RSS 2014 Workshop

From DRLWiki

Jump to: navigation, search

Contents for This Page

Communication-aware Robotics: New Tools for Multi-Robot Networks, Autonomous Vehicles, and Localization

A confirmed RSS 2014 Workshop.

Organizers


Daniela Rus: Daniela Rus is a Professor of Electrical Engineering and Computer Science and Director of the Computer Science and Artificial Intelligence Laboratory (CSAIL) at MIT. She also leads CSAIL’s Distributed Robotics Laboratory MIT Distributed Robotics Lab @ CSAIL. Rus’ research interests include distributed robotics, mobile computing and programmable matter, transportation, security, environmental modeling and monitoring, underwater exploration, and agriculture.
File:Rus.jpg


Nora Ayanian: Nora Ayanian is a Gabilan Assistant Professor at the University of Southern California in the department of Computer Science. She was previously a postdoctoral associate in the Distributed Robotics Lab at MIT. She received the MSE (2008) and PhD (2011) degrees in Mechanical Engineering from the University of Pennsylvania. Her research interests are in multi-robot coordination in uncertain environments with provable guarantees.
File:nora.jpg

Stephanie Gil: Stephanie Gil is a PhD candidate with Prof. Daniela Rus in the Distributed Robotics Lab at MIT. Her research interests are in multi-robot control, distributed optimization of ad hoc communication networks, and space robotics. She completed her MS in Aeronautics and Astronautics at MIT, and her BS in Mechanical Engineering at Cornell, where she also worked on the NASA Mars Exploration Rover team.
File:sgil.png

Swarun Kumar: Swarun Kumar is a Ph.D candidate with Prof. Dina Katabi in the Computer Science and Artificial Intelligence Laboratory at MIT. His research is focused on building robust protocols and architectures for wireless networks. Swarun received his S.M. degree from MIT in 2012 and a B.Tech in Computer Science and Engineering from IIT Madras in 2010.
File:Swarun2.jpg

Abstract

Recent advances in communication are enabling teams of robots to achieve new and exciting capabilities. Of current interest in the robotics literature are multi-agent teams for their applications to distributed exploration, search and rescue, and in the near future, global connectivity. The effectiveness of these coordinated systems inherently depends on communication infrastructure and hinges on the assumption of adequate inter-agent communication. This necessitates the development of robust communication tools with guaranteed performance in real-world environments. Moreover, recent technologies in the communications field include using information exchange as a virtual sensor to be used by autonomous cars in future networked cities, leveraging WiFi to "see through walls" to track people or objects behind occlusions, and processing of wireless signals for the purpose of localization in an environment. From providing the necessary communication quality guarantees to achieve coordination tasks amongst robot teams in real-world environments, to using wireless signals as sensors for localization and/or tracking, cutting edge advancements in communication are becoming a critical component of future robotic systems. The potential for robotic systems that are tightly coupled with the newest and most capable tools in communication is pressing. However, in order for us to achieve these goals we must encourage collaboration between the largely independent fields of communication and robotics. The success of our first workshop in this area at ICRA 2013, "Networked Multi-Agent Systems: From Theory to Practice", underscores the growing importance of this multi-disciplinary research and has motivated us to propose the current follow-up workshop at RSS 2014. The goal of this full day workshop is to bring together leaders of both fields to discuss recent and targeted advances in communication for robotic systems, identify the major needs and challenges in translating these capabilities to practical arenas, and encourage an exchanging of ideas from robotics and communication experts to tackle these challenges towards development of high performing and reliable networked multi-agent systems for the real-world.

Invited Speakers

  • Keynote Speaker Dina Katabi: Wireless@MIT, MIT Adaptive Communication Networks, RFID localization of objects in cluttered environments, Communication systems for autonomous driving [confirmed]
  • Vijay Kumar GRASP, UPenn Control and coordination of multi-robot teams [confirmed]
  • Sonia Martinez UCSD Networked control systems and robotic sensor networks [confirmed]
  • Romit Roy Choudhury EECS, UIUC Wireless networking and mobile device computing, smartphone sensing and localization [confirmed]
  • Bhaskar Krishnamachari USC Wireless and mobile networks [confirmed]
  • Brian Sadler ARL Dynamic spectrum access, signal processing, wireless signal mapping and control [confirmed]
  • Gaurav Sukhatme RESL, USC Large-scale distributed robotic systems [confirmed]
  • Yasamin Mostofi UCSB Spatial prediction of communication quality, communication-aware robot path planning [confirmed]
  • Venkat Padmanabhan Microsoft Research, India RFID geolocation, peer-to-peer networking, WLAN based user localization [tentative]

List of Topics

  • Development of spatial wireless signal strength pro- files for use in robotic path planning
  • Communication-aware multi-robot planning
  • Communication as a sensor for autonomous driving, object detection, and localization
  • Network optimization in realistic communication environments
  • Prioritized communication over multi-agent networks
  • Accurate localization using wireless signals for multi-agent networks
  • Sensing and Object tracking using wireless signal characteristics
  • Communication protocols for collaborative sensing and applications in robotic networks
  • Efficient communication Systems for vehicular ad-hoc networks
  • Tradeoffs in performance quality, correctness and convergence
  • Cooperation and communication in heterogeneous teams
  • Coordination with intermittent communication
  • Tradeoffs between guarantees and computational efficiency
  • Developing theory to accommodate events inconsistent with assumptions, i.e. loss of global positioning data

Motivation and Objectives of the Workshop

This full-day workshop aims to highlight the most recent advances for networked multi-robot system capabilities, cutting-edge developments in communications, and remaining challenges that robot systems face in transitioning from theory to application with an emphasis on communication. The objective is to bring together researchers both from the robotics and communications community on all ends of the spectrum of theory to practice, to discuss challenges of dealing with networked multi-robot systems, and to develop new techniques to deal with these challenges. The overarching aim of this workshop to cross-pollinate insights from typically divergent approaches, in order to design high-performance, reliable systems for real-world operation. In particular, we aim to address the following challenges related to communication-aware robot systems:

1) What are the major issues with communication speed and quality?

2) What kind of decisions do the multi-agent systems have to make in order to maintain performance quality, and should they be trading off correctness and/or convergence?

3) How can experimentation support theoretical claims? What are the measures that are important? For example, communication throughput, small communication delays, etc.

4) Can research in networked multi-agent or modular systems provide broadly applicable solutions, such that the same solution can be used for search and rescue or for in-vivo applications.

5) What are specific challenges related to communication in different scenarios, such as search and rescue, underwater, aerial, etc.

6) How can theory help provide a contingency plan for when events inconsistent with the theory’s assumptions occur, for example, loss of global positioning

Call for Extended Abstracts

We solicit 2-page extended abstracts to be included in the workshop as a poster presentation and short spotlight talk. Papers addressing one or more topics from List of Topics are particularly encouraged. Workshop organizers will select the top 6-8 submissions for extended 10 to 15 minute talks.

RSS 2-column format, max. 2 pages, please use the template available at: http://www.roboticsconference.org/authors.html

  • Please email submissions to Stephanie Gil at sgil@mit.edu with the the subject line RSS 2014 CaR Workshop Submission

Important Dates

  • Abstract submission deadline: May 1, 2014
  • Acceptance notification: May 10, 2014
  • Workshop date: July 13, 2014

Schedule

We intend to provide ample opportunity for round-table discussions where invited speakers and workshop participants will be encouraged to propose questions and ponder the next greatest challenges for networked robot systems. An example schedule for our proposed workshop would be the following:

Time Speaker Title
15 min Opening
45 min Keynote: Dina Katabi, MIT title TBD
30 min Invited talk Robotics topic TBD
15 min Coffee Break
30 min Invited talk Communication topic TBD
30 min Invited talk Robotics topic TBD
30 min Roundtable discussion with morning speakers
Workshop Second Half
30 min Invited talk Communication topic TBD
30 min Invited talk Robotics topic TBD
30 min Lightning Round I: Contributed papers
15 min Coffee Break
30 min Lightning Round II: Contributed papers
30 min Invited talk Communication topic TBD
30 min Invited talk Robotics topic TBD
30 min Closing roundtable discussion with afternoon speakers
End
Personal tools