Actionable insights with AI

Artificial intelligence (AI) promises to improve the efficiency of material recovery facilities (MRFs), enable sorting at a more granular level and deliver a variety of performance data points. To prevent drowning in data, panelists at the MRF Operations Forum session Emerging Technology and Approaches this October spoke of the need to focus on the information that is most pertinent to a MRF’s key priorities. They also addressed the evolution of the technology and the lessons they have learned through its deployment at MRFs.

The discussion, moderated by Rob Taylor, senior manager of recycling operations at Republic Services, headquartered in Phoenix, featured Rebecca Hu, the CEO and founder of San Francisco-based Glacier; Gaspard Duthilleul, CEO of London-based Greyparrot; Apurba Pradhan, head of product for Fremont, California-based EverestLabs; Raghav Mecheri, CEO at New York-based Visia (formerly Binit Inc.); and Steve Hastings, an advisor to Rovox, a robotics company based in Fort Worth, Texas.

Glacier makes purpose-built AI-enabled automation to help recyclers and the entire value chain trace and recover material, EverestLabs is an AI and robotics company serving sorting and recycling enterprises and Rovox, the newest entrant to the space, is a technology automation and robotics company owned by Taiwan-based Foxconn. Visia builds AI-powered X-ray and camera equipment to analyze material coming into recycling facilities to identify nonconforming items, such as lithium batteries, while Greyparrot provides data solutions powered by AI to the waste, recycling and packaging value chain.

Parsing data and building trust

Given the overwhelming array of data AI can supply, Hu said through its early deployments, Glacier realized the need to clearly understand what a facility is trying to achieve with the data collected. “What information do you need? What’s non-negotiable? And, then, what are the decisions or the actions that you would take as a result of what you’re learning?”

Using this approach helps to put “guard rails on what would otherwise be essentially like an infinite ocean of information” on what is flowing through a MRF, she said, including the different types of items, the burden depth and the volume.

Hu offered three or four types of recyclables that are being lost to the residue stream as an example of data to target. “I’d really encourage everyone in the room to stay focused on what are the key priorities of what you’re trying to learn and what you’re trying to act on.”

Duthilleul agreed. “At the end of the day, I think no one in this room wants to have a lot of data to play with.” Therefore, he said, Greyparrot spent the last two years developing the tools to make the data its technology delivers actionable. “That really depends on different markets, on the dynamic between you, your suppliers [and] your clients.”

Pradhan said EverestLabs decided early on to focus on the modularity and precision of its technology offering. “You take one robot and make it extremely successful at that task. So, that means … from AI all the way to picking up an object and dropping it in the right place. Once you’ve focused on success, then you focus on modularity. Now these are small, human-form factor [robots], … something that fits in the size of the sorting position. Now you can have multiple of those robots doing the tasks that you need.”

He also raised the issue of trust. “Recycling companies have done manual sorting, manual auditing for a long time,” he said. “So, when you’re trying to do those tasks [with AI and robotics], we have to build an infrastructure that provides trust.”

To that end, Pradhan said EverestLabs’ robotics operations center has a team monitoring all its deployed robots using the data they are capturing to ensure they’re running above a certain threshold. “That allows us to guarantee performance,” he says. “That allows us to have a much better sort of interaction with the operations team in the recycling facilities.”

Visia, which aims to prevent dangerous materials from entering recycling facilities of all types, learned two lessons early on, Mecheri said. “The first one, which I think this panel has touched upon, [is] intelligence has to be actionable. Things on graphs are typically very difficult to parse, even though our high school and college education system has made us believe that graphs are the answer to everything today.”

The second was the need to proactively audit its deployed equipment. “We show up on-site once a month with a duffel bag full of prohibitives and put them on one end of the system [and] validate that they actually got caught,” he said. “You need to have that element of transparency with your customers. I need to be able to go to someone and say, ‘I missed this type of drill battery. It will be gone by tomorrow, but between today and tomorrow, please keep an eye out for this kind of drill battery.’ And I think getting ahead of problems in that proactive manner, at least in our experience, has led to building that trust, which I think is so important, especially as you look to scale technology.”

Regarding some early entrants in the robotics space, Hastings said, “I think the industry did not recognize the complexity of the MRF. This is a tough business. … The challenges to sorting the materials into sellable commodities are not to be taken lightly.”

He mentioned the appeal of replacing labor with equipment such as robots that could be depreciated over time, saying it’s a “great formula, but it has to work, and originally it didn’t.”

Evolving technology

Earlier forays into deploying robotics and AI in MRFs have helped to shape the panelists’ approaches.

Pradhan said EverestLabs won’t take on a project it doesn’t think will be successful. “I like having the up-front alignment in terms of what the operators are trying to accomplish with what you can deliver,” he said.

“We’re kind of in this situation where AI and robotics are sort of an afterthought,” Pradhan continued. “If we had some sort of systems-level thinking, where we designed the system to accommodate some of the AI technologies, we’d get twice, three times more performance than what we’re getting today.”

Mecheri said he learned that he had to build technology that adapts to the operator instead of asking the operator to adapt to the technology. He added that building a process around what the customer believes makes the most sense rather than dictating a process is an approach that has served the company well.

“We built our products with MRF operators for MRF operators,” Duthilleul said. The company’s AI waste analytics platform, Greyparrot Analyzer, includes small and light hardware that is easily installed at different locations throughout a MRF.

“The second thing is, we don’t want to spend months building an AI model for each application,” he said. “We want to spend this time during the deployment talking to the operators to calibrate the tools for their needs.”

Greyparrot uses its master model that was built from the 5.7 million waste items it’s processed to do 95 percent of that work, Duthilleul said. “We know each MRF stream is … different, so we do this final calibration for the operators based on the use case, based on the value we need to provide.

“So, it’s this really consultative approach that we’re taking, and then we can obviously guarantee the metrics and the results you get from it because we’ve been doing this work with you all along the deployment,” he added.

Hu said Glacier also has seen success by taking a consultative approach with its customers to understand their metrics for success and being honest about the company’s technology’s limitations.

“If you come to us and tell us, ‘I need you to identify these 200 different types of materials, and I need you to do it with 99.9 percent accuracy, and I need you to be able to translate all of that into a perfect weight estimate,’ … we’ll be pretty up-front. I think most folks up here would be, too, and say, ‘The technology is really good. Maybe we’ll get there, but maybe it’s not there yet, and we should consider what you’d really like. Why are you asking for these things? Maybe there’s another way to get that for you.’”

Glacier has focused on ease of deployment, as well, providing modular hardware and software solutions. “I talk a lot about what I call the Ikea-fication of hardware. … You can order something, we send you a flat-pack box, and then you can actually set it up yourselves,” Hu said. “We’re always there to help if we need to, but we have customers that have actually elected to do that themselves, and very successfully.”

She added that AI is evolving rapidly. “Where AI was a year ago is nowhere close to where it is today, and I’m betting that we can cover that same distance in the next couple of months.”

AI will enable plantwide improvements with existing equipment, Hastings added. “Once you understand surging and what is happening, can we tie that back into variable belt speed so the existing equipment … can be adjusted. And that’s coming.”

Duthilleul said Greyparrot has partnered with Connecticut-based systems integrator Van Dyk Recycling Systems and Dutch recycling equipment manufacturer Bollegraaf. “We don’t want to build MRFs and other equipment, and we don’t have to because there’s already great players doing that today. And we believe the MRF of the future will be smarter, more automated. There will be much more dynamic control being done as well.”

Aligning the value chain

Hu said technological innovation is combining with macro tailwinds for the recycling industry, including extended producer responsibility and the desire for more recycled feedstock. “There’s a lot of demand being generated for the very stuff that’s flowing through all of our plants today in a way that really hasn’t existed before. As we’re building Glacier, we’re really thinking about not just how do we make MRFs run better, make more quantitative decisions or get access to the advantages of this new technology, but how do we position MRFs as a really crucial step in this new kind of circular supply chain that’s being developed?”

Glacier also is working with companies like Amazon and Coca-Cola. “Our AI is really shedding light on what has previously been kind of a black box,” Hu said. “Someone like Amazon is putting so many packages, so much cardboard out there, and they don’t really have a great handle on where all of it ends up; but now we’re able to give them that real-time feedback loop in working with our MRF partners so that they can make sure that the changes they’re making are actually improving the overall end-of-life outcomes for all of that material.”

Pradhan said AI has the potential to be deployed widely at MRFs old and new to optimize existing equipment and improve material recovery, with effects that are far-reaching when combined with recycled-content goals by brands.

“If you want the economy to be circular, you need information to circulate as well, and you need people to align on what needs to be done,” Duthilleul said. “We talk as well and work with brands, packaging producers [and] recyclers. … We developed this concept we call waste intelligence, which is around using the data we generate … to actually inform different stakeholders.”

“I think that the biggest opportunity isn’t one technology or one thing,” Pradhan said. “I think it’s really just for everybody in this room and everybody on this panel aligning this recycling value chain.”

The author is editorial director of Recycling Today Media Group and can be contacted at dtoto@gie.net.