A Simulator-based Planning Framework for Optimizing Autonomous Greenhouse Control Strategy


  • Zhicheng An Tsinghua-Berkeley Shenzhen Institute, Tsinghua University
  • Xiaoyan Cao School of Informatics, Xiamen University
  • Yao Yao Tsinghua-Berkeley Shenzhen Institute, Tsinghua University
  • Wanpeng Zhang Tsinghua University
  • Lanqing Li Tencent AI Lab
  • Yue Wang Tsinghua University
  • Shihui Guo School of Informatics, Xiamen University
  • Dijun Luo Tencent AI Lab


Description And Modeling Of Novel Application Domains, Industry / Application Challenge Problems, Integration Of Multiple Planning And Scheduling Techniques, Or Of Planning And Scheduling Techniques With Techniques From Other Areas Or Disciplines


The rapidly growing global population presents challenges and demands for efficient production of healthy fresh food. Autonomous greenhouse equipped with standard sensors and actuators (such as heating and lighting) which enables control of indoor climate for crop production, contributes to producing higher yields. However, it requires skilled and expensive labor, as well as a large amount of energy. An autonomous greenhouse control strategy, powered by AI algorithms by optimizing the yields and resource use simultaneously, offers an ideal solution to the dilemma. In this paper, we propose a two-stage planning framework to automatically optimize greenhouse control setpoints given specific outside weather conditions. Firstly, we take advantage of cumulative planting data and horticulture knowledge to build a multi-modular simulator using neural networks, to simulate climate change and crop growth in the greenhouse. Secondly, two AI algorithms (reinforcement learning and heuristic algorithm) as planning methods are applied to obtain optimal control strategies based on the simulator. We evaluate our framework on a cherry-tomato planting dataset and demonstrate that the simulator is able to simulate greenhouse planting processes with high accuracy and fast speed. Moreover, the control strategies produced by the AI algorithms all obtain superhuman performance, in particular, significantly outperform all teams of the second “Autonomous Greenhouse Challenge” in terms of net profits.




How to Cite

An, Z., Cao, X., Yao, Y., Zhang, W., Li, L., Wang, Y., Guo, S., & Luo, D. (2021). A Simulator-based Planning Framework for Optimizing Autonomous Greenhouse Control Strategy. Proceedings of the International Conference on Automated Planning and Scheduling, 31(1), 436-444. Retrieved from https://ojs.aaai.org/index.php/ICAPS/article/view/15989