Agents in Augmented Reality Interfaces

The technical sophistication of animated pedagogical agents has progressed rapidly. Steve, a 3D animated agent, caninteract with learners in individual and team scenarios (Rickel and Johnson 1998). PPP Persona is able to generatetutorial presentations of Web-based learning materials (André et al 1998). Cosmo is able to generate critiques andexplanations using a combination of speech and emotive gestures (Towns et al 1998). Early empirical results show thatthese agents can enhance the learning experience and improve its effectiveness (Lester et al 1997). See http://www.ssgrr.it/en/ssgrr2000/papers/188_2.pdf

Persona Project (Digital Parrot One: i.e. PDP1, or Peedy the Parrot)

Peedy indicating a misrecognition

Each time Peedy receives a spoken input, he responds with a combination of visual and audio output. All camera control and movement variability must be hand authored. Authoring effort required to produce new animation sequences (defining character motion, camera control, sound effects, and pre-recorded speech) is much higher than expected.

Bob

(Microsoft. Microsoft Bob. Redmond, WA, 1995)

The guide communicates to the user through speech balloons which present a small group of buttons for the operations most likely to be used next. User studies with Bob have verified that for many people, the social metaphor reduces the anxiety associated with computer use.

CSLU ToolKit & Baldi: „UNIVERSAL SPEECH TOOLS: THE CSLU TOOLKIT“

http://mambo.ucsc.edu

http://www.cse.ogi.edu/cslu)

http://cslu.cse.ogi.edu/toolkit/index.html

ALIVE

A project, which situates a human in a virtual 3D environment with animated characters. The resulting image is projected onto a large screen which faces the user and acts as a type of “magic mirror” (see figure): the user sees herself surrounded by objects and agents. [Maes et al., 1995]

SAM – screen based agent that interacts with the real world

http://gn.www.media.mit.edu/groups/gn/projects/castlemate/

Jack (University of Pennsylvania)

Justine Cassell, Catherine Pelachaud, Norman Badler, and Mark Steedman, at the University of Pennsylvania Center for Human Modeling and Simulation have taught Jack how to converse.

C. Phillips and N. I. Badler. "Jack: A toolkit for manipulating articulated figures," ACM/SIGGRAPH Symposium on User Interface Software, Banff, Canada, October 1988, pp. 221-229.

P. Lee, C. Phillips, E. Otani and N. I. Badler. "The Jack interactive human model," Concurrent Engineering of Mechanical Systems, Vol. 1, First Annual Symposium on Mechanical Design in a Concurrent Engineering Environment, Univ. of Iowa, Iowa City, IA, October 1989, pp. 179-198.