Robot Learning System Based on Adaptive Neural Control and Dynamic Movement Primitives

This paper proposes an enhanced robot skill learning system considering both motion generation and trajectory tracking. During robot learning demonstrations, dynamic movement primitives (DMPs) are used to model robotic motion. Each DMP consists of a set of dynamic systems that enhances the stability of the generated motion toward the goal. A Gaussian mixture model and Gaussian mixture regression are integrated to improve the learning performance of the DMP, such that more features of the skill can be extracted from multiple demonstrations. The motion generated from the learned model can be scaled in space and time. Besides, a neural-network-based controller is designed for the robot to track the trajectories generated from the motion model. In this controller, a radial basis function neural network is used to compensate for the effect caused by the dynamic environments. The experiments have been performed using a Baxter robot and the results have confirmed the validity of the proposed methods.

[1]  Long Cheng,et al.  Integrated Design of Machine Body and Control Algorithm for Improving the Robustness of a Closed-Chain Five-Bar Machine , 2012, IEEE/ASME Transactions on Mechatronics.

[2]  Jun Nakanishi,et al.  Dynamical Movement Primitives: Learning Attractor Models for Motor Behaviors , 2013, Neural Computation.

[3]  Oliver Kroemer,et al.  Learning to select and generalize striking movements in robot table tennis , 2012, AAAI Fall Symposium: Robots Learning Interactively from Human Teachers.

[4]  Nikolaos G. Tsagarakis,et al.  Statistical dynamical systems for skills acquisition in humanoids , 2012, 2012 12th IEEE-RAS International Conference on Humanoid Robots (Humanoids 2012).

[5]  Pieter Abbeel,et al.  Learning for control from multiple demonstrations , 2008, ICML '08.

[6]  Andrew W. Moore,et al.  Locally Weighted Learning for Control , 1997, Artificial Intelligence Review.

[7]  Stefan Schaal,et al.  Robot Programming by Demonstration , 2009, Springer Handbook of Robotics.

[8]  Stefan Schaal,et al.  Incremental Online Learning in High Dimensions , 2005, Neural Computation.

[9]  Chun-Yi Su,et al.  Neural Control of Bimanual Robots With Guaranteed Global Stability and Motion Precision , 2017, IEEE Transactions on Industrial Informatics.

[10]  Minija Tamosiunaite,et al.  Joining Movement Sequences: Modified Dynamic Movement Primitives for Robotics Applications Exemplified on Handwriting , 2012, IEEE Transactions on Robotics.

[11]  Aude Billard,et al.  Learning Stable Nonlinear Dynamical Systems With Gaussian Mixture Models , 2011, IEEE Transactions on Robotics.

[12]  J. MacQueen.  Some methods for classification and analysis of multivariate observations , 1967 .

[13]  Shaocheng Tong,et al.  Adaptive Neural Output Feedback Controller Design With Reduced-Order Observer for a Class of Uncertain Nonlinear SISO Systems , 2011, IEEE Transactions on Neural Networks.

[14]  Yanan Li,et al.  Haptic Identification by ELM-Controlled Uncertain Manipulator , 2017, IEEE Transactions on Systems, Man, and Cybernetics: Systems.

[15]  H. Sung.  Gaussian Mixture Regression and Classification , 2004 .

[16]  Aude Billard,et al.  Statistical Learning by Imitation of Competing Constraints in Joint Space and Task Space , 2009, Adv. Robotics.

[17]  Aude Billard,et al.  On Learning, Representing, and Generalizing a Task in a Humanoid Robot , 2007, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[18]  Sylvain Calinon,et al.  Robot Learning with Task-Parameterized Generative Models , 2015, ISRR.

[19]  Stefan Schaal,et al.  Learning and generalization of motor skills by learning from demonstration , 2009, 2009 IEEE International Conference on Robotics and Automation.

[20]  Stefan Schaal,et al.  Is imitation learning the route to humanoid robots? , 1999, Trends in Cognitive Sciences.

[21]  D. Rubin,et al.  Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .

[22]  Alin Albu-Schäffer,et al.  Human-Like Adaptation of Force and Impedance in Stable and Unstable Interactions , 2011, IEEE Transactions on Robotics.

[23]  Qijun Chen,et al.  Learning nonlinear dynamical system for movement primitives , 2014, 2014 IEEE International Conference on Systems, Man, and Cybernetics (SMC).

[24]  Chenguang Yang,et al.  Neural-Learning-Based Telerobot Control With Guaranteed Performance , 2017, IEEE Transactions on Cybernetics.

[25]  Herbert Jaeger,et al.  Reservoir computing approaches to recurrent neural network training , 2009, Comput. Sci. Rev..

[26]  Stefan Schaal,et al.  Reinforcement Learning With Sequences of Motion Primitives for Robust Manipulation , 2012, IEEE Transactions on Robotics.

[27]  Zhaoyong Mao,et al.  Structure Optimization of a Vibration Suppression Device for Underwater Moored Platforms Using CFD and Neural Network , 2017, Complex..

[28]  Carme Torras,et al.  A robot learning from demonstration framework to perform force-based manipulation tasks , 2013, Intelligent Service Robotics.

[29]  Jean-Jacques E. Slotine,et al.  Adaptive manipulator control: A case study , 1988 .

[30]  Yue Zhao,et al.  Generating a Style-Adaptive Trajectory from Multiple Demonstrations , 2014 .

[31]  Chao Xu,et al.  Fast and Stable Learning of Dynamical Systems Based on Extreme Learning Machine , 2019, IEEE Transactions on Systems, Man, and Cybernetics: Systems.

[32]  Xingjian Wang,et al.  Teleoperation Control Based on Combination of Wave Variable and Neural Networks , 2017, IEEE Transactions on Systems, Man, and Cybernetics: Systems.