Contact: The Problem and the Path to Robotic Dexterity
Assistant Professor, Duke Robotics
Attendance Link: https://docs.google.com/forms/d/e/1FAIpQLSdzU9VehavfTCy6zZk7vXcXHEx-FtcWxWNqa091cx10YlUvSQ/closedform
Abstract
Contact is at the heart of robotic manipulation, yet it is also a central source of difficulty. Contact introduces hybrid, nonsmooth dynamics, where contact mode transitions and uncertainty in geometry and friction make physical interactions difficult to plan, predict, and control. In this talk, I will discuss how understanding contact can help us turn this challenge into an opportunity. We will explore four perspectives: leveraging contact structure to guide dexterous manipulation, developing compliance for more adaptable and robust behaviors, achieving dexterity with simpler mechanisms and environment contacts, and using contact to actively reduce uncertainty. Our broader vision is that better reasoning and control of contact interactions can expand dexterous manipulation capabilities, improve generalization and scalability, make robot interaction safer and more robust, and enable dexterity with simpler mechanisms.
Bio:
Hi, I’m Xianyi (she-an-yee). I am an Assistant Professor at Duke Robotics. I obtained my PhD in Aug 2024 from Carnegie Mellon University, where I was fortunate to be advised by Matt Mason.
I’m interested in everything about robotic manipulation.
Manipulation is hard. Many manual tasks that are simple and repetitive for humans remain extremely difficult to automate.
Manipulation is intriguing. There’s still so much we don’t fully understand — from contact mechanics, the complexity of motions, controlling these complex motions, interactive perception, to problem solving for complex physical tasks. Manipulation is the intelligence of motion evolved over hundreds of millions of years. Manipulation is the art of nature, now becoming the art through engineering and science.
Manipulation is the future. Human-level dexterity in robotics will transform industries and people’s lives. I aspire to help bring a future where robotic manipulation enables more people to pursue lives of dignity, creativity, and fulfillment.
Please visit https://stanfordasl.github.io/robotics_seminar/ for this quarter’s lineup of speakers. Although we encourage in-person attendance, recordings of talks will be posted also.