Projects
|
The members of the team have a long-term experience in the design, implementation and evaluation of multimodal user interfaces and intelligent interactive systems and conducted projects for the EU, the BMBF, GIF and industries in this area. Examples include the EU-funded STREP ECIRCUS, the EU-funded IP CALLAS as well as the DFG-funded project CUBE-G. Furthermore, we are part of the EU-Network of Excellence HUMAINE (Human Machine Interaction Network on Emotions). The work is characterized by an interdisciplinary approach. Projects are usually conducted by an interdisciplinary team consisting of computer scientists, electro-engineers, media designers, cognitive psychologists. Our areas of interest include:
|
| Intuitive Interaction |
|
Our everyday environments become more and more equipped with computing power which is no longer concentrated in a single desktop box. Thus, it is indispensable to move away from traditional input devices, such as mouse or keyboard. It is our goal to enable the user to employ natural language interaction habits, such as gestures, gaze, mimics or speech, to communicate with complex systems. To ensure an intuitive interaction even for the inexperienced user, our lab focuses on multimodal input recognition and output generation including, for example, speech recognition and synthesis, computer vision, emotion recognition, and location-based interactions.
|
| |
|
| Virtual Characters |
The objective to develop more human-centered, personalized, and at the same time
more entertaining interfaces immediately leads to the metaphor of an embodied
conversational agent that employs gestures, mimics, and speech to communicate
with the human user. To ensure a believable flow of interaction, behaviour routines
of such agents should be based on socio-psychological models of human-human interaction.
Our lab investigates the use of such models, the generation and synchronization
of multimodal output as well as aspects of 3D rendering and animation. Within
the recently started EU-project e-Circus,
we are investigating the use of characters to support social and emotional learning
within Personal and Social Education (PSE). In the DFG-funded Project CUBE-G, we will investigate how to interpolate behaviors along different cultural dimensions resulting in a parameterized computational model for culture-specific generation of verbal and non-verbal behavior.
|
| |
|
| Affective Computing |
Can emotions be utilized as input for computer systems? Making use of physiological
information, such as the acoustic and prosodic features of speech, it becomes
possible, for example, to realize systems for call centres which deploy knowledge
on emotional user states to select appropriate conciliation strategies and to
decide whether or not to transfer the caller to a human agent. As part of the
EU-Network of Excellence HUMAINE
(Human Machine Interaction Network on Emotions) and the EU-funded IP CALLAS (Conveying Affectiveness in Leading-edge Living Adaptive Systems), the lab researches means for recognizing
and analyzing the emotional state of the user, taking it into account for communicative
decision-making processes, and using emotional cues from the system in the interaction
with the user.
|
| |
|
| Augmented Reality |
Exciting new experiences become possible by augmenting the real world with virtual
information, objects, and characters. Imagine yourself standing beside a virtual
character at a table where the character demonstrates the use of your newly bought
home appliance by pointing to and highlighting the buttons you have to press for
operating this device. To make this experience become real, a number of technical
challenges have to be met. Research question the lab engages in comprise, among
other things, the coordination between real and virtual moving objects, marker-based
and marker-less tracking techniques, which already led to the formation of a company
specialized in this area of expertise (http://www.inoptech.de).
|
| |
|
| Computer Graphics |
|
Many of the projects developed at our lab require the use of computer graphics. Augmented reality, virtual characters, all these techniques can make use of computer generated 3D graphics. At our lab we develope software and tools providing an easy way to integrate modern shader rendering into various different projects. Horde3D, the core of these tools, offers a lightweight conceptually clean solution to use OpenGL based computer graphics from nearly every programming or scripting language. On top of Horde3D tools like a scene and shader editor provide an intuitive way to create new graphical contents or effects for different applications.
|
| |
|
| Student Projects |
|
This category includes projects that were initiated by students at the University of Augsburg.
|
| |
|
| Further Projects |
|
|
| |
|
|
|
| |
|
