CoZ: A crowd-powered system for social robotics

Tahir Abbas; Vassilis Javed Khan; Panos Markopoulos

doi:10.1016/j.softx.2020.100421

CoZ: A crowd-powered system for social robotics

Tahir Abbas (Corresponding author), Vassilis Javed Khan, Panos Markopoulos

Research output: Contribution to journal › Article › Academic › peer-review

7 Citations (Scopus)

Abstract

We present Crowd of Oz (CoZ) — a crowd-powered system to enable a real-time dialogue between Softbank's Pepper robot and a user through a synchronous group of workers. We achieve this by: (1) providing media-rich interfaces and the underlying architecture to assist workers to contextualize the conversation; and (2) proposing and implementing the Pavilion algorithm, which ensures that the required number of workers are engaged. We have demonstrated in a lab setting that through CoZ, we can leverage crowdsourcing to drive the Pepper robot in a conversation on two topics: managing study-related stress and planning a holiday. Our preliminary results indicate that the crowd's input is both meaningful and fast enough to hold a conversation.

Original language	English
Article number	100421
Number of pages	7
Journal	SoftwareX
Volume	11
DOIs	https://doi.org/10.1016/j.softx.2020.100421
Publication status	Published - 1 Jan 2020

Funding

This work was supported by Higher Education Commission of Pakistan (HEC) in cooperation with Mirpur University of Science & Technology (MUST), Mirpur AJK-10250, Pakistan under grant number: 611-19/P.D/2017 .

Funders	Funder number
Mirpur University of Science and Technology
Iran University of Science and Technology	611-19/P.D/2017, AJK-10250

Keywords

Crowd-powered systems
Real-time human computation
Remote teleoperation
Social robotics

Access to Document

10.1016/j.softx.2020.100421

Cite this

@article{4d9d26df28cb44d79c51d14fa09cebf4,

title = "CoZ: A crowd-powered system for social robotics",

abstract = "We present Crowd of Oz (CoZ) — a crowd-powered system to enable a real-time dialogue between Softbank's Pepper robot and a user through a synchronous group of workers. We achieve this by: (1) providing media-rich interfaces and the underlying architecture to assist workers to contextualize the conversation; and (2) proposing and implementing the Pavilion algorithm, which ensures that the required number of workers are engaged. We have demonstrated in a lab setting that through CoZ, we can leverage crowdsourcing to drive the Pepper robot in a conversation on two topics: managing study-related stress and planning a holiday. Our preliminary results indicate that the crowd's input is both meaningful and fast enough to hold a conversation.",

keywords = "Crowd-powered systems, Real-time human computation, Remote teleoperation, Social robotics",

author = "Tahir Abbas and Khan, {Vassilis Javed} and Panos Markopoulos",

year = "2020",

month = jan,

day = "1",

doi = "10.1016/j.softx.2020.100421",

language = "English",

volume = "11",

journal = "SoftwareX",

issn = "2352-7110",

publisher = "Elsevier",

}

TY - JOUR

T1 - CoZ

T2 - A crowd-powered system for social robotics

AU - Abbas, Tahir

AU - Khan, Vassilis Javed

AU - Markopoulos, Panos

PY - 2020/1/1

Y1 - 2020/1/1

N2 - We present Crowd of Oz (CoZ) — a crowd-powered system to enable a real-time dialogue between Softbank's Pepper robot and a user through a synchronous group of workers. We achieve this by: (1) providing media-rich interfaces and the underlying architecture to assist workers to contextualize the conversation; and (2) proposing and implementing the Pavilion algorithm, which ensures that the required number of workers are engaged. We have demonstrated in a lab setting that through CoZ, we can leverage crowdsourcing to drive the Pepper robot in a conversation on two topics: managing study-related stress and planning a holiday. Our preliminary results indicate that the crowd's input is both meaningful and fast enough to hold a conversation.

AB - We present Crowd of Oz (CoZ) — a crowd-powered system to enable a real-time dialogue between Softbank's Pepper robot and a user through a synchronous group of workers. We achieve this by: (1) providing media-rich interfaces and the underlying architecture to assist workers to contextualize the conversation; and (2) proposing and implementing the Pavilion algorithm, which ensures that the required number of workers are engaged. We have demonstrated in a lab setting that through CoZ, we can leverage crowdsourcing to drive the Pepper robot in a conversation on two topics: managing study-related stress and planning a holiday. Our preliminary results indicate that the crowd's input is both meaningful and fast enough to hold a conversation.

KW - Crowd-powered systems

KW - Real-time human computation

KW - Remote teleoperation

KW - Social robotics

UR - http://www.scopus.com/inward/record.url?scp=85079349902&partnerID=8YFLogxK

U2 - 10.1016/j.softx.2020.100421

DO - 10.1016/j.softx.2020.100421

M3 - Article

AN - SCOPUS:85079349902

SN - 2352-7110

VL - 11

JO - SoftwareX

JF - SoftwareX

M1 - 100421

ER -

CoZ: A crowd-powered system for social robotics

Abstract

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this