用机械臂的避障路径经验，高效规划无人机中继网络部署。
Arm2Air: Cross-Embodiment Skeleton Transfer for 3D Relay Formation
- 从预训练机械臂模型提取有序骨架，通过低秩适配迁移到无人机场景。
- 在复杂城市环境中，规划速度提升64.9%，中继容量提高32.6%且更稳定。
- 仅需3张目标地图即可显著提升精度，适合数据稀缺的无人机部署任务。
无人飞行器（UAV）中继网络可在通信基础设施受损后恢复连接。城市环境中的中继部署困难，需综合考虑视线遮挡、通信范围、高度及三维障碍物。本文提出Arm2Air，通过跨体感迁移，将机械臂的避障骨架用于无人机中继布局。利用预训练神经运动规划模型生成源域机械臂运动的有序骨架，预训练基于Transformer的迁移平台，并使用少量目标域数据与低秩适配进行微调。迁移后的骨架初始化中继链，再优化连通性、瓶颈容量、延迟和移动成本。在九个高杂乱度3D城市地图上，相较于最快的传统规划器，端到端规划时间减少64.9%；在30张密集城市地图独立测试集中，瓶颈容量提升32.6%，容量方差降低74.7%，最大跳距减少13.2%，跳距方差降低75.2%，中继位移减少16.9%。仅使用三张目标域训练图，中继位置均方根误差相比从零训练降低53.6%，参数更新量仅为0.134百万，远低于从零训练（1.383百万）。结果表明该方法在计算与数据上均高效，揭示了跨异构体感任务传递有序结构先验的普适原则。
原文摘要 · Abstract (English)
Unmanned aerial vehicle (UAV) relay networks can restore connectivity after communication infrastructure is damaged. Urban relay placement is difficult because line-of-sight blockage, communication range, altitude, and three-dimensional obstacles must be considered jointly. Arm2Air transfers obstacle-avoidance skeletons from robot arms to UAV relay placement through cross-embodiment transfer. Source-domain robot-arm motions from a pretrained Neural MP model are converted into ordered skeletons that pretrain a transformer-based transfer platform, which is then adapted to the UAV domain using limited target data and Low-Rank Adaptation. The transferred skeleton initializes a relay chain that is refined for connectivity, bottleneck capacity, delay, and movement cost. On nine held-out high-clutter 3D urban maps, Arm2Air reduced median end-to-end planning runtime by 64.9 percent relative to the fastest conventional planner. On the high-obstruction group of a separate 30-map dense urban holdout, it increased bottleneck capacity by 32.6 percent, reduced capacity variance by 74.7 percent, reduced maximum hop distance by 13.2 percent, reduced hop-distance variance by 75.2 percent, and reduced relay displacement by 16.9 percent relative to IMPC-MD. With only three target-domain training maps, Arm2Air reduced relay-position root mean square error by 53.6 percent relative to training from scratch while updating 0.134 million parameters, compared with 1.383 million for Scratch and Full Fine-tuning. These results demonstrate computationally and data-efficient UAV relay placement and suggest a broader principle for transferring ordered structural priors across heterogeneous embodied tasks.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。