VASC Seminar
Anand Bhattad
PhD candidate
University of Illinois Urbana-Champaign

What do generative models know about geometry and illumination?

3305 Newell-Simon Hall

Abstract: Generative models can produce compelling pictures of realistic scenes. Objects are in sensible places, surfaces have rich textures, illumination effects appear accurate, and the models are controllable. These models, such as StyleGAN, can also generate semantically meaningful edits of scenes by modifying internal parameters. But do these models manipulate a purely abstract representation of the [...]

Seminar
Matthew Johnson-Roberson, Zeynep Temel, Kris Kitani, Deva Ramanan, Henny Admoni
Singleton Room, Roberts Engineering Hall
Robotics Institute, Carnegie Mellon University

Life as a Professor Seminar

Singleton Room, Roberts Engineering Hall

Have you ever wondered what life is like as a professor? What do professors do on a daily basis? What makes the faculty career challenging and rewarding? Maybe you have even thought about becoming a faculty member yourself? Join us on March 22nd from 2:00 - 3:30 PM, where a panel of CMU faculty will [...]

PhD Thesis Defense
Robotics Institute,
Carnegie Mellon University

System Identification and Control of Multiagent Systems Through Interactions

NSH 3305

Abstract: This thesis investigates the problem of inferring the underlying dynamic model of individual agents of a multiagent system (MAS) and using these models to shape the MAS's behavior using robots extrinsic to the MAS. We investigate (a) how an observer can infer the latent task and inter-agent interaction constraints from the agents' motion and [...]

PhD Speaking Qualifier
PhD Student
Robotics Institute,
Carnegie Mellon University

Examining the Role of Adaptation in Human-Robot Collaboration

GHC 4405

Abstract: Human and AI partners increasingly need to work together to perform tasks as a team. In order to act effectively as teammates, collaborative AI should reason about how their behaviors interplay with the strategies and skills of human team members as they coordinate on achieving joint goals. This talk will discuss a formalism for [...]

PhD Speaking Qualifier
PhD Student
Robotics Institute,
Carnegie Mellon University

A Multi-view Synthetic and Real-world Human Activity Recognition Dataset

NSH 3305

Abstract: Advancements in Human Activity Recognition (HAR) partially relies on the creation of datasets that cover a broad range of activities under various conditions. Unfortunately, obtaining and labeling datasets containing human activity is complex, laborious, and costly. One way to mitigate these difficulties with sufficient generality to provide robust activity recognition on unseen data is [...]

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.

RI Seminar
Lerrel Pinto
Assistant Professor of Computer Science
Robotics and Machine Learning, New York University

A Constructivist’s Guide to Robot Learning

1305 Newell Simon Hall

Over the last decade, a variety of paradigms have sought to teach robots complex and dexterous behaviors in real-world environments. On one end of the spectrum we have nativist approaches that bake in fundamental human knowledge through physics models, simulators and knowledge graphs. While on the other end of the spectrum we have tabula-rasa approaches [...]

VASC Seminar
Saurabh Gupta
Assistant Professor
University of Illinois Urbana-Champaign

Robot Learning by Understanding Egocentric Videos

GHC 8102

Abstract: True gains of machine learning in AI sub-fields such as computer vision and natural language processing have come about from the use of large-scale diverse datasets for learning. In this talk, I will discuss if and how we can leverage large-scale diverse data in the form of egocentric videos (first-person videos of humans conducting [...]

PhD Thesis Proposal
PhD Student
Robotics Institute,
Carnegie Mellon University

Eye Gaze for Intelligent Driving

NSH 4305

Abstract: Intelligent vehicles have been proposed as one path to increasing vehicular safety and reduce on-road crashes. Driving intelligence has taken many forms, ranging from simple blind spot occupancy or forward collision warnings to lane keeping and all the way to full driving autonomy in certain situations. Primarily, these methods are outward-facing and operate on [...]

PhD Speaking Qualifier
PhD Student
Robotics Institute,
Carnegie Mellon University

Dense 3D Representation Learning for Geometric Reasoning in Manipulation Tasks

NSH 3001

Abstract: When solving a manipulation task like "put away the groceries" in real environments, robots must understand what *can* happen in these environments, as well as what *should* happen in order to accomplish the task. This knowledge can enable downstream robot policies to directly reason about which actions they should execute, and rule out behaviors [...]