Autonomous CropTeq Robot versus human labour
- Robots do have a predictable reliability
- Robots do have a consistent quality
- Robots do not need a course or training.
- Robots are never sick, do need no housing
- Robots perform on a competitive speed at a lower "salary"/annual depreciation.
- Wirth robots there is more control over virus spread.
And
- In the long run, one robot can do more and more, such as harvesting, sorting, etc.
- Artificial intelligence (AI) will open up even more new possibilities
- Unlocking data; light, moisture, temperature, CO2, shape, weight, etc
- More and more innovative end-effectors.
CropTeq SmartTrim
The CropTeq SmartTrim is a single-arm robotic platform developed for autonomous leaf pruning in greenhouse environments. The system is designed with a target capacity of up to 1000 leaves per hour in future versions. The current MVP demonstrates the core functionality and forms the basis for further performance optimization.
The cutting technology is designed to operate very close to the stem, minimizing plant damage and reducing the risk of disease transmission. This patented cutting approach is planned for future implementations. To further support hygiene, the cutting blades are continuously heated to approximately 100°C, helping to disinfect the cutting surfaces during operation.
The CropTeq robot features a robust covering made from deep-drawn stainless steel components. This construction provides excellent durability while offering smooth surfaces that are easy to clean and maintain, making it highly suitable for greenhouse applications.
The robot consists of a stainless-steel autonomous guided vehicle (AGV) that houses the electrical hardware, AI computing platform, software systems, batteries, and space for future functionality.
The CropTeq robot can operate on both pipe rails and concrete paths. It autonomously navigates between growing rows, transferring independently from a pipe rail onto the concrete path and then to the pipe rail of the next row, without requiring human intervention.
The CropTeq robot is designed to operate reliably under real greenhouse conditions. It can autonomously bridge concrete paths of up to 2.3 meters and is capable of handling significant variations in floor and rail conditions. Uneven concrete surfaces, worn pipe rails, and other imperfections commonly found in existing greenhouse infrastructure do not prevent operation. The robotic navigation system are engineered to tolerate these variations, reducing the need for costly infrastructure modifications before deployment.
The robot is powered by rechargeable batteries based on a very convenient and unique-hot-swappable battery concept. This allows batteries to be exchanged without shutting down the system, enabling continuous 24/7 performance.
The CropTeq SmartTrim offers several unique advantages for greenhouse growers:
- Patented precision cutting close to the stem, minimizing disease risk.
- Intelligent main stem cut prevention.
- Designed for future pruning capacities of up to 1,000 leaves per hour.
- Self-disinfecting cutting system with continuously heated blades.
- Fully autonomous high-speed pipe rail transfers between growing rows.
- Battery-powered with hot-swappable batteries for 24/7 uninterrupted operation.
- Reliable performance on uneven concrete paths and worn pipe rail systems.
Return on Investment
For a grower, the payback period and the problem you solve with it is crucial. We believe that robotization is only feasible if the business case is good. Choosing well, what you are going to robotize is essential.
Platform thinking leads to more perspective
Our platform concept is basically a modular platform with defined interfaces. Standard solutions, components and functionalities are used with a roadmap to more.
Artificial intelligence, Making Automation Intelligent
Artificial Intelligence (AI) is a technology that has become a disruptive technology in recent years. Breakthroughs in a technique called deep learning are bringing new levels of performance to various AI applications, including computer vision.
AI and deep learning has enabled a first wave of successful consumer applications, powered by the leading companies, such as Google, Uber, Tesla, Facebook and Netflix. Now a second wave of AI industrial applications is achievable.
Machine learning, data versus knowledge.
For software programmers, machine learning is another way of programming. Traditionally, a software programmer, often an expert, writes the rules and conditions in his program, which translates input into a defined output.
With machine learning, things are really different. By giving it a dataset with the desired output, the machine (learning algorithm) learns itself how to generate an output for new data.
As an engineer, you train (modify) your deep learning algorithm (development environment) with your dataset, which you then use to generate your application software. With the generated software, your industrial product can autonomously associate new data with the trained output.
Machine learning is applicable to almost all industry segments, from finance to manufacturing. Predictive models help reduce costs, improve quality and enable new applications.
Deep learning
Deep Learning is a technique introduced by a Google team in 2012, which is increasingly applied and optimized for specific applications. Of course we use the available technology on which we have built our application.
Convolutional Neural Networks - AI algorithms that specialize in learning image data, used for things like detecting objects and people, taking pictures, and analyzing medical or scientific images.
Reinforcement learning - AI algorithms that specialize in learning, to take optimal sequences of actions. Mostly used for process optimization tasks and (robot) automation. Segmentation networks to give even better control to our robot movements with points clouds.
