用深度强化学习让无人机自适应不同载荷和尺寸，实现高精度轨迹跟踪。
Dynamics-Invariant Quadrotor Control using Scale-Aware Deep Reinforcement Learning
- 直接优化力/扭矩输入，跳过传统控制层，实现物理动态不变性。
- 在30g到2.1kg的多型号无人机上，追踪精度比基线提升85%。
- 适用于真实飞行场景，可应对风、地面效应和晃动负载，适合工业级无人机开发。
由于载荷变化、气动干扰及平台差异等动态变化，四旋翼飞行器轨迹跟踪仍具挑战。本文提出一种深度强化学习（DRL）框架，通过直接优化力/扭矩输入，实现物理动态不变性，无需传统中间控制层。架构融合时间序列轨迹编码器与基于历史状态-动作对训练的隐式动力学编码器，以建模平台特异性。此外，引入基于机臂长度参数化的尺度感知动态随机化策略，在30g至2.1kg范围内的无人机上保持稳定，追踪精度较其他DRL基线提升85%。在Crazyflie 2.1无人机上开展超过200次真实飞行验证，结果表明系统能有效适应风、地面效应及摆动载荷，在2.0 m/s速度下实现小于0.05m的均方根误差（RMSE）。该工作建立了一种通用四旋翼控制范式，可补偿多种条件与尺度下的动态差异，为更鲁棒的空中系统铺平道路。
原文摘要 · Abstract (English)
Due to dynamic variations such as changing payload, aerodynamic disturbances, and varying platforms, a robust solution for quadrotor trajectory tracking remains challenging. To address these challenges, we present a deep reinforcement learning (DRL) framework that achieves physical dynamics invariance by directly optimizing force/torque inputs, eliminating the need for traditional intermediate control layers. Our architecture integrates a temporal trajectory encoder, which processes finite-horizon reference positions/velocities, with a latent dynamics encoder trained on historical state-action pairs to model platform-specific characteristics. Additionally, we introduce scale-aware dynamics randomization parameterized by the quadrotor's arm length, enabling our approach to maintain stability across drones spanning from 30g to 2.1kg and outperform other DRL baselines by 85% in tracking accuracy. Extensive real-world validation of our approach on the Crazyflie 2.1 quadrotor, encompassing over 200 flights, demonstrates robust adaptation to wind, ground effects, and swinging payloads while achieving less than 0.05m RMSE at speeds up to 2.0 m/s. This work introduces a universal quadrotor control paradigm that compensates for dynamic discrepancies across varied conditions and scales, paving the way for more resilient aerial systems.
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。