| NSF Org: |
IIS Division of Information & Intelligent Systems |
| Recipient: |
|
| Initial Amendment Date: | April 23, 2008 |
| Latest Amendment Date: | April 18, 2011 |
| Award Number: | 0747522 |
| Award Instrument: | Standard Grant |
| Program Manager: |
William Bainbridge
IIS Division of Information & Intelligent Systems CSE Directorate for Computer and Information Science and Engineering |
| Start Date: | April 15, 2008 |
| End Date: | March 31, 2015 (Estimated) |
| Total Intended Award Amount: | $500,000.00 |
| Total Awarded Amount to Date: | $516,000.00 |
| Funds Obligated to Date: |
FY 2011 = $16,000.00 |
| History of Investigator: |
|
| Recipient Sponsored Research Office: |
1156 HIGH ST SANTA CRUZ CA US 95064-1077 (831)459-5278 |
| Sponsor Congressional District: |
|
| Primary Place of Performance: |
1156 HIGH ST SANTA CRUZ CA US 95064-1077 |
| Primary Place of
Performance Congressional District: |
|
| Unique Entity Identifier (UEI): |
|
| Parent UEI: |
|
| NSF Program(s): | HCC-Human-Centered Computing |
| Primary Program Source: |
01001112DB NSF RESEARCH & RELATED ACTIVIT |
| Program Reference Code(s): |
|
| Program Element Code(s): |
|
| Award Agency Code: | 4900 |
| Fund Agency Code: | 4900 |
| Assistance Listing Number(s): | 47.070 |
ABSTRACT
The goal of this project is to enable novices (non-programmers and non-expert storytellers) to create interactive dramas (IDs), artificial intelligence (AI) based interactive story experiences with autonomous characters and dynamic plot progression. Accomplishing this goal requires answering the following research question: how can one incorporate storytelling and character creation theories from the theory of dramatic writing, as well as theories of storyboard layout from comics, into an AI model of story generation and character creation that collaborates with a human author to create an ID. Most research work in ID has focused on individual components, such as autonomous character architectures or story managers/generators, not on fully integrated systems with engaging content. This is primarily due to the difficulty of authoring; creating IDs currently requires large, interdisciplinary teams of AI researchers, story authors and domain experts. This project will address the authoring problem by combining novel work in story generation, novel work in visual interfaces for programming, and authoring insights from the only publicly fielded, complete ID (Facade).
Enabling novice authoring of ID will have significant impact: as a new and powerful mode of personal expression, in applications of ID technology to education and training, and for engaging middle school and high-school students in computational expression. Unlike traditional videogames, ID focuses on interpersonal interaction, enabling rich and powerful game-like experiences that focus on meaningful social interaction with autonomous characters within a dynamically generated, changing story. Such technology is essential for serious games (games for education and training) that focus on people-to-people interaction, such as management training, and public service games that tackle complex topics such as racism. Currently, the construction of IDs requires teams of experts, putting them out of reach of individuals and organizations who are not technology and game design experts, but who wish to harness this powerful new medium. The goal of the project is to take the construction of ID out of the hands of experts, and make it available to everyone.
PUBLICATIONS PRODUCED AS A RESULT OF THIS RESEARCH
Note:
When clicking on a Digital Object Identifier (DOI) number, you will be taken to an external
site maintained by the publisher. Some full text articles may not yet be available without a
charge during the embargo (administrative interval).
Some links on this page may take you to non-federal websites. Their policies may differ from
this site.
PROJECT OUTCOMES REPORT
Disclaimer
This Project Outcomes Report for the General Public is displayed verbatim as submitted by the Principal Investigator (PI) for this award. Any opinions, findings, and conclusions or recommendations expressed in this Report are those of the PI and do not necessarily reflect the views of the National Science Foundation; NSF has not approved or endorsed its content.
The goal of this project is to enable novice-authoring of artificial intelligence (AI)-based interactive narrative. Interactive narrative experiences have huge potential as a communicative medium. Psychological research has demonstrated the deeply persuasive power of narrative, including its ability to facilitate sense-making of complex situations. Interactive narrative enables a degree of personalization and agency that will significantly increase the communicative power of narrative.
Unfortunately, the authoring challenges for AI-driven interactive narrative have hindered the creation of such experiences, and prevented the field from fully exploring their communicative and pedagogical power. Creating such experiences currently requires interdisciplinary teams of AI researchers, story authors and domain experts. This project has developed tools and approaches to allow people who aren’t AI experts to create such experiences. The major tools and architectures created include CiF and Ensemble.
A common feature of most narratives is that they include multiple characters interacting socially. Enabling social characters in interactive narrative is a challenge for novice authors (and even expert authors) as there can be an extremely large number of possibilities arising from social interaction. This makes it intractable to author the possibilities manually, but modeling them computationally requires significant simulation and modeling skills. The CiF architecture provides a framework, with a graphical authoring tool, for creating casts of characters that have the simulated intelligence to socially interact. It was applied to the creation and release of a fully-produced experimental game which went on to be nominated for a number of design awards. This validated that the architecture can indeed support the complexity of creating compelling experiences. The architecture was then applied to a number of projects, including an educational simulation designed to teach cross-cultural communication skills and tolerance on the playground, and a simulation-based training experience for soldiers and police designed to teach how to make quick sense of novel cultural situations and engage in rapport and trust-building while maintaining safety in high-stakes environments. Based on what we learned from applying CiF design principles in multiple applications, we built a generalized version of the system called Ensemble for public release.
Last Modified: 06/23/2016
Modified by: Michael Mateas
Please report errors in award information by writing to: awardsearch@nsf.gov.
