Real Time Movement Classification in Versatile CPG Control

Abstract : Everyday human tasks are composed of a succession of discrete and rhythmic movements. If we want robots to be able to interact appropriately , it appears paramount for them to be able to perform both types of movements too. Though Central Pattern Generators (CPGs) are usually employed for rhythmic movement generation, they are also able of producing discrete movements. In this paper , we present a classification method to distinguish rhythmic and discrete movements so that the CPG can switch from one mode to the other. Moreover, we introduce several new plasticity rules more suitable for discrete movements.
Document type :
Conference papers
Complete list of metadatas

Cited literature [16 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-02291647
Contributor : Melanie Jouaiti <>
Submitted on : Thursday, September 19, 2019 - 9:57:07 AM
Last modification on : Thursday, January 16, 2020 - 1:22:13 AM

File

RAINR-2.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02291647, version 1

Citation

Melanie Jouaiti, Patrick Henaff. Real Time Movement Classification in Versatile CPG Control. Workshop on Robust Artificial Intelligence for Neurorobotics, Aug 2019, Edinburgh, United Kingdom. ⟨hal-02291647⟩

Share

Metrics

Record views

20

Files downloads

20