You are here:: » Home » Team » Andrei Haidu

Andrei Haidu


				Research Staff
				Room:	2.81
				Tel:	–49 -421 218 64024
				Fax:	–49 -421 218 64047
				Mail:	haidu(at)uni-bremen[dot]de

I have joined the Institute for Artificial Intelligence from Universität Bremen in January 2014, after pursuing my Master's degree in Informatics at Technische Universität München (TUM). Before joining the group (2011 - 2014) I was a student research assistant at the Intelligent Autonomous Systems Group from TUM and latter at the Institute for Artificial Intelligence from Universität Bremen.

Research Topics

Artificial Intelligence
Commonsense and Naïve Physics Knowledge Representation
Knowledge Representation
Robot Simulation
Learning from Demonstrations
Physics-based Interaction in Virtual Reality

Projects

EASE DFG CRC
REFILLS EU project
SHERPA EU project
RoboHow EU project
ACAT EU project

Misc

github page
videos page
IROS21 slides
ICVS21 slides

Teaching

AI and Games (WS2014/15 - P[01]) (Project)
Gazebo Robotic Simulation Environment (SS2014 - S[76]) (Seminar)
AI and Games (SS2014 - S[57]) (Lecture Course)
Unreal Crash Course (SS2016 - S[96]) (Seminar)
Unreal Robots (WS2016/SS2017 - B[82]) (Bachelor project)
Unreal Robots (WS2017/SS2018- M[51]) (Master project)
Game Engines in AI (WS2019 - L) (Lecture Course)

Supervised Theses

Robotic Prospection in Cloud-Based Digital Twin Simulation (MSC Thesis, Xiaojun Lan, 2021)
Designing Human-controlled Robots in VR for Learning Everyday Manipulation Tasks (MSC Thesis, Zihe Xu, 2020)
Translating Symbolic Environments to Game Engines (BA Thesis, Björn Veit, 2019)
Learning RGB sensor models from virtual environments (BA Thesis, Jan Christian Mackenstein, 2019)
Mecanum Wheeled Robot Base Controller Simulation in Unreal Engine (BA Thesis, Patrick Kellmann, 2018)
Learning the Interpretation of Quantified Descriptions in Recipes from Multiplayer Games (BA Thesis, Fabian Kues, 2018)
Pragmatically Realistic Physics Based Grasping in Virtual Environments (BA Thesis, Marcel Meier, 2018)
Investigating the Realism of Full-body Motions Performed in Virtual Manipulation Tasks (BA Thesis, Johannes Bunk, 2018)
Crowdsourcing the Acquisition and Refinement of Task Specific Knowledge for Table Setting (BA Thesis, Alexander Wolff, 2017)
Simplified Effects Simulations for Stacking Objects in Virtual Environments (BA Thesis, David Brinkmann, 2017)
Photorealistic Rendering of Indoor Environments for Robot Perception (BA Thesis, Michael Sauerwein, 2017)

Publications

[1]

Minija Tamosiunaite, Mohamad Javad Aein, Jan Matthias Braun, Tomas Kulvicius, Irena Markievicz, Jurgita Kapociute-Dzikiene, Rita Valteryte, Andrei Haidu, Dimitrios Chrysostomou, Barry Ridge, Tomas Krilavicius, Daiva Vitkute-Adzgauskiene, Michael Beetz, Ole Madsen, Ales Ude, Norbert Krüger, Florentin Wörgötter, "Cut & recombine: reuse of robot action components based on simple language instructions", In The International Journal of Robotics Research, 2019. [bib] [doi]

[2]	Andrei Haidu, Xiaoyue Zhang, Michael Beetz, "Knowledge-enabled generation of semantically annotated image sequences of manipulation activities from VR demonstrations", In 13th International Conference on Computer Vision System (ICVS), Vienna, Austria, 2021. [bib] [doi]
[3]	Andrei Haidu, Michael Beetz, "Automated acquisition of structured, semantic models of manipulation activities from human VR demonstration", In IEEE International Conference on Robotics and Automation (ICRA), Xi'an, China, 2021. Finalist for Best Paper Award on Human-Robot Interaction [bib] [pdf]
[4]	Gayane Kazhoyan, Alina Hawkin, Sebastian Koralewski, Andrei Haidu, Michael Beetz, "Learning Motion Parameterizations of Mobile Pick and Place Actions from Observing Humans in Virtual Environments", In IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2020. [bib] [doi]
[5]	Andrei Haidu, Michael Beetz, "Automated Models of Human Everyday Activity based on Game and Virtual Reality Technology", In International Conference on Robotics and Automation (ICRA), Montreal, Canada, 2019. [bib] [pdf] [doi]
[6]	Fereshta Yazdani, Gayane Kazhoyan, Asil Kaan Bozcuoglu, Andrei Haidu, Ferenc Balint-Benczedi, Daniel Beßler, Mihai Pomarlan, Michael Beetz, "Cognition-enabled Framework for Mixed Human-Robot Rescue Team", In International Conference on Intelligent Robots and Systems (IROS), Madrid, Spain, 2018. [bib]
[7]	Andrei Haidu, Daniel Beßler, Asil Kaan Bozcuoglu, Michael Beetz, "KNOWROB-SIM — Game Engine-enabled Knowledge Processing for Cognition-enabled Robot Control", In International Conference on Intelligent Robots and Systems (IROS), Madrid, Spain, 2018. [bib] [pdf] [doi]
[8]	Michael Beetz, Daniel Beßler, Andrei Haidu, Mihai Pomarlan, Asil Kaan Bozcuoglu, Georg Bartels, "KnowRob 2.0 -- A 2nd Generation Knowledge Processing Framework for Cognition-enabled Robotic Agents", In International Conference on Robotics and Automation (ICRA), Brisbane, Australia, 2018. [bib] [pdf]
[9]	Andrei Haidu, Michael Beetz, "Action Recognition and Interpretation from Virtual Demonstrations", In International Conference on Intelligent Robots and Systems (IROS), Daejeon, South Korea, 2016. [bib] [pdf]
[10]	Michael Beetz, Daniel Beßler, Jan Winkler, Jan-H. Worch, Ferenc Balint-Benczedi, Georg Bartels, Aude Billard, Asil K. Bozcuoglu, Zhou Fang, Nadia Figueroa, Andrei Haidu, Hagen Langer, Alexis Maldonado, Ana-Lucia Pais, Moritz. Tenorth, Thiemo Wiedemeyer, "Open Robotics Research Using Web-based Knowledge Services", In International Conference on Robotics and Automation (ICRA), Stockholm, Sweden, 2016. [bib] [pdf]
[11]	Andrei Haidu, Daniel Kohlsdorf, Michael Beetz, "Learning Action Failure Models from Interactive Physics-based Simulations", In Proc. of IEEE/RSJ Int. Conf. on Intelligent Robots and Systems (IROS), Hamburg, Germany, 2015. [bib] [pdf]
[12]	Benjamin Walther-Franks, Jan Smeddinck, Peter Szmidt, Andrei Haidu, Michael Beetz, Rainer Malaka, "Robots, Pancakes, and Computer Games: Designing Serious Games for Robot Imitation Learning", In Human--Computer Interaction, Seul, Korea, 2015. [bib] [pdf]
[13]	Andrei Haidu, Daniel Kohlsdorf, Michael Beetz, "Learning Task Outcome Prediction for Robot Control from Interactive Environments", In Proc. of IEEE/RSJ Int. Conf. on Intelligent Robots and Systems (IROS), Chicago, USA, 2014. [bib] [pdf]
[14]	Lars Kunze, Andrei Haidu, Michael Beetz, "Acquiring task models for imitation learning through games with a purpose", In Proc. of IEEE/RSJ Int. Conf. on Intelligent Robots and Systems (IROS), pp. 102-107, 2013. [bib] [pdf]
[15]	Lars Kunze, Andrei Haidu, Michael Beetz, "Making Virtual Pancakes --- Acquiring and Analyzing Data of Everyday Manipulation Tasks through Interactive Physics-based Simulations", In Poster and Demo Track of the 35th German Conference on Artificial Intelligence (KI-2012), Saarbrücken, Germany, 2012. [bib] [pdf]

[16]	Michael Neumann, Andrei Haidu, Michael Beetz, "URoboSim — a simulation-based predictive modelling engine forcognition-enabled robot manipulation", In 2nd Embodied AI Workshop (CVPR), 2021. [bib] [pdf]