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

We demonstrate the possibility of learning drone swarm controllers that arezero-shot transferable to real quadrotors via large-scale multi-agentend-to-end reinforcement learning. We train policies parameterized by neuralnetworks that are capable of controlling individual drones in a swarm in afully decentralized manner. Our policies, trained in simulated environmentswith realistic quadrotor physics, demonstrate advanced flocking behaviors,perform aggressive maneuvers in tight formations while avoiding collisions witheach other, break and re-establish formations to avoid collisions with movingobstacles, and efficiently coordinate in pursuit-evasion tasks. We analyze, insimulation, how different model architectures and parameters of the trainingregime influence the final performance of neural swarms. We demonstrate thesuccessful deployment of the model learned in simulation to highlyresource-constrained physical quadrotors performing station keeping and goalswapping behaviors. Code and video demonstrations are available on the projectwebsite at https://sites.google.com/view/swarm-rl.

Decentralized Control of Quadrotor Swarms with End-to-end Deep Reinforcement Learning