Crowdsourcing Task Traces for Service Robotics

被引：0

作者：

Porfirio, David ^{[1
]}

Sauppe, Allison ^{[2
]}

Cakmak, Maya ^{[3
]}

Albarghouthi, Aws ^{[4
]}

Mutlu, Bilge ^{[4
]}

机构：

[1] NRC Postdoctoral Res Associate Naval Res Lab Wash, Washington, DC 20375 USA

[2] Univ Wisconsin La Crosse, La Crosse, WI USA

[3] Univ Washington, Seattle, WA USA

[4] Univ Wisconsin Madison, Madison, WI USA

来源：

COMPANION OF THE ACM/IEEE INTERNATIONAL CONFERENCE ON HUMAN-ROBOT INTERACTION, HRI 2023 | 2023年

基金：

美国国家科学基金会;

关键词：

service robotics; crowdsourcing; end-user development;

D O I：

10.1145/3568294.3580112

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Demonstration is an effective end-user development paradigm for teaching robots how to perform new tasks. In this paper, we posit that demonstration is useful not only as a teaching tool, but also as a way to understand and assist end-user developers in thinking about a task at hand. As a frst step toward gaining this understanding, we constructed a lightweight web interface to crowdsource step-by-step instructions of common household tasks, leveraging the imaginations and past experiences of potential end-user developers. As evidence of the utility of our interface, we deployed the interface on Amazon Mechanical Turk and collected 207 task traces that span 18 diferent task categories. We describe our vision for how these task traces can be operationalized as task models within end-user development tools and provide a roadmap for future work.

引用

页码：389 / 393

页数：5

共 26 条

[1] ARAS Human Activity Datasets In Multiple Homes with Multiple Residents
Alemdar, Hande
Ertan, Halil
Incel, Ozlem Durmaz
Ersoy, Cem
[J]. PROCEEDINGS OF THE 2013 7TH INTERNATIONAL CONFERENCE ON PERVASIVE COMPUTING TECHNOLOGIES FOR HEALTHCARE AND WORKSHOPS (PERVASIVEHEALTH 2013), 2013, : 232 - 235
[2] [Anonymous], 2008, P 3 ACMIEEE INT C HU, DOI 10.1145/1349822
[3] Brohan A, 2023, Arxiv, DOI arXiv:2212.06817
[4] V.Ra: An In-Situ Visual Authoring System for Robot-IoT Task Planning with Augmented Reality
Cao, Yuanzhi
Xu, Zhuangying
Li, Fan
Zhong, Wentao
Huo, Ke
Ramani, Karthik
[J]. PROCEEDINGS OF THE 2019 ACM DESIGNING INTERACTIVE SYSTEMS CONFERENCE (DIS 2019), 2019, : 1059 - 1070
[5] Chernova Sonia., 2011, IEEE INT WORKSHOP RO, P21, DOI DOI 10.1109/ROMAN.2011.6005284
[6] A Dataset of Routine Daily Activities in an Instrumented Home
Cumin, Julien
Lefebvre, Gregoire
Ramparany, Fano
Crowley, James L.
[J]. UBIQUITOUS COMPUTING AND AMBIENT INTELLIGENCE, UCAMI 2017, 2017, 10586 : 413 - 425
[7] Essid Slim, 2017, P ACM INT C MULT INT, P464, DOI [DOI 10.1145/3136755.3136814, 10.1145/3136755.3136814]
[8] Design of Robot Teaching Assistants Through Multi-modal Human-Robot Interactions
Ferrarelli, Paola
Lazaro, Maria T.
Iocchi, Luca
[J]. ROBOTICS IN EDUCATION: LATEST RESULTS AND DEVELOPMENTS, 2018, 630 : 274 - 286
[9] Glas DF, 2016, ACMIEEE INT CONF HUM, P303, DOI 10.1109/HRI.2016.7451766
[10] Code3: A System for End-to-End Programming of Mobile Manipulator Robots for Novices and Experts
Huang, Justin
Cakmak, Maya
[J]. PROCEEDINGS OF THE 2017 ACM/IEEE INTERNATIONAL CONFERENCE ON HUMAN-ROBOT INTERACTION (HRI'17), 2017, : 453 - 462

← 1 2 3 →