Julia Ebert creates, builds and learns. But her varied interests – in neuroscience, coding, baking, ice-rink sports, web design and robotics – make her hard to pin down, even for those who know her best. “I had no idea what you were going to do,” Ebert’s father once told her. “You were interested in everything.”
It’s no wonder then that Ebert merged a behavioral neuroscience major with computer programming at Northeastern University in Boston. Now the Department of Energy Computational Science Graduate Fellowship (DOE CSGF) recipient is combining coding and biology again, developing swarms of small robots that collaborate to perform tasks. Someday similar groups may do jobs that bore or endanger humans.
Ebert is part of Radhika Nagpal’s Harvard University lab, where researchers take lessons from biology, such as termites building collectively or bacteria cooperating, to make groups of robots that work well together. So far Ebert has focused on collective decision-making using Harvard-developed Kilobots, half-dollar-sized robots with limited intelligence, sensing and communication capacities that are deployed in groups of up to a thousand. She initially examined how 100 of them used environmental cues to make collective decisions.
To start, Ebert uses computers to simulate test runs of her experiments, letting her identify potential pitfalls and try out scenarios before setting up longer trials. She has shown that the Kilobots can use simple sensing and communication to detect colors and make decisions about environmental features. “You’re taking advantage of the fact that even though you’re small and can’t see much, everyone else is working on the same problem,” Ebert says.
Someday, robot swarms could handle a range of dirty, dull and dangerous tasks, such as setting up a habitat for humans on Mars, she says. But to do so, the devices must deal with complex situations in which one set of decisions leads to others. “One piece of this bigger puzzle that we’re trying to sort out is how you get more complex behavior out of groups of robots,” she says.
Besides herding a robot gaggle, Ebert explores a range of algorithmic approaches for solving problems. She wants to find strategies groups of devices could use in many scenarios, not just in a single situation. She’s designed and built her own devices, nicknamed LARVAbots, which mimic insects crawling over each other, to see whether the group could stay together and move faster than an individual. In experiments, the machines coordinated their actions and even enabled one of them to escape from a walled track.
Ebert’s many side projects often have programming and web-design components. As an undergraduate, she produced a website that used data from Amazon to generate fake but realistic book blurbs. Other projects have more practical applications: While in the United Kingdom, Ebert and her teammates designed a website that helped medical students learn how to suture without a doctor present.
Ebert’s polymathic tendencies appeared at an early age. Growing up, she built with LEGOs, wrote fiction, baked pizzas from scratch and went on plant-focused hikes with her science-teacher father. In high school, she became fascinated with psychology, fueled by discussions with her mother, who had a degree in the subject. It felt natural to study how the brain works, so she pursued a bachelor’s in behavioral neuroscience at Northeastern.
In an early course, Ebert learned to code in MATLAB, the ubiquitous scientific computing language. By her second year she had combined her interests in Dagmar Sternad’s laboratory, picking apart how people learn motor tasks based on feedback cues and eventually programming robots for human experiments.
In 2015 Ebert earned a Marshall Scholarship and headed to Imperial College London, where she studied human-robot interactions and earned a master’s degree in bioengineering. Working with Etienne Burdet and Ildar Farkhatdinov, Ebert helped devise the human-robot interface for the lower-limb powered exoskeleton (LOPES), a wearable robot designed to help injury or stroke victims maintain or recover their balance.
Ebert also has turned her swarm robotics skills toward space. During her summer 2018 Lawrence Livermore National Laboratory practicum, she worked with physicist Michael Schneider to develop software enabling small satellites to communicate and make collective decisions about their observations.
The small satellites offered an interesting parallel to her work with Kilobots, Ebert says. She’s still collaborating with Schneider and considering new extraterrestrial directions for her graduate research, including working with the Space Exploration Initiative at the MIT Media Lab. Ebert hopes to stay in academia after finishing her Ph.D. by 2021.
Image caption: Kilobots move through a patterned environment, sensing as individuals and signalling to their nearest neighbors. Over time the group uses that information to make collective decisions about how to move while staying together. Credit: Julia Ebert.