An Improved LWR Based Forcing Term Learning from DMPs

Nowadays, endowing robots with the capability to learn is an important goal for the robotics research community. An important part of this research is learning skills. Dynamic movement primitives (DMPs) is a very powerful model to conduct learning from demonstration for robot. In this paper, we have made a great improvement on Local weighted Regression(LWR) which is an original regression technique in DMPs. Specifically, we change the phase from integrating into time average and give an logistic function to make sure the final forcing term to be zero. Then, we can make better use of min-jerk criterion demonstrate the effect and efficient.

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

[2]  Jun Nakanishi,et al.  Movement imitation with nonlinear dynamical systems in humanoid robots , 2002, Proceedings 2002 IEEE International Conference on Robotics and Automation (Cat. No.02CH37292).

[3]  Olivier Sigaud,et al.  Non-linear regression algorithms for motor skill acquisition: a comparison , 2014 .

[4]  G. Chavent.  Identification of Distributed Parameter Systems: About the Output Least Square Method, its Implementation, and Identifiability , 1979 .

[5]  Stefan Schaal,et al.  http://www.jstor.org/about/terms.html. JSTOR's Terms and Conditions of Use provides, in part, that unless you have obtained , 2007 .

[6]  Henk Nijmeijer,et al.  Robot Programming by Demonstration , 2010, SIMPAR.

[7]  P. Verhulst.  Notice sur la loi que la population pursuit dans son accroissement , 1838 .

[8]  Stefan Schaal,et al.  Biologically-inspired dynamical systems for movement generation: Automatic real-time goal adaptation and obstacle avoidance , 2009, 2009 IEEE International Conference on Robotics and Automation.

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

[10]  Aude Billard,et al.  Incremental learning of gestures by imitation in a humanoid robot , 2007, 2007 2nd ACM/IEEE International Conference on Human-Robot Interaction (HRI).