Hamiltonian-based Neural ODE Networks on the SE(3) Manifold For Dynamics Learning and Control

Accurate models of robot dynamics are critical for safe and stable control and generalization to novel operational conditions. Hand-designed models, however, may be insufficiently accurate, even after careful parameter tuning. This motivates the use of machine learning techniques to approximate the robot dynamics over a training set of state-control trajectories. The dynamics of many robots, including ground, aerial, and underwater vehicles, are described in terms of their SE(3) pose and generalized velocity, and satisfy conservation of energy principles. This paper proposes a Hamiltonian formulation over the SE(3) manifold of the structure of a neural ordinary differential equation (ODE) network to approximate the dynamics of a rigid body. In contrast to a black-box ODE network, our formulation guarantees total energy conservation by construction. We develop energy shaping and damping injection control for the learned, potentially under-actuated SE(3) Hamiltonian dynamics to enable a unified approach for stabilization and trajectory tracking with various platforms, including pendulum, rigid-body, and quadrotor systems. SUPPLEMENTARY MATERIAL Software and videos supplementing this paper: https://thaipduong.github.io/SE3HamDL/

[1]  Biao Huang,et al.  System Identification , 2000, Control Theory for Physicists.

[2]  Andrew Gordon Wilson,et al.  Simplifying Hamiltonian and Lagrangian Neural Networks via Explicit Constraints , 2020, NeurIPS.

[3]  Jan Peters,et al.  Deep Lagrangian Networks: Using Physics as Model Prior for Deep Learning , 2019, ICLR.

[4]  David Duvenaud,et al.  Neural Ordinary Differential Equations , 2018, NeurIPS.

[5]  Stefano Stramigioli,et al.  Port-Hamiltonian Passivity-Based Control on SE(3) of a Fully Actuated UAV for Aerial Physical Interaction Near-Hovering , 2019, IEEE Robotics and Automation Letters.

[6]  J. Webster,et al.  Wiley Encyclopedia of Electrical and Electronics Engineering , 2010 .

[7]  Jason Yosinski,et al.  Hamiltonian Neural Networks , 2019, NeurIPS.

[8]  Ioannis G. Kevrekidis,et al.  On learning Hamiltonian systems from data. , 2019, Chaos.

[9]  Carl E. Rasmussen,et al.  PILCO: A Model-Based and Data-Efficient Approach to Policy Search , 2011, ICML.

[10]  Rose Yu,et al.  Incorporating Symmetry into Deep Dynamics Models for Improved Generalization , 2020, ArXiv.

[11]  Arjan van der Schaft,et al.  Port-Hamiltonian Systems Theory: An Introductory Overview , 2014, Found. Trends Syst. Control..

[12]  E. Hairer,et al.  Simulating Hamiltonian dynamics , 2006, Math. Comput..

[13]  Hamiltonian formalism for Euler parameters , 1985 .

[14]  Davide Scaramuzza,et al.  A Benchmark Comparison of Monocular Visual-Inertial Odometry Algorithms for Flying Robots , 2018, 2018 IEEE International Conference on Robotics and Automation (ICRA).

[15]  Johann Reger,et al.  IDA-PBC for Underactuated Mechanical Systems in Implicit Port-Hamiltonian Representation , 2019, 2019 18th European Control Conference (ECC).

[17]  Kim D. Listmann,et al.  Deep Lagrangian Networks for end-to-end learning of energy-based control for under-actuated systems , 2019, 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[18]  Taeyoung Lee,et al.  Geometric tracking control of a quadrotor UAV on SE(3) , 2010, 49th IEEE Conference on Decision and Control (CDC).

[19]  Taeyoung,et al.  Global Formulations of Lagrangian and Hamiltonian Dynamics on Manifolds , 2017 .

[20]  Aníbal Ollero,et al.  Robust control of underactuated Aerial Manipulators via IDA-PBC , 2014, 53rd IEEE Conference on Decision and Control.

[21]  A. G. Greenhill.  Analytical Mechanics , 1890, Nature.

[22]  Romeo Ortega,et al.  Stabilization of a class of underactuated mechanical systems via interconnection and damping assignment , 2002, IEEE Trans. Autom. Control..

[23]  Amit Chakraborty,et al.  Symplectic ODE-Net: Learning Hamiltonian Dynamics with Control , 2020, ICLR.

[24]  Eric P. Fahrenthold,et al.  Hamilton's Equations with Euler Parameters for Rigid Body Dynamics Modeling. Chapter 3 , 2004 .

[25]  Davide Scaramuzza,et al.  AutoTune: Controller Tuning for High-Speed Flight , 2021, ArXiv.

[26]  Amit Chakraborty,et al.  Dissipative SymODEN: Encoding Hamiltonian Dynamics with Dissipation and Control into Deep Learning , 2020, ArXiv.

[27]  Jan Peters,et al.  Model learning for robot control: a survey , 2011, Cognitive Processing.

[28]  Guilherme V. Raffo,et al.  Passivity Based Control of a Quadrotor UAV , 2014 .

[29]  Kevin M. Lynch,et al.  Modern Robotics: Mechanics, Planning, and Control , 2017 .

[30]  Eldad Haber,et al.  Deep Neural Networks Motivated by Partial Differential Equations , 2018, Journal of Mathematical Imaging and Vision.

[31]  Mykel J. Kochenderfer,et al.  A General Framework for Structured Learning of Mechanical Systems , 2019, ArXiv.

[32]  Vijay Kumar,et al.  Minimum snap trajectory generation and control for quadrotors , 2011, 2011 IEEE International Conference on Robotics and Automation.

[33]  Peter Goldsmith,et al.  Modified energy-balancing-based control for the tracking problem , 2008 .

[34]  Jianyu Zhang,et al.  Symplectic Recurrent Neural Networks , 2020, ICLR.

[35]  Thomas A. Runkler,et al.  Modeling System Dynamics with Physics-Informed Neural Networks Based on Lagrangian Mechanics , 2020, ArXiv.

[36]  Timothy D. Barfoot,et al.  State Estimation for Robotics , 2017 .

[37]  Vipin Kumar,et al.  Integrating Physics-Based Modeling with Machine Learning: A Survey , 2020, ArXiv.

[38]  Hannu Tenhunen,et al.  A Survey on Odometry for Autonomous Navigation Systems , 2019, IEEE Access.

[39]  Andrew Jaegle,et al.  Hamiltonian Generative Networks , 2020, ICLR.

[40]  Raia Hadsell,et al.  Graph networks as learnable physics engines for inference and control , 2018, ICML.

[41]  Sergey Levine,et al.  Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models , 2018, NeurIPS.

[42]  G. Karniadakis,et al.  Multistep Neural Networks for Data-driven Discovery of Nonlinear Dynamical Systems , 2018, 1801.01236.

[43]  Miles Cranmer,et al.  Lagrangian Neural Networks , 2020, ICLR 2020.

[44]  Nolan Wagener,et al.  Information theoretic MPC for model-based reinforcement learning , 2017, 2017 IEEE International Conference on Robotics and Automation (ICRA).

[45]  Jean-Marie Souriau,et al.  On Geometric Mechanics , 2007 .

[46]  Antonio Franchi,et al.  Modeling, control and design optimization for a fully-actuated hexarotor aerial vehicle with tilted propellers , 2015, 2015 IEEE International Conference on Robotics and Automation (ICRA).