Physics-guided Learning-based Adaptive Control on the SE(3) Manifold

In real-world robotics applications, accurate models of robot dynamics are critical for safe and stable control in rapidly changing operational conditions. This motivates the use of machine learning techniques to approximate robot dynamics and their disturbances over a training set of state-control trajectories. This paper demonstrates that inductive biases arising from physics laws can be used to improve the data efficiency and accuracy of the approximated dynamics model. For example, the dynamics of many robots, including ground, aerial, and underwater vehicles, are described using their SE(3) pose and satisfy conservation of energy principles. We design a physically plausible model of the robot dynamics by imposing the structure of Hamilton’s equations of motion in the design of a neural ordinary differential equation (ODE) network. The Hamiltonian structure guarantees satisfaction of SE(3) kinematic constraints and energy conservation by construction. It also allows us to derive an energy-based adaptive controller that achieves trajectory tracking while compensating for disturbances. Our learning-based adaptive controller is verified on an under-actuated quadrotor robot.

[1]  Aaron D. Ames,et al.  Learning to jump in granular media: Unifying optimal control synthesis with Gaussian process-based regression , 2017, 2017 IEEE International Conference on Robotics and Automation (ICRA).

[2]  Andreas Krause,et al.  Safe controller optimization for quadrotors with Gaussian processes , 2015, 2016 IEEE International Conference on Robotics and Automation (ICRA).

[3]  Girish Chowdhary,et al.  Asynchronous Deep Model Reference Adaptive Control , 2020, CoRL.

[4]  Carl E. Rasmussen,et al.  Gaussian Processes for Data-Efficient Learning in Robotics and Control , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[5]  Marco Pavone,et al.  Adaptive-Control-Oriented Meta-Learning for Nonlinear Systems , 2021, Robotics: Science and Systems.

[6]  Girish Chowdhary,et al.  Deep Model Reference Adaptive Control , 2019, 2019 IEEE 58th Conference on Decision and Control (CDC).

[7]  Davide Scaramuzza,et al.  Data-Driven MPC for Quadrotors , 2021, IEEE Robotics and Automation Letters.

[8]  Weiping Li,et al.  Composite adaptive control of robot manipulators , 1989, Autom..

[9]  Daewon Lee,et al.  Geometric Adaptive Tracking Control of a Quadrotor Unmanned Aerial Vehicle on SE(3) for Agile Maneuvers , 2015 .

[10]  Robert M. Sanner,et al.  Gaussian Networks for Direct Adaptive Control , 1991, 1991 American Control Conference.

[11]  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).

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

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

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

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

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

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

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

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

[20]  Nikolay Atanasov,et al.  Hamiltonian-based Neural ODE Networks on the SE(3) Manifold For Dynamics Learning and Control , 2021, Robotics: Science and Systems.

[21]  Juraj Kabzan,et al.  Cautious Model Predictive Control Using Gaussian Process Regression , 2017, IEEE Transactions on Control Systems Technology.

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

[23]  R. Calandra,et al.  Control Adaptation via Meta-Learning Dynamics , 2018 .

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

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

[26]  Jonathan P. How,et al.  Nonparametric adaptive control using Gaussian Processes with online hyperparameter estimation , 2013, 52nd IEEE Conference on Decision and Control.

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

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

[29]  Soon-Jo Chung,et al.  Meta-Learning-Based Robust Adaptive Flight Control Under Uncertain Wind Conditions , 2019, ArXiv.