Professional Documents
Culture Documents
Agricultural Mechanization
Data Mining
Genetic Algorithm
Simulation and Modeling
Decision on:
Quality control
Storage conditions
Marketing
ICT
Harvesting Season
(Post-Field Operation
Optimization)
Selection of:
Land
Crop (cultivar)
Cultivation contract
Yield
Monitoring
Harvesting
Growing Season
(In-Field Operation
Optimization)
Pre-harvest Sensing
Site-specific Management
Robotics and Automation
ICT
Cost- benefit
analysis
Soil Sampling
Planning Season
(Pre-field Operation
Optimization)
Data
Analysis
Crop
Scouting
ICT
Data Analysis
Variable Rate
Application
i. Map-based VRA
ii. Sensor-Based VRA
Decision on:
Soil preparation
Sowing rate and time
Fertilization
Water management
Weed control
Pest and disease control
Cost- benefit
analysis
Environmental
impact
Asian Agriculture
LABOR SHORTAGES
Japan, China, Indonesia, Malaysia, Thailand,
India, Pakistan & Bangladesh
Japan
15~24 yrs, 25~34 yrs,
2%
7%
300
250
242
234
224
217
[[VALUE]]
209
35~44 yrs,
9%
208
200
150
140
102
100
137
[[VALUE]]
97
[[VALUE]]
135
131
89
86
126
83
126
65 years
old and
over, 48%
45~54 yrs,
11%
82
50
0
2009
2010
2011
2012
2013
2014
Year
2015
55~64 yrs,
22%
30500
29976
30000
29418
29500
29000
28641
28364
28500
28065
27695
28000
27355
27500
27032
27000
26500
26000
25500
China
0.4
0.35
0.3
0.25
0.2
0.15
0.1
0.05
0
Less than
30 years
old
30-40
25000
2005
2006
2007
2008
2009
2010
2011
2012
Year
Northern Jiangsu
40-50
50-60
Age Group
Central Jiangsu
60-70
More than
70 years
old
Southern Jiangsu
35
30
26.13
25
>64 yrs
13%
21.5
20
Number of
Farmer (Million)
15
10
<15 yrs
0%
31.17
12.2
15 ~ 24 yrs
1%
25 ~ 34 yrs
12%
55 ~ 64 yrs
20%
35 ~ 44 yrs
26%
0
1963
1993
Year
2003
2013
45 ~ 54 yrs
28%
Number of Foreign
Workers in Plantation (Ten
Thousand People)
Malaysia
50
45
40
35
30
25
>55 years
old
45%
<45
years old
30%
20
15
10
5
0
Year
Figure 12: Number of foreign workers in plantation
(Source: Review of labour migration policy in Malaysia,
(2016)
45-55
years old
25%
69
68
30%
67
25%
66
20%
65
15%
64
63
10%
62
5%
61
0%
70
60
35%
Thailand
60
50
49 48
50 48
51 49
2010
2011
2012
54
56
58
51
52
2013
2014
55
40
30
20
10
0
Male
2014
Female
India
160
140
120
100
80
60
40
20
0
Uttar
Pradesh
Bihar
Rajasthan
Pakistan
60
Employment in
Agriculture (Percentage
of Total Employment)
Others
1981
1988
Areas of India
2004-05
1995
Year
2002
2009
2011-12
Bangladesh
80
70
67
60
60
55
47.5
50
40
30
20
10
25
23
10
25
15
28
20
25
0
2001
Agriculture
Industry
2003
2006
Year
2010
Service
Linear (Agriculture)
Figure 18: Workforce ratios by three sectors of Bangladesh (Source: BBS, 2010)
10
Land Preparation
11
Land Preparation
12
Land Preparation
13
Swampy Areas
14
15
(a)
(b)
Figure 23: Laboratory of Vehicle Robotics, Hokkaido University.
Courtesy: Professor Noburo Noguchi
16
Tilling Robot
Video
National Agriculture and Food Research Organization (NARO)
17
MECHANIZATION-
Transplanter
A manual rice transplanting needs 8hrs of work by 20 labors for 1ha of paddy field.
Whereas a transplanter needs 2 persons and 8hrs of work for 1ha paddy. (Joji Arihara,
2014) .
Two types of transplanter depending on seedlings usage
Washed-root seedlings: Plants are pulled from the nursery. Soil is washed from the
roots, and then the plants are placed in transplanters. The seedlings are the same
age as those for hand transplanting.
Soil-bearing seedlings: The seeds are sown and grown in a nursery box, then
transplanted with the soil in the root zone.
Transplanters based on prime mover (Bala and Wan, 2014)
Power tillers: Power tillers (KPP 315) series has two-lines a single wheel powered by
gasoline engine.
Tractor mounted: Has a capacity of 6-10 rows transplanting width. Powered by a
tractor engine of 25 h powers via power take-up shaft connected to arrangement of
linking mechanism of pulley/belts.
Self-propelled: Are of two categories, first called Walk behind type (Japanese model)
a two or four row paddy rice transplanter.
19
Transplanter
Japan developed the first rice transplanter with the patent obtained in 1898
(Han & Kim, 1971).
20
Seeders
Field Robots
22
Transplanter
Video
National Agriculture and Food Research Organization (NARO)
23
Autonomous Trends
Navigation Sensors
Navigation Planer
Steering Controller
Operational Scenario
GPS
LRF:U
RG
Road running
LRF
GPS
DR
Approaching to implement
DR
LRF:LMS211
DR
Parking inside the yard
26
Instrumentation
Controller Unit
Relay
PLC
Rotary encoder
Computer
Serial
RS232C
Interface
GPS
Generator
Bus bridge
Steering controller
LMS 211
URG
04X
DO:PCI-2424
Linear encoder
DO:PCI-2503
LMS 551
FOG
AD/DA:PCI-3521
Rotary encoder
Timer:PCI-6103
Counter:PCI-6201E
Extension Box
Figure 27: Schematic diagram of basic instrumentation system.
27
AD/DA
Desired steering angle
PCI-3521
Signal current
Electro hydraulic valve
Hydraulic motor
Computer
Counter
Steering angle
PCI-6201E
Wheel angle
Steering cylinder
Linear encoder
Polar-based Trajectory
Cartesian-based trajectory
28
Backward
Forward
Backward
Polar
Cartesian
Forward
Yard
Figure 29: (a) Approach to the implement, (b) parking of the tractor inside the yard.
29
Field Operations
30
Automatic Coupling
Video
31
Navigation Performance
1.5
MP
Forward
0.5
-7
-6
-5
-4
-3
-2
-1
0
-0.5
y [m]
SP
-1
Backward
-1.5
-2
-2.5
GP
-3
x [m]
Measured
Theoretical
32
Point-To-Go
33
stop-pattern landmark
stop-pattern landmark
stop-pattern landmark
34
35
Landmark-Navigation
Video
36
Near-Infrared Sensors
Thermal Imagers
Machine Vision
RADAR and
LIDAR
38
Seasonal Monitoring
hf
hg
hp
hp
September October
hp
hp
November December
Figure 42: Reflection height (hf) from plants are considered as a reference to develop surface map of plant growth.
40
Field Trails:URG04-LX
hg
hp
hp
387
337
Figure 44: Mean Relative distance (l) of plants from URG laser range finder (Steps 337-387).
42
Ground-based Sensing
Figure 45: Ground based sensing system trail in the University of Illinois.
43
Video
46
MECHANIZATION-HARVESTING
Yield Map
Combine Harvester
Combine owners undertake harvest of crops for
farmers at a reasonable price
One is a head-feeder type and the other is a
conventional type. Head-feeder type used in East Asia
is suitable for harvesting japonica rice. In South and
Southeast Asia, the conventional type of combine
harvester is popular and suitable for Indica rice.
48
(c)
(b)
(a)
Figure 48: A John Deer Combine Harvester with Ag Leader RTK-GPS system: a) Combine Cab; b) RTK-GPS Antenna;
c) Display Console, USA.
49
Field Robots
50
Leader-Follower Formation
(a)
(b)
Figure 50: Relationship of leader, follower and virtual follower: (a) Required formation; (b) Position of virtual follower.
52
Leader-Follower Tracking
Camera
For formation tracking
54
0.3
0.2
0.1
0
-0.1
-0.2
-0.3
-0.4
10
15
20
25
30
35
X[m]
RMS error:
With sensor noise: 0.166 m
After adding EKF: 0.053 m
0.2
0.3
0.1
0
-0.1
-0.2
-0.3
0
10
15
20
25
30
35
RMS error:
With sensor noise: 4.373
After adding EKF: 1.807
6
3
0
-3
-6
-9
0
10
15
20
25
30
10
25
30
15
X[m]
20
25
10
With sensor noise
15
X[m]
20
25
(a) Lateral error; (b) Longitudinal error; and (c) Bearing error.
30
30
RMS error:
With sensor noise: 4.672
After adding EKF: 1.718
35
20
12
9
6
3
0
-3
-6
-9
-12
X[m]
With sensor noise
15
X[m]
RMS error:
With sensor noise: 0.175 m
After adding EKF: 0.045 m
-12
10
Bearing error,[]
0.4
0.3
0.2
0.1
0
-0.1
-0.2
-0.3
-0.4
X[m]
Bearing error,[]
RMS error:
With sensor noise: 0.191 m
After adding EKF: 0.126 m
0.3
0.2
0.1
0
-0.1
-0.2
-0.3
-0.4
-0.5
-0.6
55
300
Raw Data
250
Distance, [cm]
200
200
150
150
100
100
50
50
0
0
0
200
400
600
Filted
30
250
20
200
Steering angle,[]
300
250
200
100
0
-20
0
200
400
600
100
-10
50
Filted Data
150
10
150
1000
800
Distance, [cm]
500
200
400
600
800
50
0
0
500
1000
1500
25
20
15
10
5
0
-5 0
-10
-15
-20
-25
-30
-35
-40
Steering angle, []
Distance, [cm]
250
Distance , [cm]
Raw Data
500
1000
1500
1500
800
56
Leader-follower formation
Video
57
Field Robots
59
Variable Sensor
Data processor/controller
Actuator
60
Computer
CCD Camera
Nozzle Controller
Solenoid valves
and Nozzles
Weeds
Crop
Figure 56: Schematic diagram of sensor based VRA for smart sprayer at the University of Illinois at Urbana-Champaign.
61
Smart Sprayer
Figure 60: A prototype-manipulator and robotic application to identify weeds and apply chemicals, University of Illinois at Urbana64
Champaign.
65
LEVEL 3
Conditional
Automation
LEVEL 2
Partial
Automation
Automation
Driver
LEVEL 1
Assisted
LEVEL 0
No Automation
Diver has to do
the longitudinal
and lateral control
constantly
Vehicle do not have
any intervening
system
Diver has to do
the longitudinal
or lateral control
constantly
The rest
operations done
by the system
Diver has to do
observer the
system
continuously
LEVEL 4
High
Automation
The system do
not need driver
for defined job.
LEVEL 5
Full
Automation
No driver required.
The system is capable
to deal with all
situations
automatically during
the whole process.
System is capable to
manage all situations
automatically for a
defined job.
Research Direction
Development of Autonomous Guidance with UAVSynergy of Agricultural Robotics & Precision Agronomics
and Safety Systems
Gateway
69
RS
GIS
Input
GEODATABASE
Model
GIS Dataset
- Population
- Road, land use parcels
- Soil types
- GPS points (Field survey data)
Centralized Geodatabase
- Store
- Retrieve
- Edit/update
- Manage spatial data
Spatial Modeling
- Site suitability analysis
- Land use change model
- Deforestation process
- Land degradation process
Output
End Users
Agricultural unions
Urban planners
Policy makers
70
Figure 64: Remote Sensing and GIS for decision support systems (Courtesy of Ko Ko Lwin, University of Tsukuba).
Operators Safety
Driver action dataset (7 classes):
One subjects, each action was repeated by one
subject 5 times.
The total number of the action sequences was 35.
blinking
Look back
Rubbing eye
Phone
nodding
11
Precision Agronomics
Remote Access to
On-Beard and
Optimization of
Machinery
Operation (ROM)
Variable rate
planting
Variable rate
irrigation
Variable rate
fertilizer
Genetic
Potentials of
Crops for MicroClimatic
Adaptability
High
resolution
Quality of data
mapping and
sensing
Agronomic
Decision with
Weather
Adaptation
Synergy
Remove and
reduce
Management
Variable rate
pesticides
Machine
Optimization
Targeting
Agronomy
Data
Management
Data office
computer
Tablet
Cloud
Data sharing
Data security
Data primary
user right
Figure 67: The big picture of cloud applications in the precision agronomics with machine optimization, targeting
agronomy and data management.
73
Conclusions
75
References
76
References
1.
Guancheng Guo, Qiyu Wen, and Jingjuan Zhu, (2015). The Impact of Aging Agricultural Labor Population on Farmland Output: From
the Perspective of Farmer Preferences, Mathematical Problems in Engineering, Volume 2015 (2015), Article ID 730618, 7 pages.
2. Han, S.K., S.R. Kim, and H.Y. Kim, (1971). Study on the new design of hand rice transplanter, Research Report of Agricultural
Utilization, ORD, Vol. 1.
3. Hoshino, S. (1977). Development of rice transplanters. Proceedings of the seminar on mechanization of small farms. Office of Rural
Development, Korea.
4. http://www.tradingeconomics.com/pakistan/employment-in-agriculture-percent-of-total-employment-wb-data.html
5. Japan Statistical yearbook, (2016). http://www.stat.go.jp/english/data/nenkan/
6. John F. Reid (2011). The Impact of Mechanization on Agriculture, The Bridge on Agriculture and Information Technology, Fall 2011,
Volume 41, Number 3.
7. Kumar, G. P., & Raheman, H. (2011). Development of a walk-behind type hand tractor powered vegetable transplanter for paper pot
seedlings.Biosystems Engineering, 110(2), 189-197.
8. Ministry of Agriculture And Agro-based industry , (2009). Overview of the Agriculture Sector in Malaysia.
9. NAE (National Academy of Engineering (2000). Greatest Engineering Achievements of the 20th Century. Available online at
http://www.greatachievements.org/.
10. GHI (Global Harvest Initiative) (2011). GHI website. Available online at http://www.globalharvestinitiative.org/.
11. Postel, S. L., Daily, G. C., & Ehrlich, P. R. (1996). Human appropriation of renewable fresh water. Science-AAAS-Weekly Paper
Edition, 271(5250), 785-787.
12. UN, FAO, (2007). Water Scarcity, Challenge of the twenty-first century.
13. Report on Labor Force Survey 2010 (Bangladesh Bureau of Statistics (BBS), 2010).
14. Review of labour migration policy in Malaysia, (2016).
15. The Central Statistics Agency (Badan Pusat Statistik, BPS), (2013).
16. Joji Arihara, (2014). Rice mechanization in Asia. Kubota Corporation.
17. Bala Ibrahim and Wan Ishak Wan Ismail, (2014). Development of System Rice Intensification (SRI) Paddy Transplanter, Asian Journal of
Agricultural Sciences, 6(2): 48-53.
77