Universal Semantic-Geometric Priors for Zero-Shot Robotic Manipulation
Abstract: Visual imitation learning has shown promising results in robotic manipulation in recent years. However, its generalization to unseen objects is often limited by the size and diversity of training data. Although more large-scale robotic datasets are available, they remain significantly smaller than image and text datasets. Additionally, scaling these datasets is time-consuming and labor-intensive, [...]
Personalized Context-aware Multimodal Robot Feedback
Abstract: In the field of human-robot interaction (HRI), integration of robots into social settings, such as healthcare and education, is gaining traction. Robots that provide individualized support to improve human performance and subjective experience will generally be more successful in these domains. Robots should personalize their interactions, be aware of the contextual nuances surrounding their [...]
Sensorized Soft Materials Systems with Integrated Electronics and Computing
Abstract: The integration of soft and multifunctional materials in emerging technologies is becoming more widespread due to their ability to enhance or improve functionality in ways not possible using typical rigid alternatives. This trend is evident in various fields. For example, wearable technologies are increasingly designed using soft materials to improve modulus compatibility with biological [...]
Enabling Reliable Model-Based Planning with Inaccurate Models
Abstract: This thesis aims to provide a framework for combining complementary tools that enable robots to manipulate objects in the world using diverse forms of knowledge. We consider heterogeneous types of knowledge, such as physics-based models, learned dynamics models, and model-free skills learned from human demonstrations. Each form of knowledge comes with its own assumptions [...]
Unlocking Generalization for Robotics via Scale and Modularity
Abstract: How can we build generalist robot systems? Looking at fields such as vision and language, the common theme has been large scale end-to-end learning with massive, curated datasets. In robotics, on the other hand, scale alone may not be enough due to the significant multimodality of robotics tasks, lack of easily accessible data and [...]
RI Seminar with Aaron Johnson
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 [...]
RI Seminar with Alfred Rizzi
Good Old-Fashioned LLMs (or, Autoformalizing the World)
Abstract: Classical formal approaches to artificial intelligence, based on manipulation of symbolic structures, have a number of appealing properties---they generalize (and fail) in predictable ways, provide interpretable traces of behavior, and can be formally verified or manually audited for correctness. Why are they so rarely used in the modern era? One of the major challenges [...]
Unfamiliar Intelligence: Art, AI, and Robots
Abstract: Shortly after the 1918 pandemic, the word "robot" was coined in a play about mechanical workers organizing a rebellion to defeat their human overlords. A century later, emerging advances in Artificial Intelligence and robotics, fueled by venture capital and governments, are disrupting labor, trade, and political stability. Claims about “superintelligence” and existential threats to [...]
