Once every week while school is in session, EECS invites a distinguished researcher or practitioner in a computer science or electrical and computer engineering-related field to present their ideas and/or work. Talks are generally targeted to electrical engineering and computer science graduate students. This colloquium series is free and open to everyone.

Upcoming Colloquia

Autonomous mobile systems: modelling, control and planning

Monday, February 18, 2019 - 10:00am to 11:00am
Rogers 226

Speaker Information

Corina Barbalata
Postdoctoral Research Fellow
Naval Architecture and Marine Engineering Department
University of Michigan

Abstract

The new generations of mobile robots have practical configurations and are designed to perform tasks in cluttered and dynamic environments (e.g smart factories, household environments or disaster areas) demanding robust and safe behavior. Unfortunately due to their complex mechanical design, nonlinear characteristics, and limited actuation capabilities, the mobile robots have difficulties performing complex tasks in these scenarios. Their abilities are even more limited in underwater environments, where the hydrodynamic effects and the floating-base configuration of the mobile manipulators restrain their autonomy. From a research perspective of both terrestrial mobile manipulator systems and floating-base underwater manipulators, there are important challenges to solve in topics such as coordinated whole body control, safe interaction with the environment, disturbance rejection and energy efficiency. Dr. Corina Barbalata has done extensive research in the area of mathematical modelling, control and planning architectures, addressing the previously mentioned challenges. She has focused on model-based adaptive control structures for improving the autonomy of lightweight underwater vehicle-manipulator systems, and optimal planning strategies for increasing the safety in mobile manipulation applications. Most recently, her research has explored the importance of designing robust architectures that bridge the low-level control architectures with high-level planning strategies, integrating in a systematic manner the available sensor information. In this seminar talk, Dr. Barbalata will discuss her research, its applications, and the future direction and possibilities of this work.

Speaker Bio

Corina Barbalata is currently a postdoctoral research fellow in the Deep Robot Optical Perception (DROP) Laboratory from the Naval Architecture and Marine Engineering Department at University of Michigan, USA. In 2017 she received a PhD in Robotics from Heriot-Watt University, UK and in 2013 she obtained a double MSc degree in Computer Vision and Robotics from University of Burgundy in France and Heriot-Watt University, UK. She graduated with a BSc in Automations in 2011 from Transilvania University in Romania. Between 2013-2017 she was part of the research and development department of SeeByte Ltd., UK and she held a guest investigator position in the Woods Hole Oceanographic Institution between 2017-2018. Her research interests include mathematical modelling, low-level control structures, planning algorithms and perception systems, focusing on underwater robotic systems and mobile manipulation. She is interested in developing efficient and safe solutions for real-world robotic applications with social and environmental merits.

The Challenge of Ant Sized Robots

Tuesday, February 19, 2019 - 10:00am to 11:00am
Rogers 226

Speaker Information

Ryan St. Pierre
Post-Doctoral Researcher
Carnegie Mellon University

Abstract

The highly dynamic mobility of insects inspires an entire field of microrobotics, with future visions of ubiquitous small-scale robots. However, current microrobots pale in comparison to insects not only in mobility and application capabilities, but overall in autonomy. Insects take advantage of their muscles as actuators, neural systems for control, mechanisms from multiple materials, and a variety of sensors to accomplish tasks. This leads to driving questions (1) what enables highly dynamic mobility, and ultimately autonomy, in insects and (2) how can we apply lessons learned about insects to small-scale robots that are inherently resource constrained?

To begin answering these questions, physical, robotic models are utilized as reduced parameter analogs to biological systems. An experimental platform and robots are presented to study locomotion that is scalable and adaptable for different robot designs from 1 g to 1 mg. Experimental data is coupled with numerical models to begin understanding the role of legs and material choice as robots scale down in size. Multiple materials enable dynamic behaviors in insects, while robots can use material to program desired behaviors. Bringing together experimental robotic platforms, biological system insights, and computation models, this work points toward directions to enable future autonomy in microrobotics platforms.

Speaker Bio

Ryan St. Pierre is presently a post-doctoral researcher at Carnegie Mellon University working at the intersection of biological systems and microrobotics. He received his doctoral degree in 2018 from the University of Maryland, with a research focus on small-scale locomotion, and MS  and BS degrees in 2013 from Northeastern University. His research interests include microsystems and robotics to create highly dynamic microrobots inspired by insects at similar scales. His work in microrobotics has been recognized with the Best Paper award at the 2018 Solid-State Sensors, Actuators, and Microsystems Workshop and covered by IEEE Spectrum.

Modeling and Control for Robotic Assistants

Wednesday, February 20, 2019 - 10:00am to 11:00am
Rogers 226

Speaker Information

Monroe D. Kennedy III
Ph.D. Candidate
Mechanical Engineering and Applied Mechanics
University of Pennsylvania

Abstract

As advances are made in robotic hardware, the capacity of the complexity of tasks they are capable of performing also increases. One goal of modern robotics is to introduce robotic platforms that require very little augmentation of their environments to be effective and robust. Therefore the challenge for the Roboticist is to develop algorithms and control strategies that leverage knowledge of the task while retaining the ability to be adaptive, adjusting to perturbations in the environment and task assumptions.

These strategies will be discussed in the context of a wet-lab robotic assistant. Motivated by collaborations with a local pharmaceutical company, we will explore two relevant tasks. First, we will discuss a robot-assisted rapid experiment preparation system for research and development scientists. Second, we will discuss ongoing work for intelligent human-robot cooperative transport with limited communication. These tasks are the beginning of a suite of abilities for an assisting robotic platform that can be transferred to similar applications useful to a diverse set of end-users.

Speaker Bio

Monroe D. Kennedy III is a Ph.D. candidate in the Mechanical Engineering and Applied Mechanics department at the University of Pennsylvania and is a member of the Kumar Lab. He received his Bachelor of Science from the University of Maryland Baltimore County in 2012, he then received his Masters in Robotics from the University of Pennsylvania in 2016. He is co-advised in his dissertation by Professors Kostas Daniilidis and Vijay Kumar.

Monroe’s research is in robotic manipulation for human-robot collaborative tasks. His latest research thrusts include robotic wet-lab experiment preparation for which the Penn team was a finalist in the KUKA innovation award at the Hannover Messe in April 2018. His latest work also includes human-robot cooperative carrying, where the robot leverages implicit cues from the human leader coupled with context from local obstacles to transport efficiently.

Monroe has mentored three undergraduate students through ‘Research Experiences for Undergraduates’. He has been a senior project mentor, and he was an NSF ‘Research Experience for Teachers’ mentor for two years, mentoring middle school teachers in robotics research. He received the `Outstanding Teaching Assistant Award in Mechanical Engineering’ and has given numerous presentations for community outreach through the GRASP Lab.

Monroe is a recipient of the GEM fellowship and NSF Graduate Fellowship awards. He is a member of both ASME and IEEE. Monroe’s latest research can be found at www.monroekennedy3.com.

Wildbook - Photographic Censusing of Wildlife

Monday, February 25, 2019 - 4:00pm to 4:50pm
Weniger Hall 151

Speaker Information

Jason Parham
Senior Computer Vision Research Engineer, Wild Me
Computer Science Ph.D. Candidate, Rensselaer Polytechnic Institute, Troy, NY

Abstract

As the price of photography and video equipment drops while availability improves, visual data from the public is becoming the most abundant source of wildlife data.  However, curating this high volume of data from "citizen science" and social media poses new scalability challenges for both researchers and computer scientists alike.  This talk introduces the Wildbook platform -- an open-source web-based project (wildbook.org) -- that leverages a suite of deep learning tools to automatically process high volumes of image data for conservation.  The platform uses Convolutional Neural Networks (CNNs) on several computer vision tasks, including: image classification, bounding box regression, instance classification, class segmentation, and object of interest classification.  Our deep learning stack utilizes Theano and PyTorch on the NVIDIA's CUDA, CNMeM, and CuDNN deep learning stack and employs multiple Titan V GPUs for efficient processing.  Further, instance recognition allows Wildbook to individually identify individual animals through time using a pipeline of SIFT features to find distinctive patches, Approximate Nearest Neighbors to find visual neighbors, and LNBNN to associate and re-rank visual match correspondences.  A random forest pair-wise match verifier is then used to curate animal sightings for human-in-the-loop population curation.  Lastly, our computer vision pipeline works alongside an intelligent agent that can automatically ingest video data from YouTube using NLP and OCR with Azure Cognitive Services.   We present our conservation work for wildlife across the globe in the context of the latest advances in deep learning and how Wildbook is helping to convert wildlife conservation into a data-driven science. 

Speaker Bio

Jason Parham received his B.S. in Computer Science / Mathematics from Pepperdine University in Malibu, CA in 2008 and holds a M.S. in Computer Science from RPI in Troy, NY.  Jason is finishing his Ph.D. as a candidate under the advising of Dr. Charles Stewart at RPI.  Jason’s Masters thesis was on the design and implementation of a citizen science-powered photographic censusing of the zebra and giraffe in the Nairobi National Park.  His current doctoral research focuses on animal detection and classification, using deep learning on wildlife imagery, to power automated photographic censusing.  Jason is a co-developer of Wildbook‘s Image Analysis components, which are used to monitor animal populations in conservancies around Kenya and which integrate with the Wildbook data management platform for a suite of species. Previously, Jason worked three years for Kitware, Inc. in Clifton Park on detecting vehicles and military aircraft in overhead satellite imagery.  Below are some select publications: - An Animal Detection Pipeline for Identification Lake Tahoe, CA. IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV 2018) Mar 2018
- Wildbook: Crowdsourcing, Computer Vision, and Data Science for Conservation New York, NY. BLOOMBERG DATA FOR GOOD EXCHANGE 2017 Sep 2017
- Animal Population Estimation Using Flickr Images Troy, NY ACM WEB SCIENCE CONFERENCE 2017 (WEBSCI‘17). INTERNATIONAL WORKSHOP ON THE SOCIAL WEB FOR ENVIRONMENTAL AND ECOLOGICAL MONITORING (SWEEM 2017)
- Efficient Generation of Image Chips for Training Deep Learning Networks Anaheim, CA. PROCEEDINGS OF SOCIETY OF PHOTO-OPTICAL INSTRUMENTATION ENGINEERS (SPIE) · AUTOMATIC TARGET RECOGNITION (ATR). XXVII Apr 2017.

 

Energy Efficient Computing in Nanoscale CMOS

Gaulke Distinguished Lecture
Friday, March 1, 2019 - 4:00pm to 4:50pm
TBD

Speaker Information

Vivek De
Intel Fellow
Director of Circuit Technology Research
Intel Labs

Abstract

Future computing systems spanning exascale supercomputers to wearable devices demand orders of magnitude improvements in energy efficiency while providing desired performance. The system-on-chip (SoC) designs need to span a wide range of performance and power across diverse platforms and workloads. The designs must achieve robust near-threshold-voltage (NTV) operation in nanoscale CMOS  process while supporting a wide voltage-frequency operating range with  minimal impact on die cost. We will discuss circuit and design technologies to overcome the challenges posed by device parameter variations, supply noises, temperature excursions, aging-induced degradations, workload and activity changes, and reliability considerations. The major pillars of energy-efficient SoC designs are: (1) circuit/design optimizations for fine-grain multi-voltage & wide dynamic range, (2) fine-grain on-die power delivery & management, (3) dynamic adaptation & reconfiguration, (4) dynamic on-die error detection & correction, and (5) efficient interconnects.

Speaker Bio

Vivek De is an Intel Fellow and Director of Circuit Technology Research in Intel Labs. He is responsible for providing strategic technical directions for long term research in future circuit technologies and leading energy efficiency research across the hardware stack. He has 282 publications in refereed international conferences and journals with a citation H-index of 76, and 224 patents issued with 30 more patents filed (pending). He received an Intel Achievement Award for his contributions to an integrated voltage regulator technology. He received a Best Paper Award at the 1996 IEEE International ASIC Conference, and nominations for Best Paper Awards at the 2007 IEEE/ACM Design Automation Conference (DAC) and 2008 IEEE/ACM International Conference on Computer-Aided Design (ICCAD). He also co-authored a paper nominated for the Best Student Paper Award at the 2017 IEEE International Electron Devices Meeting (IEDM). One of his publications was recognized in the 2013 IEEE/ACM Design Automation Conference (DAC) as one of the "Top 10 Cited Papers in 50 Years of DAC". Another one of his publications received the “Most Frequently Cited Paper Award” in the IEEE Symposium on VLSI Circuits at its 30th Anniversary in 2017. He was recognized as a Prolific Contributor to the IEEE International Solid-State Circuits Conference (ISSCC) at its 60th Anniversary in 2013, and a Top 10 Contributor to the IEEE Symposium on VLSI Circuits at its 30th Anniversary in 2017 . He received the Outstanding Evening Session Award at the 2018 International Solid-State Circuits Conference (ISSCC). He served as an IEEE/EDS Distinguished Lecturer in 2011 and an IEEE/SSCS Distinguished Lecturer in 2017-18. He received the 2017 Distinguished Alumnus Award from the Indian Institute of Technology (IIT) Madras. He received a B.Tech from IIT Madras, India, a MS from Duke University, Durham, North Carolina, and a PhD from Rensselaer Polytechnic Institute, Troy, New York, all in Electrical Engineering. He is a Fellow of the IEEE.

Past Colloquia

Kaushik Jayaram
Friday, February 8, 2019 - 10:00am to 11:00am
Houssam Abbas
Monday, January 28, 2019 - 4:00pm to 4:50pm
Saurabh Bagchi
Monday, November 26, 2018 - 4:00pm to 4:50pm
Brian Johnson
Monday, November 19, 2018 - 4:00pm to 4:50pm
Rodrigo Rubira Branco
Monday, November 5, 2018 - 4:00pm to 4:50pm
Finale Doshi-Velez
Monday, October 22, 2018 - 4:00pm to 4:50pm
Yvo Desmedt
Wednesday, October 17, 2018 - 11:00am to 11:50am
Sanjit K. Mitra
Monday, October 15, 2018 - 4:00pm to 4:50pm

Pages