Reach and grasp for an anthropomorphic robotic system based on sensorimotor learning

Selim Eskiizmirliler; Marc A. Maier; Loredana Zollo; Luigi Manfredi; Giancarlo Teti; Cecilia Laschi

doi:10.1109/BIOROB.2006.1639173

Reach and grasp for an anthropomorphic robotic system based on sensorimotor learning

Selim Eskiizmirliler, Marc A. Maier, Loredana Zollo, Luigi Manfredi, Giancarlo Teti, Cecilia Laschi

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

4 Citations (Scopus)

Abstract

In this article, we present a neurobiologically inspired multinetwork architecture based on knowledge of cortico-cortical connectivity and its application on an anthropomorphic head-arm-hand robotic system to provide reach-and-grasp kinematics based on multimodal sensorimotor learning. The system incorporates artificial neural network modules (matching units) trained by the locally weighted projection regression (LWPR) algorithm that enables progressive learning from simple to more complex sensorimotor tasks. We report the actual performance of the system by comparing the simulation with the experimental results obtained by the implementation on the real world artefact.

Original language	English
Title of host publication	Proceedings of the First IEEE/RAS-EMBS International Conference on Biomedical Robotics and Biomechatronics, 2006, BioRob 2006
Pages	708-713
Number of pages	6
Volume	2006
DOIs	https://doi.org/10.1109/BIOROB.2006.1639173
Publication status	Published - 20 Feb 2006
Event	1st IEEE/RAS-EMBS International Conference on Biomedical Robotics and Biomechatronics, 2006, BioRob 2006 - Pisa, Italy Duration: 20 Feb 2006 → 22 Feb 2006

Conference

Conference	1st IEEE/RAS-EMBS International Conference on Biomedical Robotics and Biomechatronics, 2006, BioRob 2006
Country/Territory	Italy
City	Pisa
Period	20/02/06 → 22/02/06

Keywords

Artificial neural networks
Multi modal sensory integration
Neuro-robotics
Sensorimotor control

ASJC Scopus subject areas

General Engineering

Access to Document

10.1109/BIOROB.2006.1639173

Cite this

Eskiizmirliler, S., Maier, M. A., Zollo, L., Manfredi, L., Teti, G., & Laschi, C. (2006). Reach and grasp for an anthropomorphic robotic system based on sensorimotor learning. In Proceedings of the First IEEE/RAS-EMBS International Conference on Biomedical Robotics and Biomechatronics, 2006, BioRob 2006 (Vol. 2006, pp. 708-713). Article 1639173 https://doi.org/10.1109/BIOROB.2006.1639173

@inproceedings{ba3db62756fe4ee9927bc6e9619d5911,

title = "Reach and grasp for an anthropomorphic robotic system based on sensorimotor learning",

abstract = "In this article, we present a neurobiologically inspired multinetwork architecture based on knowledge of cortico-cortical connectivity and its application on an anthropomorphic head-arm-hand robotic system to provide reach-and-grasp kinematics based on multimodal sensorimotor learning. The system incorporates artificial neural network modules (matching units) trained by the locally weighted projection regression (LWPR) algorithm that enables progressive learning from simple to more complex sensorimotor tasks. We report the actual performance of the system by comparing the simulation with the experimental results obtained by the implementation on the real world artefact.",

keywords = "Artificial neural networks, Multi modal sensory integration, Neuro-robotics, Sensorimotor control",

author = "Selim Eskiizmirliler and Maier, {Marc A.} and Loredana Zollo and Luigi Manfredi and Giancarlo Teti and Cecilia Laschi",

year = "2006",

month = feb,

day = "20",

doi = "10.1109/BIOROB.2006.1639173",

language = "English",

isbn = "1424400406",

volume = "2006",

pages = "708--713",

booktitle = "Proceedings of the First IEEE/RAS-EMBS International Conference on Biomedical Robotics and Biomechatronics, 2006, BioRob 2006",

note = "1st IEEE/RAS-EMBS International Conference on Biomedical Robotics and Biomechatronics, 2006, BioRob 2006 ; Conference date: 20-02-2006 Through 22-02-2006",

}

Eskiizmirliler, S, Maier, MA, Zollo, L, Manfredi, L, Teti, G & Laschi, C 2006, Reach and grasp for an anthropomorphic robotic system based on sensorimotor learning. in Proceedings of the First IEEE/RAS-EMBS International Conference on Biomedical Robotics and Biomechatronics, 2006, BioRob 2006. vol. 2006, 1639173, pp. 708-713, 1st IEEE/RAS-EMBS International Conference on Biomedical Robotics and Biomechatronics, 2006, BioRob 2006, Pisa, Italy, 20/02/06. https://doi.org/10.1109/BIOROB.2006.1639173

Reach and grasp for an anthropomorphic robotic system based on sensorimotor learning. / Eskiizmirliler, Selim; Maier, Marc A.; Zollo, Loredana et al.
Proceedings of the First IEEE/RAS-EMBS International Conference on Biomedical Robotics and Biomechatronics, 2006, BioRob 2006. Vol. 2006 2006. p. 708-713 1639173.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Reach and grasp for an anthropomorphic robotic system based on sensorimotor learning

AU - Eskiizmirliler, Selim

AU - Maier, Marc A.

AU - Zollo, Loredana

AU - Manfredi, Luigi

AU - Teti, Giancarlo

AU - Laschi, Cecilia

PY - 2006/2/20

Y1 - 2006/2/20

N2 - In this article, we present a neurobiologically inspired multinetwork architecture based on knowledge of cortico-cortical connectivity and its application on an anthropomorphic head-arm-hand robotic system to provide reach-and-grasp kinematics based on multimodal sensorimotor learning. The system incorporates artificial neural network modules (matching units) trained by the locally weighted projection regression (LWPR) algorithm that enables progressive learning from simple to more complex sensorimotor tasks. We report the actual performance of the system by comparing the simulation with the experimental results obtained by the implementation on the real world artefact.

AB - In this article, we present a neurobiologically inspired multinetwork architecture based on knowledge of cortico-cortical connectivity and its application on an anthropomorphic head-arm-hand robotic system to provide reach-and-grasp kinematics based on multimodal sensorimotor learning. The system incorporates artificial neural network modules (matching units) trained by the locally weighted projection regression (LWPR) algorithm that enables progressive learning from simple to more complex sensorimotor tasks. We report the actual performance of the system by comparing the simulation with the experimental results obtained by the implementation on the real world artefact.

KW - Artificial neural networks

KW - Multi modal sensory integration

KW - Neuro-robotics

KW - Sensorimotor control

UR - http://www.scopus.com/inward/record.url?scp=33845582006&partnerID=8YFLogxK

U2 - 10.1109/BIOROB.2006.1639173

DO - 10.1109/BIOROB.2006.1639173

M3 - Conference contribution

AN - SCOPUS:33845582006

SN - 1424400406

SN - 9781424400409

VL - 2006

SP - 708

EP - 713

BT - Proceedings of the First IEEE/RAS-EMBS International Conference on Biomedical Robotics and Biomechatronics, 2006, BioRob 2006

T2 - 1st IEEE/RAS-EMBS International Conference on Biomedical Robotics and Biomechatronics, 2006, BioRob 2006

Y2 - 20 February 2006 through 22 February 2006

ER -

Reach and grasp for an anthropomorphic robotic system based on sensorimotor learning

Abstract

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this