Autors: Farid A.M., Roshanian J., Todorov M., Serbezov, V. S.
Title: Reinforcement learning application in multi-UAV mapping and spraying
Keywords:

Abstract: UAVs attract a lot of attentions in precision agriculture because they are easy to implement, and unlike ground vehicles, do not damage the crops. Reinforcement learning can help in automating decision-making processes in precision agriculture. In this paper after detailed introduction about applications of reinforcement learning in aerial spraying, a novel approach is proposed for path planning in see and spray missions. In these missions, by using proximity policy optimization (PPO) reinforcement learning we want to optimize multiple parameters that may conflict with each other. The PPO optimizes the path of swarm of multi-rotor UAVs in terms of mission time and energy consumption. The proposed approach shows the efficiency of the proposed path planning comparing to policy gradient (PG) approach.

References

  1. United Nations Development Programme, Precision Agriculture for Smallholder Farmers (UNDP Global Centre for Technology, Innovation and Sustainable Development: Singapore, 2021).
  2. R. Gautron et al., "Reinforcement learning for crop management support: Review, prospects and challenges," Computers and Electronics in Agriculture 200, 107182 (2022). 10.1016/j.compag.2022.107182
  3. A. M. Farid, M. Mouhoub, T. Arkles, and G. Hutch, "Multi-UAV Weed Spraying," in International Conference on Robotics, Computer Vision and Intelligent Systems, ROBOVIS 2024, Communications in Computer and Information Science 2077 (Springer, Cham), pp. 210-224.
  4. B. S. Faiçal et al., "An adaptive approach for UAV-based pesticide spraying in dynamic environments," Computers and Electronics in Agriculture 138, pp. 210-223 (2017). 10.1016/j.compag.2017.04.011
  5. L. P. Zhou and H. Yong, "Simulation and optimization of multi spray factors in UAV," in Annual International Meeting, American Society of Agricultural and Biological Engineers, ASABE 2016 (17-20 July 2016, Orlando, Florida, USA).
  6. X. Wang, V. Yadav and S. N. Balakrishnan, "Cooperative UAV formation flying with obstacle/collision avoidance," IEEE Transactions on Control Systems Technology 15 (4), pp. 672-679 (2007). 10.1109/TCST.2007.899191
  7. A. Din et al., "A deep reinforcement learning-based multi-agent area coverage control for smart agriculture," Computers and Electrical Engineering 101, 108089 (2022). 10.1016/j.compeleceng.2022.108089
  8. S. Ao, T. Zhou, G. Long, Q. Lu, L. Zhu, and J. Jiang, "CO-PILOT: Collaborative planning and reinforcement learning on sub-task curriculum," Advances in Neural Information Processing Systems 34, 10444-10456 (2021).
  9. R. Gautron et al., "Reinforcement learning for crop management support: Review, prospects and challenges," Computers and Electronics in Agriculture 200, 107182 (2022). 10.1016/j.compag.2022.107182
  10. N. Rai et al., "Applications of deep learning in precision weed management: A review," Computers and Electronics in Agriculture 206, 107698 (2023). 10.1016/j.compag.2023.107698
  11. Z. Tan and M. Karaköse, "Proximal policy based deep reinforcement learning approach for swarm robots," in 2021 Zooming Innovation in Consumer Technologies Conference (ZINC) (Novi Sad, Serbia, 2021), IEEE, pp. 166-170.
  12. S. S. P. Nethala, "Autonomous harvesting via hierarchical reinforcement learning in dynamic environments," PhD dissertation, Texas A&M University-Corpus Christi, 2023.
  13. J. Schulman et al., "Proximal policy optimization algorithms," arXiv preprint arXiv:1707.06347 (2017).

Issue

AIP Conference Proceedings, vol. 3339, 2025, Bulgaria, https://doi.org/10.1063/5.0297803

Вид: публикация в международен форум, публикация в реферирано издание, индексирана в Scopus