English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Decentralized drone swarms deployed today either rely on sharing of positionsamong agents or detecting swarm members with the help of visual markers. Thiswork proposes an entirely visual approach to coordinate markerless drone swarmsbased on imitation learning. Each agent is controlled by a small and efficientconvolutional neural network that takes raw omnidirectional images as inputsand predicts 3D velocity commands that match those computed by a flockingalgorithm. We start training in simulation and propose a simple yet effectiveunsupervised domain adaptation approach to transfer the learned controller tothe real world. We further train the controller with data collected in ourmotion capture hall. We show that the convolutional neural network trained onthe visual inputs of the drone can learn not only robust inter-agent collisionavoidance but also cohesion of the swarm in a sample-efficient manner. Theneural controller effectively learns to localize other agents in the visualinput, which we show by visualizing the regions with the most influence on themotion of an agent. We remove the dependence on sharing positions among swarmmembers by taking only local visual information into account for control. Ourwork can therefore be seen as the first step towards a fully decentralized,vision-based swarm without the need for communication or visual markers.

Learning Vision-based Flight in Drone Swarms by Imitation