CHIL - Computers in the Human Interaction Loop

Type Start End
European Jan 2004 Jul 2007
Responsible URL
Josep R. Casas CHIL project page (CORDIS)

Reference

Computers in the Human Interaction Loop
Ref.: UE-IST, Integrated Project (IP) IST-2003-506909

Description

The aim of CHIL was to develop and explore a fundamental shift in the way we use computers. In contrast to building machines that have to be operated directly and explicitly (by keying in commands), CHIL target was to realize computer services that are delivered to humans in an implicit, indirect and unobtrusive way. CHIL frees people to interact with people and repositions machines to hover in the background, observing the humans and –like electronic butlers– attempt to anticipate and serve their needs. This concept was named CHIL, for  Computers in the Human Interaction Loop, since it aims to introduce Computers into a loop of Humans interacting with Humans, rather than condemning a human to operate in a loop of computers, forcing him/her to attend to and interact with an artefact on its artificial terms.

 

The following video was prepared by UPC in the context of the CHIL project to show the aim and some results from UPC contribution:

CHIL fosters new multi-modal communication paradigms, supporting in particular computer mediated Human-Human communication. CHIL services aim at providing implicit assistance requiring a minimum of human attention and disruptions, by observing the activities of users and guessing their intention. Fundamental research on specific areas such as robust speech recognition, vision analysis, data fusion, topic segmentation and summarization allowed CHIL to significantly advance the state-of-the-art in these disciplines with a direct impact on the multimodal interface community.

Innovative aspects: Provide computing services implicitly, by observing humans engaging & interacting with humans, and predicting and proactively providing services
Outcome: Reduce preoccupation with technological artifacts (techno-clutter). Improve productivity and human experience.
Scientific contributions: Full description and understanding of all human communication signals accross multiple modalities. Robustness in perceptual user interfaces, which are always on.

Publications

Canton-Ferrer C, Casas J, Pardàs M. Head Pose Detection based on Fusion of Multiple Viewpoint Information. In: Multimodal Technologies for Perception of Humans. Vol. 4122. Multimodal Technologies for Perception of Humans. Berlin / Heidelberg: Springer; 2007. pp. 305–310.
Neumann J, Casas J, Macho D, Ruiz-Hidalgo J. Multimodal Integration of Sensor Network. In: Proceedings of 3rd IFIP Conference on Artificial Intelligence Applications & Innovations. Proceedings of 3rd IFIP Conference on Artificial Intelligence Applications & Innovations. Athens, Greece: Springer; 2006. (401.58 KB)
Luque J, Morros JR, Garde A, Anguita J, Farrús M, Macho D, Marqués F, Martínez C, Vilaplana V, Hernando J. Audio, Video and Multimodal Person Identification in a Smart Room. In: Lecture notes in computer science - Multimodal Technologies for Perception of Humans. Vol. 4122. Lecture notes in computer science - Multimodal Technologies for Perception of Humans. ; 2006. pp. 258–269. (321.95 KB)
Neumann J, Casas J, Macho D, Ruiz-Hidalgo J. Multimodal Integration of Sensor Network. In: Artificial Intelligence Applications and Innovations. Vol. 204. Artificial Intelligence Applications and Innovations. Boston: Springer; 2006. pp. 312–323.
Canton-Ferrer C, Casas J, Pardàs M. Towards a Bayesian Approach to Robust Finding Correspondances in Multiple View Geometry Environments. In: Computational Science – ICCS 2005. Vol. 3515. Computational Science – ICCS 2005. Berlin / Heidelberg: Springer; 2005. pp. 281–289.

Pages