PhD Thesis Proposal
PhD Student
Robotics Institute,
Carnegie Mellon University

Sparse-view 3D in the Wild

GHC 6501

Abstract: Reconstructing 3D scenes and objects from images alone has been a long-standing goal in computer vision. We have seen tremendous progress in recent years, capable of producing near photo-realistic renderings from any viewpoint. However, existing approaches generally rely on a large number of input images (typically 50-100) in order to compute camera poses and [...]

PhD Speaking Qualifier
PhD Student
Robotics Institute,
Carnegie Mellon University

Safely Influencing Humans in Human-Robot Interaction

GHC 8102

Abstract: Robots are becoming more common in industrial manufacturing because of their speed and precision on repetitive tasks, but they lack the flexibility of human collaborators. In order to take advantage of both humans’ and robots’ abilities, we investigate how to improve the efficiency of human-robot collaborations by making sure that robots both 1. stay [...]

PhD Speaking Qualifier
PhD Student
Robotics Institute,
Carnegie Mellon University

Inductive Biases for Learning Long-Horizon Manipulation Skills

GHC 6121

Abstract: Enabling robots to execute temporally extended sequences of behaviors is a challenging problem for learned systems, due to the difficulty of learning both high-level task information and low-level control. In this talk, I will discuss three approaches that we have developed to address this problem. Each of these approaches centers on an inductive bias [...]

VASC Seminar
Shervin Ardeshir
Senior Research Scientist
Netflix

Estimating Robustness using Proxies

Newell-Simon Hall 3305

ABSTRACT: This talk covers some of our recent explorations on estimating the robustness of black-box machine learning models across data subpopulations. In other words, if a trained model is uniformly accurate across different types of inputs, or if there are significant performance disparities affecting the different subpopulations. Measuring such a characteristic is fairly straightforward if [...]

PhD Speaking Qualifier
PhD Student
Robotics Institute,
Carnegie Mellon University

Analogy-Forming Transformers for Few-Shot 3D Parsing

NSH 3305

Abstract: How do we build agents that can fast generalize to novel scenarios given only a single example? In this talk, I will present analogy-forming transformers, a semi-parametric model that segments 3D object scenes by retrieving related memories and predicting analogous part structures for the input. This enables a single neural network to continually learn [...]

PhD Speaking Qualifier
PhD Student
Robotics Institute,
Carnegie Mellon University

Range-based Gaussian Process Maps for Mobile Exploration Robots

NSH 3305

Abstract: Mobile robots exploring unknown, natural environments with limited communication must map their surroundings using onboard sensors. In this context, terrain mapping can rely on Gaussian process models to incorporate spatial correlations and provide uncertainty estimates when predicting ground height - however, these models fail to account for the oblique viewpoint of a sensor on [...]

PhD Speaking Qualifier
PhD Student
Robotics Institute,
Carnegie Mellon University

Learning Exploration Strategies to Solve Real-World Marble Runs

NSH 1109

Abstract: Tasks involving locally unstable or discontinuous dynamics (such as bifurcations and collisions) remain challenging in robotics, because small variations in the environment can have a significant impact on task outcomes. In this talk, we present a robot system that we developed to evaluate learning algorithms on real-world physical problem solving tasks which incorporate these [...]

PhD Speaking Qualifier
PhD Student
Robotics Institute,
Carnegie Mellon University

Beyond NeRF Underwater: Learning Neural Reflectance Fields for True Color Correction of Marine Imagery

NSH 4305

Abstract: Underwater imagery often exhibits distorted coloration as a result of light-water interactions, which complicates the study of benthic environments in marine biology and geography. In this research, we propose an algorithm to restore the true color (albedo) in underwater imagery by jointly learning the effects of the medium and neural scene representations. Our approach [...]

Faculty Events

RI Faculty Business Meeting

Newell-Simon Hall 4305

Meeting for RI Faculty. Discussions include various department topics, policies, and procedures. Generally meets weekly.

PhD Thesis Defense
Robotics Institute,
Carnegie Mellon University

Optimization of Small Unmanned Ground Vehicle Design using Reconfigurability, Mobility, and Complexity

Abstract: Unmanned ground vehicles are being deployed in increasingly diverse and complex environments. With modern developments in sensing and planning, the field of ground vehicle mobility presents rich possibilities for mechanical innovations that may be especially relevant for unmanned systems. In particular, reconfigurability may enable vehicles to traverse a wider set of terrains with greater [...]