit and its application

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
GB201802335D0 (en) * 2018-02-13 2018-03-28 Norwegian Univ Of Life Sciences Device for picking fruit
CN111590581B (en) * 2020-05-26 2021-10-22 珠海格力智能装备有限公司 Positioning compensation method and device for robot
CN111673755B (en) * 2020-06-24 2023-02-03 西北农林科技大学 Picking robot control system and method based on visual servo
CN116985150B (en) * 2023-09-28 2023-12-26 北京市农林科学院智能装备技术研究中心 Method and device for smooth fruit collection trajectory planning

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110249793A (en) * 2019-05-09 2019-09-20 江苏大学 A robot end-depth camera configuration method and servo control method for trellis grape harvesting
CN111602517A (en) * 2020-05-28 2020-09-01 华南农业大学 A distributed visual active perception method for string fruit and its application

Also Published As

Publication number Publication date
CN118355792A (en) 2024-07-19

Similar Documents

Publication Publication Date Title
US11202409B1 (en) Robotic harvesting system with a gantry system
Rong et al. Fruit pose recognition and directional orderly grasping strategies for tomato harvesting robots
CN109773788B (en) Fruit and vegetable picking robot and control method thereof
CN114946439B (en) An intelligent and precise topping device for field cotton
Van Henten et al. An autonomous robot for harvesting cucumbers in greenhouses
US11477942B2 (en) Robotic fruit harvesting machine with fruit-pair picking and hybrid motorized-pneumatic robot arms
WO2023050783A1 (en) Weeding robot and method and apparatus for planning weeding path thereof, and medium
Yuan et al. An autonomous pollination robot for hormone treatment of tomato flower in greenhouse
CN112715162A (en) System for intelligent string type fruit of picking
CN118355792B (en) A continuous walking cutting and harvesting robot and its operation method
CN116117807A (en) Chilli picking robot and control method
JP2014183841A (en) Automatic plant harvester, automatic plant harvesting program and method
CN110249793B (en) A robot end-depth camera configuration method and servo control method for grape harvesting on trellis
WO2023231408A1 (en) Automatic fruit harvesting apparatus mounted on unmanned aerial vehicle, and control method therefor
CN120313575A (en) An autonomous navigation system for agricultural robots based on three-dimensional point cloud model
CN117678440B (en) Automatic target adjustment gesture trimming system and method based on three-dimensional point cloud
CN117044496A (en) A broccoli selective harvesting robot and its control method
CN112703894A (en) Fully-autonomous cherry picking robot based on visual servo and SLAM
CN118140705A (en) Automatic lotus seedpod harvesting system and method based on cooperation of double unmanned aerial vehicles
JP2021122179A (en) Crop harvest vehicle
Shamshiri et al. An overview of visual servoing for robotic manipulators in digital agriculture
Hulens et al. The autonomous pollination drone
CN113924861A (en) Automatic harvesting system for greenhouse vegetable cultivation
CN113966669A (en) Automatic pineapple picking plug-in device and picking method
CN118696710B (en) A contour-profiling harvesting robot system for horizontal trellis fruits and its operation method

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant