Dexterous and autonomous robots should be capable of executing elaborated dynamical motions skillfully. Learning techniques may be leveraged to build models of such dynamic skills. To accomplish this, the learning model needs to encode a stable vector field that resembles the desired motion dynamics. This is challenging as the robot state does not evolve on a Euclidean space, and therefore the stability guarantees and vector field encoding need to account for the geometry arising from, for example, the orientation representation. To tackle this problem, we propose learning Riemannian stable dynamical systems (RSDS) from demonstrations, allowing us to account for different geometric constraints resulting from the dynamical system state representation. Our approach provides Lyapunov-stability guarantees on Riemannian manifolds that are enforced on the desired motion dynamics via diffeomorphisms built on neural manifold ODEs. We show that our Riemannian approach makes it possible to learn stable dynamical systems displaying complicated vector fields on both illustrative examples and real-world manipulation tasks, where Euclidean approximations fail.
translated by 谷歌翻译
为了执行机器人操纵任务,核心问题是确定满足任务要求的合适轨迹。存在各种计算此类轨迹的方法,是学习和优化主要驾驶技术。我们的作品建立在从示范中学习(LFD)范式的基础上,专家展示了动作,机器人学会了模仿它们。但是,专家演示不足以捕获各种任务规格,例如掌握对象的时间。在本文中,我们提出了一种新方法,以考虑LFD技能中的正式任务规格。确切地说,我们利用了系统的时间属性的一种表达形式信号时间逻辑(STL),以制定任务规格并使用黑盒优化(BBO)来相应地调整LFD技能。我们使用多个任务展示了我们的方法如何使用STL和BBO来解决LFD限制。
translated by 谷歌翻译
贝叶斯优化是一种数据高效技术,可用于机器人中的控制参数调整,参数策略适应和结构设计。这些问题中的许多问题需要优化在非欧几里德域上定义的函数,如球体,旋转组或正向矩阵的空间。为此,必须在感兴趣的空间内之前或等效地定义内核的高斯进程。有效内核通常反映它们定义的空间的几何形状,但设计它们通常是非微不足道的。基于随机部分微分方程和Laplace-Beltrami运营商的频谱理论,最近在Riemannian Mat'En内核的工作,提供了朝向构建此类几何感知内核的承诺途径。在本文中,我们研究了在机器人中的兴趣流动上实施这些内核的技术,展示了它们在一组人工基准函数上的性能,并说明了各种机器人应用的几何感知贝叶斯优化,覆盖方向控制,可操纵性优化,和运动规划,同时显示其提高性能。
translated by 谷歌翻译