POMDP based action planning and human error detection

Emilie M.D. Jean-Baptiste; Pia Rotshtein; Martin Russell

doi:10.1007/978-3-319-23868-5_18

POMDP based action planning and human error detection

Emilie M.D. Jean-Baptiste, Pia Rotshtein, Martin Russell

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

9 Citations (Scopus)

Abstract

This paper presents a Partially Observable Markov Decision Process (POMDP) model for action planning and human errors detection, during Activities of Daily Living (ADLs). This model is integrated into a sub-component of an assistive system designed for stroke survivors; it is called the Artificial Intelligent Planning System (AIPS). Its main goal is to monitor the user’s history of actions during a specific task, and to provide meaningful assistance when an error is detected in his/her sequence of actions. To do so, the AIPS must cope with the ambiguity in the outputs of the other system’s components. In this paper, we first give an overview of the global assistive system where the AIPS is implemented, and explain how it interacts with the user to guide him/her during tea-making. We then define the POMDP models and the Monte Carlo Algorithm used to learn how to retrieve optimal prompts, and detect human errors under uncertainty.

Original language	English
Title of host publication	Artificial Intelligence Applications and Innovations
Subtitle of host publication	11th IFIP WG 12.5 International Conference, AIAI 2015, Bayonne, France, September 14-17, 2015, Proceedings
Editors	Richard Chbeir, Ilias Maglogiannis, Yannis Manolopoulos, Reda Alhajj
Publisher	Springer
Pages	250-265
Number of pages	16
ISBN (Electronic)	9783319238685
ISBN (Print)	9783319238678
DOIs	https://doi.org/10.1007/978-3-319-23868-5_18
Publication status	Published - 15 Nov 2015
Event	11th IFIPWG 12.5 International Conference on Artificial Intelligence Applications and Innovations, AIAI 2015 - Bayonne, France Duration: 14 Sept 2015 → 17 Sept 2015

Publication series

Name	IFIP Advances in Information and Communication Technology
Volume	458
ISSN (Print)	1868-4238

Conference

Conference	11th IFIPWG 12.5 International Conference on Artificial Intelligence Applications and Innovations, AIAI 2015
Country/Territory	France
City	Bayonne
Period	14/09/15 → 17/09/15

Bibliographical note

Publisher Copyright:
© IFIP International Federation for Information Processing 2015.

Keywords

Assistive Technology
Planning Under Uncertainty
POMDP

ASJC Scopus subject areas

Information Systems
Computer Networks and Communications
Information Systems and Management

Access to Document

10.1007/978-3-319-23868-5_18Licence: None: All rights reserved

Cite this

Jean-Baptiste, E. M. D., Rotshtein, P., & Russell, M. (2015). POMDP based action planning and human error detection. In R. Chbeir, I. Maglogiannis, Y. Manolopoulos, & R. Alhajj (Eds.), Artificial Intelligence Applications and Innovations: 11th IFIP WG 12.5 International Conference, AIAI 2015, Bayonne, France, September 14-17, 2015, Proceedings (pp. 250-265). (IFIP Advances in Information and Communication Technology; Vol. 458). Springer. https://doi.org/10.1007/978-3-319-23868-5_18

Jean-Baptiste, Emilie M.D. ; Rotshtein, Pia ; Russell, Martin. / POMDP based action planning and human error detection. Artificial Intelligence Applications and Innovations: 11th IFIP WG 12.5 International Conference, AIAI 2015, Bayonne, France, September 14-17, 2015, Proceedings. editor / Richard Chbeir ; Ilias Maglogiannis ; Yannis Manolopoulos ; Reda Alhajj. Springer, 2015. pp. 250-265 (IFIP Advances in Information and Communication Technology).

@inproceedings{7059f48f0645429588e22ce343812e41,

title = "POMDP based action planning and human error detection",

abstract = "This paper presents a Partially Observable Markov Decision Process (POMDP) model for action planning and human errors detection, during Activities of Daily Living (ADLs). This model is integrated into a sub-component of an assistive system designed for stroke survivors; it is called the Artificial Intelligent Planning System (AIPS). Its main goal is to monitor the user{\textquoteright}s history of actions during a specific task, and to provide meaningful assistance when an error is detected in his/her sequence of actions. To do so, the AIPS must cope with the ambiguity in the outputs of the other system{\textquoteright}s components. In this paper, we first give an overview of the global assistive system where the AIPS is implemented, and explain how it interacts with the user to guide him/her during tea-making. We then define the POMDP models and the Monte Carlo Algorithm used to learn how to retrieve optimal prompts, and detect human errors under uncertainty.",

keywords = "Assistive Technology, Planning Under Uncertainty, POMDP",

author = "Jean-Baptiste, {Emilie M.D.} and Pia Rotshtein and Martin Russell",

note = "Publisher Copyright: {\textcopyright} IFIP International Federation for Information Processing 2015.; 11th IFIPWG 12.5 International Conference on Artificial Intelligence Applications and Innovations, AIAI 2015 ; Conference date: 14-09-2015 Through 17-09-2015",

year = "2015",

month = nov,

day = "15",

doi = "10.1007/978-3-319-23868-5_18",

language = "English",

isbn = "9783319238678",

series = "IFIP Advances in Information and Communication Technology",

publisher = "Springer",

pages = "250--265",

editor = "Richard Chbeir and Ilias Maglogiannis and Yannis Manolopoulos and Reda Alhajj",

booktitle = "Artificial Intelligence Applications and Innovations",

}

Jean-Baptiste, EMD, Rotshtein, P & Russell, M 2015, POMDP based action planning and human error detection. in R Chbeir, I Maglogiannis, Y Manolopoulos & R Alhajj (eds), Artificial Intelligence Applications and Innovations: 11th IFIP WG 12.5 International Conference, AIAI 2015, Bayonne, France, September 14-17, 2015, Proceedings. IFIP Advances in Information and Communication Technology, vol. 458, Springer, pp. 250-265, 11th IFIPWG 12.5 International Conference on Artificial Intelligence Applications and Innovations, AIAI 2015, Bayonne, France, 14/09/15. https://doi.org/10.1007/978-3-319-23868-5_18

POMDP based action planning and human error detection. / Jean-Baptiste, Emilie M.D.; Rotshtein, Pia; Russell, Martin.
Artificial Intelligence Applications and Innovations: 11th IFIP WG 12.5 International Conference, AIAI 2015, Bayonne, France, September 14-17, 2015, Proceedings. ed. / Richard Chbeir; Ilias Maglogiannis; Yannis Manolopoulos; Reda Alhajj. Springer, 2015. p. 250-265 (IFIP Advances in Information and Communication Technology; Vol. 458).

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

TY - GEN

T1 - POMDP based action planning and human error detection

AU - Jean-Baptiste, Emilie M.D.

AU - Rotshtein, Pia

AU - Russell, Martin

N1 - Publisher Copyright: © IFIP International Federation for Information Processing 2015.

PY - 2015/11/15

Y1 - 2015/11/15

N2 - This paper presents a Partially Observable Markov Decision Process (POMDP) model for action planning and human errors detection, during Activities of Daily Living (ADLs). This model is integrated into a sub-component of an assistive system designed for stroke survivors; it is called the Artificial Intelligent Planning System (AIPS). Its main goal is to monitor the user’s history of actions during a specific task, and to provide meaningful assistance when an error is detected in his/her sequence of actions. To do so, the AIPS must cope with the ambiguity in the outputs of the other system’s components. In this paper, we first give an overview of the global assistive system where the AIPS is implemented, and explain how it interacts with the user to guide him/her during tea-making. We then define the POMDP models and the Monte Carlo Algorithm used to learn how to retrieve optimal prompts, and detect human errors under uncertainty.

AB - This paper presents a Partially Observable Markov Decision Process (POMDP) model for action planning and human errors detection, during Activities of Daily Living (ADLs). This model is integrated into a sub-component of an assistive system designed for stroke survivors; it is called the Artificial Intelligent Planning System (AIPS). Its main goal is to monitor the user’s history of actions during a specific task, and to provide meaningful assistance when an error is detected in his/her sequence of actions. To do so, the AIPS must cope with the ambiguity in the outputs of the other system’s components. In this paper, we first give an overview of the global assistive system where the AIPS is implemented, and explain how it interacts with the user to guide him/her during tea-making. We then define the POMDP models and the Monte Carlo Algorithm used to learn how to retrieve optimal prompts, and detect human errors under uncertainty.

KW - Assistive Technology

KW - Planning Under Uncertainty

KW - POMDP

UR - http://www.scopus.com/inward/record.url?scp=84946038935&partnerID=8YFLogxK

U2 - 10.1007/978-3-319-23868-5_18

DO - 10.1007/978-3-319-23868-5_18

M3 - Conference contribution

AN - SCOPUS:84946038935

SN - 9783319238678

T3 - IFIP Advances in Information and Communication Technology

SP - 250

EP - 265

BT - Artificial Intelligence Applications and Innovations

A2 - Chbeir, Richard

A2 - Maglogiannis, Ilias

A2 - Manolopoulos, Yannis

A2 - Alhajj, Reda

PB - Springer

T2 - 11th IFIPWG 12.5 International Conference on Artificial Intelligence Applications and Innovations, AIAI 2015

Y2 - 14 September 2015 through 17 September 2015

ER -

Jean-Baptiste EMD, Rotshtein P, Russell M. POMDP based action planning and human error detection. In Chbeir R, Maglogiannis I, Manolopoulos Y, Alhajj R, editors, Artificial Intelligence Applications and Innovations: 11th IFIP WG 12.5 International Conference, AIAI 2015, Bayonne, France, September 14-17, 2015, Proceedings. Springer. 2015. p. 250-265. (IFIP Advances in Information and Communication Technology). doi: 10.1007/978-3-319-23868-5_18

POMDP based action planning and human error detection

Abstract

Publication series

Conference

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this