Adaptive Path Planning for Fusing Rapidly Exploring Random Trees and Deep Reinforcement Learning in an Agriculture Dynamic Environment UAVs uri icon


  • The authors would like to thank the following Brazilian Agencies CEFET-RJ, CAPES, CNPq, and FAPERJ. The authors also want to thank the Research Centre in Digitalization and Intelligent Robotics (CeDRI), Instituto Politécnico de Bragança–IPB (UIDB/05757/2020 and UIDP/05757/2020), the Foundation for Science and Technology (FCT, Portugal) for financial support through national funds FCT/MCTES (PIDDAC) to CeDRI, and Laboratório Associado para a Sustentabilidade e Tecnologia em Regiões de Montanha (SusTEC) and IPB, Portugal. This work was carried out under the Project “OleaChain: Competências para a sustentabilidade e inovação da cadeia de valor do olival tradicional no Norte Interior de Portugal” (NORTE-06-3559-FSE-000188), an operation to hire highly qualified human resources, funded by NORTE 2020 through the European Social Fund (ESF).
  • Unmanned aerial vehicles (UAV) are a suitable solution for monitoring growing cultures due to the possibility of covering a large area and the necessity of periodic monitoring. In inspection and monitoring tasks, the UAV must find an optimal or near-optimal collision-free route given initial and target positions. In this sense, path-planning strategies are crucial, especially online path planning that can represent the robot’s operational environment or for control purposes. Therefore, this paper proposes an online adaptive path-planning solution based on the fusion of rapidly exploring random trees (RRT) and deep reinforcement learning (DRL) algorithms applied to the generation and control of the UAV autonomous trajectory during an olive-growing fly traps inspection task. The main objective of this proposal is to provide a reliable route for the UAV to reach the inspection points in the tree space to capture an image of the trap autonomously, avoiding possible obstacles present in the environment. The proposed framework was tested in a simulated environment using Gazebo and ROS. The results showed that the proposed solution accomplished the trial for environments up to 300 m3 and with 10 dynamic objects.

publication date

  • January 2023