Soft robots have many advantages over rigid robots thanks to their compliant and passive nature. However, it is generally challenging to model the dynamics of soft robots due to their high spatial dimensionality, making it difficult to use model-based methods to accurately control soft robots. It often requires direct numerical simulation of partial differential equations to simulate soft robots. This not only requires an accurate numerical model, but also makes soft robot modeling slow and expensive. Deep learning algorithms have shown promises in data-driven modeling of soft robots. However, these algorithms usually require a large amount of data, which are difficult to obtain in either simulation or real-world experiments of soft robots. In this work, we propose KNODE-Cosserat, a framework that combines first-principle physics models and neural ordinary differential equations. We leverage the best from both worlds -- the generalization ability of physics-based models and the fast speed of deep learning methods. We validate our framework in both simulation and real-world experiments. In both cases, we show that the robot model significantly improves over the baseline models under different metrics.
Cosserat-Rod Based Dynamic Modeling of Soft Slender Robot Interacting with Environment
Inria(法国国家信息与自动化研究所);university of Lille(里尔大学);Centrale Lille(里尔中央理工学院);CRIStAL - Centre de Recherche en Informatique Signal et Automatique de Lille(里尔信息信号与自动化研究中心)
Piecewise Linear Strain Cosserat Model for Soft Slender Manipulator
Inria(法国国家信息与自动化研究所);University of Lille(里尔大学);Centrale Lille(里尔中央理工学院);CRIStAL - Centre de Recherche en Informatique Signal et Automatique de Lille - UMR 9189(里尔计算机、信号与自动化研究中心(UMR 9189))
Coordinated Science Laboratory(协调科学实验室);National Center for Supercomputing Applications(国家超级计算应用中心);Carl R. Woese Institute for Genomic Biology(卡尔·R·沃斯基因组生物学研究所);University of Illinois at Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校)
Adaptive Model-Predictive Control of a Soft Continuum Robot Using a Physics-Informed Neural Network Based on Cosserat Rod Theory
Institute of Mechatronic Systems, Leibniz University Hannover(机械系统研究所,汉诺威莱布尼茨大学);Department of Advanced Interdisciplinary Studies, The University of Tokyo(先进跨学科研究部,东京大学);Institute of Assembly Technology and Robotics, Leibniz University of Hannover(组装技术与机器人研究所,汉诺威莱布尼茨大学)
Adaptive actuation of magnetic soft robots using deep reinforcement learning
Wuhan National High Magnetic Field Center, Huazhong University of Science and Technology(华中科技大学武汉国家强磁场中心);State Key Laboratory of Advanced Electromagnetic Engineering and Technology, Huazhong University of Science and Technology(华中科技大学强电磁工程与新技术国家重点实验室)
A physics-informed, vision-based method to reconstruct all deformation modes in slender bodies
School of Electrical and Computer Engineering(电气与计算机工程学院);Georgia Institute of Technology(佐治亚理工学院);Twentieth Century Fox(二十世纪福克斯);Starfleet Academy(星际舰队学院);Tyrell Inc.(泰勒尔公司)
A Quantitative Comparison of Centralised and Distributed Reinforcement Learning-Based Control for Soft Robotic Arms
Department of Electrical and Computer Engineering, National University of Singapore(电子与计算机工程系,新加坡国立大学);Department of Computer Science, National University of Singapore(计算机科学系,新加坡国立大学);Department of Mechanical Engineering, National University of Singapore(机械工程系,新加坡国立大学)
Data-Driven Soft Robot Control via Adiabatic Spectral Submanifolds
Institute for Mechanical Systems, ETH Zürich(机械系统研究所,苏黎世联邦理工学院);Autonomous Systems Lab, Stanford University(自主系统实验室,斯坦福大学);Automatic Control Laboratory, ETH Zürich(自动控制实验室,苏黎世联邦理工学院)
University of Illinois at Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校);Coordinated Science Laboratory(协调科学实验室);National Center for Supercomputing Applications(国家超级计算应用中心);Carl R. Woese Institute for Genomic Biology(卡尔·R·沃斯基因组生物学研究所)
DeformX: A Versatile Co-Simulation Framework for Deformable Linear Objects
The Robotics Institute, Carnegie Mellon University(卡内基梅隆大学机器人研究所);Department of Mechanical Engineering, Carnegie Mellon University(卡内基梅隆大学机械工程系);School of Ocean and Civil Engineering, Shanghai Jiao Tong University(上海交通大学海洋与土木工程学院);Zhiyuan College, Shanghai Jiao Tong University(上海交通大学致远学院);John A. Paulson School of Engineering and Applied Sciences, Harvard University(哈佛大学约翰·A·保尔森工程与应用科学学院)
提出DeformX框架,集成Cosserat杆物理引擎与NVIDIA Isaac Sim,实现可变形线性物体的物理精确与视觉真实仿真,支持机器人学习,在真实线缆分割和绳索摆动任务中验证了仿真到现实的迁移能力。
A Synergistic Framework for Learning Shape Estimation and Shape-Aware Whole-Body Control Policy for Continuum Robots
School of Informatics, University of Edinburgh(爱丁堡大学信息学院);Walker Department of Mechanical Engineering, the University of Texas at Austin(德克萨斯大学奥斯汀分校沃克机械工程系)
Helical Tendon-Driven Continuum Robot with Programmable Follow-the-Leader Operation
University of Louisville(路易斯维尔大学);University of Louisville School of Medicine(路易斯维尔大学医学院);Healthcare Robotics and Telesurgery Laboratory (Heartlab)(医疗机器人与远程外科实验室);Department of Orthopedic Surgery(骨科部门);Robley Rex Va Medical Center(罗伯利雷克斯退伍军人医疗中心)