DeepSummary
The episode features an interview with Johanna Reimers, the CEO of Refined Technologies, a company that uses cameras and deep learning software to teach machines to recognize and sort objects visually. They discuss how their technology works, showing the machine numerous labeled images to train it to identify different identities like phone models, battery types, or fish species.
Reimers explains how their technology can contribute to a more circular economy by automating the initial visual inspection process for used goods, saving time and cost compared to manual labor. This could enable more reuse, repair, and remanufacturing by making it economically viable. They also discuss challenges like ensuring sufficient volumes of used products and creating closed loop systems.
Reimers describes some of Refined's projects like developing a reverse vending machine for batteries with Energizer, and recognizing fish species for conservation efforts. She sees potential for expanding their general recognition software to other image analysis applications beyond sorting used electronics and batteries.
Key Episodes Takeaways
- Refined Technologies uses machine learning visual recognition software to identify and sort objects like used electronics, batteries, and fish species.
- This technology can automate initial inspection for repair/reuse, making it more economically viable compared to manual labor.
- However, sufficient volumes of used goods are required for automation to make financial sense.
- Closed product loop systems from the start can avoid challenges recyclers face with unpredictable mixed material streams.
- AI and automation tools like visual recognition can enable more circular economy practices like refurbishing and material recovery.
- In addition to sorting used electronics, Refined has applied its technology to projects like reverse vending machines and fish population monitoring.
- The company aims to expand its general visual recognition capabilities to more industries and applications beyond its current focuses.
- Key challenges include ensuring circular economy practices are cost-effective and dealing with the unpredictability of waste streams.
Top Episodes Quotes
- “Circular economy, it's of course a very popular thing to talk about these days, and it comes down to resource efficiency, I would say we have always had the mission to reduce waste and the vision that one way to do this is that we would use more automation.“ by Johanna Reimers
- “I think definitely it can be AI or machine learning can be used for enabling more circular economy to take place, so to say. But it's just as much as any other automation technology can be used.“ by Johanna Reimers
- “I would say that for the moment. I mean, circular economy, it's of course a very popular thing to talk about these days, and it comes down to resource efficiency, I would say we have always had the mission to reduce waste and the vision that one way to do this is that we would use more automation.“ by Johanna Reimers
- “I definitely believe that our technology is really good to enable, well, that it's actually being done, that the visual inspection is being performed at all. But as with all, as with almost all automation, usually it requires a certain volume for it to make sense.“ by Johanna Reimers
- “If you would just create, I mean, more closed loops from the beginning in this different types of product streams, then I think it would be much, much easier, because now you have to weigh in the fact that you will end up with a lot of other things, you don't know what you will get.“ by Johanna Reimers
Entities
Company
Organization
Event
Person
Episode Information
Getting In the Loop: Circular Economy | Sustainability | Closing the Loop
Katherine Whalen
6/3/19