RI Seminar
C. Karen Liu
Associate Professor
School of Interactive Computing, Georgia Tech

Modeling Human Movements for Robotics

NSH 1305

Abstract: Creating realistic virtual humans has traditionally been considered a research problem in Computer Animation primarily for entertainment applications. With the recent breakthrough in collaborative robots and deep reinforcement learning, accurately modeling human movements and behaviors has become a common challenge faced by researchers in robotics, artificial intelligence, as well as Computer Animation. In this [...]

RoboOrg Meta Seminar
Professor
Robotics Institute,
Carnegie Mellon University

Don’t forget to have fun

1305 Newell Simon Hall

Abstract: I like to think that robots should be rational agents, modeled on human behavior. I teach a course about using optimization to plan over time by maximizing utility. I note that a series of Nobel Prizes in Economics, starting with CMU's own AI pioneer Herb Simon and including one to Daniel Kahneman and this [...]

RI Seminar
Dmitry Berenson
Assistant Professor
Electrical Engineering & Computer Science Department, University of Michigan

What Matters for Deformable Object Manipulation

NSH 1305

Abstract: Deformable objects such as cables and clothes are ubiquitous in factories, hospitals, and homes. While a great deal of work has investigated the manipulation of rigid objects in these settings, manipulation of deformable objects remains under-explored. The problem is indeed challenging, as these objects are not straightforward to model and have infinite-dimensional configuration spaces, [...]

VASC Seminar
Ben Burchfiel
PhD Candidate
Duke

Bayesian Eigenobjects: A Unified Framework for 3D Robot Perception

GHC 6501

  Abstract: Robot-object interaction requires several key perceptual building blocks including object pose estimation, object classification, and partial-object completion. These tasks form the perceptual foundation for many higher level operations including object manipulation and world-state estimation. Most existing approaches to these problems in the context of 3D robot perception assume an existing database of objects [...]

VASC Seminar
Laurens van der Maaten
Research Scientist
Facebook AI Research

Two Tales about Image Classification

GHC 6501

Abstract: This talk tells two tales about image-classification systems, both of which are motivated by the real-world deployment of such systems. The first tale introduces a new convolutional neural network architecture, called multi-scale DenseNets, with the ability to adapt dynamically to computational resource limits at inference time. The network uses progressively growing multi-scale convolutions, dense [...]

RI Seminar
Deanna Gates
Assistant Professor
University of Michigan

Optimizing ankle prostheses to improve walking in transtibial amputees

NSH 1305

Abstract: With a prosthetic device, people with a lower limb amputation can remain physically active, but most do not achieve medically recommended physical activity standards and are therefore at a greater risk of obesity and cardiovascular disease. Their reduced activity may be attributed to the 10 - 30% increase in energetic cost during walking compared [...]

VASC Seminar
Hongdong Li
Reader/Associate Professor
Australian National University

Dense 3D Shape Reconstruction of Complex Dynamic Scene with a Single Monocular Camera 

GHC 6501

Abstract: In this talk, I will describe our recent work (presented at ICCV 2017) on monocular camera based 3D geometry reconstruction of a non-rigid dynamic scene.   We aim to answer an open question in multi-view geometry, namely, "Is it possible to recover the 3D structure of a complex dynamic environment from two image frames captured by [...]

VASC Seminar
Larry Zitnick
Research Lead
Facebook AI Research

Learning to Visually Reason

GHC 6115

Abstract: Visual reasoning is a core capability of artificial intelligence. It is a necessity for effective communication, planning, and for question/answering tasks. In this talk, I discuss some recent explorations into visual reasoning for question/answering, game playing and dialog. I also describe our new reinforcement learning platform ELF; an Extensive, Lightweight and Flexible research platform [...]