用图神经网络让无人机同时实现平稳跟踪与剧烈稳定，训练更高效。
Multitask Reinforcement Learning for Quadcopter Attitude Stabilization and Tracking using Graph Policy
- 多任务强化学习结合图卷积网络，统一处理不同控制需求。
- 在真实飞控上以400赫兹运行，仅用24个神经元/层，零额外算力。
- 适合需要高鲁棒性飞行控制的无人机研究与工程落地。
四旋翼姿态控制包含两个任务：平滑的姿态跟踪与从任意状态下的剧烈稳定。尽管两者均可建模为追踪问题，但其不同的状态空间和控制策略使得统一奖励函数设计复杂。我们提出一种多任务深度强化学习框架，利用IsaacGym并行仿真与图卷积网络（GCN）策略，有效应对双重任务。所提出的多任务软演员-评论家（SAC）方法相比单任务方法，实现更快、更可靠的训练与更高样本效率。通过将学习到的策略部署于Pixhawk飞控，验证了其实用性：一个仅含两层、每层24个神经元的紧凑网络，在无需额外计算资源的情况下实现了400赫兹控制。代码已开源：https://github.com/robot-perception-group/GraphMTSAC_UAV/
原文摘要 · Abstract (English)
Quadcopter attitude control involves two tasks: smooth attitude tracking and aggressive stabilization from arbitrary states. Although both can be formulated as tracking problems, their distinct state spaces and control strategies complicate a unified reward function. We propose a multitask deep reinforcement learning framework that leverages parallel simulation with IsaacGym and a Graph Convolutional Network (GCN) policy to address both tasks effectively. Our multitask Soft Actor-Critic (SAC) approach achieves faster, more reliable learning and higher sample efficiency than single-task methods. We validate its real-world applicability by deploying the learned policy - a compact two-layer network with 24 neurons per layer - on a Pixhawk flight controller, achieving 400 Hz control without extra computational resources. We provide our code at https://github.com/robot-perception-group/GraphMTSAC\_UAV/.
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。