PhD Thesis Proposal
Policy Decomposition: Approximate Optimal Control with Suboptimality Estimates
Abstract: Optimal Control is a formulation for designing controllers for dynamical systems by posing it as an optimization problem, whereby the desired long-term behavior of the system is expressed using a cost function. The objective is to compute a policy, i.e. a mapping from the state of the system to its control inputs, that minimizes [...]
Audience-Aware Legibility for Social Navigation
Abstract: Robots often need to communicate their goals to humans when navigating in a shared space to assist observers in anticipating the robot’s future actions. These human observers are often scattered throughout the environment, and each observer only has a partial view of the robot and its movements. A path that non-verbally communicates with multiple [...]
On Sample-Efficient Reinforcement Learning for Nuclear Fusion
Abstract: In many practical applications of reinforcement learning (RL), it is expensive to observe state transitions from the environment. For example, in the problem of plasma control for nuclear fusion, determining the next state for a given state-action pair requires querying an expensive transition function which can lead to many hours of computer simulation or [...]
Carnegie Mellon University
Towards reconstructing non-rigidity from single camera
Abstract: In this proposal, we study how to infer 3D from images captured by a single camera, without assuming the target scenes / objects being static. The non-static setting makes our problem ill-posed and challenging to solve, but is vital in practical applications where target-of-interest is non-static. To solve ill-posed problems, the current trend in [...]
Efficient 3D Representations: Algebraic Surfaces for Differentiable Rendering
Abstract: In this proposal, we show how some classic computer vision tasks can robustly be solved via optimization techniques by using an object representation that is compact and interpretable. Specifically, we explore the applications and benefits of representing 3D objects with an analytical, algebraic function by building an approximate, ray-based differentiable renderer. Our approximate formulation [...]
Continual Robot Learning: Benchmarks and Modular Methods
Zoom Meeting Passcode: 841755 Abstract: The earliest reinforcement learning models were designed to learn one task, specified up-front. However, an agent operating freely in the real world will not in general be granted this luxury, as the demands placed on the agent may change as environments or goals change. We refer to this ever-shifting scenario [...]
Improving Robotic Exploration with Self-Supervision and Diverse Data
Abstract: Reinforcement learning (RL) holds great promise for improving robotics, as it allows systems to move beyond passive learning and interact with the world while learning from these interactions. A key aspect of this interaction is exploration: which actions should an RL agent take to best learn about the world? Prior work on exploration is typically [...]
Combining Offline Reinforcement Learning with Stochastic Multi-Agent Planning for Autonomous Driving
Abstract: Fully autonomous vehicles have the potential to greatly reduce vehicular accidents and revolutionize how people travel and how we transport goods. Many of the major challenges for autonomous driving systems emerge from the numerous traffic situations that require complex interactions with other agents. For the foreseeable future, autonomous vehicles will have to share the [...]
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 [...]
Dense Reconstruction of Dynamic Structures from Monocular RGB Videos
Abstract: We study the problem of 3D reconstruction of {\em generic} and {\em deformable} objects and scenes from {\em casually-taken} RGB videos, to create a system for capturing the dynamic 3D world. Being able to reconstruct dynamic structures from casual videos allows one to create avatars and motion references for arbitrary objects without specialized devices, [...]
Learning via Visual-Tactile Interaction
Abstract: Humans learn by interacting with their surroundings using all of their senses. The first of these senses to develop is touch, and it is the first way that young humans explore their environment, learn about objects, and tune their cost functions (via pain or treats). Yet, robots are often denied this highly informative and [...]
Tactile SLAM: perception for dexterity via vision-based touch
Abstract: Touch provides a direct window into robot-object interaction, free from occlusion and aliasing faced by visual sensing. Collated tactile perception can facilitate contact-rich tasks---like in-hand manipulation, sliding, and grasping. Here, online estimates of object geometry and pose are crucial for downstream planning and control. With significant advances in tactile sensing, like vision-based touch, a [...]
Resource Allocation for Learning in Robotics
Abstract: Robots operating in the real world need fast and intelligent decision making systems. While these systems have traditionally consisted of human-engineered behaviors and world models, there has been a lot of interest in integrating them with data-driven components to achieve faster execution and reduce hand-engineering. Unfortunately, these learning-based methods require large amounts of training [...]
Planning with Dynamics by Interleaving Search and Trajectory Optimization
Abstract: Search-based planning algorithms enable autonomous agents like robots to come up with well-reasoned long-horizon plans to achieve a given task objective. They do so by searching over the graph that results from discretizing the state and action space. However, in robotics, several dynamically rich tasks require high-dimensional planning in the continuous space. For such [...]
Utilizing Panoptic Segmentation and a Locally-Conditioned Neural Representation to Build Richer 3D Maps
Abstract: Advances in deep-learning based perception and maturation of volumetric RGB-D mapping algorithms have allowed autonomous robots to be deployed in increasingly complex environments. For robust operation in open-world conditions however, perceptual capabilities are still lacking. Limitations of commodity depth sensors mean that complex geometries and textures cannot be reconstructed accurately. Semantic understanding is still [...]
Multi-Human 3D Reconstruction from Monocular RGB Videos
Abstract: We study the problem of multi-human 3D reconstruction from RGB videos captured in the wild. Humans have dynamic motion, and reconstructing them in arbitrary settings is key to building immersive social telepresence, assistive humanoid robots, and augmented reality systems. However, creating such a system requires addressing fundamental issues with previous works regarding the data [...]
Learning and Translating Temporal Abstractions across Humans and Robots
Abstract: Humans possess a remarkable ability to learn to perform tasks from a variety of different sources-from language, instructions, demonstration, etc. In each case, they are able to easily extract the high-level strategy to solve the task, such as the recipe of cooking a dish, whilst ignoring irrelevant details, such as the precise shape of [...]
Predicting The Future and Linking the Past: Learning and Constructing Structured Models for Robotic Manipulation
Abstract: Intelligent robotic agents need to reason about the dynamics of their surrounding world, and use such dynamics reasoning to make future predictions for efficient task planning. In addition, it is also desirable for robots to associate past experience in their memories to their current observation, and conduct analogical reasoning to complete tasks at their [...]
Perception for High-Speed Off-Road Driving
Abstract: On-road autonomous driving has seen rapid progress in recent years with driverless vehicles being tested in various cities worldwide. However, this progress is limited to cities with well-established infrastructure and has yet to transfer to off-road regimes with unstructured environments and few paved roads. Advances in high-speed and reliable autonomous off-road driving can unlock [...]
Continual Learning of Compositional Skills for Robust Robot Manipulation
Abstract: Real world robots need to continuously learn new manipulation tasks in a lifelong learning manner. These new tasks often share sub-structures (in the form of sub-tasks, controllers) with previously learned tasks. To utilize these shared sub-structures, we explore a compositional and object-centric approach to learn manipulation tasks. While compositionality in robot manipulation can manifest [...]
Equivalent Policy Sets for Learning Aligned Models and Abstractions
Abstract: Recent successes in model-based reinforcement learning (MBRL) have demonstrated the enormous value that learned representations of environmental dynamics (i.e., models) can impart to autonomous decision making. While a learned model can never perfectly represent the dynamics of complex environments, models that are accurate in the "right” ways may still be highly useful for decision [...]
Adaptive Robotic Assistance through Observations of Human Behavior
Abstract: Assistive robots should take actions that support people's goals. This is especially true as robots enter into environments where personal agency is paramount, such as a person's home. Home environments have a wide variety of "optimal' solutions that depend on personal preference, making it difficult for a robot to know the goal it should [...]
Beyond Pick-and-Place: Towards Dynamic and Contact-rich Motor Skills with Reinforcement Learning
Abstract: Interactions with the physical world are at the core of robotics. However, robotics research, especially in manipulation, has been mainly focused on tasks with limited interactions with the physical world such as pick-and-place or pushing objects on the table top. These interactions are often quasi-static, have predefined or limited sequence of contact events and [...]
Adaptive-Anytime Planning and Mapping for Multi-Robot Exploration in Large Environments
Abstract: Robotic systems are being leveraged to explore environments too hazardous for humans to enter. Robot sensing, compute, and kinodynamic (SCK) capabilities are inextricably tied to the size, weight, and power (SWaP) constraints of the vehicle. When designing a robot team for exploration, the diversity and types of robots used must be carefully considered because [...]
Enabling Data-Efficient Real-World Model-Based Manipulation by Estimating Preconditions for Inaccurate Models
Abstract: This thesis explores estimating and reasoning about model deviation in robot learning for manipulation to improve data efficiency and reliability to enable real-robot manipulation in a world where models are inaccurate but still useful. Existing strategies are presented for improving planning robustness with low amounts of real-world data by an empirically estimated model precondition to guide [...]
Robust Adaptive Reinforcement Learning for Safety Critical Applications via Curricular Learning
Abstract: Reinforcement Learning (RL) presents great promises for autonomous agents. However, when using robots in a safety critical domain, a system has to be robust enough to be deployed in real life. For example, the robot should be able to perform across different scenarios it will encounter. The robot should avoid entering undesirable and irreversible [...]
Towards Photorealistic Dynamic Capture and Animation of Human Hair and Head
Abstract: Realistic human avatars play a key role in immersive virtual telepresence. To reach a high level of realism, a human avatar needs to faithfully reflect human appearance. A human avatar should also be drivable and express natural motions. Existing works have made significant progress on building drivable realistic face avatars, but they rarely include [...]