Maryland Robotics Center Research Symposium 2023

Symposium RegistrationIndustry Night Registration

Spring Berman, Associate Professor, Arizona State University                 

 

Pratik Chaudhari, Assistant Professor, University of Pennsylvania

 

Title:  Move, Manipulate, Multitask, Map: Model-Based Controllers for Versatile Swarms

Robotic swarms are being developed for a range of tasks, including environmental sensing, infrastructure inspection, disaster response, exploration, and agricultural operations. Many of these applications will require swarms to function robustly in uncertain environments. This talk will present model-based approaches to controlling swarms of robots that must rely only on local sensing and signaling, often without global localization, inter-robot communication, or prior data about the domain. Despite these constraints, it is possible to design scalable swarm controllers for a variety of objectives, including spatial coverage, collision-free navigation, cooperative payload transport, task allocation, feature mapping, and scalar field estimation, by applying feedback control and optimization techniques to stochastic and deterministic dynamical models that describe the swarm at different levels of abstraction. The swarm behaviors produced by these controllers will be illustrated in simulations and experiments with small mobile robots. Outstanding challenges and possible future directions for research and applications of swarm control will also be discussed.

Spring Berman is an Associate Professor of Mechanical and Aerospace Engineering and Graduate Faculty in Computer Science and Exploration Systems Design at Arizona State University (ASU). She directs the Autonomous Collective Systems Laboratory and is an Associate Director of the Center for Human, Artificial Intelligence, and Robot Teaming (CHART) within the ASU Global Security Initiative. Dr. Berman received Ph.D. and M.S.E. degrees in Mechanical Engineering and Applied Mechanics from the University of Pennsylvania and the B.S.E. degree in Mechanical and Aerospace Engineering from Princeton University. Prior to joining ASU in 2012, she was a postdoctoral researcher in Computer Science at Harvard University. Dr. Berman’s research focuses on the synthesis of control strategies, including bio-inspired controllers, for robotic swarms and other types of distributed systems, such as soft robot manipulators. Her current research also uses virtual and small-scale physical testbeds to develop autonomous vehicle controllers that mimic human-like driving behaviors. She was a recipient of the ONR Young Investigator Award and the DARPA Young Faculty Award.

Title: A Picture of the Prediction Space of Deep Networks

Deep networks have many more parameters than the number of training data and can therefore overfit---and yet, they predict remarkably accurately in practice. Training such networks is a high-dimensional, large-scale and non-convex optimization problem and should be prohibitively difficult---and yet, it is quite tractable. This talk aims to illuminate these puzzling contradictions.

We will argue that deep networks generalize well because of a characteristic structure in the space of learnable tasks. The input correlation matrix for typical tasks has a “sloppy” eigenspectrum where, in addition to a few large eigenvalues, there is a large number of small eigenvalues that are distributed uniformly over a very large range. As a consequence, the Hessian and the Fisher Information Matrix of a trained network also have a sloppy eigenspectrum. Using these ideas, we will demonstrate an analytical non-vacuous PAC Bayes generalization bound for general deep networks.

We will next develop information-geometric techniques to analyze the trajectories of the predictions of deep networks during training. By examining the underlying high-dimensional probabilistic models, we will reveal that the training process explores an effectively low dimensional manifold. Networks with a wide range of architectures, sizes, trained using different optimization methods, regularization techniques, data augmentation techniques, and weight initializations lie on the same manifold in the prediction space. We will also show that predictions of networks being trained on different tasks (e.g., different subsets of ImageNet) using different representation learning methods (e.g., supervised, meta-, semi supervised and contrastive learning) also lie on a low-dimensional manifold.

Pratik Chaudhari is an Assistant Professor in Electrical and Systems Engineering and Computer and Information Science at the University of Pennsylvania. He is a core member of the GRASP Laboratory. From 2018-19, he was a Senior Applied Scientist at Amazon Web Services and a Postdoctoral Scholar in Computing and Mathematical Sciences at Caltech. Pratik received his PhD (2018) in Computer Science from UCLA, and his Master's (2012) and Engineer's (2014) degrees in Aeronautics and Astronautics from MIT. He was a part of NuTonomy Inc. (now Hyundai-Aptiv Motional) from 2014-16. He is the recipient of the Amazon Machine Learning Research Award (2020), NSF CAREER award (2022) and the Intel Rising Star Faculty Award (2022).

MRC Industry Night which will take place May 24th, 2023 from 6-10pm in the 1101 A. James Clark Hall Forum. Industry Night will feature talks, panel discussion, and networking with local robotics companies and UMD students. 

Industry Night Agenda May 24, 2023 PDF iconPDF

Opening Remarks by Michael Otte, MRC Symposium General Chair 6:00pm-6:10pm

Presentation Session

  • Robotics from Sea to Space. Mark Stevens, Principal Program Manager, Microsoft Advanced Autonomy and Applied Robotics team.
  • Starting a robotics company, filing for a patent, and the state of the agricultural robotics industry in the US and Europe. Jeff Chandler, CEO Easton Robotics, LLC.
  • Robotics at the Edge: Agile and Intelligent Machines for Operating in Challenging Environments. Joseph L. Moore, Chief Scientist, Robotics, Research and Exploratory Development Department. Johns Hopkins University Applied Physics Laboratory.
  • NextStep Robotics: How StartUp's can Leverage the Local Ecosystem for Talent and Funding. Brad Hennessie, CEO/Co-Founder NextStep Robotics.
6:10pm-7:30pm
Networking Event with Coffee and Snacks 7:30pm-8:00pm

Panel Discussion: Robotics Outside of Academia

  • John Crupi, Chief Robot Officer. Kick Robotics, LLC.
  • Don Sofge, Head, Distributed Autonomous Systems Section, US Naval Research Lab.
  • Sam Migirditch, Research Scientist, Metron Inc.Derek Paley, Hydrodynamics, Sensing & Control in Schooling Fish: From Biology to Efficient Multi-Vehicle Systems
8:30pm-9:15pm
Networking Event 9:15pm-10:00pm

 

MRC Research Symposium will take place May 25th, 2023 from 8:45am-6:00pm in the 1101 A. James Clark Hall Forum. The symposium will feature keynote presentations by faculty from other institutions along with presentations from MRC faculty and students.

Agenda for Research Symposium May 25, 2023 PDF iconPDF

Opening Remarks by Derek Paley, Director of Maryland Robotics Center 8:45am-9:00am

Keynote 1
Pratik Chaudhari, talk title to be posted.

9:00am-10:00am
Morning Coffee Break 10:00am-10:20am

Technical Session 1

  • Derek Paley, Hydrodynamics, Sensing & Control in Schooling Fish: From Biology to Efficient Multi-Vehicle Systems
  • John Aloimonos, Minimal cognitive systems
  • George Kontoudis, Scalable Multi-Robot Active Exploration using Decentralized Gaussian Processes

10:20am-11:50am
Poster Spotlight Talks 11:50am:12:10pm
Lunch & Poster Session
Lunch will be provided for people who registered by May 17.
12:10pm-1:30pm

Keynote 2
Spring Berman, Move, Manipulate, Multitask, Map: Model-Based Controllers for Versatile Swarms

1:30pm-2:30pm

Technical Session 2

  • Jeffrey Herrmann, Metareasoning Engineering: Developing, Implementing, and Testing Metareasoning
  • Bassam Alrifaee, Multi-Agent Decision-Making for Cyber-Physical Mobility Systems
2:30pm-3:30pm
Afternoon Coffee Break 3:30pm-3:50pm

Technical Session 3

  • Xincheng Li, Geometry and Control for Human-Robot Interaction
  • John Schmidt, Obstacle Avoidance on a Variable-Sweep Wing UAV
3:50pm-4:30pm
Presentation of Best Poster Awards, Program Committee 4:30pm-4:45pm
Closing Remarks by Michael Otte, MRC Symposium General Chair 4:45pm-5:00pm
Maryland Robotics Center Lab Tours 5:00pm-6:00pm

 

May 1, 2023: Best consideration date for poster and talk submissions

May 17, 2023: Deadline to submit lunch selection in the registration form

May 24, 2023: MRC Industry Night

May 25, 2023: MRC Research Symposium

Industry Night on May 24th and the Research Symposium presentations on May 25th will take place in 1101 A. James Clark Hall Forum

Address: 8278 Paint Branch Dr., College Park, MD 20742

Click here to view the campus map.

With the construction of the Purple Line, road and pedestrian walkway closures and detours have increased. Please view the visitor parking map provided by DOTS to know where to park on campus. The XFINITY Center Visitor Lot is the closest to the event.

DOTS advises visitors to enter and exit campus from University Boulevard (Maryland Route 193) at the intersections with Paint Branch Drive (near the XFINITY Center), Stadium Drive (near The Clarice) or Campus Drive/Adelphi Road (near UMGC).

For more information, go to: https://transportation.umd.edu/parking/visitors

Industry Night

General Chair: Michael Otte
Organising Committee: Yancy Diez-Mercado, Pratap Tokekar, Derek Paley, Ania Picard
Industry Night Advisor: John Crupi, Kick Robotics.

Research Symposium

General Chair: Michael Otte
Organising Committee: Yancy Diez-Mercado, Pratap Tokekar, Derek Paley, Ania Picard.
Program Committee: Eleonora Tubaldi, Huaishu Peng, Cecilia Huertas Cerdeira, Kaiqing Zhang


Top