Towards Progressive Automation of Repetitive Tasks Through Physical Human-Robot Interaction

In this paper, a novel method is developed that enables quick and easy programming in repetitive industrial tasks, through kinesthetic demonstration from the operator. The robot learns the task cycle with the assistance of haptic cues and progressively transitions from manual into autonomous operation using a novel variable stiffness control strategy and assistive virtual fixtures. The training process, requires a small amount of iterations, decreasing dramatically the typical robotic programming time. In the experimental evaluation, an operator is able to program a pick and place task in less than a minute, without requiring any interaction with a user interface or pre-programming of the task sequence.

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

[2]  Christopher G. Atkeson,et al.  Constructive Incremental Learning from Only Local Information , 1998, Neural Computation.

[3]  Gordon Cheng,et al.  Robotic technologies for fast deployment of industrial robot systems , 2016, IECON 2016 - 42nd Annual Conference of the IEEE Industrial Electronics Society.

[4]  Dongheui Lee,et al.  Incremental kinesthetic teaching of motion primitives using the motion refinement tube , 2011, Auton. Robots.

[5]  Philippe Gaussier,et al.  On-line learning and planning in a pick-and-place task demonstrated through body manipulation , 2011, 2011 IEEE International Conference on Development and Learning (ICDL).

[6]  John Norrish,et al.  Recent Progress on Programming Methods for Industrial Robots , 2010, ISR/ROBOTIK.

[7]  Aude Billard,et al.  Learning from Humans , 2016, Springer Handbook of Robotics, 2nd Ed..

[8]  Rainer Palm,et al.  Programming by Demonstration of Pick-and-Place Tasks for Industrial Manipulators using Task Primitives , 2007, 2007 International Symposium on Computational Intelligence in Robotics and Automation.

[9]  Alberto Montebelli,et al.  Simultaneous kinesthetic teaching of positional and force requirements for sequential in-contact tasks , 2015, 2015 IEEE-RAS 15th International Conference on Humanoid Robots (Humanoids).

[10]  Sandra Hirche,et al.  An experience-driven robotic assistant acquiring human knowledge to improve haptic cooperation , 2011, 2011 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[11]  Dominik Henrich,et al.  One-shot robot programming by demonstration using an online oriented particles simulation , 2014, 2014 IEEE International Conference on Robotics and Biomimetics (ROBIO 2014).

[12]  Jörg Krüger,et al.  Spatial Programming for Industrial Robots through Task Demonstration , 2013 .

[13]  François Keith,et al.  Proactive behavior of a humanoid robot in a haptic transportation task with a human partner , 2012, 2012 IEEE RO-MAN: The 21st IEEE International Symposium on Robot and Human Interactive Communication.

[14]  Matteo Saveriano,et al.  Incremental kinesthetic teaching of end-effector and null-space motion primitives , 2015, 2015 IEEE International Conference on Robotics and Automation (ICRA).

[15]  Dimitrios Papageorgiou,et al.  Robot Control for Task Performance and Enhanced Safety under Impact , 2015, Front. Robot. AI.

[16]  Nikos A. Aspragathos,et al.  Online Stability in Human-Robot Cooperation with Admittance Control , 2016, IEEE Transactions on Haptics.

[17]  Paul Evrard,et al.  Homotopy-based controller for physical human-robot interaction , 2009, RO-MAN 2009 - The 18th IEEE International Symposium on Robot and Human Interactive Communication.

[18]  Ole Madsen,et al.  Human-robot interface for instructing industrial tasks using kinesthetic teaching , 2013, IEEE ISR 2013.

[19]  Keng Peng Tee,et al.  Continuous Role Adaptation for Human–Robot Shared Control , 2015, IEEE Transactions on Robotics.

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

[21]  Etienne Burdet,et al.  Slaves no longer: review on role assignment for human–robot joint motor action , 2014, Adapt. Behav..

[22]  Cagatay Basdogan,et al.  Intention Recognition for Dynamic Role Exchange in Haptic Collaboration , 2013, IEEE Transactions on Haptics.

[23]  Maya Cakmak,et al.  Trajectories and keyframes for kinesthetic teaching: A human-robot interaction perspective , 2012, 2012 7th ACM/IEEE International Conference on Human-Robot Interaction (HRI).

[24]  Andrea Lockerd Thomaz,et al.  Directing Policy Search with Interactively Taught Via-Points , 2016, AAMAS.

[25]  Alberto Montebelli,et al.  Incrementally assisted kinesthetic teaching for programming by demonstration , 2016, 2016 11th ACM/IEEE International Conference on Human-Robot Interaction (HRI).

[26]  Bruno Siciliano,et al.  Variable Impedance Control of Redundant Manipulators for Intuitive Human–Robot Physical Interaction , 2015, IEEE Transactions on Robotics.