Crowd-Sourcing Real-World Human-Robot Dialogue and Teamwork through Online Multiplayer Games
We present an innovative approach for large-scale data collection in human-robot interaction research through the use of online multi-player games. By casting a robotic task as a collaborative game, we gather thousands of examples of human-human interactions online, and then leverage this corpus of...
| Main Authors: | , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | en_US |
| Published: |
Association for the Advancement of Artificial Intelligence
2017
|
| Online Access: | http://hdl.handle.net/1721.1/106674 https://orcid.org/0000-0001-5522-0631 https://orcid.org/0000-0002-0587-2065 |
| _version_ | 1811084375510482944 |
|---|---|
| author | Chernova, Sonia DePalma, Nicholas Brian Breazeal, Cynthia Lynn |
| author2 | Program in Media Arts and Sciences (Massachusetts Institute of Technology) |
| author_facet | Program in Media Arts and Sciences (Massachusetts Institute of Technology) Chernova, Sonia DePalma, Nicholas Brian Breazeal, Cynthia Lynn |
| author_sort | Chernova, Sonia |
| collection | MIT |
| description | We present an innovative approach for large-scale data collection in human-robot interaction research through the use of online multi-player games. By casting a robotic task as a collaborative game, we gather thousands of examples of human-human interactions online, and then leverage this corpus of action and dialog data to create contextually relevant, social and task-oriented behaviors for human-robot interaction in the real world. We demonstrate our work in a collaborative search and retrieval task requiring dialog, action synchronization and action sequencing between the human and robot partners. A user study performed at the Boston Museum of Science shows that the autonomous robot exhibits many of the same patterns of behavior that were observed in the online dataset and survey results rate the robot similarly to human partners in several critical measures. |
| first_indexed | 2024-09-23T12:49:44Z |
| format | Article |
| id | mit-1721.1/106674 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T12:49:44Z |
| publishDate | 2017 |
| publisher | Association for the Advancement of Artificial Intelligence |
| record_format | dspace |
| spelling | mit-1721.1/1066742022-09-28T10:18:02Z Crowd-Sourcing Real-World Human-Robot Dialogue and Teamwork through Online Multiplayer Games Chernova, Sonia DePalma, Nicholas Brian Breazeal, Cynthia Lynn Program in Media Arts and Sciences (Massachusetts Institute of Technology) Chernova, Sonia DePalma, Nicholas Brian Breazeal, Cynthia L. We present an innovative approach for large-scale data collection in human-robot interaction research through the use of online multi-player games. By casting a robotic task as a collaborative game, we gather thousands of examples of human-human interactions online, and then leverage this corpus of action and dialog data to create contextually relevant, social and task-oriented behaviors for human-robot interaction in the real world. We demonstrate our work in a collaborative search and retrieval task requiring dialog, action synchronization and action sequencing between the human and robot partners. A user study performed at the Boston Museum of Science shows that the autonomous robot exhibits many of the same patterns of behavior that were observed in the online dataset and survey results rate the robot similarly to human partners in several critical measures. Microsoft Research United States. Office of Naval Research (Grants N000140910112 and N000140710749) 2017-01-30T16:21:16Z 2017-01-30T16:21:16Z 2011 Article http://purl.org/eprint/type/JournalArticle 0738-4602 http://hdl.handle.net/1721.1/106674 Chernova, Sonia, Nick DePalma and Cynthia Breazeal. "Crowd-Sourcing Real-World Human-Robot Dialogue and Teamwork through Online Multiplayer Games." AI Magazine 32.4 (2011): 100-111. © 2011 Association for the Advancement of Artificial Intelligence https://orcid.org/0000-0001-5522-0631 https://orcid.org/0000-0002-0587-2065 en_US http://www.aaai.org/ojs/index.php/aimagazine/article/view/2380/2245 AI Magazine Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use. application/pdf Association for the Advancement of Artificial Intelligence AAAI |
| spellingShingle | Chernova, Sonia DePalma, Nicholas Brian Breazeal, Cynthia Lynn Crowd-Sourcing Real-World Human-Robot Dialogue and Teamwork through Online Multiplayer Games |
| title | Crowd-Sourcing Real-World Human-Robot Dialogue and Teamwork through Online Multiplayer Games |
| title_full | Crowd-Sourcing Real-World Human-Robot Dialogue and Teamwork through Online Multiplayer Games |
| title_fullStr | Crowd-Sourcing Real-World Human-Robot Dialogue and Teamwork through Online Multiplayer Games |
| title_full_unstemmed | Crowd-Sourcing Real-World Human-Robot Dialogue and Teamwork through Online Multiplayer Games |
| title_short | Crowd-Sourcing Real-World Human-Robot Dialogue and Teamwork through Online Multiplayer Games |
| title_sort | crowd sourcing real world human robot dialogue and teamwork through online multiplayer games |
| url | http://hdl.handle.net/1721.1/106674 https://orcid.org/0000-0001-5522-0631 https://orcid.org/0000-0002-0587-2065 |
| work_keys_str_mv | AT chernovasonia crowdsourcingrealworldhumanrobotdialogueandteamworkthroughonlinemultiplayergames AT depalmanicholasbrian crowdsourcingrealworldhumanrobotdialogueandteamworkthroughonlinemultiplayergames AT breazealcynthialynn crowdsourcingrealworldhumanrobotdialogueandteamworkthroughonlinemultiplayergames |