arXiv cs.MA· Ray Verma, Eliseo Ferrante, Anthony Tzes·· 12 小时前AI 评分31
基于神经细胞自动机的分布式群体形态发生
Distributed Swarm Morphogenesis with Neural Cellular Automata
AI 导读
研究提出将神经细胞自动机（NCA）与现有站点选择及碰撞感知控制相结合的模块化框架，实现机器人群体形态发生。框架引入去中心化附着点发现机制，编队中的机器人通过更新并共享局部 NCA 状态识别新附着点，无需部署时预定义站点列表即可渐进生长。仿真可扩展至数百台机器人并生成多种晶格形态，离线稀疏保留微调与假阳性损失显著提升形态精度，Crazyflie 四旋翼实验验证了集成执行流程。
正文 · 原文
Abstract: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.
| Subjects: | Robotics (cs.RO); Multiagent Systems (cs.MA) |
| Cite as: | arXiv:2610.31900 [cs.RO] |
| (or arXiv:2610.31900v1 [cs.RO] for this version) | |
| https://doi.org/10.48550/arXiv.2610.31900 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Ray Verma [view email]
[v1]
Thu, 22 Oct 2026 20:52:51 UTC (1,138 KB)
来源：arXiv cs.MA · arxiv.org