VASC Seminar
Andrew Owens
Assistant Professor
Electrical Engineering & Computer Science , University of Michigan

Learning Visual, Audio, and Cross-Modal Correspondences

Newell-Simon Hall 3305

Abstract:  Today's machine perception systems rely heavily on supervision provided by humans, such as labels and natural language. I will talk about our efforts to make systems that, instead, learn from two ubiquitous sources of unlabeled data: visual motion and cross-modal sensory associations. I will begin by discussing our work on creating unified models for [...]

VASC Seminar
Lachlan MacDonald
Postdoc
Australian Institute for Machine Learning, University of Adelaide

Towards a formal theory of deep optimisation

Newell-Simon Hall 3305

Abstract:  Precise understanding of the training of deep neural networks is largely restricted to architectures such as MLPs and cost functions such as the square cost, which is insufficient to cover many practical settings.  In this talk, I will argue for the necessity of a formal theory of deep optimisation.  I will describe such a [...]

VASC Seminar
Christoph Lassner
Senior Research Scientist
Epic Games

Towards Interactive Radiance Fields

Newell-Simon Hall 3305

Abstract:  Over the last years, the fields of computer vision and computer graphics have increasingly converged. Using the exact same processes to model appearance during 3D reconstruction and rendering has shown tremendous benefits, especially when combined with machine learning techniques to model otherwise hard-to-capture or -simulate optical effects. In this talk, I will give an [...]

RI Seminar
Dorsa Sadigh
Assistant Professor
Computer Science Electrical Engineering, Stanford University

Learning Representations for Interactive Robotics

Newell-Simon Hall 1305

In this talk, I will be discussing the role of learning representations for robots that interact with humans and robots that interactively learn from humans through a few different vignettes. I will first discuss how bounded rationality of humans guided us towards developing learned latent action spaces for shared autonomy. It turns out this “bounded rationality” is not a [...]

RI Seminar
Russ Tedrake
Professor
Electrical Engineering & Computer Science, MIT

Motion Planning Around Obstacles with Graphs of Convex Sets

1305 Newell Simon Hall

Abstract: In this talk, I'll describe a new approach to planning that strongly leverages both continuous and discrete/combinatorial optimization. The framework is fairly general, but I will focus on a particular application of the framework to planning continuous curves around obstacles. Traditionally, these sort of motion planning problems have either been solved by trajectory optimization [...]

RI Seminar
Jorgen Pedersen
Chief Operating Officer
Sarcos Technology and Robotics Corporation

RE2 Robotics: from RI spinout to Acquisition

1305 Newell Simon Hall

Abstract: It was July 2001.  Jorgen Pedersen founded RE2 Robotics.  It was supposed to be a temporary venture while he figured out his next career move.  But the journey took an unexpected course.  RE2 became a leading developer of mobile manipulation systems.  Fast forward to 2022, RE2 Robotics exited via an acquisition to Sarcos Technology and [...]

VASC Seminar
Rika Antonova
Postdoctoral Scholar
Stanford University

Enabling Self-sufficient Robot Learning

3305 Newell-Simon Hall

Abstract:  Autonomous exploration and data-efficient learning are important ingredients for helping machine learning handle the complexity and variety of real-world interactions. In this talk, I will describe methods that provide these ingredients and serve as building blocks for enabling self-sufficient robot learning. First, I will outline a family of methods that facilitate active global exploration. [...]

RI Seminar
David Fouhey
Assistant Professor
University of Michigan

Understanding the Physical World from Images

1305 Newell Simon Hall

If I show you a photo of a place you have never been to, you can easily imagine what you could do in that picture. Your understanding goes from the surfaces you see to the ones you know are there but cannot see, and can even include reasoning about how interaction would change the scene. [...]

VASC Seminar
Vasudevan (Vasu) Sundarababu
SVP & Head of Digital Engineering
Centific

How Computer Vision Helps – from Research to Scale

3305 Newell-Simon Hall

Abstract:  Vasudevan (Vasu) Sundarababu, SVP and Head of Digital Engineering, will cover the topic: ‘How Computer Vision Helps – from Research to Scale’. During his time, Vasu will explore how Computer Vision technology can be leveraged in-market today, the key projects he is currently leading that leverage CV, and the end-to-end lifecycle of a CV initiative - [...]