Humanoid learns to detect its own hands

Jürgen Leitner; Simon Harding; Mikhail Frank; Alexander Förster; Jürgen Schmidhuber

doi:10.1109/CEC.2013.6557729

Humanoid learns to detect its own hands

Jürgen Leitner, Simon Harding, Mikhail Frank, Alexander Förster, Jürgen Schmidhuber

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-review

12 Citations (Scopus)

Abstract

Robust object manipulation is still a hard problem in robotics, even more so in high degree-of-freedom (DOF) humanoid robots. To improve performance a closer integration of visual and motor systems is needed. We herein present a novel method for a robot to learn robust detection of its own hands and fingers enabling sensorimotor coordination. It does so solely using its own camera images and does not require any external systems or markers. Our system based on Cartesian Genetic Programming (CGP) allows to evolve programs to perform this image segmentation task in real-time on the real hardware. We show results for a Nao and an iCub humanoid each detecting its own hands and fingers.

Original language	English
Title of host publication	2013 IEEE Congress on Evolutionary Computation, CEC 2013
Publisher	IEEE, Institute of Electrical and Electronics Engineers
Pages	1411-1418
Number of pages	8
ISBN (Print)	9781479904549
DOIs	https://doi.org/10.1109/CEC.2013.6557729
Publication status	Published - 2013
Externally published	Yes
Event	IEEE Congress on Evolutionary Computation 2013 - Cancun, Mexico Duration: 20 Jun 2013 → 23 Jun 2013 https://ieeexplore.ieee.org/xpl/conhome/6552460/proceeding (Proceedings)

Conference

Conference	IEEE Congress on Evolutionary Computation 2013
Abbreviated title	IEEE CEC 2013
Country/Territory	Mexico
City	Cancun
Period	20/06/13 → 23/06/13
Internet address	https://ieeexplore.ieee.org/xpl/conhome/6552460/proceeding (Proceedings)

Access to Document

10.1109/CEC.2013.6557729

Cite this

@inproceedings{839e1942a79344bab5bd52ec75d62a36,

title = "Humanoid learns to detect its own hands",

abstract = "Robust object manipulation is still a hard problem in robotics, even more so in high degree-of-freedom (DOF) humanoid robots. To improve performance a closer integration of visual and motor systems is needed. We herein present a novel method for a robot to learn robust detection of its own hands and fingers enabling sensorimotor coordination. It does so solely using its own camera images and does not require any external systems or markers. Our system based on Cartesian Genetic Programming (CGP) allows to evolve programs to perform this image segmentation task in real-time on the real hardware. We show results for a Nao and an iCub humanoid each detecting its own hands and fingers.",

author = "J{\"u}rgen Leitner and Simon Harding and Mikhail Frank and Alexander F{\"o}rster and J{\"u}rgen Schmidhuber",

year = "2013",

doi = "10.1109/CEC.2013.6557729",

language = "English",

isbn = "9781479904549",

pages = "1411--1418",

booktitle = "2013 IEEE Congress on Evolutionary Computation, CEC 2013",

publisher = "IEEE, Institute of Electrical and Electronics Engineers",

address = "United States of America",

note = "IEEE Congress on Evolutionary Computation 2013, IEEE CEC 2013 ; Conference date: 20-06-2013 Through 23-06-2013",

url = "https://ieeexplore.ieee.org/xpl/conhome/6552460/proceeding",

}

TY - GEN

T1 - Humanoid learns to detect its own hands

AU - Leitner, Jürgen

AU - Harding, Simon

AU - Frank, Mikhail

AU - Förster, Alexander

AU - Schmidhuber, Jürgen

PY - 2013

Y1 - 2013

N2 - Robust object manipulation is still a hard problem in robotics, even more so in high degree-of-freedom (DOF) humanoid robots. To improve performance a closer integration of visual and motor systems is needed. We herein present a novel method for a robot to learn robust detection of its own hands and fingers enabling sensorimotor coordination. It does so solely using its own camera images and does not require any external systems or markers. Our system based on Cartesian Genetic Programming (CGP) allows to evolve programs to perform this image segmentation task in real-time on the real hardware. We show results for a Nao and an iCub humanoid each detecting its own hands and fingers.

AB - Robust object manipulation is still a hard problem in robotics, even more so in high degree-of-freedom (DOF) humanoid robots. To improve performance a closer integration of visual and motor systems is needed. We herein present a novel method for a robot to learn robust detection of its own hands and fingers enabling sensorimotor coordination. It does so solely using its own camera images and does not require any external systems or markers. Our system based on Cartesian Genetic Programming (CGP) allows to evolve programs to perform this image segmentation task in real-time on the real hardware. We show results for a Nao and an iCub humanoid each detecting its own hands and fingers.

UR - http://www.scopus.com/inward/record.url?scp=84881574097&partnerID=8YFLogxK

U2 - 10.1109/CEC.2013.6557729

DO - 10.1109/CEC.2013.6557729

M3 - Conference Paper

AN - SCOPUS:84881574097

SN - 9781479904549

SP - 1411

EP - 1418

BT - 2013 IEEE Congress on Evolutionary Computation, CEC 2013

PB - IEEE, Institute of Electrical and Electronics Engineers

T2 - IEEE Congress on Evolutionary Computation 2013

Y2 - 20 June 2013 through 23 June 2013

ER -

Humanoid learns to detect its own hands

Abstract

Conference

Access to Document

Other files and links

Cite this