Georgia Tech researchers have developed Spherephones, a wearable system that uses spatialized music instead of alarms to help people anticipate movement around them — such as approaching robots — by conveying direction, distance, and timing through sound. Created in the Robotic Musicianship Lab, the technology aims to improve safety and awareness in human-robot environments while also showing promise for applications in virtual reality, gaming, and assistive navigation.

Read more »

For Dr. David Chin Yee, a Georgia Tech microneedle is opening new possibilities for treating debilitating eye disease. Developed over two decades, it delivers medication precisely where it’s needed, helping to preserve vision, ease pain, and prolong relief. For patients, that can mean fewer treatments — and more time for daily life.

Read more »

In just one course, Georgia Tech student Diya Godavarti helped develop a tool that could improve workers' responses to chemical spills or open containers.

Godavarti, then a second-year chemical and biomolecular engineering (ChBE) student, joined a course on chemical equity focused on reducing chemical exposure in vulnerable communities. The class, part of Georgia Tech’s Vertically Integrated Projects (VIP) program, embeds students in long-term research teams that span disciplines and semesters.

She and her classmates developed a computational model that estimates how dangerous chemical vapors build up in enclosed spaces, such as tanker trucks. Their work culminated in a paper, “Modeling Time-Dependent Chemical Concentrations in Confined Spaces for General Safety Applications,” published recently in ACS Chemical Health & Safety.

For Godavarti, the experience helped clarify her future career endeavors. 

“I was always motivated to keep going on this project because chemical equity is something I genuinely care about,” she said. “I realized I really enjoyed working on open-ended projects after this class, and this confirmed my desire to pursue a Ph.D.”

She will begin her ChBE doctoral studies at Northwestern University this fall.

Bridging Disciplines

The VIP class grew out of a gap between research labs and reality. Pamela Pollet, a faculty member in Tech’s School of Chemistry and Biochemistry, is used to working in controlled lab settings with safety measures like vent hoods. But after she consulted on a project where commercial workers were accidentally exposed to harmful chemicals, she started to think about safety differently.

“There was a disconnect between what we do with chemicals in our controlled environments, which we understand very well, and how people interact with chemicals every day,” she said.

To bridge that gap, Pollet partnered with Jenny Houlroyd, the occupational group health manager of the Enterprise Innovation Institute’s (EI2) Safety, Health, and Environmental Services Program. Houlroyd works with Georgia businesses to reduce workplace hazards and protect employee health.

“We realized how siloed this work can be,” Houlroyd said. “Chemical safety researchers and chemists often operate separately, but their skills are complementary. That’s how we came up with the idea for the class.”

The VIP format made that collaboration possible. The 20-student team included majors from chemistry, biochemistry, biology, computer science, neuroscience, and ChBE. In addition to research, students heard from guest speakers — including journalists, lawyers, and policymakers — whose work intersects with chemical safety.

Modeling a Real-World Risk

The students focused on a practical problem in industrial hygiene: quickly estimating a person’s exposure to hazardous chemicals after a spill or open container in a confined space.

“If you hire an industrial hygienist like me, it’s going to take time to schedule, and it’s going to be expensive,” Houlroyd said. “But if there’s a chemical spill event happening, you need that safety data right away.”

To address this, the students built a computational model that simulates how chemicals evaporate and spread through air in enclosed environments. Using benzene, a common solvent, as a test case, the model predicts how benzene concentrations change over time, from minutes to hours after a spill or residual pool in an enclosed space. It can also estimate exposure at different heights, accounting for whether someone is standing upright or crouching in a chemical-heavy area.

“We’re addressing important gaps in modeling chemical exposures,” said John Pederson, a chemistry Ph.D. student who mentored the student team. “There’s been strong work in industrial settings, but less attention to environments found in transportation, agriculture, and sanitation, for example. It's an easily overlooked fact that working with paints, coatings, cleaning solutions, and other solvents presents a risk of acute or chronic exposure.”

From Classroom to Impact

The team ultimately hopes to make the model widely accessible and create a user-friendly app. While that work is ongoing, Pollet and Houlroyd say the project already demonstrates the power of interdisciplinary learning.

“This project was a very nice overlap of our fields,” Pollet said. “It helps students understand real-world scenarios in a way you can’t replicate in a traditional classroom.”

For Houlroyd, the collaboration also extended her impact beyond the field.

“I work for EI2, and we’re primarily external-facing and helping businesses out across the state of Georgia, but this has been a great opportunity to take what I'm learning in the field and then share it with the students,” she said. “I am so proud of the students. To see them take this big issue and make it into something the industry can use is so exciting.”

Modeling Time-Dependent Chemical Concentrations in Confined Spaces for General Safety Applications

Diya Godavarti, Waynell Simbafo, John Pederson, Jenny Houlroyd, and Pamela Pollet

ACS Chemical Health & Safety Article ASAP

DOI: 10.1021/acs.chas.6c00021

News Contact

A bicycle robot from the Robotics and AI Institute (RAI) in Cambridge, Mass., has become the first to perform an unassisted acrobatic front flip.

RAI calls the bicycle robot an ultra-mobility vehicle (UMV). It can reach a height of 3 feet and can jump from the floor onto a platform.

The contributions of a Georgia Tech Ph.D. student helped make these feats possible through a robot control policy he developed.

Jeonghwan Kim, who is pursuing a Ph.D. in robotics under the advisement of Associate Professor Sehoon Ha, spent two semesters interning at RAI. His task was to design a policy to teach the UMV to land after a flip.

The result was iterative motion imitation (IMI), a novel method that imitates flip trajectories generated from prior examples. Kim said the robot bases its flip on a demonstration, and human engineers reconstruct and refine the flip path through simulation to fill in the gaps.

“To guide the robot to flip, we started with an imperfect trajectory generated by a motor-based controller and then ran simulations,” Kim said. “It’s an unstable trajectory, but we use it as a guide to train a single policy that can track it as it lands and tries to balance itself.”

Sticking the Landing

Kim interned under the supervision of Shamel Fahmi, a research scientist at the RAI Institute. RAI has been developing the UMV for nearly three years.

“We wanted to work on a different robot morphology that wasn’t legs or legs with wheels,” Fahmi said. “That’s when we thought of working with bikes. 

“We want to merge the athleticism of (Boston Dynamics’) Atlas with the mobility of a bike. We wanted a robot that can go anywhere, do parkour, and acrobatics.”

Fahmi said that before Kim arrived, the research team had trouble getting the UMV to land consistently without breaking or falling.

The UMV has two joints — an upper and a lower. The upper joint contains the motors and pulls the lower joint along as it propels into the air. The problem is getting the lighter lower joint to absorb the impact of landing without being crushed by the heavier upper joint.

“That’s what brings reinforcement learning into the equation,” Fahmi said. “We teach the robot to minimize its impact on the ground to land gracefully.”

Fahmi said that Kim proved the imitation examples the robot learns from don’t have to be perfect. The process takes some time, but all it needs is a rough idea to get started.

“You can have an imperfect sketch and then constantly refine it,” Fahmi said. “The first time, it’s not going to go well. 

“We don’t care about torque or power limits as long as it does the motion. Then we’ll have a slightly better reference, repeat it, and imitate it again. In every iteration, we can add more parameters.”

Up Against the Clock

Kim said he felt the pressure of time constraints during his two semesters with RAI as he worked to achieve consistent, successful landings. Even though he had multiple UMVs to experiment with, they broke down dozens of times. Each time one broke, a hardware team at RAI had to repair it.

“There was a lot of pressure to not only get this working before my internship ended, but also knowing there are costs behind every failed attempt, and every time the robot breaks, it takes time to repair it,” Kim said. 

“It took almost five months for it to land without breaking. Then we needed two more months for it to stay balanced after the landing. It requires a lot of engineering effort to achieve a robust control policy for a safe flip.”

By the time Kim left RAI, the IMI policy had achieved consistent, seamless landings.

“The jump right now is what we call the visitor demo,” Fahmi said. “If there are guests coming over to see it, we want to show them something that is extremely impressive, but also, more importantly, extremely reliable. It never fails.

“It was only possible because of the huge effort we put into designing, maintaining, and continuously improving the robot.”

Kim authored a paper on his framework and will present it at this week’s International Conference on Robotics and Automation (ICRA) in Vienna.

For more information about the UMV project, please visit the RAI blog or watch their video on YouTube.

Someone with no computing experience may soon be able to remotely control a robot from anywhere on the planet using a smartphone, thanks to new technology developed by Georgia Tech.

The new technology is also set to revolutionize the scale of policy training data collection, which is essential to advancing robotic capabilities and meeting growing production demand.

COBALT is a mobile app that turns smartphones into controllers for robot arms. With a secure Wi-Fi connection to a server, users can move their phones in any direction, and the robot arm will mirror the motion — from anywhere in the world.

Ayush Agarwal, a Ph.D. student in Georgia Tech’s School of Interactive Computing who leads a research team developing COBALT, said it works like the games people play on smartphones. Users can press a button to have the arm grasp an object, move it, and release it with another button.

Agarwal conducted several user studies with participants in nine countries who remotely operated robot arms inside Georgia Tech’s People, AI & Robotics (PAIR) Lab. The lab is directed by Assistant Professor Animesh Garg, who advises Agarwal.

“We built an entire distribution system for remote teleoperation scaled to where we had people from Indonesia, India, and Pakistan operating for us,” Agarwal said. “They were novice operators who had never done it before. By collecting data from these new users, we showed that we can train policies to automate certain tasks.”

Garg envisions a world where data collection for policy training is done through crowdsourcing. He began working toward this goal 10 years ago as a postdoc at Stanford University, when he developed RoboTurk, an earlier version of COBALT.

“There is a large-scale data collection requirement for mass robot production to be possible, and it will not be solved purely through simulation,” Garg said.

“Our idea was, what if we could get almost every person on the planet to be a passive source for data collection? There are almost five billion people who have smartphones and know how to use them.”

Education and Economy Impact

Another major implication of COBALT could be expanded access to CS and robotics education.

Students can learn to operate a robot remotely in any classroom. In fact, Garg and his lab recently hosted students from Midtown High School in Atlanta to demonstrate COBALT and let them control robot arms from a phone.

Garg also sees the possibility of a “gig economy” in which people pay remote operators to control assistive robots in their homes and complete household chores for them.

“It could be Uber for robots,” he said. “People who want to log onto the platform can do so at their convenience and for as long as they want.”

Companies with robot-dependent labor tasks could also use the platform to enable human oversight.

“If I deploy a robot in a factory that achieves high autonomy for most tasks, but there are still times it needs help, a human could operate the robot from anywhere in the world,” Garg said.

Building a Network

Agarwal’s studies showed that people prefer to interact with and control a robot using a smartphone rather than virtual reality (VR) headsets, controllers, keyboards, mice, or other devices.

“The phone is a more intuitive interface and can provide data quality that’s on par with other commonly used devices,” he said.

Agarwal also said there is minimal latency in the video feed sent back to operators on the other side of the world. That’s because the amount of data being processed is small.

The data is carried over Web Real-Time Communication (WebRTC), the same technology used by many streaming services and web conferencing platforms such as Zoom and Google Meet.

“There’s a connection from your phone to the teleoperation server, which is connected to the robots,” Agarwal said.

“Then there’s another connection from the teleoperation server back to the user, which allows for a video stream. We need low latency on both because you don’t want the user to move their phone and wait 10 seconds to see the visual feed.”

Agarwal is the co-lead author of a paper on COBALT that is being presented at the IEEE International Conference on Robotics and Automation this week in Vienna. He said the paper stands out because it has moved from theory to the implementation of an entire distribution network. 

“The real novelty of our paper is the systems that we build around it to actually support the scaling of remote operation and data collection at a global level,” he said. 

Augmented reality (AR) devices like smart glasses may soon be able to predict where a user will look and provide an enhanced interactive experience.

Fiona Ryan, a Ph.D. student in Georgia Tech’s School of Interactive Computing, is pioneering research that tracks and predicts user gaze from a first-person perspective in 3D environments.

Currently, most AR devices react to where users look, playing catch-up. Ryan’s method could give these devices a heads-up and make the user experience more seamless.

“It allows an AR system to anticipate what the person will interact with next and where they’re going to look next so it can proactively render the experience,” she said.

Ryan is the lead author of the paper Forecasting 3D Scanpaths in Egocentric Video, which she will present next week at the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) in Denver.

While there is existing research on predicting user gaze from 2D still images, her work is the first to address the issue through a 3D framework.

“Because we live in a 3D world and people are dynamically moving around from multiple points of view, we need to predict gaze in 3D rather than 2D,” she said. “What we’re seeing is a path of the person’s attention in 3D through space. Our paper is the first to attempt to model this.”

Ryan conducted most of the research while interning at Meta, where she used data from Meta’s Aria Digital Twin dataset. The dataset contains first-person video footage of users interacting with objects in an apartment.

“We chose that dataset because it has a high-fidelity 3D reconstruction of a full environment, which helps us get a ground-truth 3D gaze,” she said. “We can trace eye movement and see how it intersects with the environment.”

A video demonstration of Ryan’s work shows her software tracking a user’s path toward a table with a cup on it. Once the user picks up the cup, the software correctly predicts the direction the user will turn next.

“When we look at a scene, we don’t take in everything in full detail all at once,” she said. “We fixate on certain areas, and our gaze is a sequence of fixations, which might depend on what we’re trying to do. If we want to pick up a cup, we might look toward that and then the next step would be looking at where we’re going to put it down.”

Ryan said the software can predict, on average, up to three seconds into the future — and as far as 10 seconds in some cases. That’s enough time for the AR system to proactively render a more enhanced environment.

“We’re not looking that far into the future right now, but it would be interesting to explore longer forecasting windows,” she said. “I think potential futures would diverge pretty quickly, so we’re trying to explore what can reasonably be predicted from a short segment of a person looking and moving through space.”

Ryan said her paper served as a proof-of-concept, and that there is still much future work to be done. She already has some ideas.

“I think future models can include different scenarios to help narrow down possibilities. Sometimes a person’s gaze stays on one thing for a long time. If we know what someone is trying to do, we’ll have a better idea of the likely path their attention might go.”

There could also be future implications for her work in robotics research.

“It could potentially be used for training algorithms for robots to emulate active human perception. If we can understand what a person looks at as they perform a task, we could use that to facilitate a robot learning to do that same task.” 

Augmented reality (AR) devices like smart glasses may soon be able to predict where a user will look and provide an enhanced interactive experience.

Fiona Ryan, a Ph.D. student in Georgia Tech’s School of Interactive Computing, is pioneering research that tracks and predicts user gaze from a first-person perspective in 3D environments.

Currently, most AR devices react to where users look, playing catch-up. Ryan’s method could give these devices a heads-up and make the user experience more seamless.

“It allows an AR system to anticipate what the person will interact with next and where they’re going to look next so it can proactively render the experience,” she said.

Ryan is the lead author of the paper Forecasting 3D Scanpaths in Egocentric Video, which she will present next week at the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) in Denver.

While there is existing research on predicting user gaze from 2D still images, her work is the first to address the issue through a 3D framework.

“Because we live in a 3D world and people are dynamically moving around from multiple points of view, we need to predict gaze in 3D rather than 2D,” she said. “What we’re seeing is a path of the person’s attention in 3D through space. Our paper is the first to attempt to model this.”

Ryan conducted most of the research while interning at Meta, where she used data from Meta’s Aria Digital Twin dataset. The dataset contains first-person video footage of users interacting with objects in an apartment.

“We chose that dataset because it has a high-fidelity 3D reconstruction of a full environment, which helps us get a ground-truth 3D gaze,” she said. “We can trace eye movement and see how it intersects with the environment.”

A video demonstration of Ryan’s work shows her software tracking a user’s path toward a table with a cup on it. Once the user picks up the cup, the software correctly predicts the direction the user will turn next.

“When we look at a scene, we don’t take in everything in full detail all at once,” she said. “We fixate on certain areas, and our gaze is a sequence of fixations, which might depend on what we’re trying to do. If we want to pick up a cup, we might look toward that and then the next step would be looking at where we’re going to put it down.”

Ryan said the software can predict, on average, up to three seconds into the future — and as far as 10 seconds in some cases. That’s enough time for the AR system to proactively render a more enhanced environment.

“We’re not looking that far into the future right now, but it would be interesting to explore longer forecasting windows,” she said. “I think potential futures would diverge pretty quickly, so we’re trying to explore what can reasonably be predicted from a short segment of a person looking and moving through space.”

Ryan said her paper served as a proof-of-concept, and that there is still much future work to be done. She already has some ideas.

“I think future models can include different scenarios to help narrow down possibilities. Sometimes a person’s gaze stays on one thing for a long time. If we know what someone is trying to do, we’ll have a better idea of the likely path their attention might go.”

There could also be future implications for her work in robotics research.

“It could potentially be used for training algorithms for robots to emulate active human perception. If we can understand what a person looks at as they perform a task, we could use that to facilitate a robot learning to do that same task.” 

News Contact

This research is shared jointly with the Ohio State University newsroom.

Scientists have captured the most detailed structural images to date of a specific type of protein’s DNA repair process. The research could reveal ways to inhibit the effects of the BRCA1 and BRCA2 gene mutations that heighten the risk for breast, ovarian, and other cancers.

“This work lets us see, step by step, one mechanism by which cancer cells could manage to repair their DNA when BRCA genes mutate and fail,” says study co-author Vicki Wysocki, who is chair of the Georgia Tech School of Chemistry and Biochemistry. “By capturing this process in detail, this study opens the door to understanding how those cancerous cells survive and how treatments might disrupt that mechanism.”

Designated as a Breakthrough Article, the study Mechanism of single-strand annealing from native mass spectrometry and cryo-EM structures of RAD52 homolog Mgm101 was recently published in Nucleic Acids Research.

In addition to Wysocki, who is a professor in the School of Chemistry and Biochemistry and a professor emerita at Ohio State University, the Georgia Tech research team included co-first author Zihao Qi, a Ph.D. candidate in the Wysocki Lab.

They were joined by Ohio State researchers co-first author Carter Wheat and senior author Charles Bell, who is a professor of biological chemistry and pharmacology in the College of Medicine. Additional authors include Metro High School student Miqdad Hussain and CAS researcher Katerina Zakharova.

When BRCA Fails

Normally, BRCA genes help prevent cancer by acting as tumor suppressors — producing proteins that help repair broken DNA. When cancer cells lack the tumor-suppression function of normal BRCA genes, research has shown that a protein called RAD52 performs DNA repair.

Since RAD52 allows cancer cells to survive and replicate without tumor suppression, researchers have wondered if blocking it would kill the cancerous cells. Blocking RAD52, however, requires fully understanding its repair activities, which have been difficult to capture with even the most sophisticated techniques. 

DNA strands break every day in cells, which is why proteins exist to fix the breaks and keep cellular processes running smoothly, the team says. But because repairs must happen quickly and human proteins are often more complex than their ancestral counterparts, even the most advanced imaging equipment can’t capture every step in the process.

In order to understand RAD52 better, the research team turned to its ancestral protein, Mgm101, to observe several key steps in its DNA repair process.

A Clearer Image

The team decided to leverage multiple types of imaging. Wysocki’s lab at Georgia Tech conducted native mass spectrometry and mass photometry, using light to measure masses of protein-DNA complexes. The results showed that the ancestral protein Mgm101 assembled from a single copy of itself into a large multi-unit ring composed of 19 copies of the protein.

“This ring is essentially a template,” Wysocki explains. “The first strand of DNA can come down, and then the second strand comes on and starts being annealed to the first strand.” Annealing occurs when two single strands of DNA come together to form the characteristic double helix structure.

The findings were supported by what Bell’s lab determined using cryogenic electron microscopy, observing structures floating in solution and frozen in a thin layer of ice.

“RAD52 high-resolution structures have been determined with single-stranded DNA, but not with the two DNAs that it’s trying to anneal,” Bell says. “Its job is to bind single-stranded DNA and anneal it to its complement sequence. It’s been captured structurally, but only in a few states relevant to the reaction.”

“Here, we have more of the states along the full pathway from substrate, to intermediate and product. And the duplex intermediate is a conformation that’s never been seen before.”

Previously, researchers were unsure if this DNA repair process used one protein ring or two rings working together, the team says. Their findings show that just one ring is used — and that this is likely consistent across different species.

Paths to Treatment

Next, the team plans to try capturing the same phases of the DNA repair process with RAD52 from humans. A clearer understanding of how this family of proteins binds to DNA strands and coaxes them back together after a break provides insights for drug targets that could halt the process in cancer cells empowered by mutated BRCA genes, they say.

“It’s still a proposed mechanism: Just because we see these snapshots of the process doesn’t mean we know all the details, but we do have the best snapshots for any protein that does this single-strand annealing,” says Bell. “This focuses our strategies for drug development.”

DOI: https://doi.org/10.1093/nar/gkag320

Funding: This work was supported by the U.S. National Science Foundation and the National Institutes of Health. The cryo-EM data were collected at Ohio State’s Center for Electron Microscopy and Analysis and processed using the Ohio Supercomputer Center.

News Contact

A new grant from the Georgia Research Alliance (GRA) is backing an ambitious effort by Georgia Tech scientists to accelerate the development of human antibody therapies — a class of medicines that has transformed treatment across cancer, autoimmune disease, and infectious illness, yet it cannot be generated against many disease targets.

The $250,000 funding award, made through GRA’s Innovation and Entrepreneurship (I&E) program, supports the translational work of Ankur Singh, Professor in the George W. Woodruff School of Mechanical Engineering and the Wallace H. Coulter Department of Biomedical Engineering, and Andrés García, Regents’ Professor in Mechanical Engineering and the Executive Director of the Parker H. Petit Institute for Bioengineering and Bioscience. Singh and García are collaborating to develop functional human antibodies against some of the most difficult-to-treat diseases. While antibody therapies already benefit an estimated 20 million patients worldwide, fewer than 10 percent of discovery efforts ultimately yield candidates suitable for clinical use.

This shortfall spans major disease areas — from oncology and autoimmune disorders to heart and metabolism-related conditions and neurological and infectious diseases — limiting therapeutic options for patients. The challenge lies not only in identifying candidate antibodies, but in engineering them to function reliably in the human body.

“The I&E program exists to bridge the gap between a discovery that works in the lab and one that can anchor a company,” said Justin Burns, Chief Innovation Officer and Vice President for Innovation and Entrepreneurship at GRA. “Singh and García are tackling a problem the field has faced for decades: A significant fraction of drug targets remains inaccessible to antibody-based therapies. Our goal is to help move bold, high-potential science toward real-world impact.”

GRA’s model targets a well-known bottleneck in translation. While university labs generate promising technologies, many stall before reaching the marketplace due to a lack of validation and early-stage development. 

Singh and García aim to overcome this barrier by using a proprietary antibody-engineering framework developed in Singh’s laboratory, and supported by an earlier GRA grant. The objective is straightforward: Increase the success rate of discovery efforts so more antibody candidates can advance toward clinical use.

“The implications extend well beyond our laboratory,” said Singh. “By expanding the pipeline of functional human antibodies, we can begin to address diseases that currently lack durable treatment options. GRA’s support is transformative — not only for advancing the science, but for positioning Georgia as a leader in biotechnology innovation.”

The project is built with real-world use in mind, aiming to turn the research into a new company and eventually a clinical product. By testing the idea early and lowering risk, the team hopes to attract investment and move the technology quickly beyond the Institute. 

García emphasized the translational vision of the work. 

“This is a transformative platform technology that overcomes major bottlenecks in antibody discovery and will accelerate and increase the efficiency of this powerful class of therapeutics,” he said.

“This effort is about rethinking how we design antibodies from the ground up — integrating biological insight with engineering principles to produce molecules that are not just viable, but clinically meaningful,” he said. “With GRA’s support, we can de-risk early discovery and create a clearer path from promising concepts to therapies that reach patients.”

 Tracey Mullen, a seasoned biopharma executive, entrepreneur, and antibody discovery and engineering leader currently serving as Chief Strategy Officer at Mosaic Biosciences, is advising the team on translational strategy, commercial development, and company formation. 

“The ability to rapidly generate functional human antibodies in physiologically relevant systems could meaningfully change how therapeutic discovery is approached,” Mullen said. “By moving beyond largely empirical, animal- or screening-heavy workflows and incorporating human-specific, mechanism-informed evaluation earlier in the process, this platform has the potential to generate more relevant antibody candidates and create a stronger path from discovery concept to translational development.”

As global demand for advanced therapeutics grows, efforts like this reflect a broader shift in how innovation moves from bench to bedside — one driven not only by scientific ingenuity, but by targeted investment at critical early stages.

News Contact