You are here

AURA – Ascertaining Un-Reported Affect

Award Information
Agency: Department of Defense
Branch: Defense Advanced Research Projects Agency
Contract: N10PC20171
Agency Tracking Number: 10SB1-0026
Amount: $148,992.00
Phase: Phase I
Program: SBIR
Solicitation Topic Code: SB101-002
Solicitation Number: 2010.1
Solicitation Year: 2010
Award Year: 2010
Award Start Date (Proposal Award Date): 2010-08-30
Award End Date (Contract End Date): 2011-05-01
Small Business Information
4515 Seton Center Parkway Suite 320
Austin, TX 78759
United States
DUNS: 158034665
HUBZone Owned: No
Woman Owned: Yes
Socially and Economically Disadvantaged: Yes
Principal Investigator
 Ann Vanderlaan
 Principal Investigator
 (512) 342-0010
Business Contact
 Irene Williams
Title: CEO
Phone: (512) 342-0010
Research Institution

Intelligent Tutoring Systems (ITSs) functions as virtual tutors that adapt to student responses. Such ITSs, however, do not yield student learning improvements equivalent to students tutored by human instructors. Ascertaining Un-Reported Affect (AURA) is a closed-loop, platform-independent “front-end” for informing ITSs with near real-time inferences of student engagement and affect during learning sessions to further improve student learning and minimize student frustration. AURA leverages low-cost, non-invasive sensors to monitor students without disrupting their learning experience. Such an approach enables the large-scale deployment of AURA to students using ITSs. The key innovation in AURA is the ability to serve as a modular component that informs an ITS of changes in a student’s emotional or physical state that can affect the learning process by leveraging audio, video, text, and user interface feedback. AURA Phase I includes preliminary experiments to demonstrate the feasibility of the approach, and concludes with the specification of a design for an Engineering prototype. AURA leverages 21st Century Technologies expertise developing systems for the military in speech and audio processing, modeling multiple-actor interactions in a decision space using Bayesian networks, and creating machine learning algorithms.

* Information listed above is at the time of submission. *

US Flag An Official Website of the United States Government