The world’s demand for agricultural products is growing rapidly requiring an estimated 50% increase in agricultural productivity in the next 30 years. There is a strong need for more sustainable agriculture to lower the impact on the environment. Agriculture furthermore suffers from a lack of skilled labour. Agricultural robotics and precision farming can over a part of the solution to meet these challenges.

Challenges for agricultural robotics

There are three challenges for robots to operate in agri-food environments: (1) the variation in the appearance of objects, environmental properties, cultivation systems and tasks, (2) incomplete information due to occlusions, sensor noise and uncertainty, and (3) safety in the interaction with fragile plants and produce, and human beings.

Research

To tackle these challenges, the research in my group targets at the following topics:

1. Robust perception. Deep neural networks have revolutionised the field of machine vision. Compared to traditional image-processing algorithms, deep neural nets can deal better with variation in the appearance of objects and differences in illumination conditions. To further improve the performance, we study the generalisability of neural networks and develop methods to deal better with variations.
2. Active perception. To deal with occlusions, robots need to actively perceive the environment. We study methods for active perception, to allow robots to decide on new viewpoints to acquire relevant information from the environment to perform its tasks.
3. Soft robotics. To safely interact with the agri-food environment, robots need to get a soft touch. On the one hand, this requires the use of soft material and actuators. On the other hand, it requires tactile sensors and control algorithms.

http://www.gertkootstra.com

FlexCRAFT

Effectiveness, efficiency, sustainability, hygiene, and the limited availability of skilled personnel due to unap- pealing working conditions are the drivers for replacing human labor by technology in agro-food production and processing. Robots have entered this sector but current robotic technology is not able to deal with the large variations in shape, size, and softness of agro-food products nor the variation in environmental conditions and tasks that are typical for the agro-food chain. The scientific challenge of the FlexCRAFT project is to equip robot technology with generic capabilities in active perception, world modeling, planning and control, and gripping and manipulation; capabilities needed to deal with the aforementioned conditions in a robust way. These capa- bilities will be integrated in three use-case projects in greenhouse production, food processing, and food pack- aging. These use-cases represent the class of challenges encountered in the whole agro-food chain. By inte- grating all the required disciplines, this program builds on a strong multi-disciplinary consortium of experts in both research and development and a user group with leading industry. This program is a timely response to an urgent request by the Dutch agro-food industry for more advanced robot technology necessary for the contin- ued leadership of Dutch producers in the international market.

I teach several courses related to Artificial Intelligence, Machine Vision and Robotics. These courses provide the students with the theoretical background as well as the practical application of the methodologies in the agro-food domain.