The graduate students laying the groundwork for the future of robotics
The International Federation of Robotics, a group aimed at encouraging research, development, and international co-operation in the field, notes that in 2021 robots are on target to get increasingly smarter and more autonomous, more cost- and energy-efficient, and more adaptable to new industries and applications.
At NYU Tandon, researchers are pushing the needle towards that target, developing robotic technology with world-changing applications in healthcare, manufacturing, safety, infrastructure, and other areas. And working right alongside our robotics faculty members are their visionary graduate students, two of whom discuss their work below.
Avadesh Meduri
Year of projected graduation: 2024
Describe the path that brought you to Tandon:
I earned my undergraduate degree in manufacturing engineering in India, at the Birla Institute of Technology & Science, Pilani. During those years, I helped develop an Optical Character Recognition system for Sanskrit using deep neural networks and a deep learning framework for detecting and counting farm mangoes from images using Dense Semantic Segmentation and Contour Detection algorithms. I also had the privilege of going to Germany, to do an internship at the Max Planck Institute for Intelligent Systems in Tübingen. I worked there with the Movement Generation and Control Group headed by Ludovic Righetti. He was also a faculty member at NYU Tandon, so when it came time for me to decide on a graduate school, that seemed like the natural choice, because I wanted to continue working with him. In addition to my robotics studies, I take several computer science and mathematics courses, so it’s great being at NYU and having access to Courant, as well.
What lab are you working in?
I conduct my research in Professor Righetti’s Machines in Motion Laboratory, which he launched in 2017 when he arrived at Tandon. We collaborate with the Movement Generation and Control Group in Tübingen and focus on understanding the fundamental principles for robot locomotion and manipulation.
What was it like working during the pandemic?
Professor Righetti is a very hands-on, involved instructor, so even at the height of the COVID-19 crisis, we were having weekly lab meetings on Zoom, and once a week we also met to do a group reading. That way, it never felt isolated. Over the summer, however, we were facing a conference deadline, so we got back into the lab in-person, following all the safety guidelines the University had put into place. That felt great.
Describe your research in simple terms:
If you understand how humans and animals move, you can devise algorithms that will allow biped and quadruped robots to move in a similar fashion. If you can figure out a way for robots to walk on uneven terrain without falling or grasp delicate objects without breaking them, they could be used in endless ways.
What are the future practical applications for your work?
There are too many to list completely here: everything from better-performing exoskeletons for those without use of their limbs to robots capable of climbing scaffolding to aid construction workers, entering burning buildings to save inhabitants, assisting in surgery, and deactivating land mines. We’re in an exciting and transformative period. Robots are going to be making people safer, healthier, and more productive.
Guanrui Li
Year of projected graduation: 2024
Describe the path that brought you to Tandon:
In 2016 I earned my undergraduate degree in Theoretical and Applied Mechanics from Sun Yat-sen University in China. I then came to the U.S. and entered the University of Pennsylvania, and in the course of my master’s studies, I met Giuseppe Loianno, who was then a research scientist and team leader at the school’s General Robotics, Automation, Sensing & Perception (GRASP) Lab. He was so knowledgeable and so passionate about the research in aerial robotics that I wanted him to be my doctoral advisor, so when he joined the faculty at NYU Tandon, I knew that’s where I’d be conducting my doctoral research.
What lab are you working in?
Professor Loianno now heads the Agile Robotics and Perception Lab (ARPL), which is engaged in fundamental and applied research in the area of robotics. The main goal of all of us here is to create agile autonomous robots that can navigate by themselves and interact with humans using only onboard sensors and without relying on external infrastructure.
What was it like working during the pandemic?
In the earliest days of the pandemic, we worked remotely, but as soon as Tandon instituted all the public health measures called for, like social distancing, controlled access to the buildings on campus, and proper personal protective equipment, we were all eager to head back to the lab. Obviously, safety comes first, and the school did a wonderful job keeping us safe while still allowing us to do the hands-on research we love.
Describe your research in simple terms:
Like Professor Loianno, I work with autonomous aerial vehicles, commonly called drones. Our main mission is to get them to navigate totally on their own using cameras and sensors, and we want them to be capable of operating efficiently in less-than-optimal conditions, such as crowded urban areas with lots of physical obstacles or locales where GPS is difficult to access. We envision teams of drones working together in some instances, like cooperating to deliver a package or exploring unknown environments, for example. Moreover, I’m mainly focusing on developing technology and algorithms for the drone team such that they achieve the required tasks by exchanging minimal information with each other – or even not communicating at all.
What are the future practical applications for your work?
Drones can be sent into situations no person would want to be in, such as inspecting a nuclear reactor or undertaking a perilous search-and-rescue mission. But just because you might never need to personally inspect a nuclear reactor or save someone from a treacherous cliff, doesn’t mean a drone won’t impact your life: it might not be unusual to look up one day and see a team of drones delivering a heavy package to your doorstep.
