Active robot learning for building up high-order beliefs

Dayou Li; Beisheng Liu; Carsten Maple; Daming Jiang; Yong Yue

doi:10.1109/FSKD.2008.186

Active robot learning for building up high-order beliefs

Dayou Li
, Beisheng Liu
, Carsten Maple
, Daming Jiang
, Yong Yue

Institute for Research in Applicable Computing (IRAC)

Beijing Jiaotong University

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

1 Citation (Scopus)

Abstract

High-order beliefs of service robots regard the robots' thought about their users' intention and preference. The existing approaches to the development of such beliefs through machine learning rely on particular social cues or specifically defined award functions. Their applications can, therefore, be limited. This paper presents an active robot learning approach to facilitate the robots to develop the beliefs by actively collecting/discovering evidence they need. The emphasis is on active learning. Hence social cues and award functions are not necessary. Simulations show that the presented approach successfully enabled a robot to discover evidences it needs.

Original language	English
Title of host publication	nan
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9780769533056
ISBN (Print)	9780769533056
DOIs	https://doi.org/10.1109/FSKD.2008.186
Publication status	Published - 5 Nov 2008
Event	2008 Fifth International Conference on Fuzzy Systems and Knowledge Discovery - Jinan Duration: 18 Oct 2008 → 20 Oct 2008

Conference

Conference	2008 Fifth International Conference on Fuzzy Systems and Knowledge Discovery
City	Jinan
Period	18/10/08 → 20/10/08
Other	2008 Fifth International Conference on Fuzzy Systems and Knowledge Discovery (18/10/2008-20/10/2008, Jinan)

Keywords

robot learning

Access to Document

10.1109/FSKD.2008.186

https://ieeexplore.ieee.org/document/4666240

Handle.net

Persistent link

Cite this

@inproceedings{3730df1e3e63415bbca70f41112afee6,

title = "Active robot learning for building up high-order beliefs",

abstract = "High-order beliefs of service robots regard the robots' thought about their users' intention and preference. The existing approaches to the development of such beliefs through machine learning rely on particular social cues or specifically defined award functions. Their applications can, therefore, be limited. This paper presents an active robot learning approach to facilitate the robots to develop the beliefs by actively collecting/discovering evidence they need. The emphasis is on active learning. Hence social cues and award functions are not necessary. Simulations show that the presented approach successfully enabled a robot to discover evidences it needs.",

keywords = "robot learning",

author = "Dayou Li and Beisheng Liu and Carsten Maple and Daming Jiang and Yong Yue",

year = "2008",

month = nov,

day = "5",

doi = "10.1109/FSKD.2008.186",

language = "English",

isbn = "9780769533056",

booktitle = "nan",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

address = "United States",

note = "2008 Fifth International Conference on Fuzzy Systems and Knowledge Discovery ; Conference date: 18-10-2008 Through 20-10-2008",

}

TY - GEN

T1 - Active robot learning for building up high-order beliefs

AU - Li, Dayou

AU - Liu, Beisheng

AU - Maple, Carsten

AU - Jiang, Daming

AU - Yue, Yong

PY - 2008/11/5

Y1 - 2008/11/5

N2 - High-order beliefs of service robots regard the robots' thought about their users' intention and preference. The existing approaches to the development of such beliefs through machine learning rely on particular social cues or specifically defined award functions. Their applications can, therefore, be limited. This paper presents an active robot learning approach to facilitate the robots to develop the beliefs by actively collecting/discovering evidence they need. The emphasis is on active learning. Hence social cues and award functions are not necessary. Simulations show that the presented approach successfully enabled a robot to discover evidences it needs.

AB - High-order beliefs of service robots regard the robots' thought about their users' intention and preference. The existing approaches to the development of such beliefs through machine learning rely on particular social cues or specifically defined award functions. Their applications can, therefore, be limited. This paper presents an active robot learning approach to facilitate the robots to develop the beliefs by actively collecting/discovering evidence they need. The emphasis is on active learning. Hence social cues and award functions are not necessary. Simulations show that the presented approach successfully enabled a robot to discover evidences it needs.

KW - robot learning

U2 - 10.1109/FSKD.2008.186

DO - 10.1109/FSKD.2008.186

M3 - Conference contribution

SN - 9780769533056

BT - nan

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2008 Fifth International Conference on Fuzzy Systems and Knowledge Discovery

Y2 - 18 October 2008 through 20 October 2008

ER -

Active robot learning for building up high-order beliefs

Abstract

Conference

Keywords

Access to Document

Handle.net

Fingerprint

Cite this