CN113228938A - SLAM laser vision navigation method for picking robot - Google Patents
SLAM laser vision navigation method for picking robot Download PDFInfo
- Publication number
- CN113228938A CN113228938A CN202110603365.3A CN202110603365A CN113228938A CN 113228938 A CN113228938 A CN 113228938A CN 202110603365 A CN202110603365 A CN 202110603365A CN 113228938 A CN113228938 A CN 113228938A
- Authority
- CN
- China
- Prior art keywords
- picking
- picking robot
- robot
- slam
- laser
- 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 29
- 239000002420 orchard Substances 0.000 claims abstract description 25
- 235000013399 edible fruits Nutrition 0.000 claims description 16
- 239000011159 matrix material Substances 0.000 claims description 3
- 244000099147 Ananas comosus Species 0.000 claims description 2
- 235000007119 Ananas comosus Nutrition 0.000 claims description 2
- 240000008067 Cucumis sativus Species 0.000 claims description 2
- 235000010799 Cucumis sativus var sativus Nutrition 0.000 claims description 2
- 235000007688 Lycopersicon esculentum Nutrition 0.000 claims description 2
- 244000183278 Nephelium litchi Species 0.000 claims description 2
- 241000508269 Psidium Species 0.000 claims description 2
- 240000003768 Solanum lycopersicum Species 0.000 claims description 2
- 238000003306 harvesting Methods 0.000 claims 4
- 230000005540 biological transmission Effects 0.000 claims 1
- 230000000007 visual effect Effects 0.000 abstract description 6
- 238000010586 diagram Methods 0.000 description 4
- 238000009434 installation Methods 0.000 description 3
- 238000005259 measurement Methods 0.000 description 2
- 239000002184 metal Substances 0.000 description 2
- 230000000903 blocking effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 239000012636 effector Substances 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
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
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
- G01S17/86—Combinations of lidar systems with systems other than lidar, radar or sonar, e.g. with direction finders
Abstract
The invention discloses a SLAM laser visual navigation method of a picking robot, which comprises the steps of firstly shooting orchard pictures by an unmanned aerial vehicle, and establishing an SLAM map through image recognition; then the picking robot scans the reflector through the laser emitter, and the position of the picking robot in the orchard is determined through geometric calculation; and then, the autonomous navigation picking robot moves to a picking position by combining with the SLAM map, so that the picking robot realizes picking operation. According to the invention, the SLAM map is established by the unmanned aerial vehicle, so that the method is convenient and accurate in positioning; then, according to the SLAM map, the picking robot can be quickly and autonomously navigated to a picking position, and picking navigation efficiency is improved.
Description
Technical Field
The invention belongs to the field of agricultural intelligent robots, and particularly relates to a SLAM laser visual navigation method for a picking robot.
Background
Fruit picking is a laborious and time-consuming process for fruit growers. With the continuous rising of labor cost, the orchard picking hopes to adopt an automatic method to pick, and the efficiency of orchard farmers is improved. Picking robots begin to be popularized in orchard picking at present. However, the picking robot has the problems that the robot does not have a map when moving autonomously, and the robot walking autonomous navigation is difficult due to the complex field environment. Patent CN102682286A discloses a picking robot fruit identification method based on a laser vision system, the laser vision method is to scan the fruit, but not to autonomous movement navigation of the robot vehicle. Patent CN111837640A discloses an intelligent hillside orchard picking robot based on visual identification, which uses a binocular camera for visual navigation and is effective for short-distance measurement; however, the method needs to continuously repeat image scanning and image splicing for a large-scale field, so that the calculation of SLAM map measurement is relatively complex.
Disclosure of Invention
The invention aims to overcome the defects in the prior art and provide an accurate and rapid SLAM laser visual navigation method for a picking robot, so that the picking robot can rapidly reach a picking position.
The purpose of the invention is realized by the following technical scheme:
a picking robot SLAM laser visual navigation method is characterized in that an unmanned aerial vehicle is used for shooting pictures of an orchard, an SLAM map is established through image recognition, and each fruit tree, path and laser reflector of the orchard are marked in the SLAM map; the picking robot scans the reflector through the laser emitter, and the position of the picking robot in the orchard is determined through geometric calculation; and then, the self-navigation picking robot moves to a picking position by combining with a pre-made SLAM map, so that the picking robot realizes picking operation.
More specifically, the SLAM laser vision navigation method for the picking robot comprises the following steps:
(1) the method comprises the following steps of (1) establishing a SLAM map of mobile navigation of the picking robot: placing a reflector 300 with two or more positioning icons and a picking robot in a picking place; then, an unmanned aerial vehicle 1000 is adopted to shoot above the picking place, the shot picture is subjected to image recognition of a two-dimensional picture, and coordinate position data of the orchard 2000, each fruit tree 900, the picking robot 500, the laser emitter 200 and the reflector 300 are calibrated on the picture to obtain a navigation SLAM map;
(2) establishing the position coordinates of the picking robot in the orchard: the picking robot comprises a moving platform 700, a binocular vision system 400 and a manipulator 500, wherein a rotary laser emitter 200 is mounted on the moving platform 700, the laser emitter 200 scans a reflector 300 for positioning an icon, and the coordinate of the moving platform in an orchard is determined by adopting a triangular geometry method; then automatically navigating the mobile platform 700 to the picking position according to the position of the mobile platform 700 in the orchard and a predetermined SLAM map;
(3) picking operation: after the picking robot reaches the picking position, the binocular vision system 400 measures the XYZ space coordinates of the manipulator execution unit reaching the fruit picking position; then calculating the motion of each joint of the mechanical arm by a robot kinematics method, establishing a D-H coordinate, and obtaining a forward motion formula and a reverse motion formula by adopting matrix calculation; and programming by using a reverse motion formula to calculate the coordinates of each joint, and driving each joint of the picking robot to move to finish picking positioning.
The picking robot comprises a mobile platform 700, a binocular vision system 400 and a manipulator 500; the moving platform 700 is an AGV moving platform; the mobile platform 700 is provided with a laser emitter support rod 100 and a manipulator lifting platform 600, the laser emitter support rod 100 is provided with a rotary laser emitter 200, and the manipulator lifting platform 600 is provided with a picking manipulator 500.
The number of the reflecting mirrors 300 is preferably 2-3, the mounting height of the reflecting mirrors 300 can avoid the shielding of fruit trees, and the laser beams emitted by the laser emitter 200 can be made to strike the reflecting mirrors 300. The reflector is made of polished metal sheet, and the bottom of the reflector is inserted into the ground and fixed.
Compared with the prior art, the invention has the following advantages and effects: according to the invention, the SLAM map is established by the unmanned aerial vehicle, so that the method is convenient and accurate in positioning; then, according to the SLAM map, the picking robot can be quickly and autonomously navigated to a picking position, and picking navigation efficiency is improved.
Drawings
Fig. 1 is a schematic diagram of picking robot mobile navigation and picking positioning.
Fig. 2 is a schematic structural diagram of the picking robot.
Fig. 3 is a schematic diagram of the building of the SLAM map.
Fig. 4 is a schematic diagram for establishing coordinates of the picking robot in the orchard.
Fig. 5 is a schematic view of a binocular vision system of the picking robot.
The figure includes: the system comprises a laser emitter supporting rod 100, a laser emitter 200, a reflector 300, a binocular vision system 400, a picking manipulator 500, a manipulator lifting platform 600, a moving platform 700, a fruit tree 900, an unmanned aerial vehicle 1000 and an orchard 2000.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Examples
The navigation method of the invention can be implemented in the navigation of various picking robots as long as the picking robots can enter the picking position, such as: litchi picking robot, cucumber picking robot, guava picking robot, pineapple picking robot, tomato picking robot, and the like.
As shown in fig. 1 and 2, the picking robot of the present invention comprises a mobile platform 700, a binocular vision system 400 and a manipulator 500; the moving platform 700 is an AGV moving platform; the mobile platform 700 is provided with a laser emitter support rod 100 and a manipulator lifting platform 600, the laser emitter support rod 100 is provided with a rotary laser emitter 200, and the manipulator lifting platform 600 is provided with a picking manipulator 500. Binocular vision system 400 is an eye-in-hand method, in which a binocular vision camera is mounted on an end effector of a picking robot, as shown in fig. 5.
In the embodiment, 2 or more reflectors 300 are adopted, the installation height of the reflectors 300 is higher than that of a picking manipulator, the installation height of the reflectors 300 can be kept away from a fruit tree, the installation height of the reflectors 300 is higher than that of the picking manipulator, the manipulator is prevented from blocking the sight of the laser emitter, and a laser beam emitted by the laser emitter 200 is required to be capable of striking the reflectors 300. The reflector is made of polished metal sheet, and the bottom of the reflector is inserted into the ground and fixed. In operation, the reflector is fixed in advance, and a SLAM map of navigation is established through the reflection scanning of the laser to the reflector.
The SLAM laser vision navigation method of the picking robot comprises the following steps:
(1) the method comprises the following steps of (1) establishing a SLAM map of mobile navigation of the picking robot: as shown in fig. 3, two or more mirrors 300 of positioning icons, and a picking robot are placed at the picking site; then, an unmanned aerial vehicle 1000 is adopted to shoot above the picking place, the shot picture is subjected to image recognition of a two-dimensional picture, and coordinate position data of an orchard 2000, each fruit tree 900, a picking robot 500, a laser emitter 200 and two or more reflectors 300 are calibrated on the picture to obtain a navigation SLAM map;
(2) establishing the position coordinates of the picking robot in the orchard: the laser transmitter 200 scans two or more reflectors 300, and the coordinates of the mobile platform in the orchard are determined by adopting a triangular geometry method, as shown in fig. 4; then automatically navigating the mobile platform 700 to the picking position according to the position of the mobile platform 700 in the orchard and a predetermined SLAM map;
(3) picking operation: after the picking robot reaches the picking position, the binocular vision system 400 measures the XYZ space coordinates of the manipulator execution unit reaching the fruit picking position; then calculating the motion of each joint of the mechanical arm through inverse operation, establishing a D-H coordinate, and obtaining a forward motion formula and a reverse motion formula by adopting matrix calculation; and then programming and calculating the coordinates of each joint by using a reverse motion formula, and driving each joint of the picking robot to move to finish picking positioning so as to realize fruit picking.
The above description is only an example of the present invention, but the present invention is not limited to the above example, and any other changes, modifications, substitutions, combinations, and simplifications which do not depart from the spirit and principle of the present invention and are equivalent to each other are included in the protection scope of the present invention.
Claims (5)
1. A SLAM laser vision navigation method of a picking robot is characterized in that: firstly, shooting a picture of an orchard by using an unmanned aerial vehicle, and establishing an SLAM map through image recognition; then the picking robot scans the reflector through the laser emitter, and the position of the picking robot in the orchard is determined through geometric calculation; and then, the autonomous navigation picking robot moves to a picking position by combining with the SLAM map, so that the picking robot realizes picking operation.
2. The harvesting robot SLAM laser vision navigation method of claim 1, comprising the steps of:
(1) the method comprises the following steps of (1) establishing a SLAM map of mobile navigation of the picking robot: placing two or more reflectors of positioning icons and a picking robot in a picking place; then, an unmanned aerial vehicle is adopted to shoot above the picking place, the shot picture is subjected to image recognition of a two-dimensional picture, and coordinate position data of an orchard, each fruit tree, a picking robot, a laser emitter and a reflector are calibrated on the picture to obtain a navigation SLAM map;
(2) establishing the position coordinates of the picking robot in the orchard: the picking robot comprises a moving platform, a binocular vision system and a manipulator, wherein a rotary laser transmitter is mounted on the moving platform, the laser transmitter scans a reflector of a positioning icon, and the coordinate of the moving platform in the orchard is determined by adopting a triangular geometry method; then automatically navigating the mobile platform to the picking position according to the position of the mobile platform in the orchard and the SLAM map determined in the step (1);
(3) picking operation: after the picking robot reaches the picking position, an XYZ space coordinate of the position of the manipulator execution unit reaching the fruit picking position is measured by a binocular vision system; then calculating the motion of each joint of the mechanical arm through inverse operation, establishing a D-H coordinate, and obtaining a forward motion formula and a reverse motion formula by adopting matrix calculation; and programming by using a reverse motion formula to calculate the coordinates of each joint, and driving each joint of the picking robot to move to finish picking positioning.
3. The harvesting robot SLAM laser vision navigation method of claim 1 or 2, wherein: the picking robot comprises a mobile platform, a binocular vision system and a manipulator; the moving platform is an AGV moving platform; the mobile platform is provided with a laser emitter support rod and a manipulator lifting platform, the laser emitter support rod is provided with a rotary laser emitter, and the manipulator lifting platform is provided with a picking manipulator.
4. The harvesting robot SLAM laser vision navigation method of claim 1 or 2, wherein: the quantity of speculum is 2 ~ 3, and the mounting height of speculum will avoid the fruit tree to shelter from to need to make the laser beam of laser emitter transmission can beat on the speculum.
5. The harvesting robot SLAM laser vision navigation method of claim 1 or 2, wherein: the picking robot is a litchi picking robot, a cucumber picking robot, a guava picking robot, a pineapple picking robot or a tomato picking robot.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110603365.3A CN113228938A (en) | 2021-05-31 | 2021-05-31 | SLAM laser vision navigation method for picking robot |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110603365.3A CN113228938A (en) | 2021-05-31 | 2021-05-31 | SLAM laser vision navigation method for picking robot |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113228938A true CN113228938A (en) | 2021-08-10 |
Family
ID=77135905
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110603365.3A Pending CN113228938A (en) | 2021-05-31 | 2021-05-31 | SLAM laser vision navigation method for picking robot |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113228938A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113618746A (en) * | 2021-10-13 | 2021-11-09 | 季华实验室 | Robot navigation control method and device, electronic equipment and storage medium |
| CN114766207A (en) * | 2022-04-15 | 2022-07-22 | 杭州电子科技大学 | Machine vision-based Chinese cherry picking and sorting method |
| CN115104432A (en) * | 2022-07-08 | 2022-09-27 | 中山大学 | Picking robot system and method with cooperation of unmanned aerial vehicle and mechanical vehicle |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050126144A1 (en) * | 2003-12-12 | 2005-06-16 | Vision Robotics Corporation | Robot mechanical picker system and method |
| CN102124866A (en) * | 2011-01-19 | 2011-07-20 | 南京农业大学 | Wheel type mobile fruit picking robot and fruit picking method |
| CN102165880A (en) * | 2011-01-19 | 2011-08-31 | 南京农业大学 | Automatic-navigation crawler-type mobile fruit picking robot and fruit picking method |
| CN104584779A (en) * | 2015-01-23 | 2015-05-06 | 桂林电子科技大学 | Apple maturity automatic detection and picking robot based on binocular vision |
| CN107139182A (en) * | 2017-06-05 | 2017-09-08 | 重庆理工大学 | A kind of citrus picking robot system and its control method |
| CN107409634A (en) * | 2017-08-23 | 2017-12-01 | 西北农林科技大学 | One kind plucks platform automatically based on the self-propelled orchard of GPS navigation |
| CN108029340A (en) * | 2017-12-05 | 2018-05-15 | 江苏科技大学 | A kind of picking robot arm and its control method based on adaptive neural network |
| CN108562908A (en) * | 2017-12-21 | 2018-09-21 | 合肥中导机器人科技有限公司 | Laser navigation hybrid locating method, robot navigation method and Laser navigation system |
| CN109392462A (en) * | 2018-12-18 | 2019-03-01 | 北方民族大学 | Pick the robot and method of day lily |
| CN109459023A (en) * | 2018-09-18 | 2019-03-12 | 武汉三体机器人有限公司 | A kind of ancillary terrestrial robot navigation method and device based on unmanned plane vision SLAM |
| CN111602517A (en) * | 2020-05-28 | 2020-09-01 | 华南农业大学 | Distributed visual active perception method for string-type fruits and application of distributed visual active perception method |
| CN111673755A (en) * | 2020-06-24 | 2020-09-18 | 西北农林科技大学 | Picking robot control system and method based on visual servo |
| CN112243698A (en) * | 2020-10-22 | 2021-01-22 | 安徽农业大学 | Automatic walnut picking and collecting method based on multi-sensor fusion technology |
-
2021
- 2021-05-31 CN CN202110603365.3A patent/CN113228938A/en active Pending
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050126144A1 (en) * | 2003-12-12 | 2005-06-16 | Vision Robotics Corporation | Robot mechanical picker system and method |
| CN102124866A (en) * | 2011-01-19 | 2011-07-20 | 南京农业大学 | Wheel type mobile fruit picking robot and fruit picking method |
| CN102165880A (en) * | 2011-01-19 | 2011-08-31 | 南京农业大学 | Automatic-navigation crawler-type mobile fruit picking robot and fruit picking method |
| CN104584779A (en) * | 2015-01-23 | 2015-05-06 | 桂林电子科技大学 | Apple maturity automatic detection and picking robot based on binocular vision |
| CN107139182A (en) * | 2017-06-05 | 2017-09-08 | 重庆理工大学 | A kind of citrus picking robot system and its control method |
| CN107409634A (en) * | 2017-08-23 | 2017-12-01 | 西北农林科技大学 | One kind plucks platform automatically based on the self-propelled orchard of GPS navigation |
| CN108029340A (en) * | 2017-12-05 | 2018-05-15 | 江苏科技大学 | A kind of picking robot arm and its control method based on adaptive neural network |
| CN108562908A (en) * | 2017-12-21 | 2018-09-21 | 合肥中导机器人科技有限公司 | Laser navigation hybrid locating method, robot navigation method and Laser navigation system |
| CN109459023A (en) * | 2018-09-18 | 2019-03-12 | 武汉三体机器人有限公司 | A kind of ancillary terrestrial robot navigation method and device based on unmanned plane vision SLAM |
| CN109392462A (en) * | 2018-12-18 | 2019-03-01 | 北方民族大学 | Pick the robot and method of day lily |
| CN111602517A (en) * | 2020-05-28 | 2020-09-01 | 华南农业大学 | Distributed visual active perception method for string-type fruits and application of distributed visual active perception method |
| CN111673755A (en) * | 2020-06-24 | 2020-09-18 | 西北农林科技大学 | Picking robot control system and method based on visual servo |
| CN112243698A (en) * | 2020-10-22 | 2021-01-22 | 安徽农业大学 | Automatic walnut picking and collecting method based on multi-sensor fusion technology |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113618746A (en) * | 2021-10-13 | 2021-11-09 | 季华实验室 | Robot navigation control method and device, electronic equipment and storage medium |
| CN114766207A (en) * | 2022-04-15 | 2022-07-22 | 杭州电子科技大学 | Machine vision-based Chinese cherry picking and sorting method |
| CN115104432A (en) * | 2022-07-08 | 2022-09-27 | 中山大学 | Picking robot system and method with cooperation of unmanned aerial vehicle and mechanical vehicle |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113228938A (en) | SLAM laser vision navigation method for picking robot | |
| US10278333B2 (en) | Pruning robot system | |
| AU2019208265A1 (en) | Moving robot, method for controlling the same, and terminal | |
| CN111178148B (en) | Ground target geographic coordinate positioning method based on unmanned aerial vehicle vision system | |
| CN109507687B (en) | Search and tracking integrated device and implementation method thereof | |
| CN108507403B (en) | Self propelled Antiaircraft Gun multi-axial cord consistency detection device based on intelligent photoelectric calibration technique | |
| CN109917420A (en) | A kind of automatic travelling device and robot | |
| TW201327078A (en) | Method and system for navigation of movable platform | |
| CN111043963A (en) | Three-dimensional scanning system measuring method of carriage container based on two-dimensional laser radar | |
| CN109276193A (en) | A kind of robot and barrier-avoiding method of adjustable height and position | |
| CN112045682B (en) | Calibration method for solid-state area array laser installation | |
| CN112780275A (en) | Heading machine working system and method | |
| WO2022107588A1 (en) | Moving body, control unit, data generation unit, method for controlling moving body motion, and method for generating data | |
| CN112819943A (en) | Active vision SLAM system based on panoramic camera | |
| CN115299245A (en) | Control method and control system of intelligent fruit picking robot | |
| CN112285725A (en) | Indoor positioning method of single mobile robot based on laser radar | |
| WO2022107587A1 (en) | Moving body, data generating unit, and method for generating data | |
| CN113552589A (en) | Obstacle detection method, robot, and storage medium | |
| CN113503839B (en) | Vegetation parameter is measuring robot independently | |
| CN211008643U (en) | Working system of heading machine | |
| CN212112570U (en) | Camera calibration system based on robot sweeping field | |
| CN116058176A (en) | Fruit and vegetable picking mechanical arm control system based on double-phase combined positioning | |
| CN212193168U (en) | Robot head with laser radars arranged on two sides | |
| CN115060266A (en) | Positioning system for farmland map building | |
| CN113758480A (en) | Surface type laser positioning system, AGV positioning calibration system and AGV positioning 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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210810 |