Incremental learning control of the DLR-HIT-hand II during interaction tasks

Alessio Alessi; Loredana Zollo; Luca Lonini; Rosanna De Falco; Eugenio Guglielmelli

doi:10.1109/IEMBS.2010.5627411

Incremental learning control of the DLR-HIT-hand II during interaction tasks

Alessio Alessi^*, Loredana Zollo, Luca Lonini, Rosanna De Falco, Eugenio Guglielmelli

^*Corresponding author for this work

Physical Medicine and Rehabilitation

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

1 Scopus citations

Abstract

In this paper a bio-inspired control architecture for a robotic hand is presented. It relies on the same mechanisms of learning inverse internal models studied in humans. The control is capable of developing an internal representation of the hand interacting with the environment and updating it by means of the interaction forces that arise during contact. The learning paradigm exploits LWPR networks, which allow efficient incremental online learning through the use of spatially localized linear regression models. Additionally this paradigm limits negative interference when learning multiple tasks. The architecture is validated on a simulated finger of the DLRHIT- Hand II performing closing movements in presence of two different viscous force fields, perturbing its motion.

Original language	English (US)
Title of host publication	2010 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC'10
Pages	3194-3197
Number of pages	4
DOIs	https://doi.org/10.1109/IEMBS.2010.5627411
State	Published - Dec 1 2010
Event	2010 32nd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC'10 - Buenos Aires, Argentina Duration: Aug 31 2010 → Sep 4 2010

Publication series

Name	2010 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC'10

Other

Other	2010 32nd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC'10
Country/Territory	Argentina
City	Buenos Aires
Period	8/31/10 → 9/4/10

ASJC Scopus subject areas

Biomedical Engineering
Computer Vision and Pattern Recognition
Signal Processing
Health Informatics

Access to Document

10.1109/IEMBS.2010.5627411

Cite this

Alessi, A., Zollo, L., Lonini, L., De Falco, R., & Guglielmelli, E. (2010). Incremental learning control of the DLR-HIT-hand II during interaction tasks. In 2010 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC'10 (pp. 3194-3197). Article 5627411 (2010 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC'10). https://doi.org/10.1109/IEMBS.2010.5627411

@inproceedings{7f8441f260f04e79836293e513da310d,

title = "Incremental learning control of the DLR-HIT-hand II during interaction tasks",

abstract = "In this paper a bio-inspired control architecture for a robotic hand is presented. It relies on the same mechanisms of learning inverse internal models studied in humans. The control is capable of developing an internal representation of the hand interacting with the environment and updating it by means of the interaction forces that arise during contact. The learning paradigm exploits LWPR networks, which allow efficient incremental online learning through the use of spatially localized linear regression models. Additionally this paradigm limits negative interference when learning multiple tasks. The architecture is validated on a simulated finger of the DLRHIT- Hand II performing closing movements in presence of two different viscous force fields, perturbing its motion.",

author = "Alessio Alessi and Loredana Zollo and Luca Lonini and {De Falco}, Rosanna and Eugenio Guglielmelli",

year = "2010",

month = dec,

day = "1",

doi = "10.1109/IEMBS.2010.5627411",

language = "English (US)",

isbn = "9781424441235",

series = "2010 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC'10",

pages = "3194--3197",

booktitle = "2010 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC'10",

note = "2010 32nd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC'10 ; Conference date: 31-08-2010 Through 04-09-2010",

}

Alessi, A, Zollo, L, Lonini, L, De Falco, R & Guglielmelli, E 2010, Incremental learning control of the DLR-HIT-hand II during interaction tasks. in 2010 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC'10., 5627411, 2010 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC'10, pp. 3194-3197, 2010 32nd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC'10, Buenos Aires, Argentina, 8/31/10. https://doi.org/10.1109/IEMBS.2010.5627411

Incremental learning control of the DLR-HIT-hand II during interaction tasks. / Alessi, Alessio; Zollo, Loredana; Lonini, Luca et al.
2010 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC'10. 2010. p. 3194-3197 5627411 (2010 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC'10).

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

TY - GEN

T1 - Incremental learning control of the DLR-HIT-hand II during interaction tasks

AU - Alessi, Alessio

AU - Zollo, Loredana

AU - Lonini, Luca

AU - De Falco, Rosanna

AU - Guglielmelli, Eugenio

PY - 2010/12/1

Y1 - 2010/12/1

N2 - In this paper a bio-inspired control architecture for a robotic hand is presented. It relies on the same mechanisms of learning inverse internal models studied in humans. The control is capable of developing an internal representation of the hand interacting with the environment and updating it by means of the interaction forces that arise during contact. The learning paradigm exploits LWPR networks, which allow efficient incremental online learning through the use of spatially localized linear regression models. Additionally this paradigm limits negative interference when learning multiple tasks. The architecture is validated on a simulated finger of the DLRHIT- Hand II performing closing movements in presence of two different viscous force fields, perturbing its motion.

AB - In this paper a bio-inspired control architecture for a robotic hand is presented. It relies on the same mechanisms of learning inverse internal models studied in humans. The control is capable of developing an internal representation of the hand interacting with the environment and updating it by means of the interaction forces that arise during contact. The learning paradigm exploits LWPR networks, which allow efficient incremental online learning through the use of spatially localized linear regression models. Additionally this paradigm limits negative interference when learning multiple tasks. The architecture is validated on a simulated finger of the DLRHIT- Hand II performing closing movements in presence of two different viscous force fields, perturbing its motion.

UR - http://www.scopus.com/inward/record.url?scp=78650804214&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78650804214&partnerID=8YFLogxK

U2 - 10.1109/IEMBS.2010.5627411

DO - 10.1109/IEMBS.2010.5627411

M3 - Conference contribution

C2 - 21096810

AN - SCOPUS:78650804214

SN - 9781424441235

T3 - 2010 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC'10

SP - 3194

EP - 3197

BT - 2010 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC'10

T2 - 2010 32nd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC'10

Y2 - 31 August 2010 through 4 September 2010

ER -

Alessi A, Zollo L, Lonini L, De Falco R, Guglielmelli E. Incremental learning control of the DLR-HIT-hand II during interaction tasks. In 2010 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC'10. 2010. p. 3194-3197. 5627411. (2010 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC'10). doi: 10.1109/IEMBS.2010.5627411

Incremental learning control of the DLR-HIT-hand II during interaction tasks

Abstract

Publication series

Other

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this