SLGP Header

Greenbot: A Solar Autonomous Robot to Uproot Weeds in a Grape Field

IJCSEC Front Page
Author(s):
M. Sujaritha, Mahesh Lakshminarasimhan, Colin Jude Fernandez, Mahesh Chandran
Volume
4, Issue 2
Pages:
1351-1358
Year of Publication:
April,2016
International Journal of Computer Science and Engineering Communications
ISSN:
2347-8586
Citation: M. Sujaritha, Mahesh Lakshminarasimhan, Colin Jude Fernandez, Mahesh Chandran."Greenbot: A Solar Autonomous Robot to Uproot Weeds in a Grape Field" International Journal of Computer Science and Engineering Communications,Vol.4,Issue.2.(2016):1351-1358.
Full Text Download

Abstract
Greenbot, an initial step towards automation of agricultural practices in India, is an autonomous robot that is designed solely to help farmers by identifying the weeds automatically and uprooting them from the agricultural field, especially grapevine field. The power source for this robot is provided through a solar panel along with a rechargeable battery, making it an environment friendly device. The primary actuator of the proposed system is a high speed blade known as a "Rotavator" that uproots the weed and buries it back into the soil from where it is uprooted. Weed identification through image processing techniques, controlling the rotavator based on image processing output and guiding navigation through Global Positioning System (GPS) and obstacle identification sensor are the important components of the proposed intelligent system. Raspberry Pi 2 board is used to implement these components, which is based on Broadcom BCM2836 SoC and includes a quad-core Cortex-A7 CPU running at 900 MHz and 1 GB RAM using Windows 10 IOT core. MATLAB software is used to implement the system.
Keywords:Autonomous Robot, Solar Energy, Image Processing, GPS, Obstacle Identification, Raspberry Pi, MATLAB

References:

  1. Stuart Russell, Peter Norvig, “Artificial Intelligence – A Modern Approach”, 3rd edition, Pearson Education.
  2. Nils J. Nilsson, “Artificial Intelligence – A New Synthesis”, Harcourt Asia Pvt. Ltd., 2003.
  3. Y Patrick Henry Winston, “Artificial Intelligence”, Pearson Education”, 2004.
  4. Acharyya M. and Kundu M.K. (2007), Image Segmentation Using Wavelet Packet Frame and Neuro-fuzzy Tools, International journal of computational cognition, vol. 5, no. 4, pp.27-43.
  5. Adamchuck, V. I. (2005), Characterizing Soil Variability Using On-the-Go Sensing Technology. International Plant Nutrition Institute, Site-Specific Management Guidelines, SSMG-44. Norcross, Ga.
  6. Adamchuck, V. I. and P. Jasa. (2002), On-the-Go Vehicle-Based Soil Sensors. University of Nebraska-Lincoln Extension EC02-178.
  7. Dalal, R.C. and Henry, R.J. (1986) “Simultaneous Determination of Moisture, organic carbon and Total Nitrogen by Near infrared reference Spectrophotometry”. Soil Science society of America. Vol. 50 pp: 120-123.
  8. Doerge, T. A. (2002). Variable-rate nitrogen management creates opportunities and challenges for corn producers. Crop Management doi:10.1094/CM-2002-0905-01-RS. [9] Guerrero JM, Pajares G, Montalvo M, Romeo J, Guijarro M, (2012) Support vector machines for crop/weeds identification in maize fields , Expert Systems with Applications 39 (12), 11149-11155.