Fachbereich Informatik

64-476 Oberseminar Technische Aspekte Multimodaler Systeme

Raum F-334
Zeit Dienstag 16 - 18 Uhr (c.t.)
Veranstalter Jianwei Zhang


01.04. Vorbesprechung und Terminvergabe

08.04. Adaptive Slicing-Algorithmen für low-cost 3D-Drucker mit mehreren Extrudern
Vortragender: Florens Wasserfall

15.04. "Objekt-Segmentierung und Registrierung aus Punktwolken unterschiedlicher Ansichten mit Hilfe eines Serviceroboters" und
"Vergleich unterschiedlicher Algorithmen zur 3D-Rekonstruktion eines Objektes aus mehreren fusionierten Punktwolken"
Vortragende: Nikolas Slottke und Hendrik Linne
Zusammenfassung: Two colloquiums about the students master thesis concerning active object segmentation, registration and reconstruction of 3D objects with the PR2. There are two seperate theses which are closely related in their topic.
Slides Segmentierung Nikolas Slottke (6.8 MB, PDF)

29.04. Echtzeit Objekt-Verfolgung mit aktiven Markern und Multi-Kamera-System
Vortragender: Johannes Schlundt
Zusammenfassung: The talk introduces the active-marker based multi-camera vision-system for robust object pose tracking designed and implemented by Johannes Schlundt as part of his BSc thesis.

06.05. prev. research
Vortragender: Huang Liangjun

13.05. Multi-sensory household object recognition and categorization by interactive learning
Vortragender: Haojun Guan

20.05. ????

27.05 An Hyperreality Imagination based Reasoning and Evaluation System (HIRES)
Vortragender: Sebastian Rockel
Zusammenfassung: This talk is a rehearsal for presenting a paper to be published.
In this work we ask whether an integrated system based on the concept of human imagination and realized as a hyperreal setup can improve system robustness and autonomy. In particular we focus on how non-nominal failures in a planning-based system can be detected before actual failure. To investigate, we integrated a system combining an accurate physics-based simulation, robust object recognition and a symbolic planner to achieve realistic prediction of robot actions. A Gazebo simulation was used to reason about and evaluate situations before and during plan execution. The simulation enabled re-planning to take place in advance of actual plan failure. We present a restaurant scenario in which our system prevents plan failure and successfully lets the robot serve a drink on a table cluttered with objects. The results give us confidence in our approach to improving situations where unavoidable abstractions of robot action planning meet the real world.

03.06. Robot-Era
Vortragender: Hannes Bistry

10.06. Pfingstferien

17.06. ???
Vortragender: Junhu He

24.06. ???
Vortragender: Denis Graf

01.07. ???
Vortragender: Weiwei Kong