发表机构
Carnegie Mellon University; Pennsylvania State University（卡内基梅隆大学; 宾夕法尼亚州立大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究提出利用多旋翼下洗流进行操控，设计无人机足球任务，通过简化动力学模型训练强化学习策略实现运球，并成功迁移至真实世界。
AI 中文摘要
尽管多旋翼无人机传统上被设计用于“仅感知”任务，如测绘和探索，但近期工作致力于开发无人空中操控器（UAMs）以解决移动操控任务。空中操控性能可能受到“下洗流”（螺旋桨产生的气流）的影响，但当前最先进的UAMs要么忽略下洗流，要么将其视为干扰。相反，是否有可能在操控过程中主动利用下洗流作为工具？我们设计了一个无人机足球任务，以探索基于下洗流的操控可行性。具体而言，我们开发了一个简化的下洗流动力学模型，并利用该模型训练一个强化学习（RL）策略来运球。我们进一步证明了该策略能够迁移到真实世界部署中。这项工作为多旋翼无人机的新型操控能力提供了关键见解。
英文摘要
Although multicopter drones are traditionally designed for "perception-only" tasks, like mapping and exploration, recent work has sought to develop Unmanned Aerial Manipulators (UAMs) to solve mobile manipulation tasks. Aerial manipulation performance can be impacted by "downwash," the airflow produced by propellers, but current state-of-the-art UAMs either ignore downwash or treat it as a disturbance. Instead, is it possible to actively use downwash as a tool during manipulation? We design a drone soccer task to explore the feasibility of downwash-based manipulation. Specifically, we develop a simplified downwash dynamics model which we use to train an RL policy to dribble a soccer ball. We further demonstrate that our policy transfers to real world deployment. This work provides key insights into novel manipulation capabilities for multicopters.
Comments5 pages, 3 figures, IROS 2026 Workshop (Sim2Real and Classical Control)
