Optimizing navigation and chemical application in precision agriculture with deep reinforcement learning and conditional action tree

Optimizing navigation and chemical application in precision agriculture with deep reinforcement learning and conditional action tree

This paper presents a novel reinforcement learning (RL)-based planning scheme for optimized robotic management of biotic stresses in precision agriculture. The framework employs a hierarchical decision-making structure with conditional action masking, where high-level actions guide the robot's...

Full description

Saved in:
Bibliographic Details
Main Authors: Mahsa Khosravi, Zhanhong Jiang, Joshua R. Waite, Sarah E. Jones, Hernan Torres Pacin, Arti Singh, Baskar Ganapathysubramanian, Asheesh Kumar Singh, Soumik Sarkar
Format: Article
Language:English
Published: Elsevier 2025-12-01
Series:Smart Agricultural Technology
Subjects:
Deep reinforcement learning
Conditional action tree
Navigation
Chemical spraying
Precision agriculture
Yield recovery
Online Access:http://www.sciencedirect.com/science/article/pii/S2772375525004253
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This paper presents a novel reinforcement learning (RL)-based planning scheme for optimized robotic management of biotic stresses in precision agriculture. The framework employs a hierarchical decision-making structure with conditional action masking, where high-level actions guide the robot's exploration, while low-level actions optimize its navigation and efficient chemical spraying in affected areas. The key optimization objectives include improving the coverage of infested areas with limited battery power and reducing chemical usage, thus preventing unnecessary spraying of healthy areas of the field. Our numerical experimental results demonstrate that the proposed method, Hierarchical Action Masking Proximal Policy Optimization (HAM-PPO), significantly outperforms baseline practices, such as LawnMower navigation + indiscriminate spraying (Carpet Spray), in terms of yield recovery and resource efficiency. HAM-PPO consistently achieves higher yield recovery percentages and lower chemical costs across a range of infestation scenarios. The framework also exhibits robustness to observation noise and generalizability under diverse environmental conditions, adapting to varying infestation ranges and spatial distribution patterns.
ISSN:2772-3755

Similar Items