CPS: Frontier: Collaborative Research: COALESCE: COntext Aware LEarning for Sustainable CybEr-Agricultural Systems

我们这一代人面临的一个重大技术挑战是，到2050年，通过可持续地利用水和化学品，准备好养活90亿人。然而，在采用可持续农业管理做法、提高产量、保持农业盈利、应对威胁产量的致命生物和非生物压力和疾病以及气候变化方面，我们正面临前所未有的挑战。该项目旨在改变信息物理系统（CPS）在农业中的能力，使农民能够以更低的成本、更高的灵活性和显著降低的环境影响来应对作物压力。目标是在人工智能，机器学习和机器人技术方面取得基础进展，以实现单个植物级感知，建模和推理。这使得小型自主灵巧机器人取代重型农业设备，可以单独监测植物或小块土地，并使用最少量的化学品进行处理。这也降低了小规模农民的进入门槛，提高了安全性，最大限度地减少了径流和土壤压实。该项目包括与伊利诺伊大学厄巴纳-香槟分校的重要合作，该合作由美国农业部下属的国家食品和农业研究所（NIFA）资助。该研究调查了复杂网络物理系统的数据驱动估计、控制和适应的多个领域，例如：(1)将领域知识和物理原理严格结合到机器学习（ML）驱动的估计/预测/控制框架中；(2)跨模态信息融合，用于吸收不同类型（分类、离散或连续）、质量/精度/噪声和采样频率的异构数据流。(3)退化感知环境下的鲁棒机器学习；(4)资源约束下数据驱动的监督决策，如数据量、数据质量、隐私和成本；(5)在恶劣、变化和不确定的局部可观测野外环境中运行的自主机器人团队的分布式控制和协调；(6)小型移动机器人用于农业操作的柔性机械臂和机械手，以及嵌入式控制和传感系统。该小组与与农民有直接联系的生产者团体的独特合作促进了该框架的广泛接受。为CPS社区、农业社区和公众提供广泛的知识传播计划。教育和推广计划的重点是农业人口和下一代科学劳动力。参与机构的具体活动和项目旨在扩大美国原住民、西班牙裔、非裔美国人和女性学生在计算机和工程领域的参与。本计划所产生的所有研究成果和教育资料均可透过本计划网页公开。该奖项反映了美国国家科学基金会的法定使命，并通过使用基金会的知识价值和更广泛的影响审查标准进行评估，被认为值得支持。

One of the grand technical challenges of our generation is to get ready to feed 9 billion people by 2050 with sustainable use of water and chemicals. However, we are facing unprecedented challenges in adopting sustainable agricultural management practices, increasing production, keeping agriculture profitable and coping with deadly biotic and abiotic stresses and diseases as well as changing climate that threaten yield. This project aims to transform Cyber-Physical System (CPS) capabilities in agriculture to enable farmers to respond to crop stressors with lower cost, greater agility, and significantly lower environmental impact than current practices. The objective is to make foundational advances in AI, machine learning and robotics to individual plant-level sensing, modeling and reasoning. This enables small autonomous dexterous robots instead of the heavy farm equipment to monitor plants or small plots individually and treat them with minimum amount of chemicals. This also lowers the barrier to entry for small scale farmers, increases safety, minimizes runoff as well as soil compaction. This project includes a significant collaboration with the University of Illinois at Urbana-Champaign that is funded by the National Institute of Food and Agriculture (NIFA) within the U.S. Department of Agriculture.The research investigates multiple areas in data-driven estimation, control, and adaptation of complex cyber-physical systems, such as: (1) rigorous incorporation of domain knowledge and physical principles into a machine learning (ML)-driven estimation/prediction/control framework, (2) cross-modal information fusion for assimilating heterogeneous data streams that differ in type (categorical, discrete, or continuous), quality/accuracy/noise, and sampling frequency. (3) robust ML under a degraded sensing environment, (4) data-driven supervisory decision-making under resource constraints, such as data amount, data quality, privacy, and cost, (5) distributed control and coordination of autonomous teams of robots operating in harsh, changing, and uncertain field environments with partial observability, and (6) soft robotic arms and manipulators, along with embedded control and sensing systems, for agricultural manipulation by small mobile robots. The broader acceptance of the framework is facilitated by the team's unique collaboration with producer groups with direct connections to farmers. A wide range of knowledge dissemination plans target the CPS community, the farming community, and the general public. Education and outreach plans focus on the farming population and the next-generation scientific workforce. Specific activities and programs at the participating institutions are designed to broaden participation of Native American, Hispanic, African-American, and female students in computing and engineering. All research products and educational material generated by the project are being made publicly available through the project webpage.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.