Our technology and automation knowledge

With our knowledge and technology, we have developed an autonomous leaf-cutting robot for cucumber plants in high-wire cultivation. With some smart adjustments for the crop and a small adjustment of the AI algorithm, the robot is also suitable for tomato cultivation. 

Autonomous harvesting of cucumbers is also part of our roadmap, as is automation for other crops or flowers. The end effector (patent) for leaf cutting is intrinsically tolerant to positioning and cutting, making it robust for autonomous positioning. In the future, other end-effectors will also be placed on the interface. 

Think, for example, besides harvesting also precision spraying, insect detection and removal. There is a huge perspective for more with the CropTeq. In addition, we have chosen to provide the system with an option for data collection, with a perspective on, for example, harvest forecasts. Data is a much discussed topic. We measure and collect. Based on this, the grower can give his own interpretation.

Our Artificial Intelligence

A robot that has to cut leaves autonomously and therefore has to adapt continuously needs AI. With a vision system, a smart neural network and a correctly chosen camera, it is possible to recognize an object and its position. Using additional techniques and a plant model, we have developed a movement and end-effector strategy.

With enough images you can train AI algorithm so that the system recognizes the right things. Training is a new word for programming. However, you do not have to be a software specialist for this. Refining the algorithms, recognizing the plant, does require knowledge and insight. Once you have them, it is something that the grower could also improve on.

Artificial intelligence therefore makes the recognition software itself, and not a human being. AI software is therefore never 100% reliable, so you cannot cut 100% of the leaf or harvest a fruit with it. For example 95%, but that can sink in due to different light incidence, etc. Despite this limitation, it is the AI ​​that makes the automation in the greenhouse possible.

 

Data

A robot generates a lot of data. You have two types of data, machine data and application data. We use machine data to analyze and monitor the system. The aim is to be able to continuously improve performance. An example is energy management. You can calculate the energy consumption, but the practice is often different and not the same for everyone. What is your charging strategy or the required capacity, your lifespan.

Application data is interesting for the grower. Temperature, light, moisture, CO2 you could measure and monitor them all continuously. Here too, you can also draw conclusions with analysis and adjust your cultivation process. We do not measure this data by default, but it can be added. That raw data is of course the property of the grower, but he needs the help of a specialist who can analyze the data and increase the value.

Robot path planning.

A robot arm that moves from A to B is nothing new. An arm that must continuously adjust its movement and prevent collisions is the innovation. And that real time at maximum speeds. That is where the intelligence of our system lies. Ultimately, no one wants a robot to continuously hit the plant, so you get around it as much as possible.

End effector: accurate, fast and economical. 

Accuracy is generally not a problem for a robot. In the greenhouse, however, the camera and vision system determine the inaccuracy. The robustness of the cutting system is therefore decisive. We have opted for a patented gripper that also stresses the plant as little as possible.

A robot can be very fast. On the one hand, the safety requirements limit the speed of movement of the cobot arms, on the other hand careful handling of the plant also limits the speed. The bottom line is that mainly the movement from leaf to leaf and the cutting cycle time Is critical. The vision system, the image processing are not in the critical path of the movement planning. We guarantee 1000 cuts per hour on average over 100m.

Economically feasible, because the variable costs of the system are very low. The variable costs and the depreciation of the investment give a robot hourly rate that is substantially lower than the wage costs. The speed of the system is essential and it will only increase. The software dominates, which means that an important part of the variable costs is in the maintenance and licensing costs of the software.