Imitation learning of Globally Stable Non-Linear Point-to-Point Robot Motions using Nonlinear Programming

This paper presents a method to learn arbitrary discrete motions from a set of demonstrations. We model a motion as a nonlinear autonomous (i.e. time-invariant) dynamical system, and define the sufficient conditions to make such a system globally asymptotically stable at the target. The convergence of all trajectories is ensured starting from any point in the operational space. Estimation of the model's parameters is done through non-linear programming by formulating the problem as an optimization under non-linear constraints. Being time-invariant and globally stable, the system is able to handle both temporal and spatial perturbations, while performing the motion as close to the demonstrations as possible. The method is evaluated through a set of robotic experiments.


Published in:
Proceeding of the 2010 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
Presented at:
the 2010 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Taipei, Taiwan, 18-22 October, 2010
Year:
2010
Publisher:
Ieee Service Center, 445 Hoes Lane, Po Box 1331, Piscataway, Nj 08855-1331 Usa
Keywords:
Laboratories:




 Record created 2010-06-14, last modified 2018-03-17

n/a:
Download fulltext
PDF

Rate this document:

Rate this document:
1
2
3
 
(Not yet reviewed)