Seminar
From Lab to Launch
Bio: Nathan Michael is Shield AI’s Chief Technology Officer and a former Associate Research Professor in the Robotics Institute of Carnegie Mellon University (CMU). At CMU, Nathan was the Director of the Resilient Intelligent Systems Lab, a research lab dedicated to improving the performance and reliability of artificially intelligent and autonomous systems that operate in [...]
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 [...]
