用强化学习统一控制四旋翼挂载物系统，无需调参即可适应不同负载。
RoVerFly: Robust and Versatile Implicit Hybrid Control of Quadrotor-Payload Systems
- 用单一强化学习策略隐式处理混合动力学，无需切换控制器。
- 零样本泛化到不同质量与绳长的负载，且抗干扰能力强。
- 保留反馈控制结构，适合需要稳定性的实际飞行场景。
四旋翼飞行器在执行精确轨迹跟踪时，受非线性动力学和欠驱动特性影响，控制设计极具挑战性；当挂载柔性绳悬吊负载时，系统自由度增加，动态特性呈现混合模式，进一步加剧难度。传统基于模型的方法虽有稳定性保证，但需大量调参，且在负载增减、质量或绳长变化时难以自适应。本文提出 RoVerFly，一种统一的学习型控制框架：单个强化学习（RL）策略作为隐式混合控制器，无需显式识别模式或切换控制器即可应对复杂动态。通过任务与域随机化训练，该控制器对扰动和参数变化具有鲁棒性，在无重调参情况下实现跨负载配置（包括无负载、不同质量及绳长）的强零样本泛化能力，同时保持反馈跟踪控制器的可解释性与结构优势。代码与补充材料见 https://github.com/mintaeshkim/roverfly。
原文摘要 · Abstract (English)
Designing robust controllers for precise trajectory tracking with quadrotors is challenging due to nonlinear dynamics and underactuation, and becomes harder with flexible cable-suspended payloads that add degrees of freedom and hybrid dynamics. Classical model-based methods offer stability guarantees but require extensive tuning and often fail to adapt when the configuration changes-when a payload is added or removed, or when its mass or cable length varies. We present RoVerFly, a unified learning-based control framework where a single reinforcement learning (RL) policy functions as an implicit hybrid controller, managing complex dynamics without explicit mode detection or controller switching. Trained with task and domain randomization, the controller is resilient to disturbances and varying dynamics. It achieves strong zero-shot generalization across payload settings-including no payload as well as varying mass and cable length-without re-tuning, while retaining the interpretability and structure of a feedback tracking controller. Code and supplementary materials are available at https://github.com/mintaeshkim/roverfly.
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。