Electrical and Computer Engineering

Off

Mon, 03/10/2025 - 13:07

Two years after the launch of ChatGPT, generative AI has yet to produce a game-changing use case. Professor Paul Watta breaks down whether the trillion dollar bet on generative AI will pay off or go bust.

Electrical and Computer Engineering Professor Paul Watta. Photo by Annie Barker

For a ��-Dearborn student and professor, the influence goes both ways

lblouin — Mon, 24 Feb 2025 13:06:36 +0000

For a ��-Dearborn student and professor, the influence goes both ways lblouin Mon, 02/24/2025 - 08:06

In 2020, Electrical and Computer Engineering Professor Wencong Su was looking for an undergraduate student to assist with a project focused on adding innovative energy efficiency measures to the already LEED-certified Engineering Lab Building. At the time, Su was teaching all graduate courses so he didn’t have many undergrads in his orbit. So Su asked for a little help from one of his graduate assistants, who emailed the job posting to the students in a 200-level lab. LaRico Andres, a sophomore and recent transfer from Henry Ford College, thought it sounded interesting and reached out to Su with his resume. Su remembers Andres didn’t exactly fit the description of the type of student who usually applies for these kinds of opportunities. Andres was a few years older than Su, already had a full-time job working as an instrument tech at the Great Lakes Water Authority, and his GPA at the time wasn’t knocking anyone out. But after the two chatted for a little while, Su offered him the job. Andres was personable, seemed excited to learn, and though he was a research novice, it turned out his background in instrumentation was actually quite relevant to the types of things they would be investigating in the ELB.

Andres excelled on the project and it led to many more opportunities to work alongside Su. On one project supported by the National Science Foundation’s I-Corps — a program that helps researchers translate their laboratory work into marketable products — Andres traveled to conferences in Orlando, San Diego and Austin, completing a flurry of more than 100 interviews with industrial professionals in seven weeks about a product Su’s lab was developing. On another project, he and Su created an app that used the ELB’s building management software and the utility’s fuel profile to give users an idea of what being a building occupant added to their personal carbon footprint. As you’d expect, Andres picked up a lot of skills working with Su. But as often happens when two people spend a lot of time together, Andres and Su also started talking about things other than their work. Andres jokes that they initially bonded over the fact that they “both like to eat.” But the conversations gradually grew more personal. Both men had daughters, so they talked about their kids. Su shared some of the challenges he faced when he first came to the United States for college and he knew very little English. Andres reciprocated with stories about some challenges he faced growing up in Detroit, not always having enough money to pay all the bills at once, and some things that happened when he was younger that tripped up his plans to go to college earlier in his life.

Su says he enjoyed Andres' perspective — in part, because Su is someone who’s interested in people, and the ups and downs of Andres’ life made for a compelling personal story. In addition, Su says he’s always been interested in Detroit, and through Andres, a lifelong Detroiter, he enjoyed learning about a side of the city that “you don’t hear about on the TV news.” Interestingly, at a certain point, both men noticed that many of their personal conversations weren’t actually that separate from their field of study: energy systems. For example, Andres shared stories about how, in his family, when the power would go out, that meant you didn’t open the fridge so his grandfather’s insulin wouldn’t spoil. Or how, if the power was out long enough, they’d start barbequing the meat they had in the freezer so it wouldn’t go to waste. Or how he and his relatives used to take turns refilling his grandmother’s boiler when she couldn’t afford to fix it right away. “The biggest burden a lot of my people have is energy, whether it’s fuel, gassing up your car going to work, or just trying to keep your house warm,” Andres says. “I know what it’s like to struggle to pay a utility bill and choose between paying that bill on time or buying food. I know people whose furnaces go out and can’t afford to get them fixed. That’s the impact energy has. Energy helps. But if you don't have a lot of money, energy can be a burden.”

Andres’ testimony left an impression on Su, and eventually the two of them started kicking around ideas for projects focused on energy justice, an emerging field that focuses on equity, affordability, accessibility and participation in the energy system and the ongoing transition to new energy technologies. That lens became the cornerstone of their 2023 Summer Undergraduate Research Experience project, in which Andres helped create an interactive mapping tool that explores the connection between historical real estate redlining and disparities in energy access in metro Detroit. Using Andres’ dashboard, a user can quickly toggle through different layers and explore whether a neighborhood is formerly redlined, where current utility outages are and their causes, locations of renewable energy installations and EV charging stations, as well as census data that provides demographic information about the people currently living in the neighborhood. One of the big reveals from Andres’ work is that metro Detroit neighborhoods that were historically redlined tend to be lower-income, non-white, have power outages that tend to be longer, and have less access to renewable energy and EV charging infrastructure. Their work on the app led to an IEEE conference publication in 2023.

Andres shows off an interactive mapping tool he helped create that explores the connection between historical real estate redlining and disparities in energy access. Photo by Annie Barker

After the project, Andres was nearing the end of his undergraduate career, and Su began asking him a little more frequently and persistently if he’d ever thought about grad school. Andres says that honestly wasn’t on his radar when he initially transferred to ��-Dearborn. At that time, his thinking pretty much revolved around the straightforward calculus that getting an engineering degree would help him get a higher-paying job and lead to a more comfortable life for him and his family. But after working in Su’s lab, particularly on the energy justice-focused mapping project, he says his perspective began to change. “If I did the safe thing and got a job, yeah, that would help me. But working with Professor Su helped me see what it is that I really wanted to do. And what I really wanted to do was help people,” Andres says. To do that, Andres decided to take a chance and continue his education, enrolling in the department’s doctoral program, where he’s now continuing his work alongside Su. Andres is still just in his first year of the program, but the pair have already started discussing ideas for Andres’ dissertation research. Not surprisingly, energy justice topics are rising to the top of their list. One idea they’ve been kicking around recently is creating a machine learning-based app that would use weather and outage data to forecast the likelihood of power outages, sort of like the snow day prediction models that have become super popular with parents and kids. “A technology like this could have multiple applications,” Su says. “It could help a utility identify where they need to upgrade their infrastructure to make it more resilient, or where they might need to deploy the most crews ahead of a storm. But it could also directly help people. Like, if you saw that there was a 90% chance you were going to lose your power for five hours tomorrow, people could charge their batteries or make a trip out to get food.”

Andres says it’s still a little wild to think he’s in a PhD program, and the future he’s contemplating for himself now is much different than the one he was thinking about a few years ago. For the time being, he’d love to continue to do research in the energy justice field and develop innovative ways to help people. He also wants to start a nonprofit that gets young people excited about things like sustainable energy technologies and smart cities. Ultimately, if all goes well, he’d love to be a college professor just like his mentor. “It’s funny, the opportunities that come up in your life,” Andres says. “Like, what if I had ignored that email? What if I hadn’t stepped out and emailed professor Su? He saw something in me that I didn’t even know about myself. And he probably doesn't even know how many other people that’s going to touch. My daughter and little cousins, they all get to see that, ‘Hey, Uncle Rico is gonna be a doctor.’ Because of Professor Su, I’m setting a new example for the people in my life. My wife, sister and other family members, everybody is, like, ‘Wow, you was always smart.’ I just went the long way. And I’m just glad I have an opportunity now to make an impact in the community.”

That a college professor would have such a profound impact on a student isn’t super surprising. It’s what many faculty shoot to achieve every day. But Su says Andres has also had a big influence on him. On a personal level, he finds Andres' life so inspiring, and admires his work ethic, the personal sacrifices he’s making to be part of the PhD program, and his vision for using research to help people in his community. Their relationship has also had a big influence on Su’s own work. “For example, losing power for one hour in a wealthy neighborhood compared to a disadvantaged neighborhood, it has totally different impacts. Or if you lose power, then that suddenly becomes a food issue for some people. I never really thought about stuff like that before,” Su says. “Now, I'm thinking more about how our research has the potential to help people. Because, otherwise, maybe you’re just publishing a paper with some very fancy solutions and complicated equations. But how are you helping average people?”

###

Story by Lou Blouin

Off

Mon, 02/24/2025 - 12:56

Unlikely collaborators who met through a job posting, first-year PhD student LaRico Andres and Professor Wencong Su have forged a partnership that’s left a lasting mark on both men.

Electrical and Computer Engineering Professor Wencong Su (left) and doctoral student LaRico Andres have teamed up on a number of research projects focusing on energy justice. Photo by Annie Barker

Researchers prep for landmark field test of ‘second-life’ EV batteries

lblouin — Mon, 10 Feb 2025 15:30:35 +0000

Researchers prep for landmark field test of ‘second-life’ EV batteries lblouin Mon, 02/10/2025 - 10:30

Connecting large batteries to the electric grid is an idea that has multiple benefits. Most fundamentally, an electricity system powered by an increasingly large share of solar and wind will almost surely require storing energy in some fashion, given the variability of the wind and sunshine at any particular moment in the day coupled with our expectation that power will always be available. Indeed, large battery storage systems are already being deployed across the world in sophisticated ways. For example, a Massachusetts town of about 27,000 people is building a 15 MWh, grid-connected battery storage system that can help power the town during power outages, stock up on less-expensive energy during off-peak hours and feed electricity back to the grid during times of peak demand, when utilities generally have to fire up their most carbon-intensive diesel-powered backup systems. Grid-tied battery storage systems, however, come with a few caveats. For one, it takes a lot of batteries to store enough energy to actually make a significant difference, which means battery storage systems are expensive. Moreover, if you consider the climate emissions involved in manufacturing the batteries and the mining for the lithium and cobalt needed to make them, battery storage systems are far from being climate neutral.

Throw at this predicament a seemingly too-good-to-be-true solution: Right now, electric vehicles represent the largest use of large batteries, and EVs are steadily gaining market share across the globe. However, manufacturers estimate that batteries in new EVs will likely need to be replaced after eight to 12 years, or when they can hold about three quarters of their original charge. These slightly diminished batteries, however, could still be useful for other things, like — you guessed it — grid-tied storage. Now add into the mix the fact that EV sales have been strong for the past few years and we could be a decade or so away from having millions of used batteries ready for a “second life” in the electric grid. Importantly, this approach could reduce the costs and climate impacts of building large storage systems compared to those that use new batteries.

Undoubtedly, it’s an idea with tons of promise. The catch, at least for now, is that we don’t really know how well it will work, according to Associate Professor of Electrical and Computer Engineering Xuan Zhou. Zhou says our understanding of the performance of new EV batteries is pretty solid and getting better all the time. However, we simply don’t have the same level of data about what’s really going on inside used EV batteries to say for sure they’ll be as reliable an option for grid storage as we hope they’ll be. The reason is that charging and discharging a battery hundreds of times — and subjecting it to thousands of hours of road vibrations — changes its underlying chemical and physical properties. That’s ultimately why it loses capacity over time. And many details about a battery’s potential second life inside a grid storage system — like how many years it would last, how safe it would be and how cost-effective it would be — are still largely unknown.

Zhou, along with his Electrical and Computer Engineering Department collaborators Associate Professor Mengqi Wang and Professor Wencong Su, hope they’re about to provide the world with some of the best data-backed answers to date. With a new $1.48 million grant from the Michigan Department of Environment, Great Lakes, and Energy, the largest state grant in the university's history, the team of researchers is set to build a 500 kW grid-tied storage system that will use actual used EV batteries.

Su and Wang say some of the best work in this field is currently being done at Stanford University. But those experiments involve taking new EV batteries and subjecting them to hundreds of charging and discharging cycles in order to intentionally deplete them in a way that mimics what happens in an EV under certain driving conditions. “For the emulation, however, they might not be able to emulate the true environment the batteries would be operating in,” Wang says. “We can imagine, in an EV, there will be vibrations. There will be accelerations and decelerations. The devices around the pack might also generate heat. And there will be variations in the temperature and all these environmental conditions for the battery pack — they will not be constant at all. This all impacts the battery. So by using real used EV batteries, we hope our data will end up being more practical.”

From left, Associate Professor Xuan Zhou, Associate Professor Mengqi Wang and Professor Wencong Su.

Zhou says they are still working out many details for the design and build of the project. One of the unexpected challenges was simply locating used EV batteries. “Initially, it looked like we were going to have to get them from Europe, where EVs have been more popular,” Zhou says. “But now it looks likely that we will be able to get about eight to 20 battery packs from used GM vehicles.” After they secure the batteries, Zhou says they’ll perform extensive tests to get a sense of their chemical and physical properties. Meanwhile, Wang and Su will work out how the batteries can be connected and tied to the grid. Because the team is planning to test several types of use cases, this will require a carefully planned system of custom power converters, controllers and control algorithms. For example, they want to see how well the batteries perform in a “peak shaving” role. That’s when the batteries would feed electricity back to the grid during times of peak demand, which helps utilities avoid using their expensive, carbon-intensive backup systems. They also want to test “load shifting,” which is where the batteries would charge during non-peak hours and then release that energy during peak hours, when electricity is more expensive. Another variable: the partner site that will host the storage system has a solar array. Wang says connecting all those components and systems in a way that doesn’t produce harmonics on the grid, damage equipment or compromise power quality takes careful planning. Many of the components will have to be custom built, too, since this kind of system is not an off-the-shelf technology.

Another big hurdle the team might encounter is testing the system. At 500 kWh, this project is so big that the current testing facilities at ��-Dearborn — or any other university the team knows of — isn’t equipped to handle a test of the full system. Zhou says the new battery lab in Ann Arbor may be able to provide single pack-level testing, and they may need an industry partner for tests beyond that. Wang says the size and testing requirements also make it more challenging to design other aspects of the system. “I think the piece of equipment that has the highest power rating is our battery simulator in our IAVS lab, which has 100 kW testing capacity. So we’ll start with a smaller system as a proof-of-concept design. And then we’ll scale up to the real-world test. But this makes it much more challenging. The components, like the semiconductors or power converters, can’t just be scaled up. They’ll have to be swapped out with new hardware with higher power ratings. So we’re going to be busy!”

One other noteworthy feature of the project: After the study of the storage system is complete, the research team’s Genesee County-based industry partner on the project, ReCharge ReCycling, which is helping design and build the storage system, will help prepare the battery pack for a third life. “That’s why we’re calling this project ‘Closing the loop,’” Zhou says. “They’ll be dismantling the battery down to the cell level and then trying to recover the precious metals so they can be used to make a new battery. So we’ll really get a full picture of what it’s going to take to take a battery through this full cycle.”

###

Story by Lou Blouin. Photos by Annie Barker.

College of Education, Health, and Human Services

Off

Mon, 02/10/2025 - 15:30

Connecting millions of used electric vehicle batteries to the grid is an idea that holds tons of promise. But how well will this strategy work in the real world?

Associate Professor Xuan Zhou (right), Associate Professor Mengqi Wang (left) and Professor Wencong Su are heading up a new project that will tie used EV batteries to the electric grid.

Student researchers share what they learned during SURE 2024

jpow — Thu, 19 Sep 2024 15:55:35 +0000

Student researchers share what they learned during SURE 2024 jpow Thu, 09/19/2024 - 11:55

In just a few short years since its founding in 2018, the Summer Undergraduate Research Experience has grown into a mainstay of the campus’ burgeoning research culture. The program pairs faculty mentors and undergraduate students for an 8-12 week summer session in which the student researchers get to do hands-on research, attend professional development sessions and get paid a $3,200 stipend. SURE continued its steady growth this year, providing opportunities for 49 students (up from 32 in 2023), who worked in areas ranging from artificial intelligence and renewable energy to reproductive rights and healthcare. So what are students taking away from this year’s experience? Recently, we talked with two SURE researchers from the College of Engineering and Computer Science and College of Education, Health and Human Services about what they learned this summer. Next week, we’ll have student stories from the College of Business and College of Arts, Sciences and Letters.

Rayan Khalil and Assistant Professor Van Hai Bui
Project: Assessment of solar energy generation towards net-zero energy buildings

Software engineering senior Rayan Khalil says she was drawn to the SURE program mostly because the idea of doing research “just sounded like a really fulfilling experience.” It didn’t disappoint. This summer, Khalil and her faculty mentor, Assistant Professor of Electrical and Computer Engineering Van Hai Bui, ticked through a big list of projects focusing on solar energy generation for net-zero buildings. Specifically, Khalil built detailed models that predict how much solar-based electricity a building might expect to produce, given geographically specific variables like wind speed, temperature, day length, cloud cover and the amount of sunlight a site receives in a typical year. Based on those prediction models, she then created an optimization model for net-zero buildings to determine the lowest-cost solar and battery storage installations, while minimizing the amount of purchased power buildings would have to draw from the grid. She even built a user-friendly interface that enables building operators to quickly plug in site-specific variables and get accurate prediction and optimization scenarios.

Rayan Khalil (right) and Assistant Professor Van Hai Bui

Khalil says the summer felt like a super- accelerated learning experience: “In some ways, I feel like I learned as much as I did in two years in two months,” she says. She chalks that up to a couple of factors. First, she’s always had a “passion for sustainability,” and getting to apply her coding skills to something she was really interested in made the whole thing feel “a lot more fulfilling.” Second, unlike in a lot of her courses, there wasn’t a test waiting for her at the end. “Research isn’t one of those things where the answer is already predetermined, so one of the things I loved is that if I tried something and it didn’t work out, I felt like I could learn from that and try something else without worrying that I was going to be graded harshly if I didn’t do it a certain way,” she says. Indeed, Bui won’t be grading Khalil. But he says she accomplished a phenomenal amount of work over the summer, and the prediction models she worked on could be useful in upcoming projects he has planned with DTE. The two are also planning to present their findings at an upcoming conference, for which Khalil is writing the paper. “To maybe have a publication with my name on it — that’s just insane,” she says. It might not be the last either. Heading into her senior year, she says the goal was to finally be done with school and score a full-time job. Now, based on her SURE experience, she’s thinking seriously about grad school.

Sarah Chaban and Associate Professor Lisa Martin
Project: Reproductive freedom on the ballot: How gender and demands for self-determination are driving electoral politics in the post-Roe era

Professor of Health and Human Services Lisa Martin’s first piece of advice for her SURE research partner Sarah Chaban: Set up a new email account. That’s because over the course of the summer, Chaban would be tracking trends in how people are talking about reproductive rights during the election season, a conversation which, needless to say, inspires an intensity that you don't necessarily want flooding your personal email accounts. For her project, Chaban kept tabs on numerous sources, including social media accounts, advertisements, podcasts, state ballot referendums, newsletters and news articles, with a particular focus on language trends. A few of her takeaways thus far? At the highest level, she says voices on the left and right are speaking very different languages, with the latter emphasizing fetal personhood and the former framing things in terms of rights and healthcare. Moreover, especially in the realm of laws and ballot initiatives, there tends to be more uniformity on the right, which Martin and Chaban say reflects a strategy of replicating approaches which have worked well in other states. On the other side, ballot language tends to vary widely both in breadth and emphasis, with states emphasizing (one or multiple) rights and/or healthcare, depending on what organizers think will speak to their constituencies. Overall, Chaban says one of her biggest findings is that the conversation around reproductive rights now has multiple volatile fault lines. Within the post-Roe legal framework, access to contraception and fertility treatments, like IVF, are now being debated sometimes as intensely as abortion.

Sarah Chaban (left) and Professor Lisa Martin

Chaban says one of the biggest lessons she’s drawing from her research experience is how important critical thinking skills are — especially when responding to unexpected challenges. For example, during her project, President Joe Biden, a candidate who rarely uses the word abortion, withdrew from the presidential race, and Vice President Kamala Harris, who uses very different language when speaking about reproductive rights, became the Democratic nominee. “I thought, how am I supposed to put together my poster now that the world has just changed?” Chaban says, smiling. “But this just showed me that when you’re tracking something in real time, you can’t get stuck in your ways of thinking about things. Whatever changes might come, you have to pivot. No knowledge is lost.” Her experience this summer also changed the way she’s thinking about her future. Chaban was originally planning on pursuing a master’s in public health after graduation. But after seeing how many influential voices in the reproductive rights space have legal backgrounds, she’s thinking about law school. And if she can’t choose between the two, she has her eye on the dual degree in Law and Public Health (JD+MPH) at the University of Michigan.

###

Want to read more about what students are taking away from SURE 2024? Next week, we’ll feature students from the College of Business and College of Arts, Sciences and Letters. Story by Lou Blouin. Photos by Annie Barker.

Research

Student Success

Health and Human Services

Off

Wed, 09/18/2024 - 15:55

The Summer Undergraduate Research Experience had another record year, serving 49 students in 2024. We check in with students and their faculty mentors in each of the colleges, starting with CECS and CEHHS.

CEHHS student Sofia Martínez Barredo presents her research findings during the 2024 Summer Undergraduate Research Experience showcase on Sept. 17.

Research targets billion-dollar problem of counterfeit electronic components

lblouin — Fri, 30 Aug 2024 13:22:04 +0000

Research targets billion-dollar problem of counterfeit electronic components lblouin Fri, 08/30/2024 - 09:22

In early 2023, a mechanic at a Portuguese airline discovered something a little unusual while performing maintenance on a jet engine. A replacement damper designed to quiet mechanical vibrations was already showing signs of wear — despite the maintenance log showing the component had just recently been installed. The airline started digging into the issue and came to an alarming conclusion: The documentation provided with the replacement part had been faked — the part was a counterfeit. The discovery set off a wave that would ripple through the airline industry over the coming months, in which dozens of airlines, including all major U.S. carriers, discovered they had aircraft in the skies flying with counterfeit parts. Professor of Electrical and Computer Engineering Hafiz Malik says the airline scandal is hardly an isolated incident. This particular problem ended up being traced back to a shady supplier in London, but Malik says there are countless others in both the black and gray markets fueling a lucrative worldwide trade in counterfeit electronic components. Indeed, though it’s difficult to estimate, analysts think the market for things like knock-off batteries, motors, sensors and printed circuit boards is likely in the hundreds of billions of dollars. The dubious, subpar components are not just a costly headache for companies and consumers. They’re also a huge safety and cybersecurity issue for all stakeholders. “No one wants to fly in an airplane or drive a car that has counterfeit parts,” Malik says. “But the problem is so widespread that many of us probably have no choice.”

Moreover, Malik contends the old ways of countering counterfeit components are largely outdated. “Today, making counterfeit electronic parts is super easy compared to the old days,” he says. “With 3D printing and generative AI, you can recreate some parts almost to perfection. And serial numbers, or logos stamped on the parts, forget about it — those can be easily forged.” Even newer security features, like holograms, can be replicated now, says Malik. So he and a frequent collaborator, Associate Professor of Electrical and Computer Engineering Alireza Mohammadi, are working on a new system that could radically transform the transportation industry’s counterfeiting defenses. Rather than attaching something external to a component, like a serial number, stamp or hologram, the two researchers are attempting to harness the power of “digital fingerprints” that originate from within the components themselves. The core idea is that electronic devices, by their nature, create electrical outputs. And by closely analyzing these signals for, say, unique patterns of distortion that are particular to a device, they could tell if something is an authentic part or a knock-off, because the counterfeit would create a different electronic fingerprint. Malik says the digital fingerprints could then be easily verified by comparing them to a cloud-based library, maintained by the manufacturer.

In addition, Mohammadi, as co-PI on the project, will be working on a complementary defense system that focuses on the coding that controls electronic components. “Let’s say you have a malicious actor, and instead of using a counterfeit electronic control unit, or ECU, they actually reprogram the authentic part in a very smart fashion. Here, the electronic fingerprinting would not work,” Mohammadi explains. However, Mohammadi says the new programming would ultimately show itself in some kind of altered functionality of the vehicle, like, for example, steering or braking systems that aren’t performing exactly as expected. If a manufacturer or technician detected these kinds of performance anomalies, and they couldn’t be traced back to an obvious source, it would clue them in to start checking the code, which could be verified using a cloud-based database. In fact, this approach could even be useful for detecting more routine benign errors, like corrupted code.

The command line interface for Malik and Mohammadi's real-time device authentication system.

Interestingly, this new approach to threat detection could also serve as a highly efficient diagnostic tool. Right now, Malik says when a vehicle comes in for maintenance and a technician runs computer diagnostics to try to identify the problem for baseline models, it takes an average of 90 minutes to zero in on the actual issue. With their more sophisticated electronic fingerprinting system in the loop, Malik says it could help technicians quickly identify which components are malfunctioning. “We’re hoping to shrink the diagnostic time from 90 minutes to less than 30 minutes. That’s a very big deal in today’s world, where maintenance of large fleets of delivery vehicles for, say, Amazon, UPS or FedEx, is essential to their profitability,” Malik says. Another perk of the digital fingerprinting system: The fingerpointing between parts suppliers and OEMs that sometimes happens when something isn’t behaving as expected could be avoided — since the electronic fingerprints would help establish a benchmark for expected performance of electronic systems. In fact, though their research for this project will focus on components for the transportation sector, they say their anti-counterfeiting measures could ultimately be useful in any industry that uses electronic parts.

The two researchers have three years to work on the project, which is supported by a $1 million grant from the National Science Foundation — the second largest NSF award in ��-Dearborn history. But Mohammadi and Malik say the runway for this particular research has been even longer. Several related grants, including an incubator grant from the ��-Dearborn Office of Research, helped support related work that ultimately culminated in their current project. And the original idea was spawned way back in 2019, when Malik bumped into Mohammadi in a Canton coffee shop and asked if he could pick his brain about an idea he was kicking around. “Alireza immediately started diagramming his ideas about control theory on a napkin, and everything just kind of grew from there. I hope we still have the napkin,” Malik says.

In all likelihood, the napkin is long gone. But the two researchers are hopeful a much larger legacy for this work lies ahead.

###

Story by Lou Blouin. The researchers would like to acknowledge several awards in the lineage of this project, including “SaTC: CORE: Small: Linking2Source: Security of In-Vehicle Networks via Source Identification,” sponsored by the NSF through Award #2035770; “I-Corps: Physics-based Automotive Cybersecurity,” sponsored by the NSF through Award #2317368; and “Cyber-Physical Security of Industrial Robotic System,’’ sponsored by the ��-Dearborn Office of Research.

Faculty Research

Research

Off

Tue, 09/03/2024 - 13:04

With a new NSF-funded project, Professor Hafiz Malik and Associate Professor Alireza Mohammadi are creating a novel digital fingerprinting system to solve a massive safety challenge in the transportation sector.

Professor of Electrical and Computer Engineering Hafiz Malik (left) and Associate Professor of Electrical and Computer Engineering Alireza Mohammadi (right) demonstrate an early version of their digital fingerprinting system with student Hasan Arif.

��-Dearborn is infusing sustainability into its engineering programs

lblouin — Wed, 03 Jul 2024 12:57:45 +0000

��-Dearborn is infusing sustainability into its engineering programs lblouin Wed, 07/03/2024 - 08:57

The days when engineering was thought of as a purely technical discipline are disappearing fast. For sure, engineers still need strong foundational knowledge in math and science and discipline-specific technical training. But there’s a growing movement within engineering education to ensure we’re training engineers who can also think deeply about the environmental and societal impacts of their creations as a fundamental part of the engineering process.

At ��-Dearborn, this emphasis on creating holistic engineers is already taking a number of forms, from sustainability-focused classroom projects and research, to a new course in trustworthy AI, to undergraduate and graduate programs in human-centered design, a discipline that blends traditional engineering with skills borrowed from art, anthropology and sociology. Now, sustainability is poised to take an even broader role within the College of Engineering and Computer Science, say Associate Professors Alireza Mohammadi and Samir Rawashdeh. The robotics experts and frequent collaborators recently landed a $200,000 grant from the Lemelson Foundation to support CECS faculty who want to incorporate sustainability-focused projects into their courses. “In talking with the people at Lemelson, we realized if you want this to become part of the culture and not just an occasional or fringe thing, you have to reach a critical mass,” Rawashdeh says. “Sustainability has to be something students are hearing about in multiple places, across courses, across programs for them to internalize that this is part of what engineering is all about.”

Specifically, the Lemelson funding will enable Mohammadi and Rawashdeh to award minigrants to faculty who want to add course modules or projects that incorporate the Engineering for One Planet Framework, a set of fundamental environmental sustainability-focused learning outcomes developed by Lemelson and VentureWell, with input from stakeholders in academia, industry and nonprofit organizations. For example, in a smaller-scale antecedent to this larger Lemelson-funded initiative, Rawashdeh and Mohammadi used a minigrant to add sustainability-focused modules to two of their robotics courses. “It was an interesting challenge because the overlap between robotics and environmental issues isn’t obvious,” Rawashdeh says. But as they read up on it, they got all kinds of ideas — from robotics applications for environmental industries, like recycling, to end-of-life e-waste management strategies for robotics components, including their valuable lithium-based batteries. In Mohammadi’s course, the students optimized control algorithms for their lab’s fleet of mobile robots so that the machines would consume less energy while doing the same amount of work.

While the primary goal of the initiative is to develop a more environmentally focused mindset among engineering students, Mohammadi says emphasizing sustainability in CECS programs could also make engineering disciplines more attractive to a broader range of students. “The younger generation cares more about environmental and social issues, and engineering is absolutely a profession where you can make a large impact on society,” Mohammadi says. “But we don’t often describe it that way. So showing them how they can shape the world in a way they care about might make students who’ve never considered engineering before think about it as an option.” To match students and employers, they’ll also be hosting several industry events, where employers can talk with students about their sustainability-focused opportunities and students can showcase their work.

Interested faculty can apply now for minigrant funding by contacting Mohammadi or Rawashdeh. They’re hoping to fund projects in 10-16 courses over three years.

###

Story by Lou Blouin

Faculty and Staff

Nature or Environment

Computer and Information Science

Industrial and Manufacturing Systems Engineering

Mechanical Engineering

Off

Wed, 07/03/2024 - 12:55

Part of being a great engineer these days is understanding the environmental and societal impacts of your work. But how do we train students to be holistic engineers?

Graphic by Violet Dashi. Images by Marianna and KUA g Gear via Adobe Stock

Class of Spring 2024: CECS graduate Issa Hachem

lblouin — Wed, 24 Apr 2024 12:12:02 +0000

Class of Spring 2024: CECS graduate Issa Hachem lblouin Wed, 04/24/2024 - 08:12

First-generation college students often speak of the burden of having to figure out financial aid, majors and minors, and all the other mechanics of a college experience without the help of a parent who’s done it before. But that learning curve can be seriously flattened if you have older siblings blazing the trail for you, says spring ’24 graduate Issa Hachem. The computer engineering senior had three older siblings who, as he did, attended Henry Ford College for two years, then finished a four-year degree. (His two older brothers are also ��-Dearborn graduates.) Issa’s older brother, Mohamad, even studied a similar discipline, which helped him avoid his brother’s mistake of taking a bunch of classes that didn’t transfer. “It’s like the family hand-me-downs, but with advice,” Issa says. “Each kid coming up has it a little bit easier than the last.”

Indeed, the Hachem family is building an impressive story of collective achievement — one in which the American Dream label, however overused, feels apropos. Issa’s mother, Eman, came to the United States from Lebanon when she was a teenager, and his father joined her a few years later. Neither of Issa’s parents had the opportunity to go to college, but he says it was always the goal that the kids would. After graduating from ��-Dearborn, Issa’s oldest brother went to medical school and is finishing his residency in June. His sister is a NICU nurse and is pursuing a master’s in nursing education. His other older brother works as an engineer at Bosch, where Issa is currently interning in the same department. Following the well-honed Hachem formula, the youngest is now finishing his second year at Henry Ford and will be starting his computer engineering program at ��-Dearborn this fall.

Issa’s own college journey has had its unique twists. He’s worked full time or part time at six different jobs while he’s been in school. He’s also part of the unique mini-generation that started college during the COVID pandemic. He didn’t even have an in-person class until he transferred to ��-Dearborn in 2022. Issa remembers it being a pretty big adjustment. His first semester, he did well in three of his four classes, but he struggled in his “Engineering Statistics and Probability” course — the most failed course in his program. “It was almost the end of the semester, and I had to make a decision: Do I quit my job? Do I work really hard and try to not fail this class and potentially sacrifice my As and Bs? Or do I maintain the As and Bs in the other classes and retake the other class later?” For a new student, it was a veteran way to assess the situation. He ultimately decided to abandon ship on the statistics course. When he retook it a few semesters later, he aced it — which wiped out the failing grade and gave a big boost to his GPA.

After that rocky first semester, Issa found his stride in his computer engineering program. He says it’s hard to pick a favorite course or professor. Associate Professor of Electrical and Computer Engineering Paul Watta’s habit of giving students a quiz every lecture stressed Issa out at first. But he grew to love Watta’s demanding style and the fact that his classes were packed with hands-on projects. Professor of Electrical and Computer Engineering Hafiz Malik also made an impression. “This dude — I remember he just rolled up the projector screen and went full chalkboard for two hours straight,” Issa says. “I had so many questions, and he answered every single one of them in a way that made perfect sense. The guy is a genius.” (Issa later completed a directed study in computer vision with Malik.) He and Associate Professor of Electrical and Computer Engineering Samir Rawashdeh bonded over their shared interest in assistive technologies for people with disabilities. (He also loved that Rawashdeh’s passion for engineering bled over into cool side projects, like the Star Wars robots Rawashdeh builds for his kids.) Issa, himself, has been living with significant hearing loss since early childhood. For his senior design project, which Rawashdeh oversaw, Issa and his teammates built a device to assist hearing impaired people with their directional hearing — something that Issa’s top-of-the-line hearing aids can’t even do. “I got the idea when, one day, my friends and I were sitting around the garage and this cricket was chirping,” he explains. “And so we’re trying to find this cricket, and my friends all knew right where to look. And I was, like, ‘Guys, I have no idea where this cricket is!’ That’s when I realized just how bad my directional hearing was.” Their device is a 360-degree microphone array that can be worn tucked inside a ballcap. When it picks up sound, it buzzes on that side of the array, giving the user a discreet, easy-to-interpret tactile sensation of where the sound is coming from, enhancing spatial awareness for hearing impaired people. Issa and his teammates' project won the Best in Electrical and Computer Engineering Award and the Alumni Advisory Council Innovation Award at the 2024 Senior Design Competition.

Issa says it’s a little surreal to be wrapping up a senior design project and to have graduation just a few days away. The approaching milestone has definitely given him a new perspective on things — particularly regarding the role his family has played in getting him to where he is. He laughs a little now at the teenage version of himself — the kid who thought he was “coming from the trenches” because he had a family that provided him everything he needed but not everything he wanted. Now he sees how having a dad who was an auto mechanic and DIY’d almost everything in their home nurtured his love of engineering. He appreciates the hours his mom, the self-taught family accountant, spent filling out his FAFSA forms. And he sees how his college experience likely wouldn’t have gone as smoothly as it did without his older siblings’ hand-me-down wisdom.

“In high school, I think I was worried about all the wrong things. I was comparing myself to the kids whose dads owned businesses and could buy them expensive clothes and pay for college like it was nothing,” Issa says. “I thought I had nothing. I had this mentality that I had to grind. But now I see I really didn’t need to do that. When I was kind of overwhelmed working full time and trying to go to school, my family always had my back. They helped me realize that, no matter what, I was going to have a roof over my head and food to eat. Now, I see all that other material stuff didn’t matter. And I see some of the kids from high school who had it easy — they’ve switched majors three times and are still trying to figure things out. So I guess I’m just more grateful for my family and my friends. Any success I have — I wouldn't have it without them.”

###

Story by Lou Blouin

Commencement

Student Success

Off

Wed, 04/24/2024 - 12:10

One of three siblings to graduate from ��-Dearborn, computer engineering graduate Issa Hachem says getting to the commencement stage has been a family affair.

Graphic by Violet Dashi

Could we make food processing ‘smarter’?

lblouin — Mon, 15 Apr 2024 14:17:27 +0000

Could we make food processing ‘smarter’? lblouin Mon, 04/15/2024 - 10:17

How does the rice you buy at the grocery store stay shelf stable basically indefinitely? Or why can you expect your favorite crackers will always have the same color, taste and crispness — despite being made of always slightly varying batches of flour, cheese and oil? We owe a lot of the longevity and predictably of the food supply to canning, drying and dozens of other technologies and processes that are collectively known as “food processing.” Yet surprisingly, this consistency is earned through a fair amount of inefficient trial and error on the farm or factory floor, according to ��-Dearborn Associate Professor of Industrial and Manufacturing Systems Engineering Cheol Lee. In a potato chip factory, for example, Lee says an inspector might notice the chips coming off the line today are a little too brown, so they try cooking the next batch for 10 seconds less. Still too brown. So they try 20 seconds less. Just right! But then, tomorrow’s batch, which is made using potatoes from a different farm, isn’t brown enough. So they adjust the cooking time again. “Obviously, this is not an optimal way to do it. You waste a lot of energy and time and reduce yields,” Lee says.

Finding a more efficient way to make these process adjustments is the subject of new research led by Lee in collaboration with Professor of Mechanical Engineering Oleg Zikanov and partners at Michigan State University. Their project, funded by a $1.2 million grant from the U.S. Department of Agriculture — ��-Dearborn’s first from the agency — focuses on optimizing food drying processes, which are some of the most energy intensive in the industry. Lee and Zikanov’s hypothesis is that many of the tweaks that humans make now through educated guesswork could be better executed by a computer model — specifically, a high-fidelity physics-based model. The basic idea is that the dynamics inside the drying equipment, like the way air moves or heat is transferred, are subject to the basic principles of physics. And if you could build a mathematical model that described all of those dynamics, you could actually predict the output of the drying process — e.g. color, crispiness, bacteria levels — from some easy-to-measure inputs, like the moisture content of the pre-processed food, drying temperature, fan speed, speed of the conveyor, etc. Thus, with a good model, you could eliminate the need for human trial-and-error adjustments — and the wasted food, energy and carbon emissions that come with that.

Associate Professor Cheol Lee (left) and Professor Oleg Zikanov

Modeling highly complex phenomena like this is possible, but this approach typically has a major drawback: For the models to be very accurate without having to resort to trial and error themselves, they have to account for so many variables and relationships between variables that they become very large, and thus very computationally intensive. “It can take days, and sometimes weeks, to simulate one possible scenario, which is not good when you’re talking about processing conditions changing possibly every couple of hours,” Lee explains. “So you need a way to simulate the process a lot faster.” Their solution is an approach called reduced order modeling, which can drastically shrink the size of the model — thus making it speedier — while sacrificing very little accuracy, a bit like the way image compression creates photos that look nearly identical to the originals, but at a much smaller file size. “The basic philosophy is that you have an output that is very high dimensional and contains a lot of information,” Lee explains. “But most of the solutions lie in a very small subset of this very large space. We call that subspace. And the challenge is, how do we find this subspace where the solution can exist?”

Lee and Zikanov have special techniques for finding this subspace, and they’ve actually used this approach successfully on two other recent projects. One modeled how the coronavirus could spread throughout an indoor environment. The other, a collaboration with General Motors, created a reduced order model for cooling lithium ion batteries in electric vehicles. Despite the drastically reduced size and increased speed of the models, Lee says they still had more than 99 percent of the accuracy of the original model — meaning a modest computer could execute the smaller version in seconds or less, compared to the days or weeks needed for the computationally heavy models. Another advantage of this approach: It’s light on hardware. In a food processing environment, Lee says it would integrate easily into factory equipment with a few controllers and draw on information that existing sensors are already collecting.

Throughout the course of the three-year project, Lee and Zikanov will also field test their model and control algorithm on actual drying equipment located at Michigan State University. “If everything goes well, we’ll end up with a model that can, in real time, make predictions about what is going to happen, then take in data from a few sensors and optimize the process on the go. That’s the bright future for this technology,” Zikanov says. Plus, because drying is a common process in many industries, from pulp production to pharmaceuticals, Lee says the technology could have a wide range of applications.

One other cool part of their project: In an effort to get young people interested in STEM subjects, Lee and Zikanov will periodically host high school students from University Prep Academy High School in Detroit, who will also get to tour the drying facilities at Michigan State. Lee and Zikanov’s research team will also include several ��-Dearborn pre-engineering students. These are students who plan on entering engineering programs but are still working on meeting their introductory math and science requirements. Lee and Zikanov are hoping the hands-on learning from this project will help get students over the hump and into their chosen programs in the College of Engineering and Computer Science.

###

Lee and Zikanov’s project is funded through a U.S. Department of Agriculture and National Science Foundation interagency program. Story by Lou Blouin

Mechanical Engineering

Off

Mon, 04/15/2024 - 14:17

��-Dearborn professors are teaming up with Michigan State University to take the human guesswork out of modern food processing.

Photo by Lou Blouin

America needs more farmers. Could robots help?

lblouin — Tue, 09 Apr 2024 19:03:18 +0000

America needs more farmers. Could robots help? lblouin Tue, 04/09/2024 - 15:03

The workforce that powers American farms is facing stress from many directions. The average age of the country’s farmers has climbed steadily since the 1970s and now stands at 57-and-a-half years old — less than a decade shy of the Social Security retirement age. Young people, staring down the prospect of low wages, high stress and problems accessing land, aren’t rushing in to replace older farmers. For the past several years, farms have also had a hard time finding enough workers, as fewer people come to the U.S. for seasonal agricultural employment and veteran farmworkers age out of the profession. Meanwhile, a huge majority of Americans continue to show little interest in doing agricultural labor, which is hard on your body, doesn’t pay particularly well and can expose you to harmful pesticides.

Potential solutions to the labor shortage come in a variety of forms, from immigration reform to grants that help a younger, more diverse group of Americans buy increasingly expensive farmland. Assistant Professor of Electrical and Computer Engineering Jaerock Kwon thinks robots could also help ease farms’ labor challenges — particularly common sense robots that amplify the impact of human farmworkers by helping with straightforward tasks. Viewed in terms of modern agricultural history, it’s really not such a radical idea. Over the past hundred years, the number of people working on American farms has declined drastically, while yields have increased and the amount of farmland in production has decreased. The reason? We shifted work to machines like tractors, combines and food processing technology, though human labor is still needed for many tasks on both big and small farms. In particular, people will likely still be needed for the foreseeable future to harvest crops requiring gentle handling. But Kwon thinks less complicated tasks, like toting bushels of apples through an orchard or applying pesticides or fertilizers, are well within a robot’s capabilities.

Assistant Professor Jaerock Kwon

Kwon thinks some of the most practical robots for the farm, at least right now, are likely autonomous vehicles. But designing AVs for farmwork presents a much different challenge than those designed for the road or an indoor environment like a warehouse. For example, Kwon says that AVs typically keep track of where they are in space with the help of motion sensors, which measure the distance the vehicle has traveled. But this system’s programming typically assumes a flat surface. On uneven surfaces, like a farm field, the distance that an AV’s wheels travel along the ground will be greater than the as-the-crow-flies distance between two horizontal points, owing to bumps and dips in the terrain. One wheel might even travel a different distance than the one next to it. And Kwon says these little deviations could cause a traditional AV’s motion sensors to guide the vehicle off course.

Similarly, a traditional AV’s vision system might leave it totally lost on the farm. Many AVs have to map their environment first, which helps the vehicle identify important landmarks and keep track of where it is. “But if you look at, say, an orchard environment, with rows and rows of evenly spaced trees, there are no distinguishing characteristics. It all looks the same,” Kwon explains. “The robot would look around and have no idea where it was.” Kwon says the variable lighting of outdoor conditions could also confuse AVs’ optical cameras and image recognition systems, which often rely on properties like color to identify objects. A shiny red object may always look the same in a windowless warehouse. However, in the orchard, the object might appear red under cloudy skies at noon, but white if it’s reflecting bright sunlight. At sunset, it might look sort of rust-colored.

Kwon thinks fixing these individual problems with ever more complex programming — how we’ve traditionally fine-tuned AVs — isn’t the best option. Instead, he thinks farm AVs will work much better if we take a fundamentally different approach. Specifically, he thinks farm vehicles could be a great application of a concept he’s been working on called embodied cognitive driving. Typical AVs have sensors to experience their environment, and then, using a bunch of very complicated math, their powerful computing units interpret that sensor data and relay decisions about how to act to the mechanical parts of the vehicle. An embodied cognitive AV is conceptually and computationally much simpler. Using machine learning, it learns to navigate an environment simply by observing how a human driver does it first, deriving its own rules for, say, accurate steering on uneven ground. It doesn’t even have an image recognition system to do things like recognize what an apple tree is, nor programming that tells it how to not run into one. Kwon’s vehicle wouldn’t even know what an apple tree is, and it doesn’t need to. It simply learns to avoid such objects because that’s what it’s always seen its human mentor do.

This may sound like magic, but there are actually examples of machine learning-based vehicles like this learning to be pretty good drivers dating back to the 1980s. And Kwon thinks this approach, which has fallen out of favor among engineers creating driverless cars, could actually work much better for farm AVs. Traditional AVs, with their powerful interpretive capacities, would certainly outperform Kwon’s farm AV on city streets. In that environment, the traditional AV’s programming would allow it to recognize people, stop signs and lane markers — useful abilities for safe navigation on the road. Trained in the orchard, Kwon’s vehicles likely wouldn’t know how to react to such objects. But in the orchard, the traditional AV would be the one getting confused, because the environment is simply too irregular for its brand of intelligence to work very well. Meanwhile, Kwon’s vehicle would navigate the orchard rows, as humans do, with unconscious, thoughtless ease, because its motor skills have specifically evolved to move in the bumpy, irregular terrain. “They don’t have to know what they’re doing,” Kwon says. “They just need to do their jobs well.”

Kwon also notes that farmwork is full of straightforward tasks that this computationally lighter style of AV could master pretty quickly. To return to the orchard example, as a person picks apples, they collect them into bags worn on their bodies, and then they dump those bags into crates. But what if a human worker had a small, lightweight AV helper, which simply trailed them with a container for collecting the apples? That would save work for the human laborer — and relieve the burden of carrying heavy bags around, a break the country's aging farmers and farmworkers could no doubt use. In fact, Kwon says one of the first tasks they’ll be testing with their new prototype vehicle is how well it can follow a human over uneven ground. “I don’t have an orchard, though,” Kwon says, smiling. “So don't be surprised if you see one of my graduate students walking around campus with a robot following them this fall.”

###

Want to learn more about Kwon’s research on embodied cognitive AVs? Check out our story, “Have we been thinking about autonomous vehicles all wrong?” Story by Lou Blouin

Off

Tue, 04/09/2024 - 19:00

CECS Assistant Professor Jaerock Kwon is working on autonomous vehicles that could assist farmworkers. But building farm AVs presents a much different challenge than ones designed for the road.

Assistant Professor Jaerock Kwon thinks autonomous vehicles, like the one seen in simulation here, could play helpful roles in orchards and other farm environments. Image courtesy Jaerock Kwon

Could you be friends with a robot?

lblouin — Mon, 01 Apr 2024 17:10:14 +0000

Could you be friends with a robot? lblouin Mon, 04/01/2024 - 13:10

For the past few years, Associate Professor of Electrical and Computer Engineering Samir Rawashdeh has been building robots for his 7-year-old daughter, Maia, and his 5-year-old son, Adam. One of his first creations was a modified Roomba, the popular autonomous floor-cleaning robot, which he equipped with a vision system and topped with a googly-eyed Lego head and multicolor mini pom poms for hair. The souped-up Roomba would primarily look for and follow the kids around and then stop at a safe distance when it caught up to them. Even though its programming was simple, it was a huge hit with the kids. Maia would squeal as the Roomba “chased” her around the room. She’d ask it to accompany her on play missions around the house. She also figured out pretty quickly that she could trick it by hiding in her play tent, outside the reach of the Roomba’s camera.

Rawashdeh's second robot had a little more polish. Using 3-D printing plans he got from a Facebook group devoted to such things, he built a full-size replica of D-O, a scrappy Star Wars robot with a ducklike, pivoting conical head mounted to a thick off-road wheel. He then used his electrical engineering expertise to make it move. While the Roomba was autonomous, Rawashdeh opted for remote controls for D-O, thinking it would give the robot a wider range of intentional movements. With a radio controller in hand, Rawashdeh could make D-O not only chase the kids but run away from them. It could move its head in all directions, including shaking up and down for yes or sideways for no. When the kids would hug it, D-O could give them a catlike head love tap right back. With Rawashdeh’s latest version, D-O can talk.

Rawashdeh's D-O in action.

Rawashdeh says he initially started making the robots as a fun pandemic engineering activity that he and the kids could do together. But as he watched the kids play, he became fascinated by how they were interacting with the machines, especially D-O. The kids figured out pretty quickly that their dad was the one actually animating D-O, but in many ways, they didn’t care: They still reacted to D-O as though he was a “free agent.” The kids would talk with D-O and ask him to do things with them. They would give him affection. “One time, when I took D-O into one of my classes, Maia texted me and said, ‘Tell D-O that me and Adam love him,’” Rawashdeh remembers. Even without his own agency, D-O had become “somebody” to them — at least enough to miss him when he wasn’t around.

Associate Professor Samir Rawashdeh

So what’s going on here? Or as Rawashdeh frames the question: “When does a bunch of plastic and wires and batteries and motors become more than that?” It’s not a question he can claim a definitive answer to, nor likely can anyone. The modern discipline of human-robot interaction is still very new, and you’ll find a wide range of ideas about what ingredients are essential to humans having meaningful social interactions with machines. Rawashdeh’s own take is that there is still a lot of exploratory trial and error going on among the designers, engineers and philosophers who think about these things. Most robots intended for social human interactions seem to contain at least some suggestions of biological anatomy. For example, Miko, an AI-powered robot that's being marketed as a companion for kids and who can even teach them social behaviors, has a friendly face. The engineers behind Paro went with a full biomimicry approach when they built an interactive baby seal to serve as a therapeutic companion animal. But there are also examples that completely buck this trend. The engineers behind Yolo, for example, which is advertised as a “creativity boosting robot” for children, actually let kids design it. The result was something that looks like an artsy bedside table lamp. It has no face and no eyes. Other than the wiry plastic strands shooting out of the top of it, which sort of look like hair, it’s not very creaturelike.

In his own informal trials with his kids, Rawashdeh noticed a couple qualities that seemed to be important for them to connect with the robots. First, movement helps, and specifically, an ability to move in response to something the kids are doing. Both the Roomba and D-O can do this. In the Roomba’s case, its movement is fully autonomous. But interestingly, the kids seem to be more engaged by the dad-controlled D-O, who, with its nods, sounds and affectionate head bumps, has a much greater range of responses. Rawashdeh’s observation that the kids know he’s animating D-O yet don’t seem to care is actually supported by some recent research suggesting that children’s tendency to anthropomorphize robots can be a powerful bonding force — even when they know the robot is not an independent being with its own inner psychological life. Rawashdeh also comes down in the camp that thinks looks matter, but it doesn’t take much. Even D-O’s hint of ducklike anatomy is enough to give it something that can be interpreted as a face. Interestingly, Maia has more or less the same take on all this as her dad. When Rawashdeh asked her if she could ever be friends with a robot, she quickly answered in the affirmative, then clarified — as long as it could follow her and was “very cute.”

Surprisingly, one thing Rawashdeh thinks is probably not that essential to forming a bond is speech. For example, they’ve had an Alexa in their house for a long time, and the kids will occasionally ask it questions, but they don’t think of it as a “playmate.” He also points out that R2-D2 from Star Wars is beloved but does not speak, and we form very strong bonds with our pet animals, who at least don’t speak our language. He thinks this peculiarity of speech, or conversational written language, might also explain why, despite some initial fears, technologies like ChatGPT seemingly haven’t unleashed a plague of socially isolating human-chatbot friendships. “I think part of what is going on here is nobody cares what a machine thinks, which is a key part of what makes our human-to-human relationships meaningful,” Rawashdeh says. “I think this is even the case with social media, which sort of feels like a lonesome experience between humans and technology. But it’s really more of a human-to-human interaction that’s mediated by technology. Why do we post our vacation photos on Instagram? It’s to show off where we’ve been to other people. If you had a robot liking all your posts, that wouldn’t be satisfying.”

This line of inquiry also, of course, begs some important questions about whether such human-robot relationships are good for us. Could they, for example, further transform or replace the human-to-human social interactions that have already taken a beating from technologies like television, the internet and smartphones? And should we be worried, in particular, about kids forming bonds with machines? Research in this area is still very new, but it is producing some interesting findings. On the positive side, there’s work suggesting that children with autism may actually learn better from robots, due to their more predictable responses. Paro, the therapeutic robotic seal, was shown to produce many of the same effects of traditional therapy animals. At least for now, a headline-grabbing study showing that human society could be a risk should we choose to befriend robots doesn’t exist. Rawashdeh says his kids, at least, don’t seem to be overly attached to D-O. Playing with their “very cute” droid is not an everyday activity at their house. Maia and Adam still like to play outside.

For Rawashdeh, this experience building robots for his kids has, however, inspired him to do some more formal work in this area. For one of his next projects, he’s experimenting with building a therapeutic robot that would essentially be a good listener, with a goal of potentially addressing certain gaps in the availability of mental health services. Powered by a modified large language model, it could engage people who, say, were having a bad day, with supportive, helpful humanlike dialogue. For the body, he’s thinking something suggestive of an owl — an animal associated with wisdom. It likely wouldn’t move around the room, but he would give it the ability to move its head and large, empathetic eyes, so it could appropriately make and break eye contact and “wouldn’t just stare at you.” “I’m thinking about the shortage in mental health services and the current loneliness epidemic, and how there are many people out there who could benefit from a helpful companion,” he says. On the other hand, he wonders if technology can be a salve for social isolation, which, in many ways, has been caused by technology. “That’s something I guess we’re still figuring out,” he says. “I think we still lack the language for describing what is going on,” he says. “Like, with music or art, we have established traditions and genres. We know, more or less, the key ingredients that go into making a Cubist painting or a certain type of song. But what makes a robot that humans will actually connect with?” On the front, Rawashdeh thinks we may still be shooting in the dark.

###

Story by Lou Blouin