arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2602.03968eess.SYcs.SY
收藏

具备安全性的强化学习:基于可行性行动防护的高超音速纵向飞行

Safety-Critical Reinforcement Learning with Viability-Based Action Shielding for Hypersonic Longitudinal Flight

The University of Arizona(亚利桑那大学)

Hossein Rastgoftar

AI总结:

本文提出一种基于可行性行动防护的安全关键强化学习框架,用于高超音速纵向飞行,通过安全区域划分和模式依赖奖励实现安全控制与恢复。

摘要:

本文提出了一种用于非线性动力系统的安全关键强化学习框架,这些系统在连续状态和输入空间中运行,并受到显式物理约束。通过行动防护和基于可达性的可接受行动集,强制执行硬安全约束,确保在学习或执行过程中不会故意选择不安全行为。为了在单一控制架构中捕捉正常操作和恢复行为,根据是否属于安全盒成员将状态空间划分为安全和不安全区域,并使用模式依赖的奖励来促进在安全区域内的准确跟踪以及在操作外部时向其恢复。为了在连续动态上实现在线表格学习,通过状态聚合构建有限状态抽象,并且行动选择和价值更新始终被限制在可接受的行动上。该框架在具有气动和推进耦合的纵向点质量高超音速飞行器模型上得到演示,使用攻角和油门作为控制输入。

英文摘要:

This paper presents a safety-critical reinforcement learning framework for nonlinear dynamical systems with continuous state and input spaces operating under explicit physical constraints. Hard safety constraints are enforced independently of the reward through action shielding and reachability-based admissible action sets, ensuring that unsafe behaviors are never intentionally selected during learning or execution. To capture nominal operation and recovery behavior within a single control architecture, the state space is partitioned into safe and unsafe regions based on membership in a safety box, and a mode-dependent reward is used to promote accurate tracking inside the safe region and recovery toward it when operating outside. To enable online tabular learning on continuous dynamics, a finite-state abstraction is constructed via state aggregation, and action selection and value updates are consistently restricted to admissible actions. The framework is demonstrated on a longitudinal point-mass hypersonic vehicle model with aerodynamic and propulsion couplings, using angle of attack and throttle as control inputs.

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。

↑