VASC Seminar
Fuxin Li
Assistant Professor
Oregon State University

Some New Designs of Convolutional and Recurrent Networks

GHC 6501

Abstract: Convolutional networks (CNNs) and recurrent networks have driven the great engineering success of deep learning in recent years. However, as academics, we still wonder whether they are indeed the ultimate models of choice. Especially, CNNs seem unable to characterize predictive uncertainty, and they are highly dependent on small filters on small, rectangular neighborhoods. On [...]

RI Seminar
Tucker Hermans
Assistant Professor
School of Computing, University of Utah

Improving Multi-fingered Robot Manipulation by Unifying Learning and Planning

Gates Hillman Center 6115

Abstract: Multi-fingered hands offer autonomous robots increased dexterity, versatility, and stability over simple two-fingered grippers. Naturally, this increased ability comes with increased complexity in planning and executing manipulation actions. As such, I propose combining model-based planning with learned components to improve over purely data-driven or purely-model based approaches to manipulation. This talk examines multi-fingered autonomous [...]

VASC Seminar
Arthur Szlam
Research Scientist
Facebook AI Research

Language and Interaction in Minecraft

GHC 6501

Abstract:  I will discuss a research program aimed at building a Minecraft assistant, in order to facilitate the study of agents that can complete tasks specified by dialogue, and eventually, to learn from dialogue interactions.  I will describe the tools and platform we have built allowing players to interact with the agents and to record those interactions, and [...]

PhD Speaking Qualifier
Robotics Institute,
Carnegie Mellon University

Scaling Up Deep Learning with Model and Algorithm Awareness

GHC 4405

Abstract: In recent years, the pace of innovations in the fields of deep learning has accelerated. To cope with the sheer computational complexity of training large ML models on large datasets, researchers in the systems and ML communities have created software systems that parallelize training algorithms over multiple CPUs or GPUs (multi-device parallelism), or even [...]

RI Seminar
Seth Hutchinson
Professor & KUKA Chair for Robotics
School of Interactive Computing, Georgia Institute of Technology

Design, Modeling and Control of a Robot Bat: From Bio-inspiration to Engineering Solutions

Gates Hillman Center 6115

Abstract: In this talk, I will describe our recent work building a biologically-inspired bat robot. Bats have a complex skeletal morphology, with both ball-and-socket and revolute joints that interconnect the bones and muscles to create a musculoskeletal system with over 40 degrees of freedom, some of which are passive. Replicating this biological system in a [...]

VASC Seminar
Minh Hoai Nguyen
Assistant Professor
Stony Brook University

Attentive Human Action Recognition

Gates-Hillman Center 8102

Abstract:  Enabling computers to recognize human actions in video has the potential to revolutionize many areas that benefit society such as clinical diagnosis, human-computer interaction, and social robotics. Human action recognition, however, is tremendously challenging for computers due to the subtlety of human actions and the complexity of video data. Critical to the success of [...]

PhD Thesis Defense
Robotics Institute,
Carnegie Mellon University

Underwater Localization and Mapping with Imaging Sonar

NSH 3305

Abstract: Acoustic imaging sonars have been used for a variety of tasks intended to increase the autonomous capabilities of underwater vehicles. Among the most critical tasks of any autonomous vehicle are localization and mapping, which are the focus of this work. The difficulties presented by the imaging sonar sensor have led many previous attempts at [...]

RI Seminar
Pieter Abbeel
Professor
Director, Berkeley Robot Learning Lab & Co-Director, Berkeley Artificial Intelligence (BAIR) Lab, UC Berkeley

Deep Learning for Robotics

1305 Newell Simon Hall

Abstract: Programming robots remains notoriously difficult.  Equipping robots with the ability to learn would by-pass the need for what otherwise often ends up being time-consuming task specific programming.  This talk will describe recent progress in deep reinforcement learning (robots learning through their own trial and error), in apprenticeship learning (robots learning from observing people), and [...]

VASC Seminar
Xiaodong Yang
Principle Scientist
QCraft

Temporal Modeling and Data Synthesis for Visual Understanding

GHC 6501

Abstract: In this talk, I will present two recent pieces of work on leveraging temporal information and synthetic data to enhance video and image understanding. In the first part, I will introduce a progressive learning framework, Spatio-TEmporalProgressive (STEP), for action detection in videos. STEP is able to more effectively make use of longer temporal information, [...]