Exploiting co-adaptation for the design of symbiotic neuroprosthetic assistants

Justin C. Sanchez, Babak Mahmoudi, Jack DiGiovanna, Jose C. Principe

Research output: Contribution to journalArticle

28 Citations (Scopus)

Abstract

The success of brain-machine interfaces (BMI) is enabled by the remarkable ability of the brain to incorporate the artificial neuroprosthetic 'tool' into its own cognitive space and use it as an extension of the user's body. Unlike other tools, neuroprosthetics create a shared space that seamlessly spans the user's internal goal representation of the world and the external physical environment enabling a much deeper human-tool symbiosis. A key factor in the transformation of 'simple tools' into 'intelligent tools' is the concept of co-adaptation where the tool becomes functionally involved in the extraction and definition of the user's goals. Recent advancements in the neuroscience and engineering of neuroprosthetics are providing a blueprint for how new co-adaptive designs based on reinforcement learning change the nature of a user's ability to accomplish tasks that were not possible using conventional methodologies. By designing adaptive controls and artificial intelligence into the neural interface, tools can become active assistants in goal-directed behavior and further enhance human performance in particular for the disabled population. This paper presents recent advances in computational and neural systems supporting the development of symbiotic neuroprosthetic assistants.

Original languageEnglish
Pages (from-to)305-315
Number of pages11
JournalNeural Networks
Volume22
Issue number3
DOIs
StatePublished - Apr 1 2009
Externally publishedYes

Fingerprint

Aptitude
Brain-Computer Interfaces
Symbiosis
Artificial Intelligence
Neurosciences
Learning
Brain
Blueprints
Reinforcement learning
Population
Artificial intelligence
Reinforcement (Psychology)

Keywords

  • Brain-computer symbiosis
  • Brain-machine interface
  • Perception-action cycle
  • Reinforcement learning
  • Tool use

ASJC Scopus subject areas

  • Artificial Intelligence
  • Cognitive Neuroscience

Cite this

Sanchez, J. C., Mahmoudi, B., DiGiovanna, J., & Principe, J. C. (2009). Exploiting co-adaptation for the design of symbiotic neuroprosthetic assistants. Neural Networks, 22(3), 305-315. https://doi.org/10.1016/j.neunet.2009.03.015

Exploiting co-adaptation for the design of symbiotic neuroprosthetic assistants. / Sanchez, Justin C.; Mahmoudi, Babak; DiGiovanna, Jack; Principe, Jose C.

In: Neural Networks, Vol. 22, No. 3, 01.04.2009, p. 305-315.

Research output: Contribution to journalArticle

Sanchez, JC, Mahmoudi, B, DiGiovanna, J & Principe, JC 2009, 'Exploiting co-adaptation for the design of symbiotic neuroprosthetic assistants', Neural Networks, vol. 22, no. 3, pp. 305-315. https://doi.org/10.1016/j.neunet.2009.03.015
Sanchez, Justin C. ; Mahmoudi, Babak ; DiGiovanna, Jack ; Principe, Jose C. / Exploiting co-adaptation for the design of symbiotic neuroprosthetic assistants. In: Neural Networks. 2009 ; Vol. 22, No. 3. pp. 305-315.
@article{802187ea6bb941ae8118fa0260efdbbf,
title = "Exploiting co-adaptation for the design of symbiotic neuroprosthetic assistants",
abstract = "The success of brain-machine interfaces (BMI) is enabled by the remarkable ability of the brain to incorporate the artificial neuroprosthetic 'tool' into its own cognitive space and use it as an extension of the user's body. Unlike other tools, neuroprosthetics create a shared space that seamlessly spans the user's internal goal representation of the world and the external physical environment enabling a much deeper human-tool symbiosis. A key factor in the transformation of 'simple tools' into 'intelligent tools' is the concept of co-adaptation where the tool becomes functionally involved in the extraction and definition of the user's goals. Recent advancements in the neuroscience and engineering of neuroprosthetics are providing a blueprint for how new co-adaptive designs based on reinforcement learning change the nature of a user's ability to accomplish tasks that were not possible using conventional methodologies. By designing adaptive controls and artificial intelligence into the neural interface, tools can become active assistants in goal-directed behavior and further enhance human performance in particular for the disabled population. This paper presents recent advances in computational and neural systems supporting the development of symbiotic neuroprosthetic assistants.",
keywords = "Brain-computer symbiosis, Brain-machine interface, Perception-action cycle, Reinforcement learning, Tool use",
author = "Sanchez, {Justin C.} and Babak Mahmoudi and Jack DiGiovanna and Principe, {Jose C.}",
year = "2009",
month = "4",
day = "1",
doi = "10.1016/j.neunet.2009.03.015",
language = "English",
volume = "22",
pages = "305--315",
journal = "Neural Networks",
issn = "0893-6080",
publisher = "Elsevier Limited",
number = "3",

}

TY - JOUR

T1 - Exploiting co-adaptation for the design of symbiotic neuroprosthetic assistants

AU - Sanchez, Justin C.

AU - Mahmoudi, Babak

AU - DiGiovanna, Jack

AU - Principe, Jose C.

PY - 2009/4/1

Y1 - 2009/4/1

N2 - The success of brain-machine interfaces (BMI) is enabled by the remarkable ability of the brain to incorporate the artificial neuroprosthetic 'tool' into its own cognitive space and use it as an extension of the user's body. Unlike other tools, neuroprosthetics create a shared space that seamlessly spans the user's internal goal representation of the world and the external physical environment enabling a much deeper human-tool symbiosis. A key factor in the transformation of 'simple tools' into 'intelligent tools' is the concept of co-adaptation where the tool becomes functionally involved in the extraction and definition of the user's goals. Recent advancements in the neuroscience and engineering of neuroprosthetics are providing a blueprint for how new co-adaptive designs based on reinforcement learning change the nature of a user's ability to accomplish tasks that were not possible using conventional methodologies. By designing adaptive controls and artificial intelligence into the neural interface, tools can become active assistants in goal-directed behavior and further enhance human performance in particular for the disabled population. This paper presents recent advances in computational and neural systems supporting the development of symbiotic neuroprosthetic assistants.

AB - The success of brain-machine interfaces (BMI) is enabled by the remarkable ability of the brain to incorporate the artificial neuroprosthetic 'tool' into its own cognitive space and use it as an extension of the user's body. Unlike other tools, neuroprosthetics create a shared space that seamlessly spans the user's internal goal representation of the world and the external physical environment enabling a much deeper human-tool symbiosis. A key factor in the transformation of 'simple tools' into 'intelligent tools' is the concept of co-adaptation where the tool becomes functionally involved in the extraction and definition of the user's goals. Recent advancements in the neuroscience and engineering of neuroprosthetics are providing a blueprint for how new co-adaptive designs based on reinforcement learning change the nature of a user's ability to accomplish tasks that were not possible using conventional methodologies. By designing adaptive controls and artificial intelligence into the neural interface, tools can become active assistants in goal-directed behavior and further enhance human performance in particular for the disabled population. This paper presents recent advances in computational and neural systems supporting the development of symbiotic neuroprosthetic assistants.

KW - Brain-computer symbiosis

KW - Brain-machine interface

KW - Perception-action cycle

KW - Reinforcement learning

KW - Tool use

UR - http://www.scopus.com/inward/record.url?scp=67349094505&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=67349094505&partnerID=8YFLogxK

U2 - 10.1016/j.neunet.2009.03.015

DO - 10.1016/j.neunet.2009.03.015

M3 - Article

C2 - 19403263

AN - SCOPUS:67349094505

VL - 22

SP - 305

EP - 315

JO - Neural Networks

JF - Neural Networks

SN - 0893-6080

IS - 3

ER -