ZenRobotics’ CCO Mr. Rainer Rehn spoke at the MRF Operations Forum event, held in 22 October 2019 in Chicago. Here are some of Rainer’s key insights at the event.
What are the challenges for AI and robotic technologies in waste sorting?
In traditional industrial automation robots are used in defined, structured environments. The waste treatment environment is a different story, however. Here the challenge for a robot is the unstructured and complex environment. Nobody knows exactly what the waste stream will look like or the exact composition of the waste. Also, the working environment is harsh with temperature changes, dust and dirt.
This complex, unpredictable environment is the ultimate challenge for waste sorting robots. However, thanks to AI, we can make the robots flexible and adaptive enough so that they can recognize, grab and sort objects coming down the waste stream. That is the main difference when comparing traditional industrial automation and waste processing.
How did ZenRobotics solve the waste automation challenge?
ZenRobotics offers a highly integrated solution that is specifically optimized for the purpose of waste sorting. This means that ZenRobotics does not just produce the robot, but provides an intelligent combination of image recognition, machine learning, motion control with firm gripping and throwing. We also have many years of experience in waste processing. All this makes the ZenRobotics solution special because it is optimized for the waste-sorting application.
We were the first company to apply AI and robots to a real waste-sorting environment already back in 2010. Building on the latest research in the field, the technology was designed to bring the efficiency of automation to the waste industry. Thanks to AI, industrial automation has finally come to the waste industry and sorting robots can now work in new, more complex, environments.
For our solution, ZenRobotics has designed and developed both the AI software, called ZENBRAIN, and the hardware to meet the needs of a harsh waste-sorting environment. For example, the robots are more durable and designed to survive hits and collisions, in contrast to traditional industrial robots. Our experience in waste robotics has shown us how robots have to perform with complexity.
How does artificial intelligence – AI – benefit the waste industry?
When we started, robotic waste sorting was new concept and the potential of AI wasn’t well-known. Although, as the understanding has increases, we like to emphasize that AI is only a tool for improving the performance and an integrated part of our solution. Our customers do not have to be experts in AI to operate the units. Details about the best AI algorithms, neural networks or learning systems, are not the key. What’s important, and the only thing that actually matters, is the true real-life performance of the machine as a whole. There is little use of a multilayered neural network if the sorting robot is not able to successfully grip a waste fraction!
How can MRFs improve their operations with waste sorting robotics?
The main benefit for MRFs is the increased efficiency and productivity that automation allows. You can run your waste processing plant nearly 24/7 with constant speed, as robots work continuously without stops. Second, the waste industry needs more sophisticated technologies for improving the purity of end fractions. Sensors and AI software allow more versatile sorting capabilities. For example, you can train the robot to sort specific objects, not only materials. This gives businesses increased flexibility and opportunity to develop new business opportunities and provide high quality raw materials that can be marketed locally. And finally, AI and digitalization also produces more data about the waste, which helps companies to improve and monitor their operations. You cannot optimize your operations if you do not have data.
Why MRF operators should evaluate robotics and AI already today?
The waste industry needs new, smarter solutions to meet the tightening requirements. In addition, the need for more efficient waste sorting solutions will increase. Digital solutions and AI now allow companies to gather more information about the waste and their operations. This enables improved optimization and more flexible sorting capabilities as you can change the sorting task on the go. Information and the possibility to sort various new waste fractions provide new business opportunities and allow higher diversion rates. It all boils down to reducing costs.