dr.ir. C (Congcong) Sun PhD MSc

dr.ir. C (Congcong) Sun PhD MSc

Assistant Professor

My name is Congcong Sun, I am an engineer of Computer Science and Automatic Control. Since joining Wageningen University in May of 2021, my passion lies in using learning-based control for optimal and autonomous agro-food production.

Learning-based Control

Learning-based control is the overlap between machine learning and automatic control. Comparing with traditional control approach, learning-based control can combine strong points of both machine learning and automatic control. For example, learning-based control can be data-based, does not always need a good model; it can also explore optimal control actions through learning and interacting with the environment; can update and improve itself automatically during this learning process. One typical example of learning-based control is reinforcement learning.

The motivation of using learning-based control is because, comparing with other domain, agricultural production system is much more complex with lots of dynamics, uncertainties and variations. Learning-based control has lots of potential and possibilities in achieving autonomous, reliability and robustness of control. A complete control system used to involve sensing, modelling, control and planning different aspects, so that my contributions in learning-based control can be elaborated in sensing, modelling, control and planning four different pieces.


In the sensing part, I am contributing in designing and developing optimal sensing systems using green sensors, soft sensing techniques, optimal sensor placement and sensor usage methods, etc. The objective of the sensing system is mainly collecting and providing high quality data for modelling and control applications, in an efficient and sustainable way. In this part, recently, Prof. Eldert van Henten and I have won a 4TU Green Sensors project, where we are planning to develop and apply biodegradable soil sensors for sustainable agriculture.


Besides sensing, learning-based control can also contribute to develop different models, like data-based model, hybrid model, or physical model etc. Possible applications include learning animal behaviors in livestock buildings for better animal robot interaction. This applications is involved in the NWO DurableCase project.


In the control aspects, I am now working on projects like climate control in greenhouse, vertical farm and plant factories to have efficient crop cultivation; environment control of livestock building for animal welfare, emission mitigation. As well as optimal control of irrigation systems to have efficient usage of water resource, etc..


Learning-based control can also contribute to planning. Such as in NWO DurableCase project, I am now working on optimal logistics planning of multi-agent harvesting robots in order to achieve autonomous harvesting, with optimal energy usage, and less soil compaction.