Knowledge Acquisition with Selective Active Learning for Human-Robot Interaction

Batbold Myagmarjav; Mohan Sridharan

doi:10.1145/2701973.2702065

Knowledge Acquisition with Selective Active Learning for Human-Robot Interaction

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

Abstract / Description of output

This paper describes an architecture for robots interacting with non-expert humans to incrementally acquire domain knowledge. Contextual information is used to generate candidate questions that are ranked using measures of information gain, ambiguity, and human confusion, with the objective of maximizing the potential utility of the response. We report results of preliminary experiments evaluating thearchitecture in a simulated environment.

Original language	English
Title of host publication	HRI'15 Extended Abstracts: Proceedings of the Tenth Annual ACM/IEEE International Conference on Human-Robot Interaction Extended Abstracts
Place of Publication	United States
Publisher	Association for Computing Machinery (ACM)
Pages	147-148
Number of pages	2
ISBN (Print)	978-1-4503-3318-4
DOIs	https://doi.org/10.1145/2701973.2702065
Publication status	Published - 2 Mar 2015
Event	10th ACM/IEEE International Conference on Human Robot Interaction - Portland, United States Duration: 2 Mar 2015 → 5 Mar 2015 Conference number: 10 https://humanrobotinteraction.org/2015/index.html

Conference

Conference	10th ACM/IEEE International Conference on Human Robot Interaction
Abbreviated title	HRI 2015
Country/Territory	United States
City	Portland
Period	2/03/15 → 5/03/15
Internet address	https://humanrobotinteraction.org/2015/index.html

Access to Document

10.1145/2701973.2702065Licence: All Rights Reserved

https://dl.acm.org/doi/10.1145/2701973.2702065Licence: All Rights Reserved

Cite this

@inproceedings{c6c6677cd29a4dd89685e0c1a1eaf957,

title = "Knowledge Acquisition with Selective Active Learning for Human-Robot Interaction",

abstract = "This paper describes an architecture for robots interacting with non-expert humans to incrementally acquire domain knowledge. Contextual information is used to generate candidate questions that are ranked using measures of information gain, ambiguity, and human confusion, with the objective of maximizing the potential utility of the response. We report results of preliminary experiments evaluating thearchitecture in a simulated environment.",

author = "Batbold Myagmarjav and Mohan Sridharan",

note = "Tenth Annual ACM/IEEE International Conference on Human-Robot Interaction ; Conference date: 02-03-2015 Through 05-03-2015; 10th ACM/IEEE International Conference on Human Robot Interaction, HRI 2015 ; Conference date: 02-03-2015 Through 05-03-2015",

year = "2015",

month = mar,

day = "2",

doi = "10.1145/2701973.2702065",

language = "English",

isbn = "978-1-4503-3318-4",

pages = "147--148",

booktitle = "HRI'15 Extended Abstracts: Proceedings of the Tenth Annual ACM/IEEE International Conference on Human-Robot Interaction Extended Abstracts",

publisher = "Association for Computing Machinery (ACM)",

address = "United States",

url = "https://humanrobotinteraction.org/2015/index.html",

}

Myagmarjav, B & Sridharan, M 2015, Knowledge Acquisition with Selective Active Learning for Human-Robot Interaction. in HRI'15 Extended Abstracts: Proceedings of the Tenth Annual ACM/IEEE International Conference on Human-Robot Interaction Extended Abstracts. Association for Computing Machinery (ACM), United States, pp. 147-148, 10th ACM/IEEE International Conference on Human Robot Interaction, Portland, United States, 2/03/15. https://doi.org/10.1145/2701973.2702065

Knowledge Acquisition with Selective Active Learning for Human-Robot Interaction. / Myagmarjav, Batbold; Sridharan, Mohan.
HRI'15 Extended Abstracts: Proceedings of the Tenth Annual ACM/IEEE International Conference on Human-Robot Interaction Extended Abstracts. United States: Association for Computing Machinery (ACM), 2015. p. 147-148.

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

TY - GEN

T1 - Knowledge Acquisition with Selective Active Learning for Human-Robot Interaction

AU - Myagmarjav, Batbold

AU - Sridharan, Mohan

N1 - Conference code: 10

PY - 2015/3/2

Y1 - 2015/3/2

N2 - This paper describes an architecture for robots interacting with non-expert humans to incrementally acquire domain knowledge. Contextual information is used to generate candidate questions that are ranked using measures of information gain, ambiguity, and human confusion, with the objective of maximizing the potential utility of the response. We report results of preliminary experiments evaluating thearchitecture in a simulated environment.

AB - This paper describes an architecture for robots interacting with non-expert humans to incrementally acquire domain knowledge. Contextual information is used to generate candidate questions that are ranked using measures of information gain, ambiguity, and human confusion, with the objective of maximizing the potential utility of the response. We report results of preliminary experiments evaluating thearchitecture in a simulated environment.

U2 - 10.1145/2701973.2702065

DO - 10.1145/2701973.2702065

M3 - Conference contribution

SN - 978-1-4503-3318-4

SP - 147

EP - 148

BT - HRI'15 Extended Abstracts: Proceedings of the Tenth Annual ACM/IEEE International Conference on Human-Robot Interaction Extended Abstracts

PB - Association for Computing Machinery (ACM)

CY - United States

T2 - 10th ACM/IEEE International Conference on Human Robot Interaction

Y2 - 2 March 2015 through 5 March 2015

ER -

Knowledge Acquisition with Selective Active Learning for Human-Robot Interaction

Abstract / Description of output

Conference

Access to Document

Fingerprint

Cite this