Metraipolis › archive › dc_3aca4941b203

Calibrate Once, Fly Any Team: Residual-Grounded Low-Fidelity Training for Cooperative Drone Swarms — arXiv:2609.17265

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.17265
License (as archived)
CC0-1.0
Archived
2026-10-15T18:31:13.116Z
SHA-256 of the archived text
582a37089628568259c0e53e39f09ffca8d74e0553d507bca3f7692a19f3ba7d
Stable URL of this page
https://metraipolis.com/documento/dc_3aca4941b203

How to cite

Calibrate Once, Fly Any Team: Residual-Grounded Low-Fidelity Training for Cooperative Drone Swarms — arXiv:2609.17265 — arXiv (en), https://arxiv.org/abs/2609.17265 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3aca4941b203 (Metraipolis archive dc_3aca4941b203, sha256 582a37089628568259c0e53e39f09ffca8d74e0553d507bca3f7692a19f3ba7d)
BibTeX
@misc{dc3aca4941b203,
  title = {Calibrate Once, Fly Any Team: Residual-Grounded Low-Fidelity Training for Cooperative Drone Swarms — arXiv:2609.17265},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.17265},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3aca4941b203; sha256 582a37089628568259c0e53e39f09ffca8d74e0553d507bca3f7692a19f3ba7d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.17265. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Training multi-agent drone-swarm policies directly in high-fidelity (HF) rigid-body physics is accurate but computationally expensive. This cost scales poorly with team size, as each additional agent multiplies contact-resolution complexity and sharply raises the in-simulation crash rate. To address this, we propose a mixed-fidelity training scheme that eliminates HF reinforcement learning entirely. A single shared, decentralized policy is optimized inside a fully-differentiable, JAX-native low-fidelity (LF) point-mass simulator. The simulator is corrected by a small, per-agent bagged residual ensemble fit once, offline, using short calibration flights in the HF simulator. Because calibration requires only one isolated drone, the data collection budget does not compound with team size. Reference trajectories are generated by rolling out an existing LF-only policy and tracked in the HF simulator by a zero-training PD controller. Evaluated across four cooperative drone tasks and team sizes from 3 to 18, the residual-corrected policy outperforms an uncorrected LF baseline in all combinations, and a from-scratch HF policy in 22 of 24 combinations tested. It trails an HF-finetuned policy by a margin that narrows steadily with team size. Ultimately, the proposed method achieves near-equivalent performance at the largest team sizes at a fraction of the computational cost, completely avoiding the high crash rates typical of HF training.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-16 in cs.MA).
Categorie arXiv: Multiagent Systems (cs.MA) ; Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2609.17265 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-15T18:00:46.633Z dalla pagina https://arxiv.org/catchup/cs.MA/2026-09-16?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).