Kodo Millet PPT made by Ghanshyam bairwa college of Agriculture kumher bhara...
Distributed Sensing in Horticultural Environments
1. Distributed Sensing in Horticultural Environments George Kantor Carnegie Mellon University International Horticultural Congress Lisboa 2010 Colloquium 6: Technical Innovation in Horticulture 25 August 2010
5. can also send control signalsSensors (leaf wetness, temperature, humidity, etc.) node field Internet base station G. Kantor CMU Robotics Institute IHC 2010Lisboa 25 August 2010 Sensing for Horticulture
6. G. Kantor CMU Robotics Institute IHC 2010Lisboa 25 August 2010 Sensing for Horticulture
7. Visualizing Time Series(PSU FREC, ZedX Inc.) FREC Building University Drive North 50m G. Kantor CMU Robotics Institute IHC 2010Lisboa 25 August 2010 Sensing for Horticulture
9. Sensor Net Sensor Requirements Hands off operation No/little calibration required Extremely rugged Inexpensive Generate small amounts of data Require low computational power Require low electrical power Examples: today: temperature, RH, PAR, light, rain, soil moisture, soil EC, leaf wetness, wind speed/direction, etc. future: stem water potential, fruit temperature, fruit size, sap flow, others??? G. Kantor CMU Robotics Institute IHC 2010Lisboa 25 August 2010 Sensing for Horticulture
10. Technology Overview: Robot G. Kantor CMU Robotics Institute IHC 2010Lisboa 25 August 2010 Sensing for Horticulture
11. G. Kantor CMU Robotics Institute IHC 2010Lisboa 25 August 2010 Sensing for Horticulture
12. Laser Scanning G. Kantor CMU Robotics Institute IHC 2010Lisboa 25 August 2010 Sensing for Horticulture
13. Building Point Clouds G. Kantor CMU Robotics Institute IHC 2010Lisboa 25 August 2010 Sensing for Horticulture
14. point cloud created by Ben Grocholsky G. Kantor CMU Robotics Institute IHC 2010Lisboa 25 August 2010 Sensing for Horticulture
15. Technology Overview: Robot NDVI cameras G. Kantor CMU Robotics Institute IHC 2010Lisboa 25 August 2010 Sensing for Horticulture
16. Robot Sensing Requirements Hands off operation Can have non-trivial calibration step Moderately rugged Can be expensive Can generate large amounts of data Can require large computing power Can require large electrical power Examples: today: laser scanners, cameras, hyperspectral imagery future: gas exchange, chlorophyll, pheromone, leaf area,… G. Kantor CMU Robotics Institute IHC 2010Lisboa 25 August 2010 Sensing for Horticulture
17. Robots vs. Sensor Nets High spatial resolution Low temporal resolution Sophisticated sensing More Expensive Moderate spatial resolution High temporal resolution Simple sensing Less expensive G. Kantor CMU Robotics Institute IHC 2010Lisboa 25 August 2010 Sensing for Horticulture
18. Robots vs. Sensor Nets x High spatial resolution Low temporal resolution Sophisticated sensing More Expensive Moderate spatial resolution High temporal resolution Simple sensing Less expensive G. Kantor CMU Robotics Institute IHC 2010Lisboa 25 August 2010 Sensing for Horticulture
19. Robots living together in harmony with Sensor Nets High spatial resolution Low temporal resolution Sophisticated sensing More Expensive Moderate spatial resolution High temporal resolution Simple sensing Less expensive G. Kantor CMU Robotics Institute IHC 2010Lisboa 25 August 2010 Sensing for Horticulture
20. Information is Worthless… G. Kantor CMU Robotics Institute IHC 2010Lisboa 25 August 2010 Sensing for Horticulture
21. Information is Worthless… …unless you use it to do something! G. Kantor CMU Robotics Institute IHC 2010Lisboa 25 August 2010 Sensing for Horticulture
22. Set Point Irrigation low setpoint high setpoint soil moisture measurement irrigation events G. Kantor CMU Robotics Institute IHC 2010Lisboa 25 August 2010 Sensing for Horticulture
23. Ongoing Work: Experimental Setup G. Kantor CMU Robotics Institute IHC 2010Lisboa 25 August 2010 Sensing for Horticulture
24. Human in the Loop soil moisture sensors at 12 locations 38% increase in #1 stems Charles Bauers John Lea-Cox base station irrigation scheduler G. Kantor CMU Robotics Institute IHC 2010Lisboa 25 August 2010 Sensing for Horticulture
25. Automatic Decision Making: Modeling Approach Model Parameters model outputs Model Mapping to Control Decision sensor inputs control signal G. Kantor CMU Robotics Institute IHC 2010Lisboa 25 August 2010 Sensing for Horticulture
26. Example: Petunia Model [van Iersel et al.] Model Parameters variety plant age Mapping to Control Decision (replace amount of water used) model output: water use sensor inputs: temperature RH light Model irrigation command G. Kantor CMU Robotics Institute IHC 2010Lisboa 25 August 2010 Sensing for Horticulture
27. Feedforward Modification At the beginning of each day: weather forecast: temperature RH light predicted water use set daily irrigation schedule Model (with parameters) irrigation schedule At the end of each day: sensor inputs: temperature RH light Model (with parameters) replace difference water use irrigation command G. Kantor CMU Robotics Institute IHC 2010Lisboa 25 August 2010 Sensing for Horticulture
28. Example: MAESTRA [e.g., Bauerle et al.] Model Parameters tree location, geometry, soil type, LAI, leaf physiology… Mapping to Control Decision (replace amount of water used) model output: water use sensor inputs: temperature RH PAR wind Model irrigation command G. Kantor CMU Robotics Institute IHC 2010Lisboa 25 August 2010 Sensing for Horticulture
29. Example: MAESTRA [e.g., Bauerle et al.] Model Parameters tree location, geometry, soil type, LAI, leaf physiology… Mapping to Control Decision (replace amount of water used) model output: water use sensor inputs: temperature RH PAR wind Model irrigation command G. Kantor CMU Robotics Institute IHC 2010Lisboa 25 August 2010 Sensing for Horticulture
30. G. Kantor CMU Robotics Institute IHC 2010Lisboa 25 August 2010
31. Obrigado USDA SCRI CASC Project: CMU, Penn State, Washington State, Purdue, Oregon State, Vision Robotics USDA SCRI MINDS Project: U. Maryland, CMU, Georgia, Colorado State, Cornell, Decagon Devices, Antir Software Jim McFerson and WTFRC IHC 2010 Organizers G. Kantor CMU Robotics Institute IHC 2010Lisboa 25 August 2010 Sensing for Horticulture