Gaussian process-based visual pursuit control with unknown target motion learning in three dimensions

In this paper, we propose an observer-based visual pursuit control integrating three-dimensional target motion learning by Gaussian Process Regression (GPR). We consider a situation where a visual sensor equipped rigid body pursuits a target rigid body whose velocity is unknown but dependent on the target's pose. We estimate the pose from visual information and propose a Gaussian Process (GP) model to predict the target velocity from the pose estimate. We analyse stability of the proposed control by showing that estimation and control errors are ultimately bounded with high probability. Finally, simulations illustrate the performance of the proposed control schemes even if the visual measurement is corrupted by noise.

[1]  Patricio A. Vela,et al.  A Concurrent Learning Approach to Monocular, Vision-Based Regulation of Leader/Follower Systems , 2018, 2018 Annual American Control Conference (ACC).

[2]  Dana Kulic,et al.  Stable Gaussian Process based Tracking Control of Euler-Lagrange Systems , 2018, Autom..

[3]  Joao P. Hespanha,et al.  Robust Coordination of Small UAVs for Vision‐Based Target Tracking Using Output‐Feedback MPC with MHE , 2017 .

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

[5]  Masayuki Fujita,et al.  Predictive Visual Feedback Control with Eye-in/to-Hand Configuration via Stabilizing Receding Horizon Approach , 2008 .

[6]  P. Olver.  Nonlinear Systems , 2013 .

[7]  Masayuki Fujita,et al.  Passivity-Based Control and Estimation in Networked Robotics , 2015 .

[8]  Daiki Fujimoto,et al.  Autonomous Adaptive Flight Control of a UAV for Practical Bridge Inspection Using Multiple-Camera Image Coupling Method , 2019, J. Robotics Mechatronics.

[9]  Jonathan P. How,et al.  Bayesian Nonparametric Adaptive Control Using Gaussian Processes , 2015, IEEE Transactions on Neural Networks and Learning Systems.

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

[11]  Sandra Hirche,et al.  Mean Square Prediction Error of Misspecified Gaussian Process Models , 2018, 2018 IEEE Conference on Decision and Control (CDC).

[12]  Andreas Krause,et al.  Information-Theoretic Regret Bounds for Gaussian Process Optimization in the Bandit Setting , 2009, IEEE Transactions on Information Theory.

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

[14]  Thomas B. Schön,et al.  From Pixels to Torques: Policy Learning with Deep Dynamical Models , 2015, ICML 2015.

[15]  Richard M. Murray,et al.  A Mathematical Introduction to Robotic Manipulation , 1994 .

[16]  Kenji Fujimoto,et al.  Kernel-Based Hamilton–Jacobi Equations for Data-Driven Optimal and H-Infinity Control , 2020, IEEE Access.

[17]  Yasushi Iwatani,et al.  Indoor hovering flight of a micro helicopter by markerless visual servo control , 2013, The SICE Annual Conference 2013.

[18]  Sandra Hirche,et al.  Visual Pursuit Control with Target Motion Learning via Gaussian Process , 2020, 2020 59th Annual Conference of the Society of Instrument and Control Engineers of Japan (SICE).

[19]  S. Kakade,et al.  Information-Theoretic Regret Bounds for Gaussian Process Optimization in the Bandit Setting , 2012, IEEE Transactions on Information Theory.

[20]  Sandra Hirche,et al.  Computationally Efficient Rigid-Body Gaussian Process for Motion Dynamics , 2017, IEEE Robotics and Automation Letters.

[21]  Peter Corke,et al.  Autonomous aerial navigation and tracking of marine animals , 2011, ICRA 2011.

[22]  Mamoru Minami,et al.  Dual-eyes Vision-based Docking System for Autonomous Underwater Vehicle: an Approach and Experiments , 2018, J. Intell. Robotic Syst..

[23]  Andreas Krause,et al.  Safe learning of regions of attraction for uncertain, nonlinear systems with Gaussian processes , 2016, 2016 IEEE 55th Conference on Decision and Control (CDC).