CN110150260A - A kind of Intelligent target spray weed-eradicating robot based on deep learning - Google Patents
A kind of Intelligent target spray weed-eradicating robot based on deep learning Download PDFInfo
- Publication number
- CN110150260A CN110150260A CN201910501289.8A CN201910501289A CN110150260A CN 110150260 A CN110150260 A CN 110150260A CN 201910501289 A CN201910501289 A CN 201910501289A CN 110150260 A CN110150260 A CN 110150260A
- Authority
- CN
- China
- Prior art keywords
- spray unit
- weeds
- spray
- weed
- deep learning
- 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
Classifications
-
- A—HUMAN NECESSITIES
- A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
- A01M—CATCHING, TRAPPING OR SCARING OF ANIMALS; APPARATUS FOR THE DESTRUCTION OF NOXIOUS ANIMALS OR NOXIOUS PLANTS
- A01M21/00—Apparatus for the destruction of unwanted vegetation, e.g. weeds
- A01M21/04—Apparatus for destruction by steam, chemicals, burning, or electricity
-
- A—HUMAN NECESSITIES
- A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
- A01M—CATCHING, TRAPPING OR SCARING OF ANIMALS; APPARATUS FOR THE DESTRUCTION OF NOXIOUS ANIMALS OR NOXIOUS PLANTS
- A01M7/00—Special adaptations or arrangements of liquid-spraying apparatus for purposes covered by this subclass
- A01M7/0003—Atomisers or mist blowers
- A01M7/0014—Field atomisers, e.g. orchard atomisers, self-propelled, drawn or tractor-mounted
-
- A—HUMAN NECESSITIES
- A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
- A01M—CATCHING, TRAPPING OR SCARING OF ANIMALS; APPARATUS FOR THE DESTRUCTION OF NOXIOUS ANIMALS OR NOXIOUS PLANTS
- A01M7/00—Special adaptations or arrangements of liquid-spraying apparatus for purposes covered by this subclass
- A01M7/005—Special arrangements or adaptations of the spraying or distributing parts, e.g. adaptations or mounting of the spray booms, mounting of the nozzles, protection shields
-
- A—HUMAN NECESSITIES
- A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
- A01M—CATCHING, TRAPPING OR SCARING OF ANIMALS; APPARATUS FOR THE DESTRUCTION OF NOXIOUS ANIMALS OR NOXIOUS PLANTS
- A01M7/00—Special adaptations or arrangements of liquid-spraying apparatus for purposes covered by this subclass
- A01M7/0089—Regulating or controlling systems
-
- A—HUMAN NECESSITIES
- A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
- A01M—CATCHING, TRAPPING OR SCARING OF ANIMALS; APPARATUS FOR THE DESTRUCTION OF NOXIOUS ANIMALS OR NOXIOUS PLANTS
- A01M7/00—Special adaptations or arrangements of liquid-spraying apparatus for purposes covered by this subclass
- A01M7/0089—Regulating or controlling systems
- A01M7/0096—Testing of spray-patterns
Landscapes
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Insects & Arthropods (AREA)
- Pest Control & Pesticides (AREA)
- Wood Science & Technology (AREA)
- Zoology (AREA)
- Environmental Sciences (AREA)
- Catching Or Destruction (AREA)
Abstract
The present invention is directed to invent a Intelligent target based on deep learning to spray weed-eradicating robot, the robot is divided into wheelspan self-regulated vehicular platform and targeting sprays two parts of cell cube, under conditions of adapting to field complex work environment, the type of weeds, leaf age, physiological structure are recognized with depth learning technology, different types of pesticide is imposed for different types of weeds in conjunction with spray unit, to the weeds variable farm chemical applying of identical type difference leaf age, and the physiological structure of weeds is recognized, the meristematic region that medical fluid is sprayed application to weeds, accurately kills weeds.
Description
Technical field:
It is a kind of variable, multiple medicine liquid, the weeding machine precisely sprayed to target the invention belongs to agricultural engineering technology field
People.
Background technique:
Control of weeds is one of most important link in agricultural production, in recent years frequent, a large amount of application enhancing of herbicide
Weeds drug resistances, force the frequency of administration of medicament and dosage to increase year by year, so that environmental pollution, ecological disturbance, food safety
Equal crises are increasingly severe；With the continuous development of precision agriculture, a plurality of pairs of targets have been had already appeared both at home and abroad and have sprayed weed-eradicating robot,
Solve the problems, such as the application of herbicide to a certain extent, but its there is also certain defects: known using traditional identification technology
Other precision is not high, can not identify weed size and weeds three-dimensional physiological structure, cannot apply different remove for different weeds
Careless agent, these problems result in the requirement that existing weed-eradicating robot does not reach precision agriculture to a certain extent.So
The present invention for existing target spray weed-eradicating robot defect have developed it is a can identify variety classes weeds, identification weed size
Weed-eradicating robot is sprayed to target with multiple medicine liquid, the accurate variable of three-dimensional physiological structure.
Summary of the invention:
The present invention is directed to invent a Intelligent target based on deep learning to spray weed-eradicating robot, which is divided into wheelspan certainly
It shunts carrying platform and targeting sprays two parts of cell cube, under conditions of adapting to field complex work environment, with depth
Habit technology recognizes the type of weeds, leaf age, physiological structure, imposes not in conjunction with spray unit for different types of weeds
Congener pesticide is recognized to the weeds variable farm chemical applying of identical type difference leaf age, and to the physiological structure of weeds, by medicine
Liquid sprays application to the meristematic region of weeds, accurately kills weeds.
The present invention is sprayed by the targeting of wheelspan self-regulated robot platform, differential steering system, self-adaption regulation system and medical fluid
System composition, this Intelligent target spray weed-eradicating robot first passes through (4) scissors-type lifting and lifts robot before work, then leads to
It crosses push-rod electric machine cooperation (5) guide post guide sleeve structure and adjusts two sides (2) car body wheelspan to adapt to row spacing adjustable distance as 200mm,
In car body traveling, by two (3) driving wheels and two (1) universal wheels, differential steering is completed so that turning is more flexible.?
Targeting is carried out when spraying operation, due to field ridge height be not it is unalterable, the present invention first passes through in different (9) spray units
(13) ultrasonic distance measuring module calculates (9) spray unit and ground distance, then cooperates (8) sliding rail coarse adjustment by push-rod electric machine
(9) spray unit is saved at a distance from ground, the rear position for keeping (8) sliding rail is constant, and (13) according to different (9) spray units are super
The distance value that sound ranging module is measured, adjusting (10) Y axis sliding rail in real time, to keep spray unit at a distance from ground, makes
It sprays more accurate.And by (12) camera real-time capture field conditions, and (11) X-axis slide unit is adjusted by visual analysis, made
Spray unit so that (12) camera in (9) spray unit possesses the broader visual field, and uses depth in furrow
The image that the method for habit captures camera is analyzed, and weeds type, leaf age, physiological structure is identified, finally by (7) water pump
Water pump in case extracts the pesticide in (6) different pesticide box, the solenoid valve in control (9) spray unit and motor-driven (14)
Rotary nozzle completes multiple medicine liquid, accurate variable sprays target.
Detailed description of the invention:
Fig. 1 is the invention patent front overall schematic
Fig. 2 is the invention patent back side overall schematic
Fig. 3 is the invention patent spray unit schematic diagram
In Fig. 1,1, universal wheel；2, car body；3, driving wheel；4, scissors-type lifting；5, guide post guide sleeve structure；6, pesticide
Case；7, waterproof pump box；8, sliding rail；
In Fig. 2,9, spray unit；
In Fig. 3,10, Y-axis sliding rail；11, X-axis slide rail；12, camera；13, ultrasonic distance measuring module；14, rotary nozzle
Specific embodiment:
It is an object of the invention to invent a kind of Intelligent target spray weed-eradicating robot based on deep learning, the spraying of this Intelligent target
Careless robot first passes through (4) scissors-type lifting and lifts robot before work, then cooperates (5) guide post by push-rod electric machine
Guide sleeve structure adjusts two sides (2) car body wheelspan to adapt to row spacing, in car body traveling, passes through two (3) driving wheels and two (1)
Universal wheel completes differential steering so that turning is more flexible.Carry out targeting spray operation when, since field ridge height is not one one-tenth
Constant, the present invention first passes through (13) ultrasonic distance measuring module in different (9) spray units, calculate (9) spray unit with
Ground distance, then cooperate (8) sliding rail coarse adjustment (9) spray unit at a distance from ground by push-rod electric machine, it is rear to keep (8) sliding rail
Position it is constant, according to the distance value that (13) ultrasonic distance measuring module of different (9) spray units is measured, adjust (10) in real time
Y-axis sliding rail keeps sprinkling more accurate to keep spray unit at a distance from ground.And pass through (12) camera real-time capture field feelings
Condition, and (11) X-axis slide unit is adjusted by visual analysis, make spray unit in furrow, and using the method for deep learning to taking the photograph
As head capture image analyzed, identify weeds type, leaf age, physiological structure, finally by (7) waterproof pump box water pump take out
Take the pesticide in (6) different pesticide box, the solenoid valve in control (9) spray unit and motor-driven (14) rotary nozzle complete
Target is sprayed at multiple medicine liquid, accurate variable.
Claims (6)
1. the present invention is sprayed by the targeting of wheelspan self-regulated robot platform, differential steering system, self-adaption regulation system and medical fluid
System composition, this Intelligent target spray weed-eradicating robot first passes through (4) scissors-type lifting and lifts robot before work, then passes through
Push-rod electric machine cooperation (5) guide post guide sleeve structure adjusts two sides (2) car body wheelspan to adapt to row spacing adjustable distance as 200mm,
During car body is advanced, by two (3) driving wheels and two (1) universal wheels, differential steering is completed so that turning is more flexible.Into
Row targeting is when spraying operation, due to field ridge height be not it is unalterable, the present invention first passes through in different (9) spray units
(13) ultrasonic distance measuring module calculates (9) spray unit and ground distance, then cooperates (8) sliding rail coarse adjustment by push-rod electric machine
(9) spray unit is saved at a distance from ground, the rear position for keeping (8) sliding rail is constant, and (13) according to different (9) spray units are super
The distance value that sound ranging module is measured adjusts (10) Y-axis sliding rail in real time to keep spray unit at a distance from ground, makes to spray
It spills more precisely.And by (12) camera real-time capture field conditions, and (11) X-axis slide unit is adjusted by visual analysis, makes to spray
Unit is spilt in furrow, so that (12) camera in (9) spray unit possesses the broader visual field, and uses deep learning
Method image that camera is captured analyze, weeds type, leaf age, physiological structure are identified, finally by (7) waterproof pump box
In water pump extract the pesticide in (6) different pesticide box, the solenoid valve in control (9) spray unit and motor-driven (14) rotation
Turn spray head completion multiple medicine liquid, accurate variable sprays target.
2. Intelligent target according to claim 1 based on deep learning sprays weed-eradicating robot, it is characterized in that: differential steering with
The field weeding platform of wheelspan adjustable coupling is, it can be achieved that self-regulated wheelspan, unmanned, 90 ° of turnings, wheelspan adjustable range are
200mm。
3. the Intelligent target according to claim 1 based on deep learning sprays weed-eradicating robot, it is characterized in that: utilize (13) super
Sound ranging module first carries out coarse adjustment to (9) the distance between spray unit and ground by (8) sliding rail, recycles (10) Y
Axis sliding rail dynamically adjusts (9) spray unit position according to real-time range information, to keep spray unit and ground distance permanent
Fixed, guarantee precisely sprays.
4. the Intelligent target according to claim 1 based on deep learning sprays weed-eradicating robot, it is characterized in that: place three
(6) medicine-chest passes through solenoid valve respectively and connects three (14) rotary nozzles in same (9) spray unit, and carry three groups it is same
(9) spray unit is administered target with completing multiple medicine liquid, variable.
5. the Intelligent target according to claim 1 based on deep learning sprays weed-eradicating robot, it is characterized in that: made using furrow
The mode of industry is expanded the visual field of camera and the working region of rotary nozzle, and can be passed through according to the image that camera captures
(11) X-axis slide unit carries out self-positioning, keeps (9) spray unit always in furrow.
6. the Intelligent target according to claim 1 based on deep learning sprays weed-eradicating robot, it is characterized in that: use depth
The method of habit identifies weeds type, leaf age, physiological structure, accurately matches suitable medicament and medicine according to weeds type, leaf age
Measure and medical fluid sprayed application to according to physiological structure the meristematic region of weeds.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910501289.8A CN110150260A (en) | 2019-06-11 | 2019-06-11 | A kind of Intelligent target spray weed-eradicating robot based on deep learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910501289.8A CN110150260A (en) | 2019-06-11 | 2019-06-11 | A kind of Intelligent target spray weed-eradicating robot based on deep learning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110150260A true CN110150260A (en) | 2019-08-23 |
Family
ID=67628395
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910501289.8A Pending CN110150260A (en) | 2019-06-11 | 2019-06-11 | A kind of Intelligent target spray weed-eradicating robot based on deep learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110150260A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111387169A (en) * | 2020-04-24 | 2020-07-10 | 东北农业大学 | Multi-spray-way controllable spray-width type accurate targeting weeding module based on artificial intelligence technology |
| CN112056031A (en) * | 2020-08-31 | 2020-12-11 | 山东大学 | Farmland management robot suitable for different ridge widths |
| CN113100207A (en) * | 2021-04-14 | 2021-07-13 | 郑州轻工业大学 | Accurate formula pesticide application robot system based on wheat disease information and pesticide application method |
| CN114080889A (en) * | 2021-11-17 | 2022-02-25 | 东北农业大学 | Rice leaf age index management digital diagnosis unmanned vehicle |
| CN115336567A (en) * | 2022-08-10 | 2022-11-15 | 安徽省圣丹生物化工有限公司 | Continuous pesticide spraying device for pest control |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1628513A (en) * | 2003-12-18 | 2005-06-22 | 南京林业大学 | Method for employing agricultural chemicals to target accurately |
| CN104115809A (en) * | 2014-07-24 | 2014-10-29 | 中国农业大学 | Toward-target spraying machine and method for crops in field |
| CN104186450A (en) * | 2014-08-04 | 2014-12-10 | 北京农业信息技术研究中心 | Orchard variable range combined spraying method and device |
| CN106982815A (en) * | 2017-03-17 | 2017-07-28 | 东北农业大学 | It is a kind of to have to target dispenser and intelligent weed eradication unit of the seedling with tracking function |
| JP2018157775A (en) * | 2017-03-22 | 2018-10-11 | 株式会社丸山製作所 | Riding control machine |
| US10219506B2 (en) * | 2014-06-10 | 2019-03-05 | Cnh Industrial America Llc | Device and method for detecting blockages in an agricultural sprayer |
| CN109676624A (en) * | 2019-01-28 | 2019-04-26 | 东北农业大学 | A kind of field target detection robot platform based on deep learning |
-
2019
- 2019-06-11 CN CN201910501289.8A patent/CN110150260A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1628513A (en) * | 2003-12-18 | 2005-06-22 | 南京林业大学 | Method for employing agricultural chemicals to target accurately |
| US10219506B2 (en) * | 2014-06-10 | 2019-03-05 | Cnh Industrial America Llc | Device and method for detecting blockages in an agricultural sprayer |
| CN104115809A (en) * | 2014-07-24 | 2014-10-29 | 中国农业大学 | Toward-target spraying machine and method for crops in field |
| CN104186450A (en) * | 2014-08-04 | 2014-12-10 | 北京农业信息技术研究中心 | Orchard variable range combined spraying method and device |
| CN106982815A (en) * | 2017-03-17 | 2017-07-28 | 东北农业大学 | It is a kind of to have to target dispenser and intelligent weed eradication unit of the seedling with tracking function |
| JP2018157775A (en) * | 2017-03-22 | 2018-10-11 | 株式会社丸山製作所 | Riding control machine |
| CN109676624A (en) * | 2019-01-28 | 2019-04-26 | 东北农业大学 | A kind of field target detection robot platform based on deep learning |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111387169A (en) * | 2020-04-24 | 2020-07-10 | 东北农业大学 | Multi-spray-way controllable spray-width type accurate targeting weeding module based on artificial intelligence technology |
| CN112056031A (en) * | 2020-08-31 | 2020-12-11 | 山东大学 | Farmland management robot suitable for different ridge widths |
| CN113100207A (en) * | 2021-04-14 | 2021-07-13 | 郑州轻工业大学 | Accurate formula pesticide application robot system based on wheat disease information and pesticide application method |
| CN114080889A (en) * | 2021-11-17 | 2022-02-25 | 东北农业大学 | Rice leaf age index management digital diagnosis unmanned vehicle |
| CN115336567A (en) * | 2022-08-10 | 2022-11-15 | 安徽省圣丹生物化工有限公司 | Continuous pesticide spraying device for pest control |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110150260A (en) | A kind of Intelligent target spray weed-eradicating robot based on deep learning | |
| US20240268245A1 (en) | Method for autonomous detection of crop location based on tool depth and location | |
| Søgaard et al. | Application accuracy of a machine vision-controlled robotic micro-dosing system | |
| CN103999841B (en) | A kind of automatic target detection spraying system | |
| CN103988824A (en) | Automatic targeting and spraying system based on binocular vision technology | |
| CN104115809B (en) | A kind of field crops sprays machine and spraying method to target | |
| CN103891697B (en) | The variable spray method of a kind of indoor autonomous spraying machine device people | |
| CN102613162B (en) | Self-propelled automatically targeting precise pesticide spraying machine | |
| CN204104581U (en) | A kind of automatic target detection spraying system based on binocular vision technology | |
| CN111838110B (en) | Orchard targeting air-assisted sprayer based on laser radar and spraying method thereof | |
| CN203860304U (en) | Automatic targeting and spraying system | |
| CN208084344U (en) | A kind of Multifunctional field robot | |
| CN202907683U (en) | Efficient weeding robot based on multi-spectral vision | |
| CN105746481B (en) | It is a kind of to have both the weed-eradicating robot for targeting and quantitatively spraying with mechanical fixed point shovel digging function | |
| Özlüoymak | Development and assessment of a novel camera-integrated spraying needle nozzle design for targeted micro-dose spraying in precision weed control | |
| CN115024300B (en) | Intelligent pesticide spraying device, method and system of pseudo-ginseng plant disease and insect pest prevention and control plant protection unmanned aerial vehicle | |
| Guan et al. | Review on research and application of variable rate spray in agriculture | |
| CN114089650B (en) | Intelligent farmland pesticide spraying electronic automatic control system based on Internet of things | |
| Möller | Computer vision–a versatile technology in automation of agricultural machinery | |
| CN202524957U (en) | Precise pesticide applying machine capable of aiming at target automatically | |
| CN212300875U (en) | To target spraying test bench based on machine vision | |
| Søgaard et al. | Investigation of the accuracy of a machine vision based robotic micro-spray system | |
| CN116746560A (en) | Intelligent orchard precise pesticide spraying robot | |
| Xie et al. | Design and Implementation of a Machine Visionbased Spraying Technique for Smart Farming | |
| Bykov | World trends in the creation of robots for spraying crops |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20190823 |