SwarmControl: An Automated Distributed Control Framework for Self-Optimizing Drone Networks

Bertizzolo, Lorenzo; D’Oro, Salvatore; Ferranti, Ludovico; Bonati, Leonardo; Demirors, Emrecan; Guan, Zhonghong; Melodia, Tommaso; Pudlewski, Scott

doi:10.1109/infocom41043.2020.9155231

Cited by 52 publications

(30 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Unmanned Aerial Vehicle (UAV) networks are attracting the interest of the wireless community as a 'tool' to provide flexible and on-demand network infrastructure [1,2]. There are numerous applications for networked UAVs, including providing airborne emergency infrastructure in disaster scenarios [3], and off-the-grid, on-demand network provisioning in civilian and military scenarios [2,[4][5][6][7][8].…”

Section: Introductionmentioning

confidence: 99%

“…To address Challenge (I) and Challenge (II), in this paper, we propose the two following innovations: (1) We envision Software-defined UAVs equipped with programmable radio front-ends and flight control units (FCU). We leverage the real-time reconfigurability of motion, PHY, and upper-layer operations to implement full-stack cross-layer optimization.…”

Section: Introductionmentioning

confidence: 99%

“…Reconfigurability of functionalities at all layers of the protocol stack has already been demonstrated to provide superior performance with respect to systems based on inflexible hardware unable to adapt to dynamic spectrum conditions [1]. (2) To control the operations of the network of UAVs, we propose a two-tier architecture that addresses the challenges of distributed wireless system optimization mentioned above.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Learning to Fly: A Distributed Deep Reinforcement Learning Framework for Software-Defined UAV Network Control

Cheng

Bertizzolo

Buczek

et al. 2021

IEEE Open J. Commun. Soc.

Self Cite

View full text Add to dashboard Cite

Control and performance optimization of wireless networks of Unmanned Aerial Vehicles (UAVs) require scalable approaches that go beyond architectures based on centralized network controllers. At the same time, the performance of model-based optimization approaches is often limited by the accuracy of the approximations and relaxations necessary to solve the UAV network control problem through convex optimization or similar techniques, and by the accuracy of the channel network models used. To address these challenges, this article introduces a new architectural framework to control and optimize UAV networks based on Deep Reinforcement Learning (DRL). Furthermore, it proposes a virtualized, 'ready-to-fly' emulation environment to generate the extensive wireless data traces necessary to train DRL algorithms, which are notoriously hard to generate and collect on battery-powered UAV networks.The training environment integrates previously developed wireless protocol stacks for UAVs into the CORE/EMANE emulation tool. Our 'ready-to-fly' virtual environment guarantees scalable collection of high-fidelity wireless traces that can be used to train DRL agents. The proposed DRL architecture enables distributed data-driven optimization (with up to 3.7x throughput improvement and 0.2x latency reduction in reported experiments), facilitates network reconfiguration, and provides a scalable solution for large UAV networks.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Learning to Fly: A Distributed Deep Reinforcement Learning Framework for Software-Defined UAV Network Control

Cheng

Bertizzolo

Buczek

et al. 2021

IEEE Open J. Commun. Soc.

Self Cite

View full text Add to dashboard Cite

show abstract

“…In the future, they could push a government closer and closer to an all-out war (Englund, 2019). The existing technology cannot control and neutralise autonomous pilot drones (Bertizzolo et al, 2020). The following technologies can be used to disable suicide drones:…”

Section: Introductionmentioning

confidence: 99%

High power microwave for knocking out programmable suicide drones

Chaari¹

2021

Security and Defence Quarterly

View full text Add to dashboard Cite

The primary research objective is to reduce the dangers of rogue drones in our lives and the consequences of extremist groups, drug dealers, and organised criminals using them. The growing number of incidents involving modified drones proves the weakness of existing technology in stopping and neutralising errant drones such as the hand-held gun jammer, trained eagle, R.F. jammer, and others. This technology is not very likely to able to knock out a rogue drone and is incapable of stopping programmable drones. This article aims to examine the directed energy of HPM (high power microwaves) in using the electromagnetic field strength energy to damage the drone's structure or burn its PCB board electronics. It goes on to analyse electronic attack using microwave power with high frequency to immediately switch off drones. The effectiveness of high microwave power for disrupting drones at different distances and in different weather conditions is evaluated. A study of the conical horn antenna of the magnetron coupling system, which has an operating frequency of 2.45 GHz, is also included.

show abstract

“…Their results show that, not only UAVs can improve general network performance, but also they are be able to autonomously reposition themselves according to signal requirements. Perhaps combining these works with a complete algorithmic framework for distributed beamforming by a swarm of UAVs, as in (Mohanti et al, 2019), and the automated distributed control for drone networks proposed by (Bertizzolo et al, 2020) could achieve optimal results in future work.…”

Section: Systematic Reviewmentioning

confidence: 99%

Integrating cognitive radio with unmanned aerial vehicles

Santana¹

View full text Add to dashboard Cite

SwarmControl: An Automated Distributed Control Framework for Self-Optimizing Drone Networks

Cited by 52 publications

References 29 publications

Learning to Fly: A Distributed Deep Reinforcement Learning Framework for Software-Defined UAV Network Control

Learning to Fly: A Distributed Deep Reinforcement Learning Framework for Software-Defined UAV Network Control

High power microwave for knocking out programmable suicide drones

Integrating cognitive radio with unmanned aerial vehicles

Contact Info

Product

Resources

About