Copy
View this email in your browser
Visit us on the web


News from IRIM | February 10, 2021 Edition
 
Robot Graphic
Career Options in Robotics | Academia vs Industry

A Panel Discussion

February 17, 2021 | 12pm | Virtual Event
 
Last semester, our panel discussed finding faculty positions in robotics. This semester, we continue that discussion and take a broader look at career options with a particular focus on academia vs industry. Our panel will include diverse perspectives and will address important items to consider when considering and pursuing a career robotics. 
 
Panel Members

Frank Dellaert is a Professor in the School of Interactive Computing at the Georgia Institute of Technology and a Research Scientist at Google AI. He joined Georgia Tech in 2001 after obtaining a Ph.D. from Carnegie Mellon’s School of Computer Science, where he worked with Hans Moravec, Chuck Thorpe, Sebastian Thrun, and Steve Seitz.

His  research is in the overlap between robotics and computer vision, and he is particularly interested in graphical model techniques to solve large-scale problems in mapping, 3D reconstruction, and increasingly model-predictive control.

Tom Collins currently has shared appointments with the Georgia Tech Research Institute and the Georgia Tech School of Electrical and Computer Engineering. He received a Bachelor’s degree in ME in 1980, an MSEE in 1982, and a Ph.D. in EE in 1994, all from Georgia Tech. His research interests include robotics, digital hardware design, modeling and simulation, and high-performance computing. His robotics contributions began with the IBM 7565 manipulator, a large, high-accuracy hydraulic/electric robot targeted at precision assembly tasks.

Anirban Mazumdar joined Georgia Tech as an Assistant Professor in Mechanical Engineering in 2018.  Dr. Mazumdar studies robot mobility with the goal of understanding and achieving agile, versatile, and efficient robot behaviors in unstructured environments.

Aaron Young is an Assistant Professor in the Woodruff School of Mechanical Engineering at Georgia Tech and a member of the Institute for Robotics & Intelligent Machines. He also is a program faculty member of the Biomedical Engineering School. He is director of the Exoskeleton Prosthetic & Intelligent Controls (EPIC) Lab focused on lower limb robotic augmentation. His research focuses on optimizing control systems in wearable robotic devices by studying their effect on human locomotion biomechanics in clinical populations.

Anup Parikh is a Senior Member of Technical Staff in the High Consequence Automation and Robotics Group at Sandia National Labs [aparikh@sandia.gov]


Moderator


Sam Coogan is an assistant professor in  the School of Electrical and Computer Engineering &  Civil and Environmental Engineering at Georgia Tech. He received the B.S. degree in Electrical Engineering from Georgia Tech and the M.S. and Ph.D. degrees in Electrical Engineering from the University of California, Berkeley. In 2015, he was a postdoctoral research engineer at Sensys Networks, Inc., and in 2012 he was a research intern at NASA’s Jet Propulsion Lab. Before joining Georgia Tech in 2017, he was an assistant professor in the Electrical Engineering department at UCLA from 2015–2017.
 


Robograds Graphic
 
Session Topic: Multi-Agent Systems

Speaker 1 | Fixed-time Stability in Multiagent Control under Input Constraints | Kunal Gard : PhD candidate in the Department of Aerospace Engineering, University of Michigan

Abstract: Various types of constraints are present in real-world applications due to structural and operational requirements. For example, spatial constraints, i.e., constraints requiring the system trajectories to evolve in a safe set at all times, while visiting goal set(s), are common in safety-critical applications. Furthermore, temporal constraints, i.e., constraints on convergence within a given user-defined time, appear in time-critical applications, for instance when a task must be completed within a given time frame. Thus, it is desired to synthesize control input that can fulfill such spatiotemporal requirements while satisfying input constraints. In this talk, a quadratic program (QP)-based formulation is presented to compute the control input that renders a safe set forwardinvariantand drives the closed-loop trajectories to a goal set within a user-defined time in the presence of input constraints. Such formulations are effective from a practical point of view since QPs can be solved very efficiently for real-time implementation. We will discuss the role of the slack terms, used in the QP for feasibility guarantees, in determining the domain of attraction for fixed-time stability under input constraints. Then, a multiagent  case with additive disturbances in the system dynamics and imperfect state measurements is discussed briefly.

Bio: Kunal Garg received his Bachelor of Technology degree in Aerospace Engineering from the Indian Institute of Technology, Mumbai, India in 2016 and Master of Science in Engineering degree in Aerospace Engineering from University of Michigan, Ann Arbor in 2019. He is currently a PhD candidate in the Department of Aerospace Engineering, University of Michigan. His research interests include robust multi-agent path planning using optimization methods, switched and hybrid system based analysis and control synthesis, finite- and fixed time stability of dynamical systems with applications to control synthesis for spatiotemporal specifications, and continuous-time optimization.

Speaker 2 | A Resilient Task Allocation Framework for Heterogeneous Robot Teams | Yousef Emam: PhD candidate at the Georgia Institute of Technology

Abstract: For multirobot teams with heterogeneous capabilities, typical task allocation methods assign tasks to robots based on the suitability of the robots to perform certain tasks. However, in real-word deployment scenarios, the suitability of a robot might be unknown prior to deployment or might vary due to changing environmental conditions. In this presentation, we discuss an adaptive task allocation framework which dynamically updates the suitability of the robots based on the real-time conditions.

Bio: Yousef Emam is a third year Robotics PhD student at the Georgia Institute of Technology, co-advised by Dr. Magnus Egerstedt and Dr. Zsolt Kira. His research interests lie in developing heterogeneous task allocation frameworks geared towards long-duration autonomy, safety of disturbed dynamical systems and safe learning.

 

Link: https://tinyurl.com/S21robograds

RESEARCH NEWS

 

Collective Worm and Robot “Blobs” Protect Individuals, Swarm Together

Georgia Tech Professor Daniel Goldman shows a smart active particle (smarticle), a simple robot used to study interactions similar to those of the “worm blobs” formed by California blackworms. (Credit: Christopher Moore, Georgia Tech) Individually, California blackworms live an unremarkable life eating microorganisms in ponds and serving as tropical fish food for aquarium enthusiasts. But together, tens, hundreds, or thousands of the centimeter-long creatures can collaborate to form a “worm blob,” a shape-shifting living liquid that collectively protects its members from drying out and helps them escape threats such as excessive heat.

While other organisms form collective flocks, schools, or swarms for such purposes as mating, predation, and protection, the Lumbriculus variegatus worms are unusual in their ability to braid themselves together to accomplish tasks that unconnected individuals cannot. A new study reported by researchers at the Georgia Institute of Technology describes how the worms self-organize to act as entangled “active matter,” creating surprising collective behaviors whose principles have been applied to help blobs of simple robots evolve their own locomotion.

The research, supported by the National Science Foundation and the Army Research Office, was reported Feb. 5 in the journal Proceedings of the National Academy of Sciences. Findings from the work could help developers of swarm robots understand how emergent behavior of entangled active matter can produce unexpected, complex, and potentially useful mechanically driven behaviors.

The spark for the research came several years ago in California, where Saad Bhamla was intrigued by blobs of the worms he saw in a backyard pond.

“We were curious about why these worms would form these living blobs,” said Bhamla, an assistant professor in Georgia Tech’s School of Chemical and Biomolecular Engineering. “We have now shown through mathematical models and biological experiments that forming the blobs confers a kind of collective decision-making that enables worms in a larger blob to survive longer against desiccation. We also showed that they can move together, a collective behavior that’s not done by any other organisms we know of at the macro scale.”

Such collective behavior in living systems is of interest to researchers exploring ways to apply the principles of living systems to human-designed systems such as swarm robots, in which individuals must also work together to create complex behaviors.

“The worm blob collective turns out to have capabilities that are more than what the individuals have, a wonderful example of biological emergence,” said Daniel Goldman, a Dunn Family Professor in Georgia Tech’s School of Physics, who studies the physics of living systems.

Read the Full Article Here
 

New Publications

Time-Informed Exploration For Robot Motion Planning 
Sagar Suhas Joshi, Seth Hutchinson, Panagiotis Tsiotras

Q-Search Trees: An Information-Theoretic Approach Towards Hierarchical Abstractions for Agents with Computational Limitations
Daniel T. Larsson, Dipankar Maity, Panagiotis Tsiotras

A Generalized A* Algorithm for Finding Globally Optimal Paths in Weighted Colored Graphs
Jaein Lim, Panagiotis Tsiotras

Learning Nash Equilibria in Zero-Sum Stochastic Games via Entropy-Regularized Policy Approximation
Qifan Zhang, Yue Guan, Panagiotis Tsiotras
 
Researcher & Student Accolades
 
Industrial Robot with TrophyHave you won/been nominated for an award from an academic or professional society? Have you been invited to speak at a conference or advisory panel? Do you have great new publications or lab news to share? IRIM wants to know!

Enter your information in the form linked to below and we will share your news via web and social media channels, as well as keep recorded for annual progress and impact reports.

This form will remain available through June 2021
.
IRIM Faculty Lab Highlight


Ai-Ping Hu; Principal Research Engineer (GTRI), Adjunct Professor (GT-ME)


The Intelligent Sustainable Technologies Division (ISTD) develops next-generation technologies to maximize operational efficiency in the agricultural and manufacturing industries. Our interdisciplinary teams of expert engineers and scientists combine their skills to deliver breakthroughs in automation systems, robotics, autonomous systems, advanced sensing, environmental treatment, and energy harvesting. Our goal is to transition concepts into real-world prototypes for ultimate commercial release.
Tarzan-robot-swinging: Researchers Jonathan Rogers and Ai-Ping Hu are shown with the Tarzan robot in a Georgia Tech lab. The robot will swing from cables to inspect crops in the field. | Photo Credit: Jason Maderer, Georgia Tech

Current Projects:
  • Collaborative Robot Arm Path Planning for Agricultural Applications (Harvesting, Thinning, Phenotyping)
  • Robotic Sensing and Manipulation of Biomaterials
  • Learning from Demonstration for Dexterous Manual Tasks
  • Robot Brachiation to Explore Locomotion on Flexible Infrastructure
  • Medical Robotics for High-Precision Intraspinal Needle Injection
  • GTRI Agricultural Robotics VIP course
Learn more about the lab here
EVPR COVID News & Guidance

Reminder: Lab Personnel Density Guidance
Georgia Tech is piloting a revised guideline to accommodate laboratories with lower personnel numbers and sufficient excess space in their laboratory. Read the revised guideline.

Weekly Testing Locations
If you live or work on campus, we strongly encourage you to get tested weekly, even if you aren’t experiencing Covid-19 symptoms. This is an essential part of protecting yourself and the Georgia Tech community. There are several options for getting tested, both on and off campus. See the current schedules and locations at this link.

Vaccine Roll-Out
The Institute has been working diligently with the Georgia Department of Public Health (DPH) to develop a vaccine rollout plan for the entire campus community. This plan consists of consecutive phases with corresponding groups. See the vaccine plane here.
Twitter
Facebook
Website

Institute for Robotics and Intelligent Machines (IRIM)
Klaus Advanced Computing Building
266 Ferst Drive
Atlanta, GA 30332-3000

Want to change how you receive these emails?
You can update your preferences or unsubscribe from this list.

Copyright © 2021 Institute for Robotics and Intelligent Machines (IRIM) at Georgia Tech
All rights reserved.