Seminar
Uncertainty and Contact with the World
Abstract: As robots move out of the lab and factory and into more challenging environments, uncertainty in the robot's state, dynamics, and contact conditions becomes a fact of life. We will never be able to perfectly predict the forces on the robot's feet as it walks through unknown mud or control the deflections of a [...]
Towards Open World Robot Safety
Abstract: Robot safety is a nuanced concept. We commonly equate safety with collision-avoidance, but in complex, real-world environments (i.e., the “open world’’) it can be much more: for example, a mobile manipulator should understand when it is not confident about a requested task, that areas roped off by caution tape should never be breached, and [...]
Controllable Visual Imagination
Abstract: Generative models have empowered human creators to visualize their imaginations without artistic skills and labor. A prominent example is large-scale text-to-image generation models. However, these models often are difficult to control and do not respect 3D perspective geometry and temporal consistency of videos. In this talk, I will showcase several of our recent efforts to [...]
Developing Physically Capable and Intelligent Robots
Abstract: Dr. Rizzi will provide an overview of the ongoing work at the Robotics and AI Institute (RAI Institute) and its ongoing research efforts focused on the design and control of the next generation of intelligent and capable robotics systems. The focus is on the development of systems capable of performing complex dynamic tasks at [...]
Discovering and Erasing Undesired Concepts
Abstract: The rapid growth of generative models allows an ever-increasing variety of capabilities. Yet, these models may also produce undesired content such as unsafe or misleading images, private information, or copyrighted material. In this talk, I will discuss practical methods to prevent undesired generations. First, I will show how the challenge of avoiding undesired generations [...]
Is Data All You Need?: Large Robot Action Models and Good Old Fashioned Engineering
Abstract: Enthusiasm has been skyrocketing for humanoids based on recent advances in "end-to-end" large robot action models. Initial results are promising, and several collaborative efforts are underway to collect the needed demonstration data. But is data really all you need? Although end-to-end Large Vision, Language, Action (VLA) Models have potential to generalize and reliably solve [...]
The New Era of Video Generation
Abstract: Traditional video production is slow, expensive, and requires specialized skills. Founded by CMU alumni, HeyGen is an AI-native video platform designed to revolutionize the video creation process by making visual storytelling accessible to all. We've successfully grown to more than 20M users, and tens of millions revenue in less than one year, with recognition [...]
Sensing the Unseen: Dexterous Tool Manipulation Through Touch and Vision
Abstract: Dexterous tool manipulation is a dance between tool motion, deformation, and force transmission choreographed by the robot's end-effector. Take for example the use of a spatula. How should the robot reason jointly over the tool’s geometry and forces imparted to the environment through vision and touch? In this talk, I will present our recent [...]
Autoregressive Models: Foundations and Open Questions
Abstract: The success of Autoregressive (AR) models in language today is so tremendous that their scope has, in turn, been largely narrowed to specific instantiations. In this talk, we will revisit the foundations of classical AR models, discussing essential concepts that may have been overlooked in modern practice. We will then introduce our recent research [...]
Learning Environment Models for Mobile Robot Autonomy
Abstract: Robots are expected to execute increasingly complex tasks in increasingly complex and a priori unknown environments. A key prerequisite is the ability to understand the geometry and semantics of the environment in real time from sensor observations. This talk will present techniques for learning metric-semantic environment models from RGB and depth observations. Specific examples include [...]