Gaussian Processes Model-Based Control of Underactuated Balance Robots

Control of underactuated balance robot requires external subsystem trajectory tracking and internal unstable subsystem balancing with limited control authority. We present a learning-based control approach for underactuated balance robots. The tracking and balancing control is designed the controller in fast- and slow-time scales. In the slow-time scale, model predictive control is adopted to plan desired internal state profile to achieve external trajectory tracking task. The internal state is then stabilized around the planned profile in the fast-time scale. The control design is based on a learned Gaussian process (GP) regression model without need of a priori knowledge about the robot dynamics. The controller also incorporates the GP model predicted variance to enhance robustness to modeling errors. Experiments are presented using a Furuta pendulum system.

[1]  Hassan K. Khalil,et al.  Output feedback stabilization of inverted pendulum on a cart in the presence of uncertainties , 2015, Autom..

[2]  Krishna Busawon,et al.  Analysis and Control of Underactuated Mechanical Systems , 2013 .

[3]  Dana Kulic,et al.  Stable Gaussian process based tracking control of Lagrangian systems , 2017, 2017 IEEE 56th Annual Conference on Decision and Control (CDC).

[4]  J. Marsden,et al.  Dynamic inversion of nonlinear maps with applications to nonlinear control and robotics , 1995 .

[5]  KrauseAndreas,et al.  Information-Theoretic Regret Bounds for Gaussian Process Optimization in the Bandit Setting , 2012 .

[6]  E. Westervelt,et al.  Feedback Control of Dynamic Bipedal Robot Locomotion , 2007 .

[7]  Torsten Koller,et al.  Learning-based Model Predictive Control for Safe Exploration and Reinforcement Learning , 2019, ArXiv.

[8]  Yizhai Zhang,et al.  Rider Trunk and Bicycle Pose Estimation With Fusion of Force/Inertial Sensors , 2013, IEEE Transactions on Biomedical Engineering.

[9]  Dieter Fox,et al.  Gaussian Processes and Reinforcement Learning for Identification and Control of an Autonomous Blimp , 2007, Proceedings 2007 IEEE International Conference on Robotics and Automation.

[10]  Kuo Chen,et al.  Learning-based model reduction and control of underactuated balance robots , 2019 .

[11]  Yizhai Zhang,et al.  An integrated physical-learning model of physical human-robot interactions with application to pose estimation in bikebot riding , 2016, Int. J. Robotics Res..

[12]  Henry M. Rowan.  Bipedal Model and Hybrid Zero Dynamics of Human Walking with Foot Slip , 2019 .

[13]  Pieter Abbeel,et al.  Autonomous Helicopter Aerobatics through Apprenticeship Learning , 2010, Int. J. Robotics Res..

[14]  M. Spong,et al.  Robot Modeling and Control , 2005 .

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

[16]  Frank Allgöwer,et al.  A quasi-infinite horizon nonlinear model predictive control scheme with guaranteed stability , 1997, 1997 European Control Conference (ECC).

[17]  Angela P. Schoellig,et al.  An Inversion-Based Learning Approach for Improving Impromptu Trajectory Tracking of Robots With Non-Minimum Phase Dynamics , 2018, IEEE Robotics and Automation Letters.

[18]  J. Grizzle,et al.  Necessary conditions for asymptotic tracking in nonlinear systems , 1994, IEEE Trans. Autom. Control..

[19]  J. Kocijan,et al.  Gaussian process model based predictive control , 2004, Proceedings of the 2004 American Control Conference.

[20]  Jan Peters,et al.  Model Learning with Local Gaussian Process Regression , 2009, Adv. Robotics.

[21]  Yizhai Zhang,et al.  A robotic bipedal model for human walking with slips , 2015, 2015 IEEE International Conference on Robotics and Automation (ICRA).

[22]  Christopher D. McKinnon,et al.  Learning Probabilistic Models for Safe Predictive Control in Unknown Environments , 2019, 2019 18th European Control Conference (ECC).

[23]  Jan Peters,et al.  Reinforcement learning in robotics: A survey , 2013, Int. J. Robotics Res..

[24]  Bernhard Schölkopf,et al.  Learning Inverse Dynamics: a Comparison , 2008, ESANN.

[25]  Ruggero Carli,et al.  A Data-Efficient Geometrically Inspired Polynomial Kernel for Robot Inverse Dynamic , 2019, IEEE Robotics and Automation Letters.

[26]  Jingang Yi,et al.  Stability and Control of a Rider–Bicycle System: Analysis and Experiments , 2020, IEEE Transactions on Automation Science and Engineering.

[27]  Dezhen Song,et al.  Trajectory tracking and balance stabilization control of autonomous motorcycles , 2006, Proceedings 2006 IEEE International Conference on Robotics and Automation, 2006. ICRA 2006..

[28]  Agathe Girard,et al.  Adaptive, Cautious, Predictive control with Gaussian Process Priors , 2003 .

[29]  Leonid B. Freidovich,et al.  Virtual-Holonomic-Constraints-Based Design of Stable Oscillations of Furuta Pendulum: Theory and Experiments , 2007, IEEE Transactions on Robotics.

[30]  Angela P. Schoellig,et al.  Robust Constrained Learning-based NMPC enabling reliable mobile robot path tracking , 2016, Int. J. Robotics Res..

[31]  Fakhrul Alam,et al.  Gaussian Process Model Predictive Control of an Unmanned Quadrotor , 2016, Journal of Intelligent & Robotic Systems.

[32]  Sergey Levine,et al.  Learning from the hindsight plan — Episodic MPC improvement , 2016, 2017 IEEE International Conference on Robotics and Automation (ICRA).

[33]  Javier Aracil,et al.  Partial-energy-shaping control for orbital stabilization of high frequency oscillations of the Furuta pendulum , 2009, 2007 46th IEEE Conference on Decision and Control.

[34]  Dongkyoung Chwa,et al.  Orbital Stabilization of Inverted-Pendulum Systems via Coupled Sliding-Mode Control , 2009, IEEE Transactions on Industrial Electronics.

[35]  Yizhai Zhang,et al.  Stationary balance control of a bikebot , 2014, 2014 IEEE International Conference on Robotics and Automation (ICRA).

[36]  Sandra Hirche,et al.  An Uncertainty-Based Control Lyapunov Approach for Control-Affine Systems Modeled by Gaussian Process , 2018, IEEE Control Systems Letters.

[37]  Tao Liu,et al.  Learning-based modeling and control of underactuated balance robotic systems , 2017, 2017 13th IEEE Conference on Automation Science and Engineering (CASE).

[38]  Yizhai Zhang,et al.  Trajectory tracking and balance control of an autonomous bikebot , 2017, 2017 IEEE International Conference on Robotics and Automation (ICRA).

[39]  Stefan Schaal,et al.  Learning Control in Robotics , 2010, IEEE Robotics & Automation Magazine.

[40]  Angela P. Schoellig,et al.  Provably Robust Learning-Based Approach for High-Accuracy Tracking Control of Lagrangian Systems , 2019, IEEE Robotics and Automation Letters.

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

[42]  Carl E. Rasmussen,et al.  Gaussian processes for machine learning , 2005, Adaptive computation and machine learning.

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

[44]  Angela P. Schoellig,et al.  Design of deep neural networks as add-on blocks for improving impromptu trajectory tracking , 2017, 2017 IEEE 56th Annual Conference on Decision and Control (CDC).

[45]  Jingang Yi,et al.  Balance equilibrium manifold and control of rider-bikebot systems , 2016, 2016 American Control Conference (ACC).

[46]  Ross A. Knepper,et al.  DeepMPC: Learning Deep Latent Features for Model Predictive Control , 2015, Robotics: Science and Systems.