TACO让飞行器能实时调整特技动作参数，统一控制多种高难度飞行动作。
TACO: General Acrobatic Flight Control via Target-and-Command-Oriented Reinforcement Learning
- 基于目标与指令的强化学习框架，统一处理多种特技任务
- 实现在高速圆周飞行和连续翻滚中保持稳定控制
- 新提出的谱归一化方法提升动作平滑性，利于真实场景部署
尽管特技飞行控制已得到广泛研究，但现有方法通常局限于特定机动任务，无法在线调整飞行参数。本文提出一种目标与指令导向的强化学习框架TACO，可统一处理多种机动任务并支持在线参数更改。此外，我们设计了一种结合输入输出缩放的谱归一化方法，显著提升策略在时间与空间上的平滑性、独立性与对称性，有效缓解仿真到现实的差距。通过大量仿真与真实实验验证，TACO展现出在高速圆形飞行及连续多翻滚中的卓越控制能力。
原文摘要 · Abstract (English)
Although acrobatic flight control has been studied extensively, one key limitation of the existing methods is that they are usually restricted to specific maneuver tasks and cannot change flight pattern parameters online. In this work, we propose a target-and-command-oriented reinforcement learning (TACO) framework, which can handle different maneuver tasks in a unified way and allows online parameter changes. Additionally, we propose a spectral normalization method with input-output rescaling to enhance the policy's temporal and spatial smoothness, independence, and symmetry, thereby overcoming the sim-to-real gap. We validate the TACO approach through extensive simulation and real-world experiments, demonstrating its capability to achieve high-speed circular flights and continuous multi-flips.
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。