Optimizing Navigation And Chemical Application in Precision Agriculture With Deep Reinforcement Learning And Conditional Action Tree

2025-03-23

AI Summary

To address insufficient coverage, excessive pesticide application, and limited robot endurance in precision agriculture pest and disease management, this paper proposes HAM-PPO—a hierarchical reinforcement learning framework integrating conditional action masking with a structured action-tree variant of Proximal Policy Optimization (PPO). It jointly optimizes inspection path planning and targeted pesticide application. A hierarchical policy network decouples high-level exploration from low-level navigation and spraying control, while multi-source observation fusion and robust domain-adaptive training enhance both diseased-region coverage and decision interpretability. Experiments demonstrate that, compared to the conventional LawnMower+Carpet Spray baseline, HAM-PPO achieves a 27.4% higher average crop yield recovery rate and reduces pesticide consumption by 41.8%. Moreover, it exhibits strong generalization and stability under observational noise and diverse infection distributions.

Technology Category

• Intelligent Robots: Learning & Optimization for ROB
• Search and Optimization: Learning to Search
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

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 direct the robot's exploration, while low-level actions optimize its navigation and efficient chemical spraying in affected areas. The key objectives of optimization include improving the coverage of infected 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 infection scenarios. The framework also exhibits robustness to observation noise and generalizability under diverse environmental conditions, adapting to varying infection ranges and spatial distribution patterns.

Problem

• Optimize robotic navigation and chemical spraying in precision agriculture
• Reduce chemical usage while improving infected area coverage
• Enhance yield recovery and resource efficiency with HAM-PPO

Innovation

• Hierarchical RL with conditional action masking
• Optimized navigation and chemical spraying
• HAM-PPO for yield recovery and efficiency