Address

Building 50.21

Adenauerring 4

D-76128 Karlsruhe

Germany

Dr.-Ing. Pascal Meißner

Phone: +49 (0)721 608 45942

Fax: +49 (0)721 608 45959

E-Mail: pascal(dot)meissner(at)kit(dot)edu

2011

R. Jäkel, P. Meißner, S. R. Schmidt-Rohr and R. Dillmann. Distributed generalization of learned planning models in robot programming by demonstration. In International Conference on Intelligent Robots and Systems, 2011.

S. R. Schmidt-Rohr, G. Dirschl, P. Meißner and R. Dillmann. A knowledge base for learning probabilistic decision making from human demonstrations by a multimodal service robot. In International Conference on Advanced Robotics, 2011.

P. Meißner, S. R. Schmidt-Rohr, M. Lösch, R. Jäkel and R. Dillmann. Robust localization of furniture parts by integrating depth and intensity data suitable for range sensors with varying image quality. In International Conference on Advanced Robotics, 2011.

2013

P. Meißner, R. Reckling, R. Jäkel, S. R. Schmidt-Rohr and R. Dillmann. Recognizing scenes with hierarchical implicit shape models based on spatial object relations for programming by demonstration. In International Conference on Advanced Robotics, 2013.

S. R. Schmidt-Rohr, F. Romahn, P. Meissner, R. Jäkel and R. Dillmann. Learning probabilistic decision making by a service robot with generalization of user demonstrations and interactive refinement. In Frontiers of Intelligent Autonomous Systems, 2013.

2012

R. Jäkel, Y. Xie, P. Meißner and R. Dillmann. Online-generation of task-dependent search heuristics to execute learned planning models in programming by demonstration. In International Conference on Humanoid Robots, 2012.

S. R. Schmidt-Rohr, F. Romahn, P. Meissner, R. Jäkel and R. Dillmann. Learning probabilistic decision making by a service robot with generalization of user demonstrations and interactive refinement. In International Conference on Intelligent Autonomous Systems, 2012.

2015

P. Meißner, F. Hanselmann, R. Jäkel, S. R. Schmidt-Rohr and R. Dillmann. Automated selection of spatial object relations for modeling and recognizing indoor scenes with hierarchical implicit shape models. In International Conference on Intelligent Robots and Systems, 2015. [video]

Active Scene Recognition (ASR) is an open source framework in which the core findings of my PhD research at the Chair of Prof. Dr.-Ing. R. Dillmann are implemented. The integrated system controlling a mobile robot is based on the Robot Operating System (ROS). Research contributions are designed as standalone libraries with ROS wrappers.

We are continuously publishing additional packages of this framework including documentation on their interfaces and tutorials.

We publish the source code on GitHub.

An overview on our documentation can be found in the ROS Wiki.

2016

P. Meißner, R. Schleicher, R. Hutmacher, S. R. Schmidt-Rohr and R. Dillmann. Scene Recognition for Mobile Robots by Relational Object Search using Next-Best-View Estimates from Hierarchical Implicit Shape Models. In International Conference on Intelligent Robots and Systems, 2016. [video]

Learning the Context in Programming by Demonstration of Manipulation Tasks. DFG - German Research Association, 2014 - 2018, Germany.

ECHORD++ experiment - DexBuddy (Dexterous Robotic Co-Worker). European Commission (EC), 2015 - 2016, European Union.

2014

P. Meißner, R. Reckling, V. Wittenbeck, S. R. Schmidt-Rohr and R. Dillmann. Active scene recognition for programming by demonstration using next-best-view estimates from hierarchical implicit shape models. In International Conference on Robotics and Automation, 2014. [video]

P. Meißner, S. R. Schmidt-Rohr, M. Lösch, R. Jäkel and R. Dillmann. Localization of furniture parts by integrating range and intensity data robust against depths with low signal-to-noise ratio. In Robotics and Autonomous Systems, 2014.