An AI-powered robot could someday recycle your smartphone


In 2016, Apple announced that it had developed a recycling robot called Liam, which could disassemble an iPhone in 11 seconds. Six years and several machine generations later, Apple still won’t reveal how many iPhones its robots have recycled for parts.

But the potential impact of artificially intelligent robots on e-waste recycling in a broader sense may soon become apparent, thanks to a new research project that aims to develop AI-powered tools that allow a robot recycler to harvest parts from many different phone models. If such technology can be commercialized, researchers hope it could vastly improve the recycling of smartphones and other small, wearable electronics.

While e-waste recyclers today mostly handle larger legacy devices such as CRT TVs, a growing number of smaller electronics such as smartphones and tablets are beginning to reach their facilities. This presents new challenges as these devices are often difficult and time consuming to take apart. Rather than salvaging potentially valuable components like the motherboard, recyclers usually remove the battery and shred the rest. Precious materials are lost and all the energy put into component manufacturing has to be reused to make new ones.

For several years now, scientists have been investigating whether artificially intelligent robots can streamline the recycling process, making the recovery and reuse of parts from dead consumer electronics more economical. In December, the idea got a huge boost when the U.S. Department of Energy awarded a $445,000 grant to researchers from Idaho National Laboratory, the University of Buffalo, Iowa State University and e-waste recycler Sunnking to develop software that would identify robots. Automatically put different types of smartphones on a recycling line, remove the batteries and harvest various high-quality components. By the end of the two-year research project, the team hopes to field-test an early version of its technology at one of Sunnking’s facilities, after which it can seek additional funding to commercialize robotic smartphone recyclers.

Amanda LaGrange, CEO of St. Paul-based e-waste recycler TechDump, says the work of these researchers is critical to improving the sustainability of consumer electronics, which contain valuable metals and minerals that support current crude oil recycling processes. not reclaim. “It’s so important to find ways, as these scientists are with robots, to recover rare earths,” said LaGrange. The edge. “Also, my jaded self isn’t convinced it can be done on a large scale at this point.”

Applying robotics and AI to e-waste recycling is indeed a fairly new idea, and there aren’t many practical examples of it working. The most famous example is Apple’s much-hyped line of recycling robots, but there are only a few versions of these robots in the wild, they only work on iPhones, and their impact on Apple’s overall e-waste remains obscure at best. An all-rounder version that could be installed in an e-waste facility that handles dozens of different models of smartphones has not yet been released. The new research project aims to demonstrate that such a robot can in any case be developed.

Different research teams will lead the way on different possibilities for robot recycling. Researchers at INL will focus on developing methods for removing batteries from smartphones using a robotic arm. At the same time, researchers from the University at Buffalo and Iowa State University will identify high-quality components, such as circuit boards, cameras and magnets, that can be removed from dead phones with the same robots, and find or develop hardware to make the actual smartphone. surgery.

A robotic sorter developed by AMP Robotics for sorting solid waste
National Laboratory of Idaho

The robots not only need good hardware, but also software that allows them to quickly recognize different phone types and look up their internal anatomy. For this part of the project, researchers from Iowa State University and Sunnking will develop a database containing 2D images and 3D scan data on various makes and models of smartphones. Using a machine learning approach, that database will train the software that guides the robots to locate and extract the phone’s battery and high-quality components.

“We’re going to train that system to look at phones and say, ‘This is an iPhone, this is a Samsung model XYZ,’ then go to a database and say, ‘Here we are going to cut the battery,'” he says. INL’s Neal Yancey, the principal investigator of the project.

Eventually, the researchers hope to have a smartphone stripping robot that can plug into existing e-waste recycling operations. Sunnking, which will provide 100 samples of five different phone models for the researchers to experiment with, will be the first to test that system by the end of the two-year project period.

At the same time, researchers from INL will analyze the economics of the entire robot disassembly process to determine whether it actually reduces recycling costs. The team’s goal is to improve materials recovery by at least 10 percent and the recycling economy by at least 15 percent, compared to current standard recycling operations.

Even those seemingly modest goals can be difficult to achieve. Adding specialized robotic arms to e-waste operations where phones are currently taken apart by hand requires a potentially significant upfront investment. (The cost of robotic arms can vary widely, but the popular UR5 series sells for over $35,000 each.) And with most of today’s robots designed for simple, repetitive tasks rather than the precision work of removing of tiny phone parts, developed a robot that can measure up to its human counterparts in terms of disassembly speed and accuracy is no small feat, said Minghui Zheng, a roboticist at the University at Buffalo and co-principal investigator on the project.

“There are many limitations to robots,” Zheng says. Basic tasks, such as using robotic grippers to extract small parts, can be “very challenging,” she says.

Developing AI-based software tools that can sort through the complex mix of dead devices in an e-waste stream and classify them accurately could also be challenging, although similar tools exist for sorting solid waste such as plastic. Other groups are also trying to develop AI-based sorting methods for e-waste, including Carnegie Mellon University’s Biorobotics Lab, which recently worked with Apple on such a project.

Even if the initial research is promising, more work will be needed before AI-powered robots are a practical solution for handling the estimated 150,000 tons of portable consumer electronic waste Americans produce each year (a figure that includes not just smartphones, but also tablets and wearables such as Apple Watch). With the first project targeting just five of the hundreds of smartphones out there, the technology needs to be further developed to be practical for most recyclers. In order to process large volumes of smartphones in an industrial setting, the system will also have to be scaled up.

Changes in product design can create a new barrier to robotic recycling. As companies adapt their devices year after year, recycling robots need to be kept up-to-date with hardware and software that can handle the latest models. An e-waste recycler considering investing in such technology could reasonably worry that 10 years from now, new phone designs will have rendered the robots obsolete.

That’s why it’s so important that recyclability is baked into product design, said Sara Behdad, a sustainable electronics researcher at the University of Florida who is not involved in the new research project. While Behdad says greater use of robots could improve e-waste recycling “a lot”, she believes that many of the problems recyclers face today, from glued-on batteries to proprietary screws, need to be addressed through of design for disassembly standards.

Such an approach would mean “less uncertainty” for recyclers in the future, Behdad says. And taking phones apart would be “much more within the capabilities of robots.”

Leave a Reply

Your email address will not be published.