Beating-Time Gestures Imitation Learning for Humanoid Robots

Journal Title: EAI Endorsed Transactions on Creative Technologies - Year 2017, Vol 4, Issue 13

Abstract

Beating-time gestures are movement patterns of the hand swaying along with music, thereby indicating accented musical pulses. The spatiotemporal configuration of these patterns makes it diÿcult to analyse and model them. In this paper we present an innovative modelling approach that is based upon imitation learning or Programming by Demonstration (PbD). Our approach - based on Dirichlet Process Mixture Models, Hidden Markov Models, Dynamic Time Warping, and non-uniform cubic spline regression - is particularly innovative as it handles spatial and temporal variability by the generation of a generalised trajectory from a set of periodically repeated movements. Although not within the scope of our study, our procedures may be implemented for the sake of controlling movement behaviour of robots and avatar animations in response to music.

Authors and Affiliations

Denis Amelynck, Pieter-Jan Maes, Jean-Pierre Martens, Marc Leman

Keywords

Related Articles

Varianish: Jamming with Pattern Repetition

In music, patterns and pattern repetition are often regarded as a machine-like task, indeed often delegated to drum Machines and sequencers. Nevertheless, human players add subtle differences and variations to repeated p...

CuriousMind photographer: distract the robot from its initial task

Mainly present in industry, robots begin to invade our every-day lives for very precise tasks. In order to reach a level where more general robots get involved in our lives, the robots' abilities to communicate and to re...

Facilitating Requirements Inspection with Search-Based Selection of Diverse Use Case Scenarios

Use case scenarios are often used for conducting requirements inspection and other relevant downstream activities. While working with industrial partners, we discovered that an automated solution is required for optimall...

Solitude or co-existence – or learning-together-apart with digital dialogic technologies for kids with developmental and attention difficulties

An overall political vision of a prosperous society is one in which everyone has the same access and possibilities of participating in democratic processes, and in which everyone has equal access to the resources, life a...

PaisleyTrees: A Size-Invariant Tree Visualization

Squeezing large tree structures into suitable visualizations has been a perennial problem. In response to this challenge, we present PaisleyTrees, a size-invariant tree visualization. PaisleyTrees integrate node-of-inter...

Download PDF file
  • EP ID EP45882
  • DOI http://dx.doi.org/10.4108/eai.8-11-2017.153335
  • Views 264
  • Downloads 0

How To Cite

Denis Amelynck, Pieter-Jan Maes, Jean-Pierre Martens, Marc Leman (2017). Beating-Time Gestures Imitation Learning for Humanoid Robots. EAI Endorsed Transactions on Creative Technologies, 4(13), -. https://europub.co.uk/articles/-A-45882