Working to advance the nuclear renaissance

Today, there are 94 nuclear reactors operating in the United States, more than in any other country in the world, and these units collectively provide nearly 20 percent of the nation’s electricity. That is a major accomplishment, according to Dean Price, but he believes that our country needs much more out of nuclear energy, especially at a moment when alternatives to fossil fuel-based power plants are desperately being sought. He became a nuclear engineer for this very reason — to make sure that nuclear technology is up to the task of delivering in this time of considerable need.

“Nuclear energy has been a tremendous part of our nation’s energy infrastructure for the past 60 years, and the number of people who maintain that infrastructure is incredibly small,” says Price, an MIT assistant professor in the Department of Nuclear Science and Engineering (NSE), as well as the Atlantic Richfield Career Development Professor in Energy Studies. “By becoming a nuclear engineer, you become one of a select number of people responsible for carbon-free energy generation in the United States.” 

That was a mission he was eager to take part in, and the goals he set for himself were far from modest: He wanted to help design and usher in a new class of nuclear reactors, building on the safety, economics, and reliability of the existing nuclear fleet.

Price has never wavered from this objective, and he’s only found encouragement along the way. The nuclear engineering community, he says, “is small, close-knit, and very welcoming. Once you get into it, most people are not inclined to do anything else.”

Illuminating the relationships between physical processes

In his first research project as an undergraduate at the University of Illinois Urbana at Champaign, Price studied the safety of the steel and concrete casks used to store spent reactor fuel rods after they’ve cooled off in tanks of water, typically for several years. His analysis indicated that this storage method was quite safe, although the question as to what should ultimately be done with these fuel casks, in terms of long-term disposal, remains open in this country.

After starting graduate studies at the University of Michigan in 2020, Price took up a different line of research that he’s still engaged in today. That area of study, called multiphysics modeling, involves looking at various physical processes going on in the core of a nuclear reactor to see how they interact — an alternative to studying these processes one at a time.

One key process, neutronics, concerns how neutrons buzz around in the reactor core causing nuclear fission, which is what generates the power. A second process, called thermal hydraulics, involves cooling the reactor to extract the heat generated by neutrons. A multiphysics simulation, analyzing how these two processes interact, could show how the heat carried away as the reactor produces power affects the behavior of neutrons, because the hotter the fuel is, the less likely it is to cause fission.

“If you ever want to change your power level, or do anything with the reactor, the temperature of the fuel is a critical input that you need to know,” says Price. “Multiphysics modeling allows us to correlate the fission neutronics processes with a thermal property, temperature. That, in turn, can help us predict how the reactor will behave under different conditions.”

Multiphysics modeling for light water reactors, which are the ones operating today with capacities on the order of 1,000 megawatts, are pretty well established, Prices says. But methods for modeling advanced reactors — small modular reactors (SMRs with capacities ranging from around 20 to 300 MW) and microreactors (rated at 1 to 20 MW) — are far less advanced. Only a very small number of these reactors are operating today, but Price is focusing his efforts on them because of their potential to produce power more cheaply and more safely, along with their greater flexibility in power and size.   

Although multiphysics simulations have supplied the nuclear community with a wealth of information, they can require supercomputers to solve, or find approximate solutions to, coupled and extremely difficult nonlinear equations. In the hopes of greatly reducing the computational burden, Price is actively exploring artificial intelligence approaches that could provide similar answers while bypassing those burdensome equations altogether. That has been a central theme of his research agenda since he joined the MIT faculty in September 2025.

A crucial role for artificial intelligence

What artificial intelligence and machine-learning methods, in particular, are good at is finding patterns concealed within data, such as correlations between variables critical to the functioning of a nuclear plant. For example, Price says, “if you tell me the power level of your reactor, it [AI] could tell you what the fuel temperature is and even tell you the 3-dimensional temperature distribution in your core.” And if this can be done without solving any complicated differential equations, computational costs could be greatly reduced.

Price is investigating several applications where AI may be especially useful, such as helping with the design of novel kinds of reactors. “We could then rely on the safety frameworks developed over the past 50 years to carry out a safety analysis of the proposed design,” he says. “In this way, AI will not be directly interfacing with anything that is safety-critical.” As he sees it, AI’s role would be to augment established procedures, rather than replacing them, helping to fill in existing gaps in knowledge.

When a machine-learning model is given a sufficient amount of data to learn from, it can help us better understand the relationship between key physical processes — again without having to solve nonlinear differential equations. 

“By really pinning down those relationships, we can make better design decisions in the early stages,” Price says. “And when that technology is developed and deployed, AI can help us make more intelligent control decisions that will enable us to operate our reactors in a safer and more economical way.”

Giving back to the community that nurtured him

Simply put, one of his chief goals is to bring the benefits of AI to the nuclear industry, and he views the possibilities as vast and largely untapped. Price also believes that he is well-positioned as a professor at MIT to bring us closer to the nuclear future that he envisions. As he sees it, he’s working not only to develop the next generation of reactors, but also to help prepare the next generation of leaders in the field.

Price became acquainted with some prospective members of that “next generation” in a design course he co-taught last fall with Curtis Smith, the KEPCO Professor of the Practice of Nuclear Science and Engineering. For Price, that introduction lasted just a few months, but it was long enough for him to discover that MIT students are exceptionally motivated, hard-working, and capable. Not surprisingly, those happen to be the same qualities he’s hoping to find in the students that join his research team.

Price vividly recalls the support he received when taking his first, tentative steps in this field. Now that he’s moved up the ranks from undergraduate to professor, and acquired a substantial body of knowledge along the way, he wants his students “to experience that same feeling that I had upon entering the field.” Beyond his specific goals for improving the design and operation of nuclear reactors, Price says, “I hope to perpetuate the same fun and healthy environment that made me love nuclear engineering in the first place.”

de MIT News https://ift.tt/LBkOu2J

Toward cheaper, cleaner hydrogen production

Hydrogen sits at the center of some of the world’s most important industrial processes, but its production still comes with a heavy environmental cost. Today, most hydrogen is produced through high-emissions processes like steam methane reforming and coal gasification.

But hydrogen can also be made by splitting water molecules using renewable electricity, eliminating fossil fuel emissions and other toxic byproducts. Such “green hydrogen” is made by running an electric current through water in an electrolyzer.

Green hydrogen won’t scale through decarbonization alone. It also has to be cost-competitive with the traditional methods of production.

1s1 Energy thinks it has the technology to finally make green hydrogen go mainstream. The company says its boron-based membrane material unlocks previously unachievable performance and durability in electrolyzers.

In tests with partners, 1s1 says, electrolyzers with its membranes needed just 70 percent of the energy to produce each kilogram of hydrogen, compared to incumbent devices.

“Green hydrogen has been a hard industry to have success in so far,” acknowledges 1s1 co-founder Dan Sobek ’88, SM ’92, PhD ’97. “The difference with us is we’ve done very targeted customer discovery. We have a very strong value proposition that’s not just about decarbonization. We have a pipeline of potential customers that see around a 60 percent reduction in operating costs with our technology. That’s a nice point of entry.”

Although 1s1 is focused on hydrogen production now, its technology could also be used in fuel cells and solid-state batteries, and to extract critical metals from mining waste. The company is beginning trials in some of those applications, and it is working with a large materials company to scale up production of its membranes for hydrogen production.

“We’re at an inflection point for the company,” Sobek says. “The plan is, by 2030, to have a solid business in several segments: electrolyzers, mineral extraction, and in collaborations with several large companies. But right now, we have to be judicious and focused.”

Improving electrolyzers

Sobek was born and raised in Argentina, but he also grew up at MIT over the course of three degrees and more than a decade. He first studied aeronautics and astronautics at MIT, then jumped to mechanical engineering as a graduate student, then moved to the Department of Electrical Engineering and Computer Science, where he worked under PhD advisors and MIT professors Martha Gray and Stephen Senturia. His thesis focused on a technique for quickly measuring optical properties of large numbers of biological cells.

“A lot of my learnings around microfabrication and materials chemistry ended up being really relevant for 1s1,” Sobek says. “A class that was very important to me was taught by Professor Amar Bose. I was a teaching assistant for him for a couple of semesters, and that had an incredible influence on my thinking.”

Following graduation, Sobek worked in microelectronics and microfluidics before founding his own company, Zymera, in 2004. The company developed deep-tissue imaging technology for detecting cancer and other serious diseases.

Around 2013, Sobek started talking to his Zymera co-founder, Sukanta Bhattacharyya, about making electrolysis more efficient, focusing on “proton exchange membrane” electrolyzers. Such electrolyzers employ a large amount of electricity to split water into hydrogen and oxygen ions. At their center is a membrane that can lose efficiency through voltage resistance.

On top of the efficiency challenge, electricity is often more expensive than fossil fuels in many parts of the world. Traditional hydrogen production also has the benefit of existing infrastructure, making it that much more difficult for green hydrogen production to scale.

Sobek and Bhattacharyya knew the most important part of such electrolyzers is their proton-conducting membrane, which shuttles hydrogen ions from the anode to the cathode in the electrolyzer’s electrochemical cell.

“I asked Sukanta how we could improve the efficiency and durability of that element,” Sobek recalls. “He gave me a one-word answer: boron.”

Boron can be given a negative charge, which makes hydrogen ions, or protons, bond to it more quickly. The hydrogen ions can then be filtered through the membrane and released as they move through the cell. Boron-based materials are also more stable and resistant to corrosion, further improving the long-term performance of electrolyzers.

The company was officially founded in late 2019. After years of development, today 1s1 attaches a chemically tailored version of boron onto polymer materials to create its membranes for exchanging protons.

“These are first-of-a-kind membranes with stable and durable, super-acid proton exchange groups that do not poison catalysts,” Sobek says.

Tiny membranes with big impact

In 2021, the U.S. Department of Energy set a goal for proton exchange membrane electrolysis to achieve 77 percent electrical efficiency by 2031. Sobek says 1s1 is already reaching that milestone in tests.

“It’s not just the technology, but the way we’re applying it,” Sobek says, “We’re making hydrogen viable for use in the production of different industrial chemicals.”

1s1 is currently conducting pilots with partners, including an electrical utility owned by a large steel company in Brazil. The company is also actively exploring other applications for its technology. Last year, 1s1 announced a project to produce green ammonia with the company Nitrofix through joint funding from the U.S. Department of Energy and the Israeli Ministry of Energy and Infrastructure. It’s also working with a large mine in Brazil to extract a material called niobium, which is useful for high-strength steel as well as fast-charging batteries. A similar process could even be used to extract gold.

“We can do that without using harsh chemicals, because the standard processes used to extract niobium and gold use extremely strong acids at high temperatures or extremely toxic chemicals,” Sobek says. “It’s gratifying for me because my home country of Argentina has had a lot of problems with the use of toxic chemicals to extract gold. We’re trying to enable low-cost, responsible mining.”

As 1s1 scales its membrane technology, Sobek says the goal is to deploy wherever the technology can improve processes.

“We have a large number of potential customers because this technology is really foundational,” Sobek says. “Creating high-impact technologies is always fun.”

de MIT News https://ift.tt/g9xFua3

Lincoln Laboratory laser communications terminal launches on historic Artemis II moon mission

In 1969, Apollo 11 astronaut Neil Armstrong stepped onto the moon's surface — a momentous engineering and science feat marked by his iconic words: "That's one small step for man, one giant leap for mankind." Now, NASA is making history again.

With the successful launch of NASA's Artemis II mission yesterday, four astronauts are set to become the first humans to travel to the moon in more than 50 years. In 2022, the uncrewed Artemis I mission demonstrated that NASA's new Orion spacecraft could travel farther into space than ever before and return safely to Earth. Building on that success, the 10-day Artemis II mission will pave the way for future Artemis missions, which aim to land astronauts on the moon to prepare for a lasting lunar presence, and eventually human missions to Mars.

As it orbits the moon, the Orion spacecraft will carry an optical (laser) communications system developed at MIT Lincoln Laboratory in collaboration with NASA Goddard Space Flight Center. Called the Orion Artemis II Optical Communications System (O2O), the system is capable of higher-bandwidth data transmissions from space compared to traditional radio-frequency (RF) systems. During the Artemis II mission, O2O will use laser beams to send high-resolution video and images of the lunar surface down to Earth.

"Space-based communications has always been a big challenge," says lead systems engineer Farzana Khatri, a senior staff member in the laboratory's Optical and Quantum Communications Group. "RF communications have served their purpose well. However, the RF spectrum is highly congested now, and RF does not scale well to longer distances across space. Laser communication [lasercom] is a solution that could solve this problem, and the laboratory is an expert in the field, which was really pioneered here."

Artemis II is historic not only for renewing human exploration beyond Earth, but also for being the first crewed lunar flight to demonstrate lasercom technologies, which are poised to revolutionize how spacecraft communicate. Lincoln Laboratory has been developing such technologies for more than two decades, and NASA has been infusing them into its missions to meet the growing demands of long-distance and data-intensive space exploration.

"The Orion spacecraft collects a huge amount of data during the first day of a mission, and typically these data sit on the spacecraft until it splashes down and can take months to be offloaded," Khatri says. "With an optical link running at the highest rate, we should be able to get all the data down to Earth within a few hours for immediate analysis. Furthermore, astronauts will be able to communicate in real-time over the optical link to stay in touch with Earth during their journey, inspiring the public and the next generation of deep-space explorers, much like the Apollo 11 astronauts who first landed on the moon 57 years ago."

At the heart of O2O is the laboratory-developed Modular, Agile, Scalable Optical Terminal (MAScOT). About the size of a house cat, MAScOT features a 4-inch telescope mounted on a two-axis pivoted support (gimbal) with fixed backend optics. The gimbal precisely points the telescope and tracks the laser beam through which communications signals are emitted and received in the direction of the desired data recipient or sender. Underneath the gimbal, in a separate assembly, are the backend optics, which contain light-focusing lenses, tracking sensors, fast-steering mirrors, and other components to finely point the laser beam.

MAScOT made its debut in space as part of the laboratory's Integrated Laser Communications Relay Demonstration (LCRD) LEO User Modem and Amplifier Terminal (ILLUMA-T), which launched to the International Space Station in November 2023. Over the following six months, the laboratory team performed experiments to test and characterize the system's basic functionality, performance, and utility for human crews and user applications. Initially, the team checked whether the ILLUMA-T-to-LCRD optical link was operating at the intended data rates in both directions: 622 Mbps down and 51 Mbps up. In fact, even higher data rates were achieved: 1.2 Gbps down and 155 Mbps up. MAScOT's lasercom terminal architecture, which was recognized with a 2025 R&D 100 Award, is now being used for Artemis II and will support future space missions.

"Our success with ILLUMA-T laid the foundation for streaming HD [high-definition] video to and from the moon," says co-principal investigator Jade Wang, an assistant leader of the Optical and Quantum Communications Group. "You can imagine the Artemis astronauts using videoconferencing to connect with physicians, coordinate mission activities, and livestream their lunar trips."

A dedicated operations team from Lincoln Laboratory is following the 10-day Artemis II mission from ground stations in Houston, Texas, and White Sands, New Mexico, and even as far as an experimental ground station in Australia, which allows for a better view of the spacecraft from the Southern Hemisphere. Leading up to the launch, the operations team had been making monthly trips to the Houston and White Sands ground stations to perform maintenance and simulations of various stages of the Artemis mission — from prelaunch to launch to the journey to the moon and back to the splashdown at the end of the mission. 

"Doing these monthly simulations is important so we all stay fresh and engaged, especially when there is a launch delay," says Khatri, who adds that team members have had the opportunity to meet and speak with the four astronauts several times during these trips.

Lessons learned throughout the Artemis II mission will pave the way for humans to return to the lunar surface and beyond, eventually to Mars. Through the Artemis program, NASA will travel farther into space and explore more of the moon while creating an enduring presence in deep space and a legacy for future generations.

O2O is funded by the Space Communication and Navigation (SCaN) program at NASA Headquarters in Washington. O2O was developed by a team of engineers from NASA's Goddard Space Flight Center and Lincoln Laboratory. This partnership has led to multiple lasercom missions, such as the 2013 Lunar Laser Communication Demonstration (LLCD), the 2021 LCRD, the 2022 TeraByte Infrared Delivery (TBIRD), and the 2023 ILLUMA-T.

de MIT News https://ift.tt/cQ52uXd

MIT researchers measure traffic emissions, to the block, in real-time

In a study focused on New York City, MIT researchers have shown that existing sensors and mobile data can be used to generate a near real-time, high-resolution picture of auto emissions, which could be used to develop local transportation and decarbonization policies.

The new method produces much more detailed data than some other common approaches, which use intermittent samples of vehicle emissions. The researchers say it is also more practical and scales up better than some studies that have aimed for very granular emissions data from a small number of automobiles at once. The work helps bridge the gap between less-detailed citywide emissions inventories and highly detailed analyses based on individual vehicles.

“Our model, by combining real-time traffic cameras with multiple data sources, allows extrapolating very detailed emission maps, down to a single road and hour of the day,” says Paolo Santi, a principal research scientist in the MIT Senseable City Lab and co-author of a new paper detailing the project’s results. “Such detailed information can prove very helpful to support decision-making and understand effects of traffic and mobility interventions.”

Carlo Ratti, director of the MIT Senseable City Lab, notes that the research “is part of our lab’s ongoing quest into hyperlocal measurements of air quality and other environmental factors. By integrating multiple streams of data, we can reach a level of precision that was unthinkable just a few years ago — giving policymakers powerful new tools to understand and protect human health.”

The new method also protects privacy, since it uses computer vision techniques to recognize types of vehicles, but without compiling license plate numbers. The study leverages technologies, including those already installed at intersections, to yield richer data about vehicle movement and pollution.

“The very basic idea is just to estimate traffic emissions using existing data sources in a cost-effective way,” says Songhua Hu, a former postdoc in the Senseable City Lab, and now an assistant professor at City University of Hong Kong.

The paper, “Ubiquitous Data-driven Framework for Traffic Emission Estimation and Policy Evaluation,” is published in Nature Sustainability.

The authors are Hu; Santi; Tom Benson, a researcher in the Senseable City Lab; Xuesong Zhou, a professor of transportation engineering at Arizona State University; An Wang, an assistant professor at Hong Kong Polytechnic University; Ashutosh Kumar, a visiting doctoral student at the Senseable City Lab; and Ratti. The MIT Senseable City Lab is part of MIT’s Department of Urban Studies and Planning.

Manhattan measurements

To conduct the study, the researchers used images from 331 cameras already in use in Manhattan intersections, along with anonymized location records from over 1.75 million mobile phones. Applying vehicle-recognition programs and defining 12 broad categories of automobiles, the scholars found they could correctly place 93 percent of vehicles in the right category. The imaging also yielded important information about the specific ways traffic signals affect traffic flow. That matters because traffic signals are a major reason for stop-and-go driving patterns, which strongly affect urban emissions but are often omitted in conventional inventories.

The mobile phone data then provided rich information about the overall patterns of traffic and movement of individual vehicles throughout the city. The scholars combined the camera and phone data with known information about emissions rates to arrive at their own emissions estimates for New York City.

“We just need to input all emission-related information based on existing urban data sources, and we can estimate the traffic emissions,” Hu says.

Moreover, the researchers evaluated the changes in emissions that might occur in different scenarios when traffic patterns, or vehicle types, also change.

For one, they modeled what would happen to emissions if a certain percentage of travel demand shifted from private vehicles to buses. In another scenario, they looked at what would happen if morning and evening rush hour times were spread out a bit longer, leaving fewer vehicles on the road at once. They also modeled the effects of replacing fine-grained emissions inputs with citywide averages — finding that the rougher emissions estimates could vary widely, from −49 percent to 25 percent of the more fine-tuned results. That underscores how seemingly small simplifications can introduce large errors into emission estimates.

Major emissions drop

On one level, this work involved altering inputs into the model and seeing what emerged. But one scenario the researchers studied is based on a real-world change: In January 2025, New York City implemented congestion pricing south of 60th Street in Manhattan.

To study that, the researchers looked at what happened to vehicle traffic at intervals of two, four, six, and eight weeks after the program began. Overall, congestion pricing lowered traffic volume by about 10 percent — but there was a corresponding drop in emissions of 16-22 percent.

This finding aligns with a previous study by researchers at Cornell University, which reported a 22 percent reduction in particulate matter (PM2.5) levels within the pricing zone. The MIT team also found that these reductions were not evenly distributed across the network, with larger declines on some major streets and more mixed effects outside the pricing zone.

“We see these kinds of huge changes after the congestion pricing began, Hu says. “I think that’s a demonstration that our model can be very helpful if a government really wants to know if a new policy converts into real-world impact.”

There are additional forms of data that could be fed into the researchers’ new method. For instance, in related work in Amsterdam, the team leveraged dashboard cams from vehicles to yield rich information about vehicle movement.

“With our model we can make any camera used in cities, from the hundreds of traffic cameras to the thousands of dash cams, a powerful device to estimate traffic emissions in real-time,” says Fábio Duarte, the associate director of research and design at the MIT Senseable City Lab, who has worked on multiple related studies.

The research was supported by the MIT Senseable City Consortium, which consists of Atlas University, the city of Laval, the city of Rio de Janeiro, Consiglio per la Ricerca in Agricoltura e l’Analisi dell’Economia Agraria, the Dubai Future Foundation, FAE Technology, KAIST Center for Advanced Urban Systems, Sondotecnica, Toyota, and Volkswagen Group America.

de MIT News https://ift.tt/6vSt4wA

Evaluating the ethics of autonomous systems

Artificial intelligence is increasingly being used to help optimize decision-making in high-stakes settings. For instance, an autonomous system can identify a power distribution strategy that minimizes costs while keeping voltages stable.

But while these AI-driven outputs may be technically optimal, are they fair? What if a low-cost power distribution strategy leaves disadvantaged neighborhoods more vulnerable to outages than higher-income areas?

To help stakeholders quickly pinpoint potential ethical dilemmas before deployment, MIT researchers developed an automated evaluation method that balances the interplay between measurable outcomes, like cost or reliability, and qualitative or subjective values, such as fairness.   

The system separates objective evaluations from user-defined human values, using a large language model (LLM) as a proxy for humans to capture and incorporate stakeholder preferences. 

The adaptive framework selects the best scenarios for further evaluation, streamlining a process that typically requires costly and time-consuming manual effort. These test cases can show situations where autonomous systems align well with human values, as well as scenarios that unexpectedly fall short of ethical criteria.

“We can insert a lot of rules and guardrails into AI systems, but those safeguards can only prevent the things we can imagine happening. It is not enough to say, ‘Let’s just use AI because it has been trained on this information.’ We wanted to develop a more systematic way to discover the unknown unknowns and have a way to predict them before anything bad happens,” says senior author Chuchu Fan, an associate professor in the MIT Department of Aeronautics and Astronautics (AeroAstro) and a principal investigator in the MIT Laboratory for Information and Decision Systems (LIDS).

Fan is joined on the paper by lead author Anjali Parashar, a mechanical engineering graduate student; Yingke Li, an AeroAstro postdoc; and others at MIT and Saab. The research will be presented at the International Conference on Learning Representations.

Evaluating ethics

In a large system like a power grid, evaluating the ethical alignment of an AI model’s recommendations in a way that considers all objectives is especially difficult.

Most testing frameworks rely on pre-collected data, but labeled data on subjective ethical criteria are often hard to come by. In addition, because ethical values and AI systems are both constantly evolving, static evaluation methods based on written codes or regulatory documents require frequent updates.

Fan and her team approached this problem from a different perspective. Drawing on their prior work evaluating robotic systems, they developed an experimental design framework to identify the most informative scenarios, which human stakeholders would then evaluate more closely.

Their two-part system, called Scalable Experimental Design for System-level Ethical Testing (SEED-SET), incorporates quantitative metrics and ethical criteria. It can identify scenarios that effectively meet measurable requirements and align well with human values, and vice versa.   

“We don’t want to spend all our resources on random evaluations. So, it is very important to guide the framework toward the test cases we care the most about,” Li says.

Importantly, SEED-SET does not need pre-existing evaluation data, and it adapts to multiple objectives.

For instance, a power grid may have several user groups, including a large rural community and a data center. While both groups may want low-cost and reliable power, each group’s priority from an ethical perspective may vary widely.

These ethical criteria may not be well-specified, so they can’t be measured analytically.

The power grid operator wants to find the most cost-effective strategy that best meets the subjective ethical preferences of all stakeholders.

SEED-SET tackles this challenge by splitting the problem into two, following a hierarchical structure. An objective model considers how the system performs on tangible metrics like cost. Then a subjective model that considers stakeholder judgements, like perceived fairness, builds on the objective evaluation.

“The objective part of our approach is tied to the AI system, while the subjective part is tied to the users who are evaluating it. By decomposing the preferences in a hierarchical fashion, we can generate the desired scenarios with fewer evaluations,” Parashar says.

Encoding subjectivity

To perform the subjective assessment, the system uses an LLM as a proxy for human evaluators. The researchers encode the preferences of each user group into a natural language prompt for the model.

The LLM uses these instructions to compare two scenarios, selecting the preferred design based on the ethical criteria.

“After seeing hundreds or thousands of scenarios, a human evaluator can suffer from fatigue and become inconsistent in their evaluations, so we use an LLM-based strategy instead,” Parashar explains.

SEED-SET uses the selected scenario to simulate the overall system (in this case, a power distribution strategy). These simulation results guide its search for the next best candidate scenario to test.

In the end, SEED-SET intelligently selects the most representative scenarios that either meet or are not aligned with objective metrics and ethical criteria. In this way, users can analyze the performance of the AI system and adjust its strategy.

For instance, SEED-SET can pinpoint cases of power distribution that prioritize higher-income areas during periods of peak demand, leaving underprivileged neighborhoods more prone to outages.

To test SEED-SET, the researchers evaluated realistic autonomous systems, like an AI-driven power grid and an urban traffic routing system. They measured how well the generated scenarios aligned with ethical criteria.

The system generated more than twice as many optimal test cases as the baseline strategies in the same amount of time, while uncovering many scenarios other approaches overlooked.

“As we shifted the user preferences, the set of scenarios SEED-SET generated changed drastically. This tells us the evaluation strategy responds well to the preferences of the user,” Parashar says.

To measure how useful SEED-SET would be in practice, the researchers will need to conduct a user study to see if the scenarios it generates help with real decision-making.

In addition to running such a study, the researchers plan to explore the use of more efficient models that can scale up to larger problems with more criteria, such as evaluating LLM decision-making.

This research was funded, in part, by the U.S. Defense Advanced Research Projects Agency.

de MIT News https://ift.tt/uo4xFUj

Preview tool helps makers visualize 3D-printed objects

Designers, makers, and others often use 3D printing to rapidly prototype a range of functional objects, from movie props to medical devices. Accurate print previews are essential so users know a fabricated object will perform as expected.

But previews generated by most 3D-printing software focus on function rather than aesthetics. A printed object may end up with a different color, texture, or shading than the user expected, resulting in multiple reprints that waste time, effort, and material.

To help users envision how a fabricated object will look, researchers from MIT and elsewhere developed an easy-to-use preview tool that puts appearance first.

Users upload a screenshot of the object from their 3D-printing software, along with a single image of the print material. From these inputs, the system automatically generates a rendering of how the fabricated object is likely to look.

The artificial intelligence-powered system, called VisiPrint, is designed to work with a range of 3D-printing software and can handle any material example. It considers not only the color of the material, but also gloss, translucency, and how nuances of the fabrication process affect the object’s appearance.

Such aesthetics-focused previews could be especially useful in areas like dentistry, by helping clinicians ensure temporary crowns and bridges match the appearance of a patient’s teeth, or in architecture, to aid designers in assessing the visual impact of models.

“3D printing can be a very wasteful process. Some studies estimate that as much as a third of the material used goes straight to the landfill, often from prototypes the user ends of discarding. To make 3D printing more sustainable, we want to reduce the number of tries it takes to get the prototype you want. The user shouldn’t have to try out every printing material they have before they settle on a design,” says Maxine Perroni-Scharf, an electrical engineering and computer science (EECS) graduate student and lead author of a paper on VisiPrint.

She is joined on the paper by Faraz Faruqi, a fellow EECS graduate student; Raul Hernandez, an MIT undergraduate; SooYeon Ahn, a graduate student at the Gwangju Institute of Science and Technology; Szymon Rusinkiewicz, a professor of computer science at Princeton University; William Freeman, the Thomas and Gerd Perkins Professor of EECS at MIT and a member of the Computer Science and Artificial Intelligence Laboratory (CSAIL); and senior author Stefanie Mueller, an associate professor of EECS and Mechanical Engineering at MIT, and a member of CSAIL. The research will be presented at the ACM CHI Conference on Human Factors in Computing Systems.

Accurate aesthetics

The researchers focused on fused deposition modeling (FDM), the most common type of 3D printing. In FDM, print material filament is melted and then squirted through a nozzle to fabricate an object one layer at a time.

Generating accurate aesthetic previews is challenging because the melting and extrusion process can change the appearance of a material, as can the height of each deposited layer and the path the nozzle follows during fabrication.

VisiPrint uses two AI models that work together to overcome those challenges.

The VisiPrint preview is based on two inputs: a screenshot of the digital design from a user’s 3D-printing software (called “slicer” software), and an image of the print material, which can be taken from an online source or captured from a printed sample.

From these inputs, a computer vision model extracts features from the material sample that are important for the object’s appearance.

It feeds those features to a generative AI model that computes the geometry and structure of the object, while incorporating the so-called “slicing” pattern the nozzle will follow as it extrudes each layer.

The key to the researchers’ approach is a special conditioning method. This involves carefully adjusting the inner workings of the model to guide it, so it follows the slicing pattern and obeys the constraints of the 3D-printing process.

Their conditioning method utilizes a depth map that preserves the shape and shading of the object, along with a map of the edges that reflects the internal contours and structural boundaries.

“If you don’t have the right balance of these two things, you could use up with bad geometry or an incorrect slicing pattern. We had to be careful to combine them in the right way,” Perroni-Scharf says.

A user-focused system

The team also produced an easy-to-use interface where one can upload the required images and evaluate the preview.

The VisiPrint interface enables more advanced makers to adjust multiple settings, such as the influence of certain colors on the final appearance.

In the end, the aesthetic preview is intended to complement the functional preview generated by slicer software, since VisiPrint does not estimate printability, mechanical feasibility, or likelihood of failure.

To evaluate VisiPrint, the researchers conducted a user study that asked participants to compare the system to other approaches. Nearly all participants said it provided better overall appearance as well as more textural similarity with printed objects.

In addition, the VisiPrint preview process took about a minute on average, which was more than twice as fast as any competing method.

“VisiPrint really shined when compared to other AI interfaces. If you give a more general AI model the same screenshots, it might randomly change the shape or use the wrong slicing pattern because it had no direct conditioning,” she says.

In the future, the researchers want to address artifacts that can occur when model previews have extremely fine details. They also want to add features that allow users to optimize parts of the printing process beyond color of the material.

“It is important to think about the way that we fabricate objects. We need to continue striving to develop methods that reduce waste. To that end, this marriage of AI with the physical making process is an exciting area of future work,” Perroni-Scharf says.

“‘What you see is what you get’ has been the main thing that made desktop publishing ‘happen’ in the 1980s, as it allowed users to get what they wanted at first try. It is time to get WYSIWYG for 3D printing as well. VisiPrint is a great step in this direction,” says Patrick Baudisch, a professor of computer science at the Hasso Plattner Institute, who was not involved with this work.

This research was funded, in part, by an MIT Morningside Academy for Design Fellowship and an MIT MathWorks Fellowship.

de MIT News https://ift.tt/nC3YmkK

Turning muscles into motors gives static organs new life

What if a technology could reanimate parts of the body that have lost their connection to the brain — like a bladder that can no longer empty due to a spinal cord injury, or intestines that can’t push food forward due to Crohn’s disease? What if this technology could also send sensations such as hunger or touch back to the brain?

New MIT research offers a glimpse into this future. In an open-access study published today in Nature Communications, the researchers introduce a novel myoneural actuator (MNA) that reprograms living muscles into fatigue-resistant, computer-controlled motors that can be implanted inside the body to restore movement in organs.

“We’ve built an interface that leverages natural pathways used by the nervous system so that we can seamlessly control organs in the body, while also enabling the transmission of sensory feedback to the brain,” says Hugh Herr, senior author of the study, a professor of media arts and sciences at the MIT Media Lab, co-director of the K. Lisa Yang Center for Bionics, and an associate member of the McGovern Institute for Brain Research at MIT. The study was co-led by Herr’s postdoc Guillermo Herrera-Arcos and former postdoc Hyungeun Song.

By repurposing existing muscle in the body, the researchers have developed the first “living” implant that uses rewired sensory nerves to revive paralyzed organs — which may present a new genre of medicine, where a person’s own tissue becomes the hardware.

Rewiring the brain-body interface

Many scientists have toiled to restore function in paralyzed organs, but it’s extremely challenging to design a technology that both communicates with the nervous system and doesn't fatigue over time. Some have tried to insert miniaturized actuators — small machines that can power bionic limbs — into the body. However, Herrera-Arcos says, “it’s hard to make actuators at the centimeter level, and they aren’t very efficient.” Others have focused on creating muscle tissue in the lab, but building muscles cell by cell is time-intensive and far from ready for human use.

Herr’s team tried something different.

“We engineered existing muscles to become an actuator, or motor, that reinstates motion in organs,” says Song.

To do this, the researchers had to navigate the delicate dynamics within the nervous system. The actuator would have to interface with the nervous system to work properly, but it must also somehow evade the brain’s control. “You don’t want the brain to consciously control the muscle actuator because you want the actuator to automatically control an organ, like the heart,” explains Herrera-Arcos. Establishing a computer-controlled muscle to move organs could ensure automatic function and also bypass damaged brain pathways.

Incorporating motor neurons into the actuator may help generate movement, but these neurons are directly controlled by the brain. “Sensory neurons, however, are wired to receive, not to command,” explains Song. “We thought we could leverage this dynamic and reroute motor signals through sensory fibers, making a computer — rather than the brain — the muscle’s new command center.”

To achieve this, sensory nerves would need to fuse fluidly with muscle, and scientists had not yet determined if this was possible. Remarkably, when the team replaced motor nerves in rodent muscle with sensory ones, “the sensory nerves re-innervated the muscles and formed functional synapses. It’s a tremendous discovery,” says Herrera-Arcos.

Sensory neurons not only enabled the use of a digital controller, but also helped curb muscle fatigue — increasing fatigue resistance in rodent muscle by 260 percent compared to native muscles. That’s because muscle fatigue depends largely on the diameter of the axons, or cable-like projections that innervate muscles. Motor neuron axons vary greatly in size, and when a motor nerve is electrically stimulated, the largest axons fire first — exhausting the muscle quickly. However, sensory axons are all nearly the same size, so the signal is broadcast more evenly across muscle fibers, avoiding fatigue, explains Herrera-Arcos.

Designing a biohybrid system

They combined all of these elements into a fatigue-resistant biohybrid motor called a myoneural actuator (MNA). By wrapping their actuator around a paralyzed intestine in a rodent, the researchers reinstated the organ’s squeezing motion. They also successfully controlled rodent calf muscles in an experiment designed to mimic residual muscle in human lower-limb amputations. Importantly, the MNA system transmitted sensory signals to the brain. “This suggests that our technology could seamlessly link organs to the brain. For example, we might be able to make a paralyzed stomach relay hunger,” explains Song.

Bringing their MNA to clinic will require further testing in larger animal models, and eventually, humans. But if it passes the regulatory gauntlet, their system could pave a smoother and safer path toward reviving static organs. Implanting MNAs would require a surgery that is already commonplace in clinic, the researchers say, and their system might be simpler and safer to implement than mechanical devices or organ transplants that introduce foreign material into the body.

The team is hopeful that their new technology could improve the lives of millions living with organ dysfunctions. “Today’s solutions are mostly synthetic: pacemakers and other mechanical assist devices. A living muscle actuator implanted alongside a weakened organ would be part of the body itself. That is a category of medicine different from anything seen in clinic,” explains Herrera-Arcos.

Song says that skin is of special interest. “Hypothetically, we could wrap MNAs around skin grafts to relay tactile feedback, such as strain or tension, which is currently missing for users of prostheses.” Their technology could even augment virtual reality systems, too. “The idea is that, if we couple the MNA system to skin and muscles, a person could feel what their virtual avatar is touching even though their real body isn’t moving,” says Song.

“Our research is on the brink of giving new life to various parts and extensions of the body,” adds Herrera-Arcos. “It’s exciting to think that our system could enhance human potential in ways that once only belonged to the realm of science fiction.”

This research was funded, in part, by the Yang Tan Collective at MIT, K. Lisa Yang Center for Bionics at MIT, Nakos Family Bionics Research Fund at MIT, and the Carl and Ruth Shapiro Foundation.

de MIT News https://ift.tt/bVg2R9d