基于线性参数变化动力系统组合的高维演示可扩展学习
Scalable Learning of High-Dimensional Demonstrations with Composition of Linear Parameter Varying Dynamical Systems
AI总结：
本文针对从演示中学习稳定动力系统时BMI约束非凸优化计算成本高且数值不稳定问题，提出一种新颖的组合式方法，以提升稳定DS学习的适用性和可扩展性。
摘要：
从演示中学习（Learning from Demonstration, LfD）技术使机器人能够从用户演示中学习并泛化任务，从而免除终端用户对编码专业知识的需求。在机器人中实现LfD的一种成熟技术是将演示编码到一个稳定的动力系统（Dynamical System, DS）中。然而，寻找一个稳定的动力系统需要求解一个带有双线性矩阵不等式（bilinear matrix inequality, BMI）约束的优化问题，这是一个非凸问题，根据标量约束和变量数量的不同，该问题需要大量计算资源，并且容易受到浮点误差等数值问题的影响。为了应对这些挑战，我们提出了一种新颖的组合式方法，该方法增强了学习带有BMI约束的稳定DS的适用性和可扩展性。
英文摘要：
Learning from Demonstration (LfD) techniques enable robots to learn and generalize tasks from user demonstrations, eliminating the need for coding expertise among end-users. One established technique to implement LfD in robots is to encode demonstrations in a stable Dynamical System (DS). However, finding a stable dynamical system entails solving an optimization problem with bilinear matrix inequality (BMI) constraints, a non-convex problem which, depending on the number of scalar constraints and variables, demands significant computational resources and is susceptible to numerical issues such as floating-point errors. To address these challenges, we propose a novel compositional approach that enhances the applicability and scalability of learning stable DSs with BMIs.
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。
