Open AccessBook
Robot Programming by Demonstration
Sylvain Calinon
- 24 Aug 2009
1K
TL;DR: Programming by demonstration (PbD) as discussed by the authors is a technique for teaching new skills to a robot by imitation, tutelage, or apprenticeship learning through human guidance.
read more
Abstract: Also referred to as learning by imitation, tutelage, or apprenticeship learning, Programming by Demonstration (PbD) develops methods by which new skills can be transmitted to a robot. This book examines methods by which robots learn new skills through human guidance. Taking a practical perspective, it covers a broad range of applications, including service robots. The text addresses the challenges involved in investigating methods by which PbD is used to provide robots with a generic and adaptive model of control. Drawing on findings from robot control, human-robot interaction, applied machine learning, artificial intelligence, and developmental and cognitive psychology, the book contains a large set of didactic and illustrative examples. Practical and comprehensive machine learning source codes are available on the books companion website: http://www.programming-by-demonstration.org
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Motion Adaptation Based on Learning the Manifold of Task and Dynamic Movement Primitive Parameters
TL;DR: A methodology for learning the manifold of task and DMP parameters is suggested, which facilitates runtime adaptation to changes in task requirements while ensuring predictable and robust performance.
Fast trajectory replanning using Laplacian mesh optimization
Thomas Nierhoff,Sandra Hirche +1 more
- 01 Dec 2012
TL;DR: A framework that can alter the shape of a trajectory by defining the position of a set of sampling points while maintaining local properties in a least-squares manner is presented, inspired by mesh processing used for 3D surface editing.
Trajectory Generation With Spatio-Temporal Templates Learned From Demonstrations
Xiaochuan Yin,Qijun Chen +1 more
TL;DR: A novel trajectory generation method based on spatio-temporal templates that is verified through synthetic trajectories and using the Pioneer-3AT wheeled mobile robot platform.
11
Online quantum mixture regression for trajectory learning by demonstration
Dimitrios Korkinof,Yiannis Demiris +1 more
- 01 Nov 2013
TL;DR: This work proposes an efficient stochastic online learning algorithm based on the online Expectation Maximization (EM), as well as a generation and decay scheme for model components, which is suitable for complex robotic applications.
•Proceedings Article
Extracting Semantic Rules from Human Observations
Karinne Ramirez-Amaro,Michael Beetz,Gordon Cheng +2 more
- 01 Jan 2013
TL;DR: A new methodology is presented that account for the extraction of observed human behaviors with an estimation of the intended activities, follow by the automatic generation of action rules for the synthesis of robot behaviors and the enhancement of the semantic representation with the reasoning system.
11
References
Neurophysiological mechanisms underlying the understanding and imitation of action.
TL;DR: Evidence for the existence of a system, the 'mirror system', that seems to serve this mapping function in primates and humans is discussed, and its implications for the understanding and imitation of action are explored.
3.4K
Cortical Mechanisms of Human Imitation
Marco Iacoboni,Roger P. Woods,Marcel Brass,Harold Bekkering,John C. Mazziotta,Giacomo Rizzolatti +5 more
TL;DR: Two areas with activation properties that become active during finger movement, regardless of how it is evoked, and their activation should increase when the same movement is elicited by the observation of an identical movement made by another individual are found.
Multiple paired forward and inverse models for motor control
Daniel M. Wolpert,Mitsuo Kawato +1 more
TL;DR: A modular approach to motor learning and control based on multiple pairs of inverse (controller) and forward (predictor) models that can simultaneously learn the multiple inverse models necessary for control as well as how to select the inverse models appropriate for a given environment is proposed.
2.3K
Is imitation learning the route to humanoid robots
TL;DR: In this article, a review of recent developments in artificial intelligence and neural computation: learning from imitation and the development of humanoid robots is presented. But the authors focus on three important issues: efficient motor learning, the connection between action and perception, and modular motor control in the form of movement primitives.
1.5K