Aerial Surveying for precision agriculture Joo Valente - - PowerPoint PPT Presentation

▶
aerial surveying for precision agriculture
SMART_READER_LITE
LIVE PREVIEW

Aerial Surveying for precision agriculture Joo Valente - - PowerPoint PPT Presentation

Dec 09, 2023 359 likes •761 views

Aerial Surveying for precision agriculture Joo Valente [jvalente@ing.uc3m.es] UNIVERSIDAD CARLOS III DE MADRID SYSTEMS ENGINEERING AND AUTOMATION DEPARTMENT Webinar 45 21/02/2017 Technical Committee on: Agricultural Robotics and Automation

slide-1
SLIDE 1

Aerial Surveying for precision agriculture

João Valente [jvalente@ing.uc3m.es]

UNIVERSIDAD CARLOS III DE MADRID SYSTEMS ENGINEERING AND AUTOMATION DEPARTMENT

Technical Committee on: Agricultural Robotics and Automation

Webinar 45

21/02/2017

slide-2
SLIDE 2

2

Outline

  • 1. Background
  • 2. Precision agriculture (PA)
  • 3. Unmanned Aerial Systems (UAS) in PA
  • 4. Aerial Mission planning (AMP)
  • 5. Field experiments
  • 6. Future challenges
slide-3
SLIDE 3

3

  • Population booming:

– 1980: 4.5 Billions – 2016: 7.3 Billions – 2050: 9.3 Billions

  • Wrong food call

Background

slide-4
SLIDE 4

4

Precision Agriculture

slide-5
SLIDE 5

5

Unmanned Aerial Systems (UAS) in PA

QuantaLab, IAS-CSIC, Spain CAR UPM-CSIC, Spain NASA, USA UARSF-WUR, Netherlands UC Davis, USA

slide-6
SLIDE 6

6

Aerial Mission planning (AMP)

Problem definition

slide-7
SLIDE 7

7

Aerial Mission planning (AMP)

Problem definition

slide-8
SLIDE 8

8

Aerial Mission planning (AMP)

Problem definition

slide-9
SLIDE 9

9

Aerial Mission planning (AMP)

Problem definition

slide-10
SLIDE 10

10

Aerial Mission planning (AMP)

Problem definition

slide-11
SLIDE 11

11

Aerial Mission planning (AMP)

Problem definition

slide-12
SLIDE 12

12

Aerial Mission planning (AMP)

Problem definition

slide-13
SLIDE 13

13

Aerial Mission planning (AMP)

Mission summary:

  • Specifications:
  • Field polyline/area
  • Camera parameters
  • Requirements:
  • Spatial resolution
  • Overlapping
  • Minimum flying time
  • Constraints:
  • Initial and final TOL position
  • Prohibited areas
  • Safety distance
slide-14
SLIDE 14

14

Aerial Mission planning (AMP)

Mission summary:

  • Specifications:
  • Field polyline/area
  • Camera parameters ✔
  • Requirements:
  • Spatial resolution ✔
  • Overlapping ✔
  • Minimum flying time
  • Constraints:
  • Initial and final TOL position
  • Prohibited areas
  • Safety distance
slide-15
SLIDE 15

15

Aerial Mission planning (AMP)

Workspace sampling

Field Discretized polylines (4)

N

<Lat1, lon1> <Lat2, lon2> <Lat3, lon3> <Lat4, lon4>

slide-16
SLIDE 16

16

Aerial Mission planning (AMP)

Workspace sampling

I II III IV V VI

slide-17
SLIDE 17

17

Aerial Mission planning (AMP)

Workspace sampling

Mission summary:

  • Specifications:
  • Field polyline/area ✔
  • Camera parameters ✔
  • Requirements:
  • Spatial resolution ✔
  • Overlapping ✔
  • Minimum flying time
  • Constraints:
  • Initial and final TOL position
  • Prohibited areas
  • Safety distance
slide-18
SLIDE 18

18

Aerial Mission planning (AMP)

Workspace sampling

Mission summary:

  • Specifications:
  • Field polyline/area ✔
  • Camera parameters ✔
  • Requirements:
  • Spatial resolution ✔
  • Overlapping ✔
  • Minimum flying time
  • Constraints:
  • Initial and final TOL position
  • Prohibited areas
  • Safety distance

Ψ (

slide-19
SLIDE 19

19

Aerial Mission planning (AMP)

Workspace sampling

Mission summary:

  • Specifications:
  • Field polyline/area ✔
  • Camera parameters ✔
  • Requirements:
  • Spatial resolution ✔
  • Overlapping ✔
  • Minimum flying time
  • Constraints:
  • Initial and final TOL position
  • Prohibited areas
  • Safety distance

width height

<x,y> ???

slide-20
SLIDE 20

20

Aerial Mission planning (AMP)

Workspace sampling

dy dx

  • Spatial resolution (Pixel/cm)
  • Overlapping (%)
  • Field size (m)
slide-21
SLIDE 21

21

Aerial Mission planning (AMP)

Workspace sampling

slide-22
SLIDE 22

22

Aerial Mission planning (AMP)

Workspace sampling

Area sub-division, the robot assignment problem and discretization.

slide-23
SLIDE 23

23

Aerial Mission planning (AMP)

Path planning

What is the best Coverage path?

slide-24
SLIDE 24

24

Aerial Mission planning (AMP)

Path planning

Grid graph

slide-25
SLIDE 25

25

Aerial Mission planning (AMP)

Path planning Heuristicless

  • Rules-of-thumb
  • Brute force
  • Bread-first search (BFS)
  • Deep-limited search (DLS)
slide-26
SLIDE 26

26

Aerial Mission planning (AMP)

Path planning Heuristics

  • Wave-front planner algorithm
  • Deep limited search (DLS)
  • With backtracking procedure
slide-27
SLIDE 27

27

Aerial Mission planning (AMP)

Path planning Meta-Heuristics

  • Genetic algorithm (GA)
  • Ant colony optimization (ACO)
  • Harmony Search (HS)
slide-28
SLIDE 28

28

Aerial Mission planning (AMP)

Mosaicing (tools)

  • OpenCV
  • Matlab
  • Panorama tools
slide-29
SLIDE 29

29

Aerial Mission planning (AMP)

Implementation

slide-30
SLIDE 30

30

Field experiments

Workstation setup Mission assignment and validation Mission execution Mission Real-time feedback

Working cycle

slide-31
SLIDE 31

31

Field experiments

AMP system inputs

Image requisites Field characteristics Camera specification Number of UAS

slide-32
SLIDE 32

32

Field experiments

  • Vineyard parcel (irregular shape)
  • Irregular shape field
  • ~63765 m²
  • Corn field (regular shape)
  • Regular shape field
  • ~20000 m²
slide-33
SLIDE 33

33

Field experiments

  • Weed management
  • FP7 Project: RHEA (Robot

Fleets for Highly Effective Agriculture and Forestry Management)

http://www.rhea-project.eu

slide-34
SLIDE 34

34

Field experiments

Corn field https://youtu.be/1VM9VWWbLv4

slide-35
SLIDE 35

35

Field experiments

  • Frost monitoring
slide-36
SLIDE 36

36

Field experiments

Vineyard parcel https://youtu.be/F4bJdpG8gbw

slide-37
SLIDE 37

37

Future challenges

  • Multi-UAS
  • Alternative payload systems
  • Close-the-loop
  • Farmer-robot interaction
  • Education
slide-38
SLIDE 38

38

Short BIO

  • Education
  • PhD. Robotics and Automation, Polytechnic

University of Madrid (UPM), Spain, 2014

  • MSc. Robotics and Automation, UPM, Spain, 2011
  • Integrated MSc. Electronics and Computer science,

New University of Lisbon (UNL), Portugal, 2008

  • Positions
  • Research fellow, Wageningen University &

Research (WUR), Netherlands, 2017-

  • Visiting professor, Carlos III University of Madrid,

Spain, 2015-2017

  • Early stage researcher, UPM, Spain, 2008-2014
  • Junior researcher, University of Rome La Sapienza,

Italy, 2007-2008

  • Further information
  • Webpage: www.joao-valente.com
slide-39
SLIDE 39

39

Thank y u!