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 2310.03246cs.RO
收藏

${\tt MORALS}$:通过潜在空间中的拓扑工具分析高维机器人控制器

${\tt MORALS}$: Analysis of High-Dimensional Robot Controllers via Topological Tools in a Latent Space

Rutgers(罗格斯大学);DIMACS(DIMACS中心);Dept. of Mathematics(数学系);Dept. of Computer Science(计算机科学系)

Ewerton R. Vieira, Aravind Sivaramakrishnan, Sumanth Tangirala, Edgar Granados, Konstantin Mischaikow, Kostas E. Bekris

AI总结:

本文提出MORALS方法,结合自编码神经网络与Morse图,在潜在空间中高效估计高维机器人控制器的吸引域,适用于数据驱动控制器,并在67维人形机器人和96维三指机械手上验证了数据效率。

摘要:

估计机器人控制器的吸引域(${\tt RoA}$)对于安全应用和控制器组合至关重要。许多现有方法需要闭环表达式,这限制了它们对数据驱动控制器的适用性。仅基于轨迹展开的方法往往需要大量数据。在先前的工作中,我们证明了基于${\it Morse Graphs}$(有向无环图,组合表示底层非线性动力学)的拓扑工具能够提供数据高效的${\tt RoA}$估计,无需解析模型。然而,这些方法在处理高维系统时面临困难,因为它们依赖于状态空间离散化。本文提出了在学习的潜在空间中进行Morse图辅助的吸引域发现(${\tt MORALS}$)。该方法结合了自编码神经网络和Morse图。${\tt MORALS}$在估计数据驱动控制器在高维系统(包括一个67维人形机器人和一个96维三指机械手)中的吸引子及其${\tt RoA}$方面显示出有前景的预测能力。它首先将受控系统的动力学投影到学习的潜在空间中。然后,它构建一种简化形式的Morse图,以表示底层动力学的双稳定性,即检测控制器何时导致期望行为与非期望行为。在高维机器人数据集上的评估表明,${\tt RoA}$估计具有数据效率。

英文摘要:

Estimating the region of attraction (${\tt RoA}$) for a robot controller is essential for safe application and controller composition. Many existing methods require a closed-form expression that limit applicability to data-driven controllers. Methods that operate only over trajectory rollouts tend to be data-hungry. In prior work, we have demonstrated that topological tools based on ${\it Morse Graphs}$ (directed acyclic graphs that combinatorially represent the underlying nonlinear dynamics) offer data-efficient ${\tt RoA}$ estimation without needing an analytical model. They struggle, however, with high-dimensional systems as they operate over a state-space discretization. This paper presents ${\it Mo}$rse Graph-aided discovery of ${\it R}$egions of ${\it A}$ttraction in a learned ${\it L}$atent ${\it S}$pace (${\tt MORALS}$). The approach combines auto-encoding neural networks with Morse Graphs. ${\tt MORALS}$ shows promising predictive capabilities in estimating attractors and their ${\tt RoA}$s for data-driven controllers operating over high-dimensional systems, including a 67-dim humanoid robot and a 96-dim 3-fingered manipulator. It first projects the dynamics of the controlled system into a learned latent space. Then, it constructs a reduced form of Morse Graphs representing the bistability of the underlying dynamics, i.e., detecting when the controller results in a desired versus an undesired behavior. The evaluation on high-dimensional robotic datasets indicates data efficiency in ${\tt RoA}$ estimation.

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。

↑