Parametrization of robotic deburring process with motor skills from motion primitives of human skill model

In this paper, a new method for learning robotic debarring process motor skills from human skill model is presented. The skill of a human expert is obtained by using the human skill model. This model is implemented in robot control systems that make robots imitate human skills in deburring process tasks. Based on deburring process, family of basic pattern motions are listed by identifying the movement in the task (e.g. circular, straight line and sharp corners). These motions depend on a number of complex parameters; therefore, it is hard to fit a completely mathematical model to the process. By inspecting the movements of the human expert in task and analyzing these movements, the dynamic movement primitives are examined using an ordinary differential equation. In this paper, the standard method of Dynamic Movement Primitives (DMP) that would help extracting the trajectory for human interaction behaviors without using its explicit model, is modified to extract human expertise to provide a more accurate approximation of the robotic deburring process tasks. The experiments are conducted on haptic device, in which the robotic deburring processes on workpiece are imitated and the results are used as primitives to accomplish automatic deburring on the workpiece.

[1]  Homayoon Kazerooni,et al.  An Approach to Automated Deburring by Robot Manipulators , 1986 .

[2]  H. Harry Asada,et al.  Adaptive control of deburring robots based on human skill models , 1991, [1991] Proceedings of the 30th IEEE Conference on Decision and Control.

[3]  Maurice Clerc,et al.  The particle swarm - explosion, stability, and convergence in a multidimensional complex space , 2002, IEEE Trans. Evol. Comput..

[4]  Jean-Jacques E. Slotine,et al.  Motion Primitives for Robotic Flight Control , 2006, ArXiv.

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

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

[7]  Russell C. Eberhart,et al.  A new optimizer using particle swarm theory , 1995, MHS'95. Proceedings of the Sixth International Symposium on Micro Machine and Human Science.

[8]  Riccardo Poli,et al.  Particle swarm optimization , 1995, Swarm Intelligence.

[9]  E. Ilhan Konukseven,et al.  New parameter estimation method of linear adaptive filter for modeling kinematic motion primitive of effective DOF of hand , 2015, 2015 IEEE Conference on Control Applications (CCA).

[10]  Dagmar Sternad,et al.  Dynamic primitives of motor behavior , 2012, Biological Cybernetics.