Riemannian geometry is a mathematical field which has been the cornerstone of revolutionary scientific discoveries such as the theory of general relativity. Despite early uses in robot design and recent applications for exploiting data with specific geometries, it mostly remains overlooked in robotics. With this blue sky paper, we argue that Riemannian geometry provides the most suitable tools to analyze and generate well-coordinated, energy-efficient motions of robots with many degrees of freedom. Via preliminary solutions and novel research directions, we discuss how Riemannian geometry may be leveraged to design and combine physically-meaningful synergies for robotics, and how this theory also opens the door to coupling motion synergies with perceptual inputs.
One Problem, One Solution: Unifying Robot and Environment Design Optimization
wbk Institute of Production Science, Karlsruhe Institute of Technology(卡尔斯鲁厄理工学院生产科学研究所);Institute for System Dynamics, University of Stuttgart(斯图加特大学系统动力学研究所)
Decentralized Pose Graph Riemannian Optimization for Object-based Multi-Robot SLAM
College of Control Science and Engineering, Zhejiang University(浙江大学控制科学与工程学院);Shanghai Research Institute for Intelligent Autonomous Systems, Tongji University(同济大学上海智能自主系统研究院);Division of Decision and Control Systems, School of EECS, KTH Royal Institute of Technology(瑞典皇家理工学院电气工程与计算机科学学院决策与控制系统系)
A Riemannian Metric for Geometry-Aware Singularity Avoidance by Articulated Robots
University of Toronto Institute for Aerospace Studies(多伦多大学航空航天研究所);University of Zagreb Faculty of Electrical Engineering and Computing(萨格勒布大学电气工程与计算学院)
Unifying Object-Centric World Models and Diffusion Policy: A Hierarchical Framework for Multi-Stage Robotic Tasks
Tandon School of Engineering, New York University(纽约大学坦登工程学院);Courant Institute of Mathematical Sciences, New York University(纽约大学库朗数学科学研究所);AMI Labs(AMI实验室)
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)
Riemannian Optimization for Distance-Geometric Inverse Kinematics
University of Toronto, Institute for Aerospace Studies(多伦多大学航空航天研究所);University of Zagreb, Faculty of Electrical Engineering and Computing(萨格勒布大学电气工程与计算学院)
Learning-Based Robust Control: Unifying Exploration and Distributional Robustness for Reliable Robotics via Free Energy
Mechanical Engineering Program, New York University Abu Dhabi(纽约大学阿布扎赫尔分校机械工程项目);Department of Information and Electrical Engineering & Applied Mathematics, University of Salerno(萨勒诺大学信息与电气工程及应用数学系);Mohammed bin Zayed University for Artificial Intelligence, Abu Dhabi, UAE(穆罕默德·本·扎耶德人工智能大学)
Unifying Deep Predicate Invention with Pre-trained Foundation Models
Robotics Institute, Carnegie Mellon University(卡内基梅隆大学机器人研究所);Computer Science and Engineering Division, University of Michigan(密歇根大学计算机科学与工程系);Department of Computer Science, University of Pittsburgh(匹兹堡大学计算机科学系);Centaur AI Institute(Centaur人工智能研究所);Department of Electrical and Computer Engineering, Princeton University(普林斯顿大学电气与计算机工程系)
Unifying Complementarity Constraints and Control Barrier Functions for Safe Whole-Body Robot Control
Division of Robotics, Perception and Learning, KTH Royal Institute of Technology(机器人、感知与学习系,皇家理工学院);Munich Institute of Robotics and Machine Intelligence, TUM(慕尼黑机器人与智能机械研究所,技术大学);School of Computer Science, University of Nottingham(nottingham大学计算机科学学院);Department of Mechanical Engineering, Stony Brook University(石溪大学机械工程系)
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)
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)
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)
Learning Riemannian Manifolds for Geodesic Motion Skills
Bosch Center for Artificial Intelligence (BCAI)(博世人工智能中心);Karlsruhe Institute of Technology (KIT)(卡尔斯鲁厄理工学院);Technical University of Denmark (DTU)(丹麦技术大学);Max Planck Institute for Intelligent Systems (MPI-IS)(马克斯·普朗克智能系统研究所)
Trinity: Unifying Class-Agnostic Terrain and Semantic Segmentation for Unstructured Outdoor Environments by Leveraging Synthetic Data
Institute of Robotics and Mechatronics, German Aerospace Center (DLR)(机器人与机电系统研究所,德国航空航天中心(DLR));Federal Institute of Technology Zurich (ETH Zurich)(苏黎世联邦理工学院(ETH Zurich));Robotics and AI Institute (RAI)(机器人与人工智能研究所(RAI))
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)
A Unifying Variational Framework for Gaussian Process Motion Planning
University College London(伦敦大学学院);ETH Zürich(苏黎世联邦理工学院);Imperial College London(帝国理工学院);University of Cambridge(剑桥大学);Cornell University(康奈尔大学);TU Delft(代尔夫特理工大学);Chalmers University of Technology(查尔姆斯理工大学)