Persönlicher Status und Werkzeuge

Home People Daniel Nyga

About

I have moved to the Institute for Artificial Intelligence, University of Bremen. My new contact data can be found here:http://ai.uni-bremen.de/team/daniel_nyga

Before I joined the Intelligent Autonomous Systems Group I studied Computer Science at TUM. I'm currently working on the import of knowledge from the world wide web into the knowledge base of our mobile robots. In particular, my current research focuses on understanding natural-language, in order to enable a robot to autonomously acquire new high-level skills by querying web pages such as eHow.com or wikiHow.com.

My work aims at building up action-specific knowledge bases from various knowledge sources, such as natural language, interactive computer games, observations of humans performing everyday activity or experience data of a robot:

Knowledge about actions and objects is represented as Probabilistic Robot Action Cores (PRAC), which can be thought of generic event patterns that enable a robot to infer important information that is missing in an original natural-language instruction. PRAC models are represented in Markov Logic Networks, a powerful knowlegde represenation formalism combing first-order logic and probability theory.

If you are interested in a student project in any of the above topics, please contact me via E-Mail or just drop into my office.

Fields of Interest

  • Artificial Intelligence/Knowledge Processing
  • Machine Learning
  • Statistical Relational Learning
  • Data Mining/Knowledge Discovery
  • Automated Learning/Understanding of WWW information
  • Natural-Language Understanding

Teaching

  • Technical Cognitive Systems (Tutorial) (SS2012)
  • Techniques in Artificial Intelligence (Tutorial) (WS2011/12)
  • Discrete Probability Theory (Tutorial) (SS2011)

Supervised Theses

  • Web-enabled Learning of Models for Word Sense Disambiguation (Bachelor Thesis, Stephan Epping)

Publications

Journal Articles and Book Chapters

RoboSherlock: Unstructured Information Processing Framework for Robotic Perception (Michael Beetz, Ferenc Bálint-Benczédi, Nico Blodow, Christian Kerl, Zoltán-Csaba Márton, Daniel Nyga, Florian Seidel, Thiemo Wiedemeyer, Jan-Hendrik Worch), In Handling Uncertainty and Networked Structure in Robot Control (Lucian Busoniu, Levente Tamás, eds.), Springer International Publishing, 2015. [bib] [doi]

Conference Papers

RoboSherlock: Unstructured Information Processing for Robot Perception (Michael Beetz, Ferenc Balint-Benczedi, Nico Blodow, Daniel Nyga, Thiemo Wiedemeyer, Zoltan-Csaba Marton), In IEEE International Conference on Robotics and Automation (ICRA), 2015. (Best Service Robotics Paper Award) [bib]
Everything Robots Always Wanted to Know about Housework (But were afraid to ask) (Daniel Nyga, Michael Beetz), In 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2012. [bib] [pdf]
How-Models of Human Reaching Movements in the Context of Everyday Manipulation Activities (Daniel Nyga, Moritz Tenorth, Michael Beetz), In IEEE International Conference on Robotics and Automation (ICRA), 2011. [bib] [pdf]
Understanding and Executing Instructions for Everyday Manipulation Tasks from the World Wide Web (Moritz Tenorth, Daniel Nyga, Michael Beetz), In IEEE International Conference on Robotics and Automation (ICRA), 2010. [bib] [pdf]

Other Publications

Understanding and Executing Instructions for Everyday Manipulation Tasks from the World Wide Web (Moritz Tenorth, Daniel Nyga, Michael Beetz), Technical report, IAS group, Technische Universität München, Fakultät für Informatik, 2009. [bib] [pdf]
Powered by bibtexbrowser
Export as PDF or BIB

Last edited 03.03.2014 12:06 by nyga