Student Talks
Causal Robot Learning for Manipulation
Abstract: Two decades into the third age of AI, the rise of deep learning has yielded two seemingly disparate realities. In one, massive accomplishments have been achieved in deep reinforcement learning, protein folding, and large language models. Yet, in the other, the promises of deep learning to empower robots that operate robustly in real-world environments [...]
Learning to Manipulate Using Diverse Datasets
Abstract: Autonomous agents can play games (like Chess, Go, and even Starcraft), they can help make complex scientific predictions (e.g., protein folding), and they can even write entire computer programs, with just a bit of prompting. However, even the most basic physical manipulation skills, like unlocking and opening a door, still remain literally out-of-reach. The [...]
3D Perception In-The-Wild
Abstract: State estimation is a fundamental component of embodied perception. Contemporary autonomous vehicle (AV) benchmarks have advanced techniques for training 3D detectors, particularly on large-scale data. Notably, although prior work has nearly solved 3D object detection for a few common classes (e.g., pedestrian and car), detecting many rare classes in-the-tail (e.g., debris and stroller) remains [...]
Learning on the Move: Integrating Action and Perception for Mobile Manipulation
Abstract: While there has been remarkable progress recently in the fields of manipulation and locomotion, mobile manipulation remains a long-standing challenge. Compared to locomotion or static manipulation, a mobile system must make a diverse range of long-horizon tasks feasible in unstructured and dynamic environments. While the applications are broad and interesting, there are a plethora [...]
Differentiable Convex Modeling for Robotic Planning and Control
Abstract: Robotic simulation, planning, estimation, and control, have all been built on top of numerical optimization. In this same time, modern convex optimization has matured into a robust technology delivering globally optimal solutions in polynomial time. With advances in differentiable optimization and custom solvers capable of producing smooth derivatives, convex modeling has become fast, reliable, [...]
Plan to Learn: Active Robot Learning by Planning
Abstract: Robots need a diverse repertoire of capable motor skills to succeed in the open world. Such a skillset cannot be learned or designed purely on human initiative. In this thesis, we advocate for an active continual learning approach that enables robots to take charge of their own learning. The goal of an autonomously learning [...]
Continual Personalization of Human Actions with Prompt Tuning
Abstract: In interactive computing devices (VR/XR headsets), users interact with the virtual world using hand gestures and body actions. Typically, models deployed in such XR devices are static and limited to their default set of action classes. The goal of our research is to provide users and developers with the capability to personalize their experience by [...]
Policy Decomposition
Abstract: Optimal Control is a popular formulation for designing controllers for dynamic robotic systems. Under the formulation, the desired long-term behavior of the system is encoded via a cost function and the policy, i.e. a mapping from the state of the system to control commands, to achieve the desired behavior are obtained by solving an [...]
Analysis by Synthesis for Modern Computer Vision
Abstract: Image denoising, depth completion, scene flow, and dynamic 3D reconstruction are all examples of recovery problems: the estimation of multidimensional signals from corrupted or partial measurements. This thesis examines these problems from the classic analysis-by-synthesis perspective, where a signal model is used to propose hypotheses, which are then compared to observations. This paradigm has [...]
Reinforcement Learning with Spatial Reasoning for Dexterous Robotic Manipulation
Abstract: Robotic manipulation in unstructured environments requires adaptability and the ability to handle a wide variety of objects and tasks. This thesis presents novel approaches for learning robotic manipulation skills using reinforcement learning (RL) with spatially-grounded action spaces, addressing the challenges of high-dimensional, continuous action spaces and alleviating the need for extensive training data. Our [...]