External Force/Torque Estimation With Only Position Sensors for Antagonistic VSAs

Recent use scenarios involving human–robot collaboration have revealed that the robots require elastic joints to safely interact with humans. It is also critical to know applied force/torque (f/t) during the interaction for control and motion planning purposes. In this article, we estimate the external f/t values without using any sensors other than low-cost encoders by exploiting the inherent elastic properties of the joint. For estimation, the following two different approaches are used: model based and model free. In the model-based approach, an extended Kalman filter (EKF) and an external force observer (EFOB) are used considering the dynamical behavior of the system to estimate the interaction force. In the model-free approach, the artificial neural network (ANN) utilizes the data gathered from mechanical systems. In comparative analysis, we have, therefore, considered three different estimation methods, two of which are model based and the remaining one is model free (i.e., data driven). Implementing these estimation algorithms experimentally on a variable stiffness joint, we performed an extensive evaluation of their performances. All methods show similar level of performance in terms of the root-mean-square (RMS) error with 0.0847, 0.0841, and 0.1082 N for the EKF, EFOB, and ANN, respectively. Model-based methods do not require continuous data stream through the experimental set up. On the other hand, the ANN does not need an explicit model of the system; therefore, it may become preferable when the detailed model derivation is not possible.

[1]  Hong Z. Tan,et al.  HUMAN FACTORS FOR THE DESIGN OF FORCE-REFLECTING HAPTIC INTERFACES , 1994 .

[2]  Steven K. Rogers,et al.  Neural network payload estimation for adaptive robot control , 1991, IEEE Trans. Neural Networks.

[3]  Jörn Malzahn,et al.  Comparison of open-loop and closed-loop disturbance observers for series elastic actuators , 2016, 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[4]  D. Caleb Rucker,et al.  Deflection-based force sensing for continuum robots: A probabilistic approach , 2011, 2011 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[5]  Nabil Simaan,et al.  Kinematics-Based Detection and Localization of Contacts Along Multisegment Continuum Robots , 2012, IEEE Transactions on Robotics.

[6]  Oussama Khatib,et al.  Variable radius pulley design methodology for pneumatic artificial muscle-based antagonistic actuation systems , 2011, 2011 IEEE/RSJ International Conference on Intelligent Robots and Systems.

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

[8]  Kai Xu,et al.  An Investigation of the Intrinsic Force Sensing Capabilities of Continuum Robots , 2008, IEEE Transactions on Robotics.

[9]  Dieter Fox,et al.  SE3-nets: Learning rigid body motion using deep neural networks , 2016, 2017 IEEE International Conference on Robotics and Automation (ICRA).

[10]  Alessandro De Luca,et al.  A pure signal-based stiffness estimation for VSA devices , 2014, 2014 IEEE International Conference on Robotics and Automation (ICRA).

[11]  Keyvan Hashtrudi-Zaad,et al.  Neural-Network-Based Contact Force Observers for Haptic Applications , 2006, IEEE Transactions on Robotics.

[12]  Tatsuo Narikiyo,et al.  Proof of Concept for Robot-Aided Upper Limb Rehabilitation Using Disturbance Observers , 2015, IEEE Transactions on Human-Machine Systems.

[13]  N. Durlach,et al.  Manual discrimination of force using active finger motion , 1991, Perception & psychophysics.

[14]  Toshiyuki Murakami,et al.  Observer-based adaptive force control of multi-degrees-of-freedom manipulator , 1992, Proceedings of the 1992 International Conference on Industrial Electronics, Control, Instrumentation, and Automation.

[15]  Yuan Yu,et al.  TensorFlow: A system for large-scale machine learning , 2016, OSDI.

[16]  Zhiqiang Gao,et al.  A survey of state and disturbance observers for practitioners , 2006, 2006 American Control Conference.

[17]  J. L. Roux.  An Introduction to the Kalman Filter , 2003 .

[18]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[19]  Wenjie Wang,et al.  Toward force detection of a cable-driven micromanipulator for a surgical robot based on disturbance observer , 2017 .

[20]  Bertil Ekstrand,et al.  Some aspects on filter design for target tracking , 2012 .

[21]  Geoffrey E. Hinton,et al.  Rectified Linear Units Improve Restricted Boltzmann Machines , 2010, ICML.

[22]  Tatsuo Narikiyo,et al.  A framework for sensorless torque estimation and control in wearable exoskeletons , 2012, 2012 12th IEEE International Workshop on Advanced Motion Control (AMC).

[23]  L. A. Jones.  Matching Forces: Constant Errors and Differential Thresholds , 1989, Perception.

[24]  Kouhei Ohnishi,et al.  An Adaptive Reaction Force Observer Design , 2015, IEEE/ASME Transactions on Mechatronics.

[25]  P. Meckl,et al.  Intelligent feedforward control and payload estimation for a two-link robotic manipulator , 2003 .

[26]  Kiyoshi Ohishi,et al.  Robust position control using double disturbance observers based state feedback for two mass system , 2016, IECON 2016 - 42nd Annual Conference of the IEEE Industrial Electronics Society.

[27]  Matthew M. Williamson,et al.  Series elastic actuators , 1995, Proceedings 1995 IEEE/RSJ International Conference on Intelligent Robots and Systems. Human Robot Interaction and Cooperative Robots.

[28]  Ertugrul Bayraktar,et al.  Object manipulation with a variable-stiffness robotic mechanism using deep neural networks for visual semantics and load estimation , 2019, Neural Computing and Applications.

[29]  Akihiro Suzumura,et al.  On explicit implementation of multiple disturbance observers derived from three-degree-of-freedom control , 2016, 2016 IEEE 14th International Workshop on Advanced Motion Control (AMC).

[30]  Pinar Boyraz,et al.  Low-cost variable stiffness joint design using translational variable radius pulleys , 2018 .

[31]  Jeffrey K. Uhlmann,et al.  New extension of the Kalman filter to nonlinear systems , 1997, Defense, Security, and Sensing.

[32]  Richard D. Braatz,et al.  On the "Identification and control of dynamical systems using neural networks" , 1997, IEEE Trans. Neural Networks.

[33]  Wan Kyun Chung,et al.  External torque-sensing algorithm for flexible-joint robot based on Kalman filter , 2013 .

[34]  Arne Wahrburg,et al.  Contact force estimation for robotic assembly using motor torques , 2014, 2014 IEEE International Conference on Automation Science and Engineering (CASE).

[35]  Michael R. Zinn,et al.  A New Actuation Approach for Human Friendly Robot Design , 2004, Int. J. Robotics Res..

[36]  Stephen P. DeWeerth,et al.  Biologically Inspired Joint Stiffness Control , 2005, Proceedings of the 2005 IEEE International Conference on Robotics and Automation.

[37]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[38]  Giorgio Grioli,et al.  A real time robust observer for an Agonist-Antagonist Variable Stiffness Actuator , 2013, 2013 IEEE International Conference on Robotics and Automation.

[39]  James D. Yegerlehner,et al.  Experimental implementation of neural network controller for robot undergoing large payload changes , 1993, [1993] Proceedings IEEE International Conference on Robotics and Automation.

[40]  Takamasa Hori,et al.  Adaptive robust force control by disturbance observer , 1992, Proceedings of the 1992 International Conference on Industrial Electronics, Control, Instrumentation, and Automation.