ASTER: 通过高效强化学习实现面向姿态的悬挂载荷四旋翼飞行
ASTER: Attitude-aware Suspended-payload Quadrotor Traversal via Efficient Reinforcement Learning
AI总结：
ASTER通过高效强化学习实现缆悬系统自主倒飞，利用混合动力学指导的状态初始化策略提升姿态控制与轨迹敏捷性。
摘要：
四旋翼缆悬系统敏捷机动性显著受到其非光滑混合动力学的阻碍。尽管无模型强化学习（RL）可以规避复杂模型的显式求导，但在严格姿态要求下，实现姿态约束或倒飞仍面临极大挑战，因为极端的奖励稀疏性导致难以取得成功。本文提出了ASTER，一种稳健的RL框架，实现了我们所知的首个成功实现缆悬系统自主倒飞。我们提出了一种混合动力学指导的状态初始化策略（HDSS），该策略通过物理一致的运动学逆运算在紧绷和松散缆索阶段之间反向传播目标配置。HDSS使策略能够发现无法通过标准探索实现的激进机动。广泛的仿真和实际实验表明，该方法在复杂轨迹上表现出显著的敏捷性、精确的姿态对齐以及鲁棒的零样本仿真到现实转移。
英文摘要：
Agile maneuvering of the quadrotor cable-suspended system is significantly hindered by its non-smooth hybrid dynamics. While model-free Reinforcement Learning (RL) circumvents explicit differentiation of complex models, achieving attitude-constrained or inverted flight remains an open challenge due to the extreme reward sparsity under strict orientation requirements. This paper presents ASTER, a robust RL framework that achieves, to our knowledge, the first successful autonomous inverted flight for the cable-suspended system. We propose hybrid-dynamics-informed state seeding (HDSS), an initialization strategy that back-propagates target configurations through physics-consistent kinematic inversions across both taut and slack cable phases. HDSS enables the policy to discover aggressive maneuvers that are unreachable via standard exploration. Extensive simulations and real-world experiments demonstrate remarkable agility, precise attitude alignment, and robust zero-shot sim-to-real transfer across complex trajectories.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
