Robot Communication in the Wild: Meeting the Challenges of Real-World Systems


Organizers: Robert Fitch, Don Sofge, Geoffrey Hollinger, Karthik Dantu, Michael Otte, Shayegan Omidshafiei

Website: http://rss2017-rcw.mit.edu

Robots and multi-robot teams use communication to facilitate data sharing, coordination, and cooperation with other robots and human users. Real-world communication is often unreliable, expensive, non-ideal, and/or otherwise challenging in a variety of ways. These challenges lead to interesting theoretical and practical ramifications for the design, analysis, and deployment of robotic systems, algorithms, and hardware. This workshop aims to foster a better understanding of the communication challenges faced by robots/teams, and how we analyze them, model them, and overcome their negative effects in practice. Topics are expected to have well defined assumptions, constraints, or experimental observations that reflect the real-world communication challenges faced by robots/teams, but may come from any sub-field of robotics and be motivated by any robotic problem. Example topics may include, but are not limited to:

  • Communication assumed/observed to be intermittent, lossy, difficult to model, highly asymmetric, partial, blocked, expensive, compressed, encrypted, or non-ideal in other ways.
  • Any-Com algorithms (graceful performance declines vs. decreasing quality).
  • Robotic systems that adapt to communication constraints.
  • Robotic hardware designed to overcome communication issues common in robotics.
  • More accurate modeling of real-world communication.
  • Overcoming real-world communication constraints in practice (e.g., undersea, air, ground, space environments).