This Wednesday at 12:30pm in CB11.09.215, Nick will be presenting Lightweight Approximations for Resilient Multi-Robot Communication by Himself.
Afterwards, we'll read through T-FR, Volume 2: pp: 26-40: https://url.au.m.mimecastprotect.com/s/MNoICJyBrGfAgl1l6FVfLuyIW07?domain=ie...
Any papers we're interested in hearing more about will be added to the stack: https://url.au.m.mimecastprotect.com/s/E33rCK1DvKTMZPBPXTvh1u5bhgk?domain=do...
The next presenters after this will be: - 05 November: Cancelled due to Indopac - 12 November: Cancelled due to field trials - 19 November: Ed
See you all there!
Abstract:
Multi-robot systems are increasingly more capable than ever thanks to sophisticated algorithms that are continually improved by researchers. However, while more capable, recent trends suggests that they will require more data than their communication methods can sustainably support. This motivates research into efficient communication mechanisms developed expressly for multi-robot coordination. Multi-robot communication, a sub- discipline of multi-robot coordination, contains many facets that need to be addressed; among these is resilient communication, or the ability to both degrade gracefully and adapt to overcome adverse circumstances. Inspired by the gap in literature, we developed an algorithm for explicit resilient multi-robot communication that is based on approximate set membership. Our method demonstrates a significant improvement in resiliency, and reduction in communication resource requirements while maintaining performance comparable to baseline in an exploration task. Encouraged by the results and contextualising our work within literature trends, we submitted our work to ICRA 2026. We believe our work to date holds promise to improve the state of the art in multi-robot communication. Therefore, we discuss our plans to develop a new algorithm based on it that supports fuzzy or rough sets as opposed to exact sets, with the intention of supporting other types of coordination algorithms that take inexact sets as input, such as loop closure. Finally, we outline our plans to test the proposed methods on either autonomous surface vessels in a coastal environment or, if unavailable, a laboratory environment that simulates coastal communication constraints.
UTS CRICOS Provider Code: 00099F DISCLAIMER: This email message and any accompanying attachments may contain confidential information. If you are not the intended recipient, do not read, use, disseminate, distribute or copy this message or attachments. If you have received this message in error, please notify the sender immediately and delete this message. Any views expressed in this message are those of the individual sender, except where the sender expressly, and with authority, states them to be the views of the University of Technology Sydney. Before opening any attachments, please check them for viruses and defects. Think. Green. Do. Please consider the environment before printing this email.