Agricultural Field Trials – Today and Tomorrow / 08. – 10 ...€¦ · Agricultural Field Trials...

Autonomous robots in agricultural field trialsAgricultural Field Trials – Today and Tomorrow / 08. – 10. October 2007

1

„Agricultural Field Trials – Today and Tomorrow“

University of Hohenheim Stuttgart - 08.-10. October 2007

Autonomous robots in agricultural field trials

Arno Ruckelshausen

Faculty of Engineering and Computer Science

COALA - Competence Center of Applied Agricultural Engineering

http://www.uni-hohenheim.de/


2

1. Introduction

2. Sensors in agriculture

3. Individual plant detection

4. Autonomous field robots

5. Conclusions

Overview


3

1. Introduction

2.2.2. Sensors in Sensors in Sensors in agricultureagricultureagriculture

3.3.3. IndividualIndividualIndividual plant plant plant detectiondetectiondetection

4.4.4. AutonomousAutonomousAutonomous fieldfieldfield robotsrobotsrobots

5.5.5. ConclusionsConclusionsConclusions

OverviewOverviewOverview


4

From the field to the single plant

Conventional farming : Field-related figures

Precision farming: Sub-field-related figures

“Single-plant farming“: Plant-related figures


5

Weed in row cultures

Source: Astrand 2005


6

Technology challenge

Precision Farming Individual Plant Farming

GPS

Off-line sensors /

Averaging on-line sensors

Standard system technology

High precise GPS / landmarks

Non-averaging on-line sensors

Advanced system technology


7

Electronic systems

Software / Algorithms

Experience

Sensors

MechatronicSystem

MechancisApplication Knowledge

Electronics andSoftware

Interdisciplinary approach for agricultural engineering

Experience

Sensors

Electronic systems

Software


8

1.1.1. IntroductionIntroductionIntroduction

2. Sensors in agriculture






9

Robust

Smart

Low-cost

Interpretation of sensor signals

Sensor Fusion

Robust algorithms

Behaviour guidelines

Key issues for sensors in agriculture


10

Applications: Measurement of crop height and density, stalk detection

Triangulation sensor

“Optoelektronisches Sensorsystem zur Messung der Pflanzenbestandsdichte“ G. Thösink, J. Preckwinkel, A.Linz, A. Ruckelshausen, J.Marquering; Landtechnik 59, S.78-79, 2004

Example 1: Optoelectronic distance measurement


11

Results

Velocities up to 10 km/h

Spotsize in the mm2-range

Statistical online analysis

Sensor signals Reduced data


12

dire

ction

of m

otio

n

latitude

side view

trigger

Test setup (laboratory)

Maize plants (field)

Example 2: Imaging sensor system (“1-bit-imaging“)


13


14

Online-measurement of the degree of maturity for maize plants

Example 3: Sensor for automatic cutting length variation


15

Method: Optoelectronic NIR sensor system

Pulsed LEDs (spectral characteristics)

Microcontroller-based solution (embedded system)

Self-cleaning effect


16

Field Tests


17

Position

Wav

elen

gth

Example: 4 LEDs with different wavelengths

Example 4: Hyperspectral Imaging


18

System integration: spectral imaging with ImSpector/CMOS-camera

"Weed detection based on spectral imaging systems with CMOS cameras“ ; S. In der Stroth, B.Ramler, A.Linz, A.Ruckelshausen ; 4th European Conference on Precision Agriculture ECPA, Berlin, Programme book, ISBN 9076998345, Juni 2003


19

Potatos, stones, earth, plants Pointwise spectral analysis and online image processing

Förderung Arbeitsgruppe Innoavite Projekte beim Miniserium für Wissenschaft und Kultur, NIedersachsen

Application: Harvesting, quality control


20

0

10

20

30

40

50

60

70

80

450 550 650 750 850 950

Wavelength [nm]

Reflection [%]

Sensor Fusion: Properties of plants (examples)

Spectral properties

(reflection of various „green“ plants)

Geometrical properties

top view

side view

Maize Forgetmenot

Combination of different sensors with varying selectivties


21

HostμC

CAN - Bus

Height profilesensor

Distance sensor Sensor …

Hoe Sprayer

Interface

Position Sensing

Actuator …

Architecture of a sensor fusion based mechatronic system

μC μC

μCμC μC

μC


22

First application of sensor fusion in weed control (1998)

Application: Mechanical intra-row weed control

Multi-sensor system / microcontroller-based architecture

Transversal cycloid hoe („Querhacke“)

Plant database

" Microcontroller-based multi-sensor system for online crop/weed detection “ , A.Ruckelshausen, T.Dzinaj, F.Gelze, S.Kleine Hörstkamp, A.Linz, J.Marquering, Proceedings of the International Brighton Conference "Weeds", 1999, pages 601-606


23



3. Individual plant detection





24

System technology (real-time, embedded systems, CAN-bus)

Software (examples: data acquisition, algorithms, testing, communication)

User interface

Sensors for crop detection (examples: photo diode arrays, spectral imaging)

Positioning with GPS and other sensors (encoder)

Power management

Alarm unit (example: voltages, temperature, dust)

Mechanical mobile unit

Test environment

Technologies for individual plant detection


25

System architecture for individual plant detection (sensors)

HostμC

CAN - Bus

Height Profile Sensor

Distance Sensor Sensor

GPS Spectral Imaging

User Interface

μC μC

μC μC

μC


26

GPS technologies

Application in maize fields: typical distance of 2 maize plants is 8 to 12 cm

⇒ GPS accuracy better than 5 cm (RTK/DGPS)

Typical measured RTK/DGPS accuracy: ± 2 cm

Interpolation of two GPS signals with encoder information

GIS-tool OpenJUMP (open-source application)

RTK/DGPS system MS750 from Trimble


27

Mobile sensor unit in a maize field


28

Visualization of data with the GIS-tool OpenJUMP


29

4 different runs in the same maize row

Vertical variations due to different tracks of the mobile unit

⇒ Identification of an individual plant

⇒ “Reidentification“ of an individual plant

Results


30

Joe

Hey Joe,

you look better today than last week. Moreover you have grown more than 2 cm.

See you next week !

Joe


31




4. Autonomous field robots




32

Cost reduction, environmental protection, jobs

Technologies: Sensors, software, algorithms, actuators, system technology, vehicles, safety, application related aspects, user interface

☺ Fun, as for example: International Field Robot Event

Autonomous Service Robots: Field Robots


33

International „Field Robot Event“Initialized by Wageningen University.

Interdisciplinary teams from all over the world compete.

Tasks:Navigation through straight and curved maize rows

Make a turn at the end of the row into the next or another row

Counting of the plants

Weed control

Freestyle

Aufgabe 2Aufgabe 1

75 cm 75 cm


34

Sensor fusion concept

Sensors

Drawing white line

Speed race

Finding holes

Watering flowers

Navigation

Counting yellow balls

Turn on end of row

AVRc

amIR

Sen

sor

Flex

Sen

sor

Ultra

Son

ic Se

nsor

Gyr

osco

peHa

ll Sen

sor

Phot

odio

des

Ligh

t sen

sor

Rob

ot ta

sks


35

Architecture of an autonomous field robot (Amaizeing)


36

Smart low-cost camera “CMUCam“

Integrated microcontroller for image processing

Options for reduced data (example: windowing)

Tracking options (example: color tracking)

Resolution up to 160 x 255 Pixel

Low cost solution (ca. 140 €)


37

Navigation: Examples

Navigation within the row Turnaround


38

Integration of actuators

Drawing a white line Watering flowers


39

User Interface

System tests

Test of sensors

WLAN

Strategies (Software)

Algorithms

Parameter

Documentation

…

GUI Field Robot Amaizeing


40

Communication

“Learn-Mode“, transfer of software and parameters, electronic documentation, safety

Platform for teleservice, robot swarms


41

From experimental studies to prototypes: first steps

Autonomous tractor: University of Kopenhagen (Cooperation „Querhacke“; Osnabrück)

Autonomous vehicles for weed control (examples): HortiBot (Aarhus, DK) and Weedy (Osnabrück, G)


42

A concept for an autonomous robot for field trials (“BoniRob“)

Complete analysis: field, site, plant Analysis of individual plant parameters

Key technologies:

Application orientation, sensor systems, robust software, safety

Source: Satconsystem „Kinderfinder“; www.was-wir-essen.de


43





5. Conclusions



44

Conclusions

Autonomous robots for field trials: Interdisciplinary challenge

Key technologies: Robust software, sensor technologies, safety

Individual plant detection is possible (first tests have been performed)

First experiences with autonomous field robots are available

Major problem of autonomous field robots: Robust navigation

Next steps:

Development of a robust platform for agricultural field trials (“BoniRob“)

Experimental period : tests, improvements, extensions

Integration of actuators


45

Field Robot Event2008 June 12 - 14 Osnabrück/Germany

Autonomous Field Robots

Hall 16 – Stand 16D17 / DLGHall 14 – Stand A16 / Amazonen-Werke

Autonomous robots in agricultural field trials ��Arno Ruckelshausen �Faculty of Engineering and Computer Science �COALA - C

Date post:	28-Aug-2020
Category:	Documents
Upload:	others
View:	1 times
Download:	1 times

Agricultural Field Trials – Today and Tomorrow / 08. – 10 ...€¦ · Agricultural Field Trials...

Documents