Metraipolis › archive › dc_dddf8eb2621b
Distributed Swarm Morphogenesis with Neural Cellular Automata — arXiv:2610.31900
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.31900
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-26T19:47:21.679Z
- SHA-256 of the archived text
53f7b3d0d3d5c61798664ba9d3300ffa0d88c7d6c5e5be53b6fa7abc0ca6e6a4- Stable URL of this page
https://metraipolis.com/documento/dc_dddf8eb2621b
How to cite
Distributed Swarm Morphogenesis with Neural Cellular Automata — arXiv:2610.31900 — arXiv (en), https://arxiv.org/abs/2610.31900 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_dddf8eb2621b (Metraipolis archive dc_dddf8eb2621b, sha256 53f7b3d0d3d5c61798664ba9d3300ffa0d88c7d6c5e5be53b6fa7abc0ca6e6a4)
BibTeX
@misc{dcdddf8eb2621b,
title = {Distributed Swarm Morphogenesis with Neural Cellular Automata — arXiv:2610.31900},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.31900},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_dddf8eb2621b; sha256 53f7b3d0d3d5c61798664ba9d3300ffa0d88c7d6c5e5be53b6fa7abc0ca6e6a4},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.31900. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Swarm morphogenesis requires robots to assemble desired shapes through local interactions. We present a modular framework integrating neural cellular automata (NCA) with existing site selection and collision-aware control. Within this framework, we introduce a decentralized attachment-site discovery mechanism. Robots already in the formation update and share local NCA states to identify new attachment sites, enabling progressive growth without a predefined list of sites during deployment. To bridge the mismatch between conventional NCA growth and gradual physical assembly, we additionally propose offline sparse-retention fine-tuning that simulates partial attachment, together with a false-positive loss that penalizes invalid site activations. Simulations demonstrate formation of diverse lattice morphologies, scaling to several hundred robots, and substantial improvements in morphology accuracy from the proposed fine-tuning. Experiments with Crazyflie quadrotors validate the integrated execution pipeline using robot-relative observations reconstructed from external tracking. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.MA, nuovi lavori del giorno). Categorie arXiv: Robotics (cs.RO) ; Multiagent Systems (cs.MA). Pagina del lavoro: https://arxiv.org/abs/2610.31900 — 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 2026-10-26T19:45:18.248Z dalla pagina https://arxiv.org/list/cs.MA/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).