Dynamical System Modulation for Robot Learning via Kinesthetic Demonstrations

Authors:
M. Hersch;F. Guenter;S. Calinon;A. Billard
Affiliations:
Learning Algorithms & Syst. Lab., Ecole Polytech. Fed. de Lausanne, Lausanne;-;-;-
Venue:
IEEE Transactions on Robotics
Year:
2008

Citing 0
Cited 16

On-line learning and modulation of periodic movements with nonlinear dynamical systems

Autonomous Robots
Learning to search: Functional gradient techniques for imitation learning

Autonomous Robots
Kinesthetic bootstrapping: teaching motor skills to humanoid robots through physical interaction

KI'09 Proceedings of the 32nd annual German conference on Advances in artificial intelligence
Task-specific generalization of discrete and periodic dynamic movement primitives

IEEE Transactions on Robotics
Learning Non-linear Multivariate Dynamics of Motion in Robotic Manipulators

International Journal of Robotics Research
Learning from failure: extended abstract

Proceedings of the 6th international conference on Human-robot interaction
End-user programming of a social robot by dialog

Robotics and Autonomous Systems
Trajectories and keyframes for kinesthetic teaching: a human-robot interaction perspective

HRI '12 Proceedings of the seventh annual ACM/IEEE international conference on Human-Robot Interaction
Improving biped walk stability with complementary corrective demonstration

Autonomous Robots
Learning to pour with a robot arm combining goal and shape learning for dynamic movement primitives

Robotics and Autonomous Systems
On-line motion synthesis and adaptation using a trajectory database

Robotics and Autonomous Systems
A study on the use of tactile instructions for developing robot's motions

Artificial Life and Robotics
Compliant skills acquisition and multi-optima policy search with EM-based reinforcement learning

Robotics and Autonomous Systems
iProgram: intuitive programming of an industrial hri cell

Proceedings of the 8th ACM/IEEE international conference on Human-robot interaction
Motion planning and reactive control on learnt skill manifolds

International Journal of Robotics Research
Teaching robots to cooperate with humans in dynamic manipulation tasks based on multi-modal human-in-the-loop approach

Autonomous Robots

Quantified Score

Hi-index	0.00

Visualization

Abstract

We present a system for robust robot skill acquisition from kinesthetic demonstrations. This system allows a robot to learn a simple goal-directed gesture and correctly reproduce it despite changes in the initial conditions and perturbations in the environment. It combines a dynamical system control approach with tools of statistical learning theory and provides a solution to the inverse kinematics problem when dealing with a redundant manipulator. The system is validated on two experiments involving a humanoid robot: putting an object into a box and reaching for and grasping an object.