VASC Seminar
Assistant Research Professor
Robotics Institute,
Carnegie Mellon University

Challenges Facing Computational Face

GHC 6501

Abstract: Recent advances in computational face research make possible a growing range of scientific, behavioral, and commercial applications. Many companies are focusing on the future of computational face products and services, but number of critical research questions remain to be solved. These include 3D face alignment from 2D image, face analysis under extreme pose variation [...]

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 [...]