Welcome to the Institute for Artificial Intelligence!

The Institute for Artificial Intelligence (IAI) directed by Prof. Michael Beetz is part of the Faculty of Computer Science and member of the Center for Computing and Communication Technologies (TZI) at the University of Bremen.

openEASE video: Finalist for Fast Forward Science Community Award

We were excited to learn that our informative video about openEASE is one of the 21 finalists nominated for the Fast Forward Science Community Award. The German version of the video has been uploaded to YouTube and an can be voted for until the 31st of October:

https://www.youtube.com/watch?v=0NEhqwIuQl8

2017/10/11 12:56

Finalist Best Cognitive Robotics Award at IROS '17

We are happy to announce that our research paper

  • Multidimensional Time Series Shapelets Reliably Detect and Classify Contact Events in Force Measurements of Wiping Actions, Simon Stelter, Georg Bartels, and Michael Beetz

has been selected as a finalist for the best cognitive robotics award at IEEE IROS 2017.

2017/09/27 23:51

6 out of 200

We are pleased to announce that one of our team members was selected in the Kicking off the “6 Out Of 200” in the 5th Heidelberg Laureate Forum, September 24-29, 2017. Lisset Salinas Pinacho! expects “to get new ideas about my topic and other areas” and is looking forward to meeting Frederick Brooks, Jeffrey Dean, Barbara Liskov among many others at HLF17!. Please visit the following website for more information: https://scilogs.spektrum.de/hlf/6-200-lisset-salinas-pinacho-teaches-robots-cook/.

2017/09/06 14:00

Finalist at ICAR'17

We are pleased to announce that our joint paper with the Institute of Robotics and Mechatronics,DLR:

* Storing and Retrieving Perceptual Episodic Memories for Long-term Manipulation Tasks, Ferenc Balint-Benczedi, Zoltan-Csaba Marton, Maximilian Durner and Michael Beetz

has been selected as an ICAR 2017 best paper award finalist.

The paper presents a robotic perception system that generates perceptual episodic memories during the execution of a task. To allow easy retrieval of these memories we introduce an object and scene description language that serves as a layer of abstraction between the structure of the perception logs and the semantic interpretation of these. The description language can be used through a query interface to retrieve specific parts of the generated episodic memory. The purpose of the proposed system is two-fold: to enable on-line retrospection and specialized training of perception routines and to enable researchers to interactively explore perception results.

2017/06/14 14:28

DFG has approved funding for EASE

We are very happy that the Deutsche Forschungsgemeinschaft (DFG) has approved funding for the collaborative research center 'Everyday Activity Science and Engineering' (EASE). In EASE we will investigate the design, realization, and analysis of information processing models that enable robotic agents (and humans) to master complex human-scale manipulation tasks that are mundane and routine. EASE not only investigates action selection and control but also the methods needed to acquire the knowledge, skills, and competence required for flexible, reliable, and efficient mastery of these activities. Please visit the new EASE project website http://ease.informatik.uni-bremen.de/ for further information.

2017/05/26 15:10