Adaptive-Control-Oriented Meta-Learning for Nonlinear Systems
Adaptive-Control-Oriented Meta-Learning for Nonlinear Systems
复制标题
DOI：
10.15607/rss.2021.xvii.056
复制
发表时间：
2021-03
期刊：
影响因子：
--
通讯作者：
Spencer M. Richards;Navid Azizan;J. Slotine;M. Pavone
中科院分区：
文献类型：
--
作者：
Spencer M. Richards;Navid Azizan;J. Slotine;M. Pavone
实时自适应对于在复杂动态环境中操作的机器人的控制是必不可少的。自适应控制律可以赋予即使是非线性系统良好的轨迹跟踪性能，只要任何不确定的动态项是线性参数化与已知的非线性特征。然而，通常很难先验地指定这些特征，例如旋翼机上的空气动力学扰动或操纵器臂与各种物体之间的相互作用力。在本文中，我们转向数据驱动的建模与神经网络学习，离线从过去的数据，这些非线性特征的内部参数模型的自适应控制器。我们的关键见解是，我们可以更好地准备控制器的部署与控制为导向的元学习功能在闭环仿真，而不是回归为导向的元学习功能，以适应输入输出数据。具体地说，我们元学习的自适应控制器与闭环跟踪仿真作为基础学习者和平均跟踪误差作为元目标。与非线性平面旋翼机受风，我们证明了我们的自适应控制器优于其他控制器训练回归导向的元学习时，部署在闭环轨迹跟踪控制。
Real-time adaptation is imperative to the control of robots operating in complex, dynamic environments. Adaptive control laws can endow even nonlinear systems with good trajectory tracking performance, provided that any uncertain dynamics terms are linearly parameterizable with known nonlinear features. However, it is often difficult to specify such features a priori, such as for aerodynamic disturbances on rotorcraft or interaction forces between a manipulator arm and various objects. In this paper, we turn to data-driven modeling with neural networks to learn, offline from past data, an adaptive controller with an internal parametric model of these nonlinear features. Our key insight is that we can better prepare the controller for deployment with control-oriented meta-learning of features in closed-loop simulation, rather than regression-oriented meta-learning of features to fit input-output data. Specifically, we meta-learn the adaptive controller with closed-loop tracking simulation as the base-learner and the average tracking error as the meta-objective. With a nonlinear planar rotorcraft subject to wind, we demonstrate that our adaptive controller outperforms other controllers trained with regression-oriented meta-learning when deployed in closed-loop for trajectory tracking control.