Atman Kendira

The TATIN-PIC project: A multi-modal collaborative work environment for preliminary design

The recently launched TATIN-PIC Project at the University of Technology of Compiègne is a multi-modal collaborative work environment for teams performing preliminary design. In this paper, we present the design and reasoning for the plans of our groupware system. Effective preliminary design teamwork requires alternating stages of discussion, exploration, and diverging ideas, coupled with stages of focus, decision-making, and convergence. We believe providing a design team with an interactive tabletop can fulfill the first role and an interactive whiteboard can satisfy the second. Users will be able to switch seamlessly between the two, shifting content from one to the other when necessary. In this paper, we begin with a discussion of the advantages and characteristics of preliminary design. We continue with a review of the state-of-the-art in interactive, board-sized surfaces. We discuss experiments and results from TATIN, the precursory project to TATIN-PIC. Finally, we introduce our plans for an innovative work environment. Its multi-agent software architecture will be capable of supporting voice commands, tablets, smartphones, and personalized assistants capable of ontological reasoning about the project work.

Personal assistant agents and multi-agent middleware for CSCW

In recent years, there has been an increased interest for research on computer-supported cooperative work performed in collaborative interactive spaces. The TATIN-PIC project envisions a true multi-surface collaborative work environment with an interactive tabletop, an interactive board display, tablet PCs, and smartphones. In this paper, we first present the middleware based on a multi-agent architecture which use in our implementation, and then we detail how voice-controlled personal assistant agents can be implemented to provide unique interactions within a multi-surface environment.

Vocal interaction in collocated cooperative design

Using vocal interfaces in complex applications leads to more intuitive interactions. At the University of Technology of Compiègne, we have built a collaborative environment from a large graphics table, interactive board and peripheral devices for supporting preliminary cooperative design. The environment support unique multimodal interaction through intelligent personal assistant agents and this paper details the architecture and implementation of their vocal interfaces, as well as the multi-agent middleware, using two different multi-agent platforms.

Verbal and nonverbal communication for evaluating interactive spaces.

There exists a lack of comparative evaluations between interactive tabletops and their traditional counterparts due to the radically different nature of the two environments and the overly complex dynamics of collocated collaboration. We seek to address this gap in the literature with a preliminary comparative evaluation of the two paradigms. The most significant contribution of this work-in-progress is the application of an experimental coding scheme for categorizing both verbal and nonverbal communication, which allows for an effective comparison of group dynamics across the two conditions.

Ambiguity in Multimodal Interaction with Multi-touch Multi-user Graphics Tables

Graphics surfaces have a great potential for supporting cooperative work provided they can accommodate a large enough team. However, using large multi-user multi-touch tables leads to a problem of ambiguity as to know who is actually interacting with the table, since gestures are anonymous. This problem is even more severe when one introduces multimodal interaction for example through vocal channels. At UTC we have built a system including a large graphics table and peripheral devices for supporting preliminary cooperative design using multimodal interaction. The paper relates the ambiguity problems that we encountered and how we are trying to solve them.