# 在真实世界中学习敏捷四旋翼飞行

> 原文链接：https://robotics.hellobike.com/papers/2026-07-13-2602-10111
> 频道：papers | 更新日期：2026-07-13 | 标签：arxiv, cs.RO
> 核心摘要：针对敏捷四旋翼对仿真建模与保守裕度的依赖，提出自适应在线学习框架，并在真实飞行实验中验证。

# 在真实世界中学习敏捷四旋翼飞行

::: v-pre
> 原文链接：[Learning Agile Quadrotor Flight in the Real World](https://arxiv.org/abs/2602.10111)（arXiv 2602.10111 · 发布日期：2026-07-13）

**Learning Agile Quadrotor Flight in the Real World**

针对敏捷四旋翼对仿真建模与保守裕度的依赖，提出自适应在线学习框架，并在真实飞行实验中验证。

## 核心要点

- 动机是学习控制器依赖大量仿真和精确系统辨识，固定策略在分布外扰动或硬件退化下易受影响。
- 方法引入 ATS 主动探索平台物理极限，并用在线残差学习增强简单标称模型。
- 基于学习到的混合模型，提出 RASH-BPTT，实现高效且鲁棒的飞行中策略更新。
- 实验显示四旋翼可在接近执行器饱和限制时可靠执行敏捷机动，约100秒内峰值速度由1.9 m/s提升至7.3 m/s。

**验证范围与局限**：验证范围为真实世界四旋翼敏捷飞行实验，任务为接近执行器饱和限制的敏捷机动。

## 英文摘要 (Abstract)

Learning-based controllers have achieved impressive performance in agile quadrotor flight but typically rely on massive training in simulation, necessitating accurate system identification for effective Sim2Real transfer. However, even with precise modeling, fixed policies remain susceptible to out-of-distribution scenarios, ranging from external aerodynamic disturbances to internal hardware degradation. To ensure safety under these evolving uncertainties, such controllers are forced to operate with conservative safety margins, inherently constraining their agility outside of controlled settings. While online adaptation offers a potential remedy, safely exploring physical limits remains a critical bottleneck due to data scarcity and safety risks. To bridge this gap, we propose a self-adaptive framework that eliminates the need for precise system identification or offline Sim2Real transfer. We introduce Adaptive Temporal Scaling (ATS) to actively explore platform physical limits, and employ online residual learning to augment a simple nominal model. {Based on the learned hybrid model, we further propose Real-world Anchored Short-horizon Backpropagation Through Time (RASH-BPTT) to achieve efficient and robust in-flight policy updates. Extensive experiments demonstrate that our quadrotor reliably executes agile maneuvers near actuator saturation limits. The system evolves a conservative base policy with a peak speed of 1.9 m/s to 7.3 m/s within approximately 100 seconds of flight time. These findings underscore that real-world adaptation serves not merely to compensate for modeling errors, but as a practical mechanism for sustained performance improvement in aggressive flight regimes.

作者：Yunfan Ren, Zhiyuan Zhu, Jiaxu Xing, Davide Scaramuzza
:::

## 原始参考来源 (Sources)

- [arXiv 2602.10111：Learning Agile Quadrotor Flight in the Real World](https://arxiv.org/abs/2602.10111)