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 2206.12450eess.SYcs.SY
收藏

快速最优自适应跟踪控制:一种基于条件生成对抗网的元强化学习算法

Fast and Optimal Adaptive Tracking Control: A Novel Meta-Reinforcement Learning via Conditional Generative Adversarial Net

Mohammad Mahmoudi, Nasser Sadati

摘要:

具有未知动态的非线性系统的控制一直是一个重要的研究领域。本文提出了一种新的数据驱动的最优自适应控制结构,与标准的自适应控制相比,具有更少的控制工作量和更快的适应速度。所提出的控制结构利用系统的记录数据,以提高适应速度和性能显着。在这项研究中,我们采用了一个条件生成对抗网络(CGAN)作为一种新的中央模式发生器,以再现稳态谐波模式的控制信号匹配系统的不确定性在很大范围内。我们还可以使用CGAN架构作为故障检测器。CGAN提供了一个低维的不确定性潜在空间。当存在许多参数不确定性时,特别是对于大规模系统,它可以快速方便地自适应。然后,我们引入了一种新的元强化学习框架,使CGAN的潜在空间适应系统的不确定性,作为一个最优的直接自适应控制器,而无需任何系统标识符。控制结构的另一部分是一个调节器,实现半全局渐近跟踪使用的李雅普诺夫稳定性分析。最后,通过一些模拟,我们评估了两个动力系统,机器人机械手和大型肌肉骨骼结构,在干扰和扰动的存在下,所提出的设计的能力。

英文摘要:

The control of nonlinear systems with unknown dynamics has been a significant field of research for many years. This paper presents a novel data-driven optimal adaptive control structure with less control effort and faster adaptation than standard adaptive control counterparts. The proposed control structure utilizes the system's recorded data to increase the speed of adaptation and performance dramatically. In this study, we employ a conditional generative adversarial net (CGAN) as a novel central pattern generator to reproduce the steady-state harmonic pattern of the control signals matching the system's uncertainties over a wide range. We can also use the CGAN architecture as a fault detector. The CGAN provides a low-dimensional latent space of uncertainties. It enables rapid and convenient adaptation when there are many parametric uncertainties, especially for large-scale systems. Then, we introduce a novel meta-reinforcement learning framework to adapt the latent space of CGAN to the system's uncertainties as an optimal direct adaptive controller without any system identifier. Another part of the control structure is a regulator that achieves semi-global asymptotic tracking using the Lyapunov stability analysis. Finally, via some simulations, we evaluate the capabilities of the proposed designs on two dynamical systems, a robot manipulator and a large-scale musculoskeletal structure, in the presence of disturbance and perturbation.

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。

↑