Towards Spatial Intelligence for Behaviors and Environments
Abstract: We are in an era of foundation models and spatial intelligence (AR/VR). Despite significant advancements in natural language processing for reasoning, other modalities like vision lag behind, offering limited contributions: current video-language models (VLMs) struggle even with basic spatial reasoning tasks. The challenge lies in the disparate training needs of different modalities. To enhance [...]
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 [...]
Mass-Constrained Robotic Climbing on Irregular Terrain
Abstract: Climbing robots can operate in steep and unstructured environments that are inaccessible to other ground robots, with applications ranging from the inspection of artificial structures on Earth to the exploration of natural terrain features throughout the solar system. Climbing robots for planetary exploration face many challenges to deployment, including mass restrictions, irregular surface features, [...]
Towards Annotation-Free Visual-Geometric Representations and Learning for Navigation in Unstructured Environments
Abstract: Navigation in unstructured environments is a capability critical to many robotics applications such as forestry, construction, disaster response and defense. In these domains, robots have the potential to eliminate much of the dull, dirty and/or dangerous work that is currently performed by humans. Unfortunately, these environments pose a unique set of challenges for navigation [...]
RI Faculty Business Meeting
Meeting for RI Faculty. Agenda was sent via a calendar invite.
Creative Tools: In Press, In Submission, and In Progress
Abstract: It's been a while since I've had a chance to show the rest of the RI what I and my various collaborators have been working on. So this talk will be an informal and rapid-fire tour through some of the freshest results from my lab, including work that is in press, in submission, and in [...]
Stabilizing Reinforcement Learning in Differentiable Multiphysics Simulation
Abstract: Recent advances in GPU-based parallel simulation have enabled practitioners to collect large amounts of data and train complex control policies using deep reinforcement learning (RL), on commodity GPUs. However, such successes for RL in robotics have been limited to tasks sufficiently simulated by fast rigid-body dynamics. Simulation techniques for soft bodies are comparatively several [...]
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 [...]
Informative Path Planning Toward Autonomous Real-World Applications
Abstract: Gathering information from the physical world is critical for applications such as scientific research, environmental monitoring, search and rescue, defense, and disaster response. Autonomous robots provide significant advantages for information gathering, particularly in situations where human access is constrained, hazardous, or impractical. By leveraging intelligent algorithms, these robots can efficiently collect data, enhancing decision-making [...]