Teaching at KBSG
Our sound localization framework should be adapted to speech signals to enhance human-machine interaction. In order to do this, the system should be able to distinguish between speech signals and ambient noise. Currently, the whole sound mixture that is captured by the microphones is taken into account to establish the sound localization map.
Submitted by Tom Goeckel on 10. January 2011 - 15:18 categories [ ]
To simulate the filtering processes of the cochlea a digital signal should be segregated into an arbitrary number of narrowband signals. In subsequent stages, the software should be able to process the narrowband signals in real time. This requires a high degree of parallelism that is unsufficiently supported by currently available CPUs.
Submitted by Tom Goeckel on 10. January 2011 - 12:04 categories [ ]
Knowledge Representation (KR) is a vibrant and exciting field in artificial intelligence. The endeavor rests on two fundamental ideas. First, to reason about the problem domain one must formalize it, perhaps in some logical formalism such as propositional logic or first-order logic. Second, for the representation to be useful one must be able to obtain reasonable and intuitive inferences in a timely fashion.
Unfortunately, propositional reasoning is intractable (Boolean reasoning is NP-COMPLETE) and first-order logic is undecidable. Thus, an important goal in the KR enterprise is to find a tradeoff be- tween the expressiveness of the representational language and the computational behavior of associated reasoning tasks. A main objective of this seminar is to discuss approaches bordering this tradeoff.
Submitted by vaishakbelle on 4. January 2011 - 17:11 categories [ ]
Die Veranstaltung ist eine der von der Fachgruppe Informatik seit dem Wintersemester 2001/2002 angebotenen Einführungsvorlesungen für Hörer aller Fakultäten:
Submitted by stf on 6. October 2010 - 8:34 categories [ ]
Submitted by Jens Claßen on 5. October 2010 - 16:26 categories [ ]
[This topic has already been assigned.]
In Domestic Service Robotics (DSR) human-robot interaction has to be as natural as possible since the robot should be easily operable even by laymen. Spoken language is a feasible means to do so but commands issued to a robot are often ill-formed or incomplete. The goal is to develop a system that is capable of successfully interpreting such commands.
Submitted by stf on 2. September 2010 - 15:44 categories [ ]
An announcement of the course can soon be found in the course information system CAMPUS.
Submitted by stf on 11. June 2010 - 13:36 categories [ ]
Robots that operate in human environments need to be able to detect and preferably also track humans around them by using all of their sensory capabilities.
The objective of this thesis is to develop and implement a system that allows a robot to detect and track person using several different modalities such as a laser range finder and a sound source localization.
Submitted by stf on 8. March 2010 - 8:26 categories [ ]
Based on Visual Hand Recognition the task is to develop and implement a system to recognize known (and possibly also define new) simple gestures meant to be used as commands issued to a robot.
Submitted by stf on 12. February 2010 - 19:22 categories [ ]
The second exam of the course "Introduction to Artificial Intelligence" in WS 2009/2010 will be on 24th March 2010 at 10:00h. Students in the programmes Informatik (Diplom), Informatik (vorgezogene Masterprüfung) and Automatisierungstechnik (Master) had to register via a webform. The list of registered students can be found here. A list of students who registered via ZPA is available here.
It takes place in the lecture halls AH II and AH III. Please distribute as follows:
Submitted by Jens Claßen on 19. January 2010 - 14:47 categories [ ]