Open Access Open Access  Restricted Access Subscription Access

Adigar: a drone simulator for agriculture


Affiliations
1 University of Colombo School of Computing, UCSC Building Complex, 35, Reid Avenue, Colombo 7, 00700, Sri Lanka
2 Department of Computer Science, University of Oxford, Wolfson Building, Parks Road, Oxford, OX1 3QD, United Kingdom
 

Adigar is a drone simulator developed to reduce the adverse effects of pesticides during the spraying process. Here, we propose a path planning algorithm to cover all arable areas of a farmland, while avoiding unsafe areas. The proposed solution outputs the optimal path for the farmland and the drone can fly over along this path to spray pesticides without human intervention. This approach highlights the concept of using drones for agricultural purposes with minimum human intervention.

Keywords

Agriculture, autonomous drones, human intervention, reinforcement learning, pesticides.
User
Notifications
Font Size


  • Adigar: a drone simulator for agriculture

Abstract Views: 427  |  PDF Views: 192

Authors

Akarshani Amarasinghe
University of Colombo School of Computing, UCSC Building Complex, 35, Reid Avenue, Colombo 7, 00700, Sri Lanka
Lakshman Jayaratne
University of Colombo School of Computing, UCSC Building Complex, 35, Reid Avenue, Colombo 7, 00700, Sri Lanka
Viraj B. Wijesuriya
Department of Computer Science, University of Oxford, Wolfson Building, Parks Road, Oxford, OX1 3QD, United Kingdom

Abstract


Adigar is a drone simulator developed to reduce the adverse effects of pesticides during the spraying process. Here, we propose a path planning algorithm to cover all arable areas of a farmland, while avoiding unsafe areas. The proposed solution outputs the optimal path for the farmland and the drone can fly over along this path to spray pesticides without human intervention. This approach highlights the concept of using drones for agricultural purposes with minimum human intervention.

Keywords


Agriculture, autonomous drones, human intervention, reinforcement learning, pesticides.

References





DOI: https://doi.org/10.18520/cs%2Fv122%2Fi8%2F945-950