PhD student receives fellowship from Apple Scholars program

Anonymous — Thu, 11 Apr 2024 17:43:26 +0000

PhD student receives fellowship from Apple Scholars program Anonymous (not verified) Thu, 04/11/2024 - 11:43

Grace Wilson

Nataliya Nechyporenko, a computer science Ph.D. student advised by Alessandro Roncone in the Human Interaction and Robotics (HIRO) group, has received a PhD fellowship in AI and Machine Learning (AIML) through the Apple Scholars program. The program was created by Apple to recognize the contributions of emerging leaders in computer science and engineering at the graduate and postgraduate level.

The fellowship provides Nechyporenko support for her research and academic travel for two years, internship opportunities and a two-year mentorship with an Apple researcher.

Let's learn more about Nechyporenko's research aims and her perspective on the future of robotics research:

What research do you hope to accomplish through this fellowship?

Think about how you might manually feel around an object to understand its shape, weight, and texture. Or if something is in your way, you'd just push it aside without overthinking it. If you drop something, you'll persistently keep trying to pick it up from different angles until you get it. As you're doing these everyday tasks, you're constantly building up an intuitive sense of your surroundings through trial-and-error. That's the kind of resourceful, flexible, multi-sensory approach I want robots to have when manipulating things – rather than just blindly following a fixed routine.

The goal is for robotic arms to move and behave with that same kind of curious, improvisational, problem-solving spirit we take for granted as humans. As an Apple AIML scholar, I hope to gain insights into this problem with the help of a fresh network of mentors and collaborators.

Is this an extension of work you are already doing in your lab? If so, how?

Driven to establish contact-rich planning as a dominant feature in robotics, I focused the first two years of my PhD on analyzing the methods used by state-of-the-art planners and solving the shortcomings leading to the lack of physical robot interaction.

I have started to extend this work by integrating the empirical formulation of machine learning with model-based algorithmic approaches. I believe this is the path to making robots more adaptable to chaotic human environments. I will continue this work as an Apple scholar.

What do you think of the current hype around AI and ML? What do you wish people understood about this research area?

The AI and machine learning hype trains have been barreling full steam ahead lately. But robotics? That's an entirely different beast that doesn't follow the overnight disruption narratives. It's a synergy of achievements in areas like materials, manufacturing, sensing, controls theory, and others aligning to reshape the physical world.

The robotics future will reshape industries and labor concepts, but it will be catalyzed through the patient advancement of many disciplines.

How did you come to study at ŷ��ڱ��Ƶ Boulder?

I spent a couple years in the trenches, getting my hands dirty actually building and deploying robots in industry. But after a while, I got this craving -- like there was so much more potential waiting to be unlocked if I could really dive into the deep scientific questions around robotics. That's why I decided to take the plunge back into academia.

What is one of your plans or hopes for the future, either professionally or personally?

I hope to be an expert, a leader, a thinker and a builder. Outside of research endeavors, I aim to be a leader and educator for the robotics and the AI community. Previously, I’ve led volunteering activities, mentored students, and co-organized events that foster discussions around AI. I hope to continue to do so in the future at a larger scale.

Nataliya Nechyporenko has been recognized as an emerging leader in computer science at the graduate level.

Off

Traditional

White

Helping robots recover from failure: a Q+A with NASA graduate fellowship winner Gilberto Briscoe-Martinez

Anonymous — Mon, 27 Jun 2022 22:39:15 +0000

Helping robots recover from failure: a Q+A with NASA graduate fellowship winner Gilberto Briscoe-Martinez Anonymous (not verified) Mon, 06/27/2022 - 16:39

Grace Wilson

We all fail sometimes, but how we respond to those failures is important. Classical robotic failure mitigation focuses on trying to anticipate every way a system could fail and having an answer.

Gilberto Briscoe-martinez (PhDCompSci‘26) wants robots to be able to learn from their mistakes and continue persevering to finish a task as best they can. He was recently awarded a NASA Space Technology Graduate Research (NSTGRO) fellowship for his exploration of this topic, titled “Enabling Long-term Robot Autonomy through Adaptable Fault Resilience”. He is the first Computer Science P.h.D. student at ŷ��ڱ��Ƶ Boulder to receive this award. The fellowship will fund Gilberto for 4 years and will allow him to collaborate with scientists at NASA research centers.

Alessandro Roncone, Briscoe-martinez' advisor and director of the Human Interaction and RObotics (HIRO) Group at ŷ��ڱ��Ƶ Boulder, said "The NASA NSTGRO is one of the most prestigious fellowships awarded to graduate students in robotics at the national level. With this support from NASA, Gilberto will be able to not only advance the science of robotic fault resilience, but also understand how to transfer his discoveries to real systems, and, eventually, see his research deployed in space."

We asked Briscoe-martinez a few questions about his research and fellowship, here are his answers:

How would you describe this project to someone not familiar with your area of research?

Humans have an incredible, innate ability to compensate for an injury that we experience. If you’ve ever stubbed your toe, you’ve probably tried not to put weight on it without explicitly thinking about doing so. On the other hand, robots have an unchanging understanding of their physical selves. If anything breaks, even something as small as a piece of the robot’s gripper falling off, the robot is useless until a human can fix it. For NASA, this presents a problem. Robots will need to work reliably for months or even years on new space stations and future inter-planetary missions with few or no ways to fix themselves. My research will discover methods for these robots to compensate for injuries and wear they experience, as humans do, so they can continue to do their mission-critical work.

What does winning this fellowship mean to you?

For me, receiving this fellowship feels like a transition point. Until now, I’ve only used robotic technology developed by others, solving “engineering problems,” as my advisor likes to say. Now, I look forward to researching the ways that will push robotic abilities to the stars. The research I will be conducting through this fellowship is critical to enabling humans to go beyond the reaches of our planet. I am beyond excited to be at the forefront of space robotics.

How has it been working in the Human Interaction and RObotics (HIRO) Group?

My experience in the HIRO lab has been fantastic. The lab, as a whole, is focused on wholistically researching robotic systems. This enables unique collaboration opportunities between those working on the main research threads of robotic ability, physical Human-Robot Interaction(HRI), and Social HRI. My colleagues have been great inspirations because we have different outlooks, experiences, and research approaches. In addition, I believe the lab has a great work-life balance, where we are pushed to excel but can go out to ski on a snow day in the middle of the week.

What inspired your love of robotics?

My curiosity was first piqued when I took a middle-school robotics class after my school received a grant from LEGO to use their Mindstorm systems. I realized robotics would be a lifelong passion when I joined my high school robotics club. We competed in both the VEX and FIRST robotics competitions. By designing and building robots to complete many challenges, I realized that the only limits of robotic ability are the limits of our imagination. From those experiences, I was inspired to pursue the robotics research that I do today.

Any advice for folks not sure if STEM is right for them?

My advice for someone on the fence about entering STEM is to not be afraid to try it. If you’re thinking about it then that curiosity is already there which can turn into your life’s work. And it is important to remember that if it turns out that STEM is not right for you, switching majors, and even switching careers is something that many people successfully do.

Briscoe-martinez was recently awarded a NASA Space Technology Graduate Research (NSTGRO) fellowship. He is the first Computer Science P.h.D. student at ŷ��ڱ��Ƶ Boulder to receive this award, which will provide him with 4 years of research funding and NASA collaboration in enabling long-term robot autonomy through adaptable fault resilience.

Off