DurableCASE: Durable Cooperative Agrobotics Systems Engineering
DurableCASE is a collaboration to develop solutions for collaborative robotic vehicles in the agricultural sector. DurableCASE stands for Durable Cooperative Agrobotics Systems Engineering: sustainable solutions for collaborative robots in the agricultural sector.
The use of robots as a replacement for labor in this sector is increasingly becoming a necessity due to a lack of manpower. The perspective offers many possibilities, for example in the field of sustainability. Multiple compact robots can take over the tasks of one large machine. That saves soil compaction. It also provides greater operational reliability: if one robot fails, other robots can take over tasks. The robots have to work well together.
DurableCASE develops solutions for communication between collaborating robots. The goal: robust cooperativity, where robust stands for safe, secure & performant. In other words, safe, secure and with optimum performance, under all circumstances. For robotics, there is a lot available in the rich ecosystem of ROS (Robot Operating System). DurableCASE makes grateful use of this.
AutoFarming: Autonomous production control of greenhouse farming system using Reinforcement Learning
Greenhouse is an important protected horticulture system in providing fresh food for the growing global population. However, it is also a big resource consumer, such as the large amount of energy usage from LED lighting and heating to maintain ideal growing climate for the crops. The main objective of greenhouse production control is realizing resource-effective crop growth and development through operating indoor climate actuators (e.g. lighting, heating, CO2 dosing, ventilation, screening, watering). In high-tech greenhouses, the modern sensing, control and computing systems are equipped but the operating set-points for the climate actuators are still rely on growers. However, the number of experienced growers is rare while the scale of greenhouse production system is expanding worldwide. Therefore, using advanced techniques to control the greenhouse production system with more optimality and autonomous in a reliable and robust way is in need nowadays challenge.
Reinforcement learning is the kind of learning system, which uses continuous feedback to adjust its own actions to obtain the best. It is also a dynamic control strategy which can update automatically the current control algorithm (policy) through incorporating newly developed knowledge learning from historical and real time data. The motivation of this project is developing autonomous production control of greenhouse farming systems using reinforcement learning, aiming to optimize the production system with desired growing climate, efficient resource usage, and at the same time adaptability to variable conditions (amongst individual plants, species and growing stages).
In this project, you will develop control-oriented crop-climate model based on crop/climate sensor measurements; develop autonomous control scheme of greenhouse production systems using reinforcement learning to achieve efficient crop growth/yield and energy usage. All the proposed approaches will be validated in real greenhouse for lettuce production. The performance will also be explored and analysed with state-of-the-practice.
SmartFarming: smart vertical farming production using plant monitoring and self-learning control
Vertical farming (VF), the practice of growing crops in vertically stacked layers under a highly controlled environment, represents a solution to sustainably produce high-quality fresh vegetables at any time of the year, especially in urbanized areas where the cultivable lands are scarce. Despite its considerable potential, VF development is currently limited by the high energy use and operating costs, increasing the selling price for the public and reducing the profit margins for shareholders. Therefore, advanced climate control techniques taking advantage of the predictability of plant behavior in VF could improve plant growth and development, whilst decreasing energy consumption. Automation also reduces the dependence on experienced growers that are not in sufficient number to fulfill the growing needs of the VF industry.
Self-learning control is a dynamic control strategy which can automatically update the current control model through incorporating newly developed knowledge learning from historical and real time data. Using self-learning control, the control model of climate in VF could be learned and updated from monitoring measurements with optimal solution adaptively for different stage of plant development. Reinforcement Learning (RL) is the only machine learning algorithm with both learning and optimization abilities, which can give reward feedback for each result to the algorithm to learn from and improve in future.
This project focus on developing a proof of concept of a smart VF production system using real-time plant monitoring and self-learning control to achieve fully autonomous climate control, as well as optimization of crop growth, energy consumption and operational cost. This project will combine the expertise of two chair groups HPP and FTE.