Trajectory Planning for UAV-Based Smart Farming Using Imitation-Based Triple Deep Q-Learning

2025-12-21

AI Summary

Trajectory planning for agricultural drones under high uncertainty, partial observability, and stringent energy constraints remains challenging in intelligent farming. Method: We formulate the problem as a multi-agent Markov decision process (MAMDP) and propose an Imitation-based Triple Deep Q-Network (ITDQN). ITDQN integrates an elite imitation mechanism to reduce exploration cost and introduces an auxiliary Q-network to enhance training stability and accelerate convergence over standard Double DQN (DDQN). Contribution/Results: Evaluated in both simulated and real-world farmland environments, ITDQN achieves a 4.43% improvement in weed detection accuracy and a 6.94% increase in wireless sensor data collection rate compared to baseline DDQN. This work provides a scalable, robust reinforcement learning framework for resource-constrained, autonomous cooperative perception among agricultural drones.

Technology Category

• Multiagent Systems: Teamwork
• Machine Learning: Imitation Learning & Inverse Reinforcement Learning
• Intelligent Robots: Multimodal Perception & Sensor Fusion

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
• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI

Abstract

Unmanned aerial vehicles (UAVs) have emerged as a promising auxiliary platform for smart agriculture, capable of simultaneously performing weed detection, recognition, and data collection from wireless sensors. However, trajectory planning for UAV-based smart agriculture is challenging due to the high uncertainty of the environment, partial observations, and limited battery capacity of UAVs. To address these issues, we formulate the trajectory planning problem as a Markov decision process (MDP) and leverage multi-agent reinforcement learning (MARL) to solve it. Furthermore, we propose a novel imitation-based triple deep Q-network (ITDQN) algorithm, which employs an elite imitation mechanism to reduce exploration costs and utilizes a mediator Q-network over a double deep Q-network (DDQN) to accelerate and stabilize training and improve performance. Experimental results in both simulated and real-world environments demonstrate the effectiveness of our solution. Moreover, our proposed ITDQN outperforms DDQN by 4.43% in weed recognition rate and 6.94% in data collection rate.

Problem

• Optimizes UAV trajectory planning for smart farming tasks
• Addresses environmental uncertainty and partial observation challenges
• Improves weed recognition and data collection efficiency

Innovation

• Uses imitation-based triple deep Q-network algorithm
• Employs elite imitation to reduce exploration costs
• Utilizes mediator Q-network for stable training