论文标题
学习从专家演示中控制
Learning to control from expert demonstrations
论文作者
论文摘要
在本文中，我们重新审视了从专家的有限演示中学习稳定控制器的问题。首先关注反馈可线化的系统，我们展示了如何将专家演示组合到稳定控制器中，前提是演示足够长，至少有$ n+1 $，其中$ n $是系统控制的系统的数量。当我们有超过$ n+1 $示范时，我们将讨论如何最佳选择最佳的$ n+1 $示范来构建稳定控制器。然后，我们将这些结果扩展到一类系统，这些系统可以嵌入包含一系列积分器链的较高维度系统中。该算法的可行性通过将其应用于Crazyflie 2.0四型四个四型。
In this paper, we revisit the problem of learning a stabilizing controller from a finite number of demonstrations by an expert. By first focusing on feedback linearizable systems, we show how to combine expert demonstrations into a stabilizing controller, provided that demonstrations are sufficiently long and there are at least $n+1$ of them, where $n$ is the number of states of the system being controlled. When we have more than $n+1$ demonstrations, we discuss how to optimally choose the best $n+1$ demonstrations to construct the stabilizing controller. We then extend these results to a class of systems that can be embedded into a higher-dimensional system containing a chain of integrators. The feasibility of the proposed algorithm is demonstrated by applying it on a CrazyFlie 2.0 quadrotor.
