Calendar

Sep
15
Wed
LCSR Seminar: Tariq Iqbal “Toward Fluent Collaboration in Human-Robot Teams” @ https://wse.zoom.us/s/94623801186
Sep 15 @ 12:00 pm – 1:00 pm

Link for Live Seminar

Link for Recorded seminars – 2021/2022 school year

 

 

Abstract:

Robots currently have the capacity to help people in several fields, including health care, assisted living, and manufacturing, where the robots must share physical space and actively interact with people in teams. The performance of these teams depends upon how fluently all team members can jointly perform their tasks. To be successful within a group, a robot requires the ability to perceive other members’ actions, model interaction dynamics, predict future actions, and adapt their plans accordingly in real-time. In the Collaborative Robotics Lab (CRL), we develop novel perception, prediction, and planning algorithms for robots to fluently coordinate and collaborate with people in complex human environments. In this talk, I will highlight various challenges of deploying robots in real-world settings and present our recent work to tackle several of these challenges.

 

Biography:

Tariq Iqbal is an Assistant Professor of Systems Engineering and Computer Science (by courtesy) at the University of Virginia (UVA). Prior to joining UVA, he was a Postdoctoral Associate in the Computer Science and Artificial Intelligence Lab (CSAIL) at MIT. He received his Ph.D. in CS from the University of California San Diego (UCSD). Iqbal leads the Collaborative Robotics Lab (CRL), which focuses on building robotic systems that work alongside people in complex human environments, such as factories, hospitals, and educational settings. His research group develops artificial intelligence, computer vision, and machine learning algorithms to enable robots to solve problems in these domains.

Sep
22
Wed
LCSR Seminar: Andreas Maier “Known Operator Learning – An Approach to Unite Machine Learning, Signal Processing and Physics” @ https://wse.zoom.us/s/94623801186
Sep 22 @ 12:00 pm – 1:00 pm

Link for Live Seminar

Link for Recorded seminars – 2021/2022 school year

 

Abstract: We describe an approach for incorporating prior knowledge into machine learning algorithms. We aim at applications in physics and signal processing in which we know that certain operations must be embedded into the algorithm. Any operation that allows computation of a gradient or sub-gradient towards its inputs is suited for our framework. We derive a maximal error bound for deep nets that demonstrates that inclusion of prior knowledge results in its reduction. Furthermore, we show experimentally that known operators reduce the number of free parameters. We apply this approach to various tasks ranging from computed tomography image reconstruction over vessel segmentation to the derivation of previously unknown imaging algorithms. As such, the concept is widely applicable for many researchers in physics, imaging and signal processing. We assume that our analysis will support further investigation of known operators in other fields of physics, imaging and signal processing.

Short Bio: Prof. Dr. Andreas Maier was born on 26th of November 1980 in Erlangen. He studied Computer Science, graduated in 2005, and received his PhD in 2009. From 2005 to 2009 he was working at the Pattern Recognition Lab at the Computer Science Department of the University of Erlangen-Nuremberg. His major research subject was medical signal processing in speech data. In this period, he developed the first online speech intelligibility assessment tool – PEAKS – that has been used to analyze over 4.000 patient and control subjects so far.
From 2009 to 2010, he started working on flat-panel C-arm CT as post-doctoral fellow at the Radiological Sciences Laboratory in the Department of Radiology at the Stanford University. From 2011 to 2012 he joined Siemens Healthcare as innovation project manager and was responsible for reconstruction topics in the Angiography and X-ray business unit.
In 2012, he returned the University of Erlangen-Nuremberg as head of the Medical Reconstruction Group at the Pattern Recognition lab. In 2015 he became professor and head of the Pattern Recognition Lab. Since 2016, he is member of the steering committee of the European Time Machine Consortium. In 2018, he was awarded an ERC Synergy Grant “4D nanoscope”.  Current research interests focuses on medical imaging, image and audio processing, digital humanities, and interpretable machine learning and the use of known operators.

 

 

 

Sep
29
Wed
LCSR Seminar: Angie Liu “Towards Trustworthy AI: Distributionally Robust Learning under Data Shift” @ https://wse.zoom.us/s/94623801186
Sep 29 @ 12:00 pm – 1:00 pm

Link for Live Seminar

Link for Recorded seminars – 2021/2022 school year

 

Abstract:

The unprecedented prediction accuracy of modern machine learning beckons for its application in a wide range of real-world applications, including autonomous robots, fine-grained computer vision, scientific experimental design, and many others. In order to create trustworthy AI systems, we must safeguard machine learning methods from catastrophic failures and provide calibrated uncertainty estimates. For example, we must account for the uncertainty and guarantee the performance for safety-critical systems, like autonomous driving and health care, before deploying them in the real world. A key challenge in such real-world applications is that the test cases are not well represented by the pre-collected training data.  To properly leverage learning in such domains, especially safety-critical ones, we must go beyond the conventional learning paradigm of maximizing average prediction accuracy with generalization guarantees that rely on strong distributional relationships between training and test examples.

 

In this talk, I will describe a distributionally robust learning framework that offers accurate uncertainty estimation and rigorous guarantees under data distribution shift. This framework yields appropriately conservative yet still accurate predictions to guide real-world decision-making and is easily integrated with modern deep learning.  I will showcase the practicality of this framework in applications on agile robotic control and computer vision.  I will also introduce a survey of other real-world applications that would benefit from this framework for future work.

 

Biography:

Anqi (Angie) Liu is an Assistant Professor in the Department of Computer Science at the Whiting School of Engineering of the Johns Hopkins University. She is broadly interested in developing principled machine learning algorithms for building more reliable, trustworthy, and human-compatible AI systems in the real world. Her research focuses on enabling the machine learning algorithms to be robust to the changing data and environments, to provide accurate and honest uncertainty estimates, and to consider human preferences and values in the interaction. She is particularly interested in high-stake applications that concern the safety and societal impact of AI. Previously, she completed her postdoc in the Department of Computing and Mathematical Sciences of the California Institute of Technology. She obtained her Ph.D. from the Department of Computer Science of the University of Illinois at Chicago. She has been selected as the 2020 EECS Rising Stars. Her publications appear in top machine learning conferences like NeurIPS, ICML, ICLR, AAAI, and AISTATS.

Oct
6
Wed
LCSR Seminar: Daniela Rus “Learning Risk and Social Behavior in Mixed Human-Autonomous Vehicles Systems” @ https://wse.zoom.us/s/94623801186
Oct 6 @ 12:00 pm – 1:00 pm

Link for Live Seminar

Link for Recorded seminars – 2021/2022 school year

 

Abstract:

Deployment of autonomous vehicles (AV) on public roads promises increases in efficiency and safety, and requires intelligent situation awareness. We wish to have autonomous vehicles that can learn to behave in safe and predictable ways, and are capable of evaluating risk, understanding the intent of human drivers, and adapting to different road situations. This talk describes an approach to learning and integrating risk and behavior analysis in the control of autonomous vehicles. I will introduce Social Value Orientation (SVO), which captures how an agent’s social preferences and cooperation affect interactions with other agents by quantifying the degree of selfishness or altruism. SVO can be integrated in control and decision making for AVs. I will provide recent examples of self-driving vehicles capable of adaptation.

 

Biography:

Daniela Rus is the Andrew (1956) and Erna Viterbi Professor of Electrical Engineering and Computer Science, Director of the Computer Science and Artificial Intelligence Laboratory (CSAIL) at MIT, and Deputy Dean of Research in the Schwarzman College of Computing at MIT. Rus’ research interests are in robotics and artificial intelligence. The key focus of her research is to develop the science and engineering of autonomy. Rus is a Class of 2002 MacArthur Fellow, a fellow of ACM, AAAI and IEEE, a member of the National Academy of Engineering, and of the American Academy of Arts and Sciences. She is a senior visiting fellow at MITRE Corporation. She is the recipient of the Engelberger Award for robotics. She earned her PhD in Computer Science from Cornell University.

Oct
13
Wed
LCSR Seminar: Danail Stoyanov “Towards Understanding Surgical Scenes Using Computer Vision” @ https://wse.zoom.us/s/94623801186
Oct 13 @ 12:00 pm – 1:00 pm

Link for Live Seminar

Link for Recorded seminars – 2021/2022 school year

 

 

Abstract:

Digital cameras have dramatically changed interventional and surgical procedures. Modern operating rooms utilize a range of cameras to minimize invasiveness or provide vision beyond human capabilities in magnification, spectra or sensitivity. Such surgical cameras provide the most informative and rich signal from the surgical site containing information about activity and events as well as physiology and tissue function. This talk will highlight some of the opportunities for computer vision in surgical applications and the challenges in translation to clinically usable systems.

 

Bio:

Dan Stoyanov is a Professor of Robot Vision in the Department of Computer Science at University College London, Director of the Wellcome/EPSRC Centre for Interventional and Surgical Sciences (WEISS), a Royal Academy of Engineering Chair in Emerging Technologies and Chief Scientist at Digital Surgery Ltd. Dan first studied electronics and computer systems engineering at King’s College London before completing a PhD in Computer Science at Imperial College London where he specialized in medical image computing.

 

Oct
20
Wed
LCSR Seminar: Pablo Arbelaez “Towards Robust Artificial Intelligence” @ https://wse.zoom.us/s/94623801186
Oct 20 @ 12:00 pm – 1:00 pm

Link for Live Seminar

Link for Recorded seminars – 2021/2022 school year

 

 

Abstract:

I will discuss recent efforts at CinfonIA in enhancing interpretability in deep neural networks through the use of adversarial robustness and multimodal information.

 

Biography:

Pablo Arbeláez received the PhD with honors in Applied Mathematics from the Université Paris Dauphine in 2005. He was Senior Research Scientist with the Computer Vision Group at UC Berkeley from 2007 to 2014. He currently holds a faculty position in the Department of Biomedical Engineering at Universidad de los Andes in Colombia. Since 2020, he leads the Center for Research and Formation in Artificial Intelligence (CinfonIA) at UniAndes. His research interests are in computer vision and machine learning, in which he has worked on several problems, including perceptual grouping, object recognition and the analysis of biomedical images.

Oct
27
Wed
LCSR Seminar: LCSR Faculty “Interviewing for Jobs in Academia and Industry” @ https://wse.zoom.us/s/94623801186
Oct 27 @ 12:00 pm – 1:00 pm

Link for Live Seminar

Link for Recorded seminars – 2021/2022 school year

 

LCSR Faculty “Interviewing for Jobs in Academia and Industry”

 

Speakers: Louis Whitcomb, Marin Kobilarov, and the LCSR Faculty

Abstract:
This LCSR professional development seminar will review the process of interviewing for jobs in academia (e.g. faculty, post-doc, and scientist positions) and industry (e.g. engineering, scientist, and management positions), and will provide tips and best-practices for successful interviewing.

 

Nov
3
Wed
LCSR Seminar: Kel Guerin “Building an End-User Focused Operating System for Robotics” @ https://wse.zoom.us/s/94623801186
Nov 3 @ 12:00 pm – 1:00 pm

Link for Live Seminar

Link for Recorded seminars – 2021/2022 school year

 

Abstract:

There are more than 2 million industrial robots used worldwide every day, and yet these devices represent one of the most fragmented technologies in the world. With more than 100 brands of industrial robots, each with their own proprietary, difficult to learn software and programming languages, we are not seeing the exponential growth we expected out of robots. The computer industry faced a similar challenge in the early 1980s with the advent of the PC, and computers did not see explosive growth until a few key platforms emerged that focused on making computers accessible to end users, and run on a common software platform. At READY robotics, we believe the same is true for robots, and that is why we are building Forge/OS, our “Windows” for the robotics space that lets every robot speak the same language and provide the same award winning user experience to end-users. We will talk about how this technology came about, how we think it can change the future, and discuss the journey from the initial research performed at Johns Hopkins University up to today.

 

Biography:

Kel Guerin has been working in the robotics space for more than 10 years, focusing on the design and usability of a wide variety of robots, including systems for space exploration, deep mining, surgery, and industrial manufacturing. While obtaining his Ph.D. from Johns Hopkins University (Defended 2016), Kel worked specifically on the challenge of making industrial robots more flexible and easy to use. The result was his award-winning Forge Operating System and easy-to-use programming interface for industrial robots. Kel spun out his technology into READY Robotics, an industrial robotics start-up he co-founded in 2016. His work has been featured in the Wall Street Journal, Forbes, and READY’s products have been called “the Swiss Army knife of robots” by Inc. magazine.

Nov
10
Wed
LCSR Seminar: Maya Cakmak @ https://wse.zoom.us/s/94623801186
Nov 10 @ 12:00 pm – 1:00 pm
Nov
17
Wed
LCSR Seminar: Alaa Eldin Abdelaal “An “Additional View” on Human-Robot Interaction and Autonomy in Robot-Assisted Surgery” @ https://wse.zoom.us/s/94623801186
Nov 17 @ 12:00 pm – 1:00 pm

Link for Live Seminar

Link for Recorded seminars – 2021/2022 school year

 

Abstract:

Robot-assisted surgery (RAS) has gained momentum over the last few decades with nearly 1,200,000 RAS procedures performed in 2019 alone using the da Vinci Surgical System, the most widely used surgical robotics platform. The current state-of-the-art surgical robotic systems use only a single endoscope to view the surgical field. In this talk, we present a novel design of an additional “pickup” camera that can be integrated into the da Vinci Surgical System. We then explore the benefits of our design for human-robot interaction (HRI) and autonomy in RAS. On the HRI side, we show how this “pickup” camera improves depth perception as well as how its additional view can lead to better surgical training. On the autonomy side, we show how automating the motion of this camera provides better visualization of the surgical scene. Finally, we show how this automation work inspires the design of novel execution models of the automation of surgical subtasks, leading to superhuman performance.

 

Biography:

Alaa Eldin Abdelaal is a PhD candidate at the Robotics and Control Laboratory at the University of British Columbia and a visiting graduate scholar at the Computational Interaction and Robotics Lab at Johns Hopkins University. He holds a B.Sc. in Computer and Systems Engineering from Mansoura University in Egypt and a M.Sc. in Computing Science from Simon Fraser University in Canada. His research interests are at the intersection of autonomy and human-robot interaction for human skill augmentation and decision support with application to surgical robotics. His work is co-advised by Dr. Tim Salcudean and Dr. Gregory Hager. His research has been recognized with the Best Bench-to-Bedside Paper Award at the International Conference on Information Processing in Computer-Assisted Interventions (IPCAI) 2019. He is the recipient of the Vanier Canada Graduate Scholarship, the most prestigious scholarship for PhD students in Canada.