Iterative Learning Procedure With Reinforcement for High-Accuracy Force Tracking in Robotized Tasks

The paper focuses on industrial interaction robotics tasks, investigating a control approach involving multiples learning levels for training the manipulator to execute a repetitive (partially) changeable task, accurately controlling the interaction. Based on compliance control, the proposed approach consists of two main control levels: 1) iterative friction learning compensation controller with reinforcement and 2) iterative force-tracking learning controller with reinforcement. The learning algorithms rely on the iterative learning and reinforcement learning procedures to automatize the controllers parameters tuning. The proposed procedure has been applied to an automotive industrial assembly task. A standard industrial UR 10 Universal Robot has been used, equipped by a compliant pneumatic gripper and a force/torque sensor at the robot end-effector.

[1]  Stefan Schaal,et al.  Learning variable impedance control , 2011, Int. J. Robotics Res..

[2]  Nicola Morelli,et al.  Design in new industrial contexts: shifting design paradigms and methodologies , 2005 .

[3]  Jang-Myung Lee,et al.  Robust adaptive deadzone and friction compensation of robot manipulator using RWCMAC network , 2011 .

[4]  Kuu-young Young,et al.  Reinforcement Learning and Robust Control for Robot Compliance Tasks , 1998, J. Intell. Robotic Syst..

[5]  Shuzhi Sam Ge,et al.  Impedance Learning for Robots Interacting With Unknown Environments , 2014, IEEE Transactions on Control Systems Technology.

[6]  J. De Schutter,et al.  Dynamic Model Identification for Industrial Robots , 2007, IEEE Control Systems.

[7]  H. B. Barlow,et al.  Unsupervised Learning , 1989, Neural Computation.

[8]  Lorenzo Molinari Tosatti,et al.  Exploiting impedance shaping approaches to overcome force overshoots in delicate interaction tasks , 2016 .

[9]  Ismael Lopez-Juarez,et al.  On-line incremental learning for unknown conditions during assembly operations with industrial robots , 2015, Evol. Syst..

[10]  Anders Robertsson,et al.  Robotic assembly of emergency stop buttons , 2013, 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[11]  Terrence J. Sejnowski,et al.  Unsupervised Learning , 2018, Encyclopedia of GIS.

[12]  Carlos E. Ventura,et al.  Damping estimation by frequency domain decomposition , 2001 .

[13]  Antonio Visioli,et al.  On the trajectory tracking control of industrial SCARA robot manipulators , 2002, IEEE Trans. Ind. Electron..

[14]  Nolan Wagener,et al.  Learning contact-rich manipulation skills with guided policy search , 2015, 2015 IEEE International Conference on Robotics and Automation (ICRA).

[15]  Francesco Braghin,et al.  Optimal Impedance Force-Tracking Control Design With Impact Formulation for Interaction Tasks , 2016, IEEE Robotics and Automation Letters.

[16]  Sotiris B. Kotsiantis,et al.  Supervised Machine Learning: A Review of Classification Techniques , 2007, Informatica.

[17]  Andrew W. Moore,et al.  Reinforcement Learning: A Survey , 1996, J. Artif. Intell. Res..

[18]  Changyin Sun,et al.  Adaptive Neural Impedance Control of a Robotic Manipulator With Input Saturation , 2016, IEEE Transactions on Systems, Man, and Cybernetics: Systems.

[19]  Francis J. Doyle,et al.  Survey on iterative learning control, repetitive control, and run-to-run control , 2009 .

[20]  Rong-Jong Wai,et al.  Design of Fuzzy-Neural-Network-Inherited Backstepping Control for Robot Manipulator Including Actuator Dynamics , 2014, IEEE Transactions on Fuzzy Systems.

[21]  Lorenzo Molinari Tosatti,et al.  Deformation-tracking impedance control in interaction with uncertain environments , 2013, 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[22]  Maolin Jin,et al.  Robust Compliant Motion Control of Robot With Nonlinear Friction Using Time-Delay Estimation , 2008, IEEE Transactions on Industrial Electronics.

[23]  Carme Torras,et al.  Learning Collaborative Impedance-Based Robot Behaviors , 2013, AAAI.

[24]  Carme Torras,et al.  Learning Physical Collaborative Robot Behaviors From Human Demonstrations , 2016, IEEE Transactions on Robotics.

[25]  Neville Hogan,et al.  Impedance Control: An Approach to Manipulation , 1984, 1984 American Control Conference.

[26]  Nathan van de Wouw,et al.  Friction compensation in a controlled one-link robot using a reduced-order observer , 2004 .

[27]  Jongwon Kim,et al.  Position-based impedance control for force tracking of a wall-cleaning unit , 2016 .

[28]  Neville Hogan,et al.  An analysis of contact instability in terms of passive physical equivalents , 1989, Proceedings, 1989 International Conference on Robotics and Automation.

[29]  Lorenzo Molinari Tosatti,et al.  On robot dynamic model identification through sub-workspace evolved trajectories for optimal torque estimation , 2013, 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[30]  Wisama Khalil,et al.  Identification of the dynamic parameters of a closed loop robot , 1995, Proceedings of 1995 IEEE International Conference on Robotics and Automation.

[31]  Ethem Alpaydin,et al.  Introduction to machine learning , 2004, Adaptive computation and machine learning.