Date: TUESDAY, 09 JANUARY 2024
Time: 08:30 – 12:00 (PST)
Room: TBD
08:30 – 08:40
Opening Remarks
08:40 – 09:30
Keynote Session
Prof. Dr. Nicholas Mastronarde (University at Buffalo, USA)
Title: Simulating swarms of small unmanned aircraft systems with the UB-ANC Emulator
Abstract: Miniaturization of hardware, sensing, and battery technologies have enabled practical design of low-cost small unmanned aircraft systems (sUAS) for civilian and military applications. In parallel, many such applications have been envisioned that bring together multiple networked sUAS to execute complex missions. However, designing, implementing, and testing these missions on actual hardware poses numerous inter-disciplinary challenges spanning communications, networking, planning, and multi-agent control, as well as regulatory challenges. To mitigate these, we have developed an open software/hardware platform called the University at Buffalo’s Airborne Networking and Communications (UB-ANC) Emulator. The UB-ANC Emulator not only provides a platform to study problems at the intersection of the aforementioned disciplines, but it also facilitates rapid transition from theory to simulation to deployment on actual sUAS.
In this talk, we motivate the need for the UB-ANC Emulator, describe its software architecture, and demonstrate its utility through several illustrative examples. To accurately reflect the performance of a swarm where communication links are subject to interference and packet losses, and protocols at all layers affect network throughput, latency, and reliability, we have connected UB-ANC to different network simulators including ns-3, EMANE, and a custom-built software-in-the-loop channel emulator in GNU Radio.
09:30 – 10:30
Break
10:30 – 11:00
Invited Talk
Prof. Dr. Zhangyu Guan (University at Buffalo, USA)
Title: Towards Zero-Touch Automated UAV-Enabled NextG Networks Through Digital Twin-Assisted Domain Adaptation
Abstract: In existing wireless networks, the control programs have been designed manually and for certain predefined scenarios. This process is complicated and error-prone, and the resulting control programs are not resilient to disruptive changes. Data-driven control based on Artificial Intelligence and Machine Learning (AI/ML) has been envisioned as a key technique to automate the modeling, optimization and control of complex wireless systems. However, existing AI/ML techniques rely on sufficient well-labeled data and may suffer from slow convergence and poor generalizability. In this talk, focusing on digital twin-assisted wireless unmanned aerial vehicle (UAV) systems, I will discuss the emerging techniques that can enable fast-converging data-driven control of wireless systems with enhanced generalization capability to new environments. These include SLAM-based sensing and network softwarization for digital twin construction, robust reinforcement learning and system identification for domain adaptation, and testing facility sharing and federation. The corresponding research opportunities are also discussed.
11:00 – 12:00
Paper Session
(11:00 – 11:20) – Does Twinning Vehicular Networks Enhance Their Performance in Dense Areas?
Sarah Al-Shareeda (Istanbul Techincal University, Turkey); Sema Oktug (Istanbul Technical University, Turkey); Yusuf Yaslan (Istanbul Technical University, Turkey); Gökhan Yurdakul (BTS Group, Turkey); Berk Canberk (Edinburgh Napier University, United Kingdom (Great Britain))
(11:20 – 11:40) – An Information Processing System Design Approach to Underwater Robotic Swarms
David Mortimore (Naval Postgraduate School & Naval Undersea Warfare Center Division, Keyport, USA); Raymond R. Buettner, Jr. (Naval Postgraduate School, USA); Marc S. Ramsey (Stanford University, USA)
(11:40 – 12:00) – Virtualization in Robot Swarms: Past, Present, and Future
Reinhardt Karnapke (Brandenburg University of Technology, Germany); Martin Richter (Technische Universität Chemnitz, Germany); Matthias Werner (Technische Universität Chemnitz, Germany)
