稳定的Transformer-Actor-Critic模型预测控制：一种收缩分析方法
Stable Transformer-Actor-Critic Model Predictive Control: A Contraction Analysis Approach
AI总结：
提出一种Transformer-Actor-Critic MPC架构，通过证明Transformer满足增量输入-状态稳定性并利用黎曼收缩理论分析互联动力学，将理论界作为训练正则化项，实现可证明鲁棒的控制策略。
摘要：
Actor-Critic模型预测控制（MPC）有效解决了复杂的非凸控制问题，但保证这些流程中基于序列的学习模型的闭环稳定性仍然具有挑战性。本文介绍了一种新颖的Transformer-Actor-Critic MPC架构，具有形式化的鲁棒性保证。首先，我们证明了Transformer网络可以满足全局增量输入-状态稳定性（$\delta$ISS）。然后，我们利用黎曼收缩理论分析物理对象与预测神经网络之间的互联动力学。最后，我们将这些理论界作为训练正则化项，以产生可证明鲁棒的策略。该框架在非线性3D无人机模型上进行了验证，执行目标到达和避障机动。
英文摘要：
Actor-Critic Model Predictive Control (MPC) effectively addresses complex, non-convex control problems, but guaranteeing the closed-loop stability of sequence-based learning models within these pipelines remains challenging. This paper introduces a novel Transformer-Actor-Critic MPC architecture with formal robustness guarantees. First, we prove that Transformer networks can satisfy global incremental Input-to-State Stability ($δ$ISS). We then leverage Riemannian contraction theory to analyze the interconnected dynamics between the physical plant and the predictive neural network. Finally, we integrate these theoretical bounds as a training regularizer to yield a certifiably robust policy. The framework is validated on a nonlinear 3D drone model executing target-reaching and obstacle-avoidance maneuvers.
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。
