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

Authors:
Heni Ben Amor;Erik Berger;David Vogt;Bernhard Jung
Affiliations:
VR and Multimedia Group, TU Bergakademie Freiberg, Freiberg, Germany;VR and Multimedia Group, TU Bergakademie Freiberg, Freiberg, Germany;VR and Multimedia Group, TU Bergakademie Freiberg, Freiberg, Germany;VR and Multimedia Group, TU Bergakademie Freiberg, Freiberg, Germany
Venue:
KI'09 Proceedings of the 32nd annual German conference on Advances in artificial intelligence
Year:
2009

Citing 6
Cited 4

curlybot: designing a new class of computational toys

Proceedings of the SIGCHI conference on Human Factors in Computing Systems
The correspondence problem

Imitation in animals and artifacts
From turtles to Tangible Programming Bricks: explorations in physical language design

Personal and Ubiquitous Computing
Learning to walk through imitation

IJCAI'07 Proceedings of the 20th international joint conference on Artifical intelligence
Dynamical System Modulation for Robot Learning via Kinesthetic Demonstrations

IEEE Transactions on Robotics
Codevelopmental Learning Between Human and Humanoid Robot Using a Dynamic Neural-Network Model

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics

Usability of force-based controllers in physical human-robot interaction

Proceedings of the 6th international conference on Human-robot interaction
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
Probabilistic model-based imitation learning

Adaptive Behavior - Animals, Animats, Software Agents, Robots, Adaptive Systems
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

Programming of complex motor skills for humanoid robots can be a time intensive task, particularly within conventional textual or GUI-driven programming paradigms. Addressing this drawback, we propose a new programming-by-demonstration method called Kinesthetic Bootstrapping for teaching motor skills to humanoid robots by means of intuitive physical interactions. Here, "programming" simply consists of manually moving the robot's joints so as to demonstrate the skill in mind. The bootstrapping algorithm then generates a low-dimensional model of the demonstrated postures.To find a trajectory through this posture space that corresponds to a robust robot motion, a learning phase takes place in a physics-based virtual environment. The virtual robot's motion is optimized via a genetic algorithm and the result is transferred back to the physical robot. The method has been successfully applied to the learning of various complex motor skills such as walking and standing up.