SafeSwarm: Decentralized Safe RL for the Swarm of Drones Landing in Dense Crowds
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912259580624896 |
|---|---|
| author | Tadevosyan, Grik Osipenko, Maksim Aschu, Demetros Fedoseev, Aleksey Serpiva, Valerii Sautenkov, Oleg Karaf, Sausar Tsetserukou, Dzmitry |
| author_facet | Tadevosyan, Grik Osipenko, Maksim Aschu, Demetros Fedoseev, Aleksey Serpiva, Valerii Sautenkov, Oleg Karaf, Sausar Tsetserukou, Dzmitry |
| contents | This paper introduces a safe swarm of drones capable of performing landings in crowded environments robustly by relying on Reinforcement Learning techniques combined with Safe Learning. The developed system allows us to teach the swarm of drones with different dynamics to land on moving landing pads in an environment while avoiding collisions with obstacles and between agents.
The safe barrier net algorithm was developed and evaluated using a swarm of Crazyflie 2.1 micro quadrotors, which were tested indoors with the Vicon motion capture system to ensure precise localization and control.
Experimental results show that our system achieves landing accuracy of 2.25 cm with a mean time of 17 s and collision-free landings, underscoring its effectiveness and robustness in real-world scenarios. This work offers a promising foundation for applications in environments where safety and precision are paramount. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_07566 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SafeSwarm: Decentralized Safe RL for the Swarm of Drones Landing in Dense Crowds Tadevosyan, Grik Osipenko, Maksim Aschu, Demetros Fedoseev, Aleksey Serpiva, Valerii Sautenkov, Oleg Karaf, Sausar Tsetserukou, Dzmitry Robotics This paper introduces a safe swarm of drones capable of performing landings in crowded environments robustly by relying on Reinforcement Learning techniques combined with Safe Learning. The developed system allows us to teach the swarm of drones with different dynamics to land on moving landing pads in an environment while avoiding collisions with obstacles and between agents. The safe barrier net algorithm was developed and evaluated using a swarm of Crazyflie 2.1 micro quadrotors, which were tested indoors with the Vicon motion capture system to ensure precise localization and control. Experimental results show that our system achieves landing accuracy of 2.25 cm with a mean time of 17 s and collision-free landings, underscoring its effectiveness and robustness in real-world scenarios. This work offers a promising foundation for applications in environments where safety and precision are paramount. |
| title | SafeSwarm: Decentralized Safe RL for the Swarm of Drones Landing in Dense Crowds |
| topic | Robotics |
| url | https://arxiv.org/abs/2501.07566 |