RTK-Vision PPO for Autonomous Micro UAV Recovery on an Airborne Carrier

📄 arXiv: 2609.20629v1 📥 PDF

作者: Aashish Sahu, R Prasanth Kumar

分类: cs.RO

发布日期: 2026-09-17

备注: 9 pages, 6 figures

💡 一句话要点

提出RTK-Vision PPO框架以实现自主微型无人机在空中载体上的回收

🎯 匹配领域: 支柱二：RL算法与架构 (RL & Architecture)

关键词: 无人机回收 强化学习 RTK-GNSS 自主飞行 物理仿真 PPO策略 动态环境 移动载体

📋 核心要点

  1. 现有方法在微型无人机自主回收过程中面临长距离会合、近距离感知和载体运动等多重挑战。
  2. 论文提出了一种RTK视觉引导的强化学习框架，通过PPO策略实现无人机的自主起飞、任务执行和回收。
  3. 实验结果显示，PPO策略在2000个随机终端试验中成功率达到99.55%，显著优于传统PD基线的78.4%。

📝 摘要（中文）

本论文探讨了微型无人机（UAV）在移动空中载体上的自主回收，旨在实现可重复使用的部署-任务-回收操作。研究提出了一种基于RTK视觉的强化学习框架，子无人机在空中从载体起飞，独立执行任务后返回并重新对接。通过在物理仿真环境中训练的PPO策略，论文展示了在复杂环境下的高成功率，表明该方法在检查、监视和移动物流等应用中的潜在价值。

🔬 方法详解

问题定义：本论文旨在解决微型无人机在移动空中载体上的自主回收问题，现有方法在长距离会合和近距离对接时存在感知和控制的不足。

核心思路：提出了一种基于RTK-GNSS和视觉信息的强化学习框架，利用PPO策略优化无人机的回收过程，以应对复杂的动态环境。

技术框架：整体架构包括载体和子无人机的RTK-GNSS系统，载体实时共享导航状态，子无人机在接近回收平台时使用下向摄像头和标记检测器进行对接。

关键创新：最重要的创新在于将RTK视觉与强化学习相结合，利用物理仿真环境中的传感器噪声模型和气动干扰代理进行训练，显著提高了回收成功率。

关键设计：在PPO策略中，采用了明确的损失函数设计和网络结构，确保在复杂环境下的稳定性和高效性，同时PX4系统负责低级别的稳定控制。

🖼️ 关键图片

fig_0
fig_1
fig_2

📊 实验亮点

实验结果表明，PPO策略在2000个随机终端试验中成功率达到99.55%，而调优后的PD基线仅为78.4%。在14次户外试验中，任务成功率为92.9%，展示了该方法在实际应用中的有效性。

🎯 应用场景

该研究的潜在应用领域包括无人机检查、监视和移动物流等，能够有效提升无人机在动态环境中的自主操作能力，具有重要的实际价值和未来影响。

📄 摘要（原文）

Autonomous recovery of a micro unmanned aerial vehicle (UAV) onto a moving airborne carrier enables reusable deploy-mission-recover operation, but couples long-range rendezvous, close-range perception, carrier motion, aerodynamic interaction, and a discontinuous contact event. This paper presents an RTK-vision-guided reinforcement-learning framework in which a child UAV is physically transported by a larger carrier, takes off from the carrier while airborne, executes an independent sortie, returns to the carrier's current position, redocks, and subsequently descends with the carrier. Both vehicles carry RTK-GNSS, and the carrier continuously shares its navigation state with the child. Near the recovery deck, RTK remains active while a downward-facing camera with a fiducial marker detector provides marker-relative alignment cues. A proximal policy optimization (PPO) policy governing the terminal recovery phase is trained in a physics-based MuJoCo simulation environment with explicit sensor noise models, an aerodynamic disturbance surrogate, and marker-latency randomization, then transferred to hardware. PX4 retains low-level stabilization, and a deterministic safety gate authorizes descent independently of the learned policy. The PPO checkpoint achieves 99.55% success over 2,000 held-out randomized terminal episodes, compared with 78.4% for a tuned PD baseline under identical conditions, with a median planar terminal error of 6.62 cm. Across 14 outdoor trials, the full mission succeeds in 13 trials (92.9%), spanning both near-region recovery and recovery after the carrier translates away from the release point. The results demonstrate a complete autonomous aerial deployment-and-recovery cycle rather than an isolated landing maneuver, establishing a practical basis for reusable carrier-child operation in inspection, surveillance, and mobile-logistics applications.