Geometry-aware Bayesian Optimization in Robotics using Riemannian Matérn Kernels
St. Petersburg State University(圣彼得堡国立大学);University of Cambridge(剑桥大学);Karlsruhe Institute of Technology(卡尔斯鲁厄理工学院);Bosch Center for Artificial Intelligence(博世人工智能中心);Imperial College London(帝国理工学院);St. Petersburg Department of Steklov Mathematical Institute of Russian Academy of Sciences(俄罗斯科学院斯捷克洛夫数学研究所圣彼得堡分所)
Noémie Jaquier, Viacheslav Borovitskiy, Andrei Smolensky, Alexander Terenin, Tamim Asfour, Leonel Rozo
Bayesian optimization is a data-efficient technique which can be used for control parameter tuning, parametric policy adaptation, and structure design in robotics. Many of these problems require optimization of functions defined on non-Euclidean domains like spheres, rotation groups, or spaces of positive-definite matrices. To do so, one must place a Gaussian process prior, or equivalently define a kernel, on the space of interest. Effective kernels typically reflect the geometry of the spaces they are defined on, but designing them is generally non-trivial. Recent work on the Riemannian Matérn kernels, based on stochastic partial differential equations and spectral theory of the Laplace-Beltrami operator, offers promising avenues towards constructing such geometry-aware kernels. In this paper, we study techniques for implementing these kernels on manifolds of interest in robotics, demonstrate their performance on a set of artificial benchmark functions, and illustrate geometry-aware Bayesian optimization for a variety of robotic applications, covering orientation control, manipulability optimization, and motion planning, while showing its improved performance.
The University of Tokyo, Department of Information Physics and Computing(东京大学信息物理与计算系);The University of Tokyo, Department of Precision Engineering(东京大学精密工程系);National Institute of Informatics, Principles of Informatics Research Division(国家信息研究所信息原理研究部)
Department of Computational Applied Mathematics;Operations Research, Rice University, Houston, TX, USA;Department of Statistics, Texas A\&M University, College Station, TX, USA
Gradient based Bilevel for Inverse Optimal Control, a Riemannian approach
INRIA Bordeaux, Université de Bordeaux(法国国家信息与自动化研究所波尔多中心,波尔多大学);INRIA Nancy, Université de Lorraine(法国国家信息与自动化研究所南锡中心,洛林大学);LAAS-CNRS, Université de Toulouse, CNRS(法国国家科学研究中心系统分析与架构实验室,图卢兹大学,法国国家科学研究中心)
Riemannian Flow Matching Policy for Robot Motion Learning
Institute for Anthropomatics and Robotics, Karlsruhe Institute of Technology(卡尔斯鲁厄理工学院人形机器人与智能系统研究所);Bosch Center for Artificial Intelligence(博世人工智能中心)
Fast and Robust Visuomotor Riemannian Flow Matching Policy
Bosch Center for Artificial Intelligence(博世人工智能中心);Division of Robotics, Perception, and Learning, KTH Royal Institute of Technology(机器人、感知与学习 division,皇家理工学院);Computer Science Department of the Technische Universität Darmstadt(达姆施塔特技术大学计算机科学系)
Maximally manipulable vision-based motion planning for robotic rough-cutting on arbitrarily shaped surfaces
UK National Centre for Nuclear Robotics(英国国家核机器人中心);University of Birmingham(伯明翰大学);National Nuclear Laboratory(国家核实验室);University of West England(西英格兰大学)
Riemannian Time Warping: Multiple Sequence Alignment in Curved Spaces
Technology and Innovation Center (TIC), KUKA Deutschland GmbH(技术与创新中心(TIC),KUKA德国公司);Institute of Robotics and Process Control (IRP), Technische Universität Braunschweig(机器人与过程控制研究所(IRP),柏林工业大学)
Geometric Reinforcement Learning For Robotic Manipulation
Istanbul Technical University(伊斯坦布尔理工大学);University of Trento(特伦托大学);Technical University of Munich(慕尼黑工业大学);Munich Institute of Robotics and Machine Intelligence(慕尼黑机器人与机器智能研究所);Colorado State University(科罗拉多州立大学);Aalto University(阿尔托大学)