A Preliminary Study of Transfer Learning between Unicycle Robots

Methods from machine learning have successfully been used to improve the performance of control systems in cases when accurate models of the system or the environment are not available. These methods require the use of data generated from physical trials. Transfer Learning (TL) allows for this data to come from a different, similar system. The goal of this work is to understand in which cases a simple, alignment-based transfer of data is beneficial. A scalar, linear, time invariant(LTI) transformation is applied to the output from a source system to align with the output from a target system. In a theoretic study, we have already shown that for linear, single-input, single-output systems, the upper bound of the transformation error depends on the dynamic properties of the source and target system, and is small for systems with similar response times. We now consider two nonlinear, unicycle robots. Based on our previous work, we derive analytic error bounds for the linearized robot models. We then provide simulations of the nonlinear robot models and experiments with a Pioneer 3-AT robot that confirm the theoretical findings. As a result, key characteristics of alignment based transfer learning observed in our theoretic study prove to be also true for real, nonlinear unicycle robots.

[1]  Bruce A. Francis,et al.  Feedback Control Theory , 1992 .

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

[3]  Peter Stone,et al.  Transfer Learning for Reinforcement Learning Domains: A Survey , 2009, J. Mach. Learn. Res..

[4]  Goele Pipeleers,et al.  Initialization of ILC based on a previously learned trajectory , 2012, 2012 American Control Conference (ACC).

[5]  Jan Peters,et al.  Alignment-based transfer learning for robot models , 2013, The 2013 International Joint Conference on Neural Networks (IJCNN).

[6]  Raffaello D'Andrea,et al.  Optimization-based iterative learning for precise quadrocopter trajectory tracking , 2012, Autonomous Robots.

[7]  Angela P. Schoellig,et al.  Safe and robust learning control with Gaussian processes , 2015, 2015 European Control Conference (ECC).

[8]  Daniel D. Lee,et al.  Semisupervised alignment of manifolds , 2005, AISTATS.

[9]  Xiaoping Yun,et al.  On Feedback Linearization of Mobile Robots , 1992 .

[10]  Bruce A. Francis,et al.  An upper bound on the error of alignment-based Transfer Learning between two linear, time-invariant, scalar systems , 2015, 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[11]  Raffaello D'Andrea,et al.  Knowledge transfer for high-performance quadrocopter maneuvers , 2013, 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[12]  Chang Wang,et al.  A General Framework for Manifold Alignment , 2009, AAAI Fall Symposium: Manifold Learning and Its Applications.

[13]  Ioannis P. Vlahavas,et al.  Transfer Learning in Multi-Agent Reinforcement Learning Domains , 2011, EWRL.

[14]  Balaraman Ravindran,et al.  Transfer learning across heterogeneous robots with action sequence mapping , 2010, 2010 IEEE/RSJ International Conference on Intelligent Robots and Systems.

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

[16]  Sridhar Mahadevan,et al.  Manifold alignment using Procrustes analysis , 2008, ICML '08.

[17]  Moritz Tenorth,et al.  The RoboEarth language: Representing and exchanging knowledge about actions, objects, and environments , 2012, 2012 IEEE International Conference on Robotics and Automation.

[18]  Javier Alonso-Mora,et al.  Limited benefit of joint estimation in multi‐agent iterative learning , 2012 .

[19]  Jonathan P. How,et al.  Rapid transfer of controllers between UAVs using learning-based adaptive control , 2013, 2013 IEEE International Conference on Robotics and Automation.

[20]  Gerhard Weiss,et al.  Multiagent Learning: Basics, Challenges, and Prospects , 2012, AI Mag..

[21]  Andrew G. Barto,et al.  Transfer in Reinforcement Learning via Shared Features , 2012, J. Mach. Learn. Res..

[22]  Angela P. Schoellig,et al.  Learning-based nonlinear model predictive control to improve vision-based mobile robot path-tracking in challenging outdoor environments , 2014, 2014 IEEE International Conference on Robotics and Automation (ICRA).

[23]  Hikaru Inooka,et al.  Incorporation of experience in iterative learning controllers using locally weighted learning , 2001, Autom..

[24]  Dieter Fox Distributed Multi-Robot Exploration and Mapping , 2005, CRV.