Development of tomato harvester robotic arm prototype using IoT application

  • Abstract
  • Keywords
  • References
  • PDF
  • Abstract

    In order to replace harvesting tomato manually, a robotic arm prototype for harvesting tomatoes using Internet of things (IoT) is presented in this paper. The objective to develop a robotic arm prototype which works autonomously is achieved. Due to the lack and high cost of labour, acrylic plastic materials prototype robot that controlled by Rasberry Pi3 is used for tomato recognition and localization. A coordinate or location used to pick tomatoes is identified. The usage of hue-saturation-value (HSV) colour could improve the harvesting efficiency. The movement of the actuator or the robotic arm from the initial position to the target’s position is adopted to increase the accuracy of the targeted tomato. Concerning the control software, a graphic user interface is designed to submit the operator’s commands and display the output. The performances of the robotic arm are shown.


  • Keywords

    IoT Application; Prototype; Raspberry Pi3; Robotic arm; Tomato harvester.

  • References

      [1] C. E. Schertz and G.K. Brown, “Basic considerations in mechanizing citrus harvest”, Trans. ASAE, Vol. 11, No. 2, (1968), pp.343–346.

      [2] C. Ji, J. Zhang, T. Yuan and W. Li, “Research on key technology of truss tomato harvesting robot in greenhouse”, Applied Mechanics and Materials, Vol. 442, (2014), pp.480–486.

      [3] S. S. Mehta, W. MacKunis and T. F. Burks, “Nonlinear robust visual servo control for robotic citrus harvesting”, The 19th world congress of the International Federation of Automatic. Control, Cape Town South Africa, (2014), pp.8110–8115.

      [4] Y. S. Si, G. Liu and J. Feng, “Location of apples in trees using stereoscopic vision”, Comput. Electr. Agric., Vol. 112, No. 3, (2015), pp.68–74.

      [5] F. Kurtulmus, W.S. Lee and A. Vardar, “Immature peach detection in colour images acquired in natural illumination conditions using statistic classifiers and neural network”. Precis. Agric., Vol. 15, (2014), pp.57–79.

      [6] X. Q. Wei, J. Kun and H.L. Jin, “Automatic method of fruit object extraction under complex agricultural background for vision system of fruit picking robot”, Optics, Vol. 125, No. 12, (2014), pp.5684–5689.

      [7] G. Gatica, S. Best, J. Ceroni and G. Lefranc, “Olive fruits recognition using neural networks”, Procedia Comput. Sci., Vol. 17, (2013), pp.412–419.

      [8] R. Xiang, H.Y. Jiang and Y.B. Ying, “Recognition of clustered tomatoes based on binocular stereo vision”, Comput. Electr. Agric., Vol. 106, No. 8, (2014), pp.75–90.

      [9] Y.S. Si, G. Liu and J. Feng, “Location of apples in trees using stereoscopic vision”, Comput. Electr. Agric., Vol. 112, No. 3, (2015), pp.68–74.

      [10] S. Dhvani and B. Vinayak, “IoT based Biometrics Implementation on Raspberry Pi”, Procedia Computer Science, Vol. 79, (2016), pp.328 – 336.

      [11] D. Xu, W. H. Li and S. Li, “Internet of things in industries: A survey”, IEEE Trans. Ind. Inf., Vol. 10, No. 4, (2014), pp.2233–2243.

      [12] S. Li, T. Tryfonas and H. Li, “The internet of things: a security point of view”, Internet Res., Vol. 26, No. 2, (2016), pp.337–359.

      [13] Y.I. Yuehong, Y. Zeng, X. Chen and Y. Fan, “The internet of things in healthcare: An overview”, J. Ind. Inf. Integr., Vol. 31, no. 1, (2016), pp.3–13.




Article ID: 20246
DOI: 10.14419/ijet.v7i4.20246

Copyright © 2012-2015 Science Publishing Corporation Inc. All rights reserved.