A Combination of Central Pattern Generator-based and Reflex-based Neural Networks for Dynamic, Adaptive, Robust Bipedal Locomotion

Giuliano Di Canio, Jørgen Christian Larsen, Florentin Wörgötter, Poramate Manoonpong

Publikation: Bidrag til bog/antologi/rapport/konference-proceedingKonferencebidrag i proceedingsForskningpeer review

Resumé

Robotic systems inspired from humans have always been lightening up the curiosity of engineers and scientists. Of many challenges, human locomotion is a very difficult one where a number of different systems needs to interact in order to generate a correct and balanced pattern. To simulate the interaction of these systems, implementations with reflexbased or central pattern generator (CPG)-based controllers have been tested on bipedal robot systems. In this paper we will combine the two controller types, into a controller that works with both reflex and CPG signals. We use a reflex-based neural network to generate basic walking patterns of a dynamic bipedal walking robot (DACBOT) and then a CPG-based neural network to ensure robust walking behavior
OriginalsprogEngelsk
TitelProceedings of the First International Symposium on Swarm Behavior and Bio-Inspired Robotics
Antal sider4
ForlagSWARM
Publikationsdato2016
StatusUdgivet - 2016
Begivenhed1st International Symposium on Swarm Behavior and Bio-Inspired Robotics - Kyoto, Japan
Varighed: 26. okt. 201528. okt. 2015
Konferencens nummer: 1

Konference

Konference1st International Symposium on Swarm Behavior and Bio-Inspired Robotics
Nummer1
LandJapan
ByKyoto
Periode26/10/201528/10/2015

Fingeraftryk

Neural networks
Controllers
Robots
Signal generators
Robotics
Engineers

Bibliografisk note

Published on USB

Citer dette

Di Canio, G., Larsen, J. C., Wörgötter, F., & Manoonpong, P. (2016). A Combination of Central Pattern Generator-based and Reflex-based Neural Networks for Dynamic, Adaptive, Robust Bipedal Locomotion. I Proceedings of the First International Symposium on Swarm Behavior and Bio-Inspired Robotics SWARM.
Di Canio, Giuliano ; Larsen, Jørgen Christian ; Wörgötter, Florentin ; Manoonpong, Poramate. / A Combination of Central Pattern Generator-based and Reflex-based Neural Networks for Dynamic, Adaptive, Robust Bipedal Locomotion. Proceedings of the First International Symposium on Swarm Behavior and Bio-Inspired Robotics. SWARM, 2016.
@inproceedings{e890e8a89c2948df8033592aa9e8dced,
title = "A Combination of Central Pattern Generator-based and Reflex-based Neural Networks for Dynamic, Adaptive, Robust Bipedal Locomotion",
abstract = "Robotic systems inspired from humans have always been lightening up the curiosity of engineers and scientists. Of many challenges, human locomotion is a very difficult one where a number of different systems needs to interact in order to generate a correct and balanced pattern. To simulate the interaction of these systems, implementations with reflexbased or central pattern generator (CPG)-based controllers have been tested on bipedal robot systems. In this paper we will combine the two controller types, into a controller that works with both reflex and CPG signals. We use a reflex-based neural network to generate basic walking patterns of a dynamic bipedal walking robot (DACBOT) and then a CPG-based neural network to ensure robust walking behavior",
keywords = "Biped robot, Neural control, Locomotion control, Embodied learning, Legged robots",
author = "{Di Canio}, Giuliano and Larsen, {J{\o}rgen Christian} and Florentin W{\"o}rg{\"o}tter and Poramate Manoonpong",
note = "Published on USB",
year = "2016",
language = "English",
booktitle = "Proceedings of the First International Symposium on Swarm Behavior and Bio-Inspired Robotics",
publisher = "SWARM",

}

Di Canio, G, Larsen, JC, Wörgötter, F & Manoonpong, P 2016, A Combination of Central Pattern Generator-based and Reflex-based Neural Networks for Dynamic, Adaptive, Robust Bipedal Locomotion. i Proceedings of the First International Symposium on Swarm Behavior and Bio-Inspired Robotics. SWARM, 1st International Symposium on Swarm Behavior and Bio-Inspired Robotics, Kyoto, Japan, 26/10/2015.

A Combination of Central Pattern Generator-based and Reflex-based Neural Networks for Dynamic, Adaptive, Robust Bipedal Locomotion. / Di Canio, Giuliano; Larsen, Jørgen Christian; Wörgötter, Florentin; Manoonpong, Poramate.

Proceedings of the First International Symposium on Swarm Behavior and Bio-Inspired Robotics. SWARM, 2016.

Publikation: Bidrag til bog/antologi/rapport/konference-proceedingKonferencebidrag i proceedingsForskningpeer review

TY - GEN

T1 - A Combination of Central Pattern Generator-based and Reflex-based Neural Networks for Dynamic, Adaptive, Robust Bipedal Locomotion

AU - Di Canio, Giuliano

AU - Larsen, Jørgen Christian

AU - Wörgötter, Florentin

AU - Manoonpong, Poramate

N1 - Published on USB

PY - 2016

Y1 - 2016

N2 - Robotic systems inspired from humans have always been lightening up the curiosity of engineers and scientists. Of many challenges, human locomotion is a very difficult one where a number of different systems needs to interact in order to generate a correct and balanced pattern. To simulate the interaction of these systems, implementations with reflexbased or central pattern generator (CPG)-based controllers have been tested on bipedal robot systems. In this paper we will combine the two controller types, into a controller that works with both reflex and CPG signals. We use a reflex-based neural network to generate basic walking patterns of a dynamic bipedal walking robot (DACBOT) and then a CPG-based neural network to ensure robust walking behavior

AB - Robotic systems inspired from humans have always been lightening up the curiosity of engineers and scientists. Of many challenges, human locomotion is a very difficult one where a number of different systems needs to interact in order to generate a correct and balanced pattern. To simulate the interaction of these systems, implementations with reflexbased or central pattern generator (CPG)-based controllers have been tested on bipedal robot systems. In this paper we will combine the two controller types, into a controller that works with both reflex and CPG signals. We use a reflex-based neural network to generate basic walking patterns of a dynamic bipedal walking robot (DACBOT) and then a CPG-based neural network to ensure robust walking behavior

KW - Biped robot

KW - Neural control

KW - Locomotion control

KW - Embodied learning

KW - Legged robots

M3 - Article in proceedings

BT - Proceedings of the First International Symposium on Swarm Behavior and Bio-Inspired Robotics

PB - SWARM

ER -

Di Canio G, Larsen JC, Wörgötter F, Manoonpong P. A Combination of Central Pattern Generator-based and Reflex-based Neural Networks for Dynamic, Adaptive, Robust Bipedal Locomotion. I Proceedings of the First International Symposium on Swarm Behavior and Bio-Inspired Robotics. SWARM. 2016