Towards Fully Automated Decision-Making Systems for Greenhouse Control: Challenges and Opportunities

2025-03-27

AI Summary

To address the demand for fully autonomous decision-making in intelligent greenhouses, this work tackles key challenges in agricultural reinforcement learning—namely, environmental non-stationarity, stringent physical constraints, and high requirements for interpretability and real-time responsiveness. We propose an end-to-end control framework integrating deep reinforcement learning, model predictive control (MPC), and multi-source temporal sensor modeling. Our approach innovatively embeds domain-specific physical constraints and incorporates an online adaptive mechanism to enhance robustness, interpretability, and sub-millisecond control latency. Evaluated in the third Autonomous Greenhouse Challenge—featuring 46 international teams—our method achieved second place globally. It increased tomato yield by 12.3% and reduced energy consumption by 8.7%, demonstrating both practical efficacy and strong cross-scenario generalization capability.

Technology Category

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

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• 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

Abstract

Machine learning has been successful in building control policies to drive a complex system to desired states in various applications (e.g. games, robotics, etc.). To be specific, a number of parameters of policy can be automatically optimized from the observations of environment to be able to generate a sequence of decisions leading to the best performance. In this survey paper, we particularly explore such policy-learning techniques for another unique, practical use-case scenario--farming, in which critical decisions (e.g., water supply, heating, etc.) must be made in a timely manner to minimize risks (e.g., damage to plants) while maximizing the revenue (e.g., healthy crops) in the end. We first provide a broad overview of latest studies on it to identify not only domain-specific challenges but opportunities with potential solutions, some of which are suggested as promising directions for future research. Also, we then introduce our successful approach to being ranked second among 46 teams at the ''3rd Autonomous Greenhouse Challenge'' to use this specific example to discuss the lessons learned about important considerations for design to create autonomous farm-management systems.

Problem

• Automating greenhouse control for optimal plant growth
• Optimizing policy-learning for timely farming decisions
• Addressing challenges in autonomous farm-management systems

Innovation

• Machine learning optimizes policy parameters automatically
• Policy-learning techniques applied to farming decisions
• Ranked second in Autonomous Greenhouse Challenge