Andreas Eitel
|
Albert-Ludwigs-Universität Freiburg |
About me
- Since 01/2021: Working at Geospin GmbH as a machine learning engineer for spatial intelligence.
- 06/2014 - 12/2020: Working at the Autonomous Intelligent Systems group of Prof. Dr. Wolfram Burgard and finished my PhD.
- 04/2014: Diploma in Mechanical Engineering.
- 09/2012 - 03/2013: Internship at Dr. Ing. h.c. F. Porsche AG, Department Driving Simulator.
- 08/2011 - 05/2012: Visiting student at the University of Oklahoma, USA, Department of Aerospace Engineering.
- 2007 - 2014: Studies in Mechanical Engineering with major in Mechatronics and Automatic Control at the University of Stuttgart, Germany.
Research Interests
- Object Recognition and Detection
- Deep Neural Networks
- Robotics Perception
- Robot Manipulation
Publications
-
Adaptive Curriculum Generation from Demonstrations for Sim-to-Real Visuomotor Control
Lukas Hermann, Max Argus, Andreas Eitel, Artemij Amiranashvili, Wolfram Burgard, Thomas Brox
International Conference on Robotics and Automation (ICRA), Paris, France, 2020
Download BibTeX Project Page -
Self-supervised Transfer Learning for Instance Segmentation through Physical Interaction
Andreas Eitel, Nico Hauff, Wolfram Burgard
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Macau, China, 2019
Download BibTeX Code -
Optimization Beyond the Convolution: Generalizing Spatial Relations with End-to-End Metric Learning
Philipp Jund, Andreas Eitel, Nichola Abdo, Wolfram Burgard
International Conference on Robotics and Automation (ICRA), Brisbane, Australia, 2018
Best Paper Award in Robot Vision
Preprint BibTeX Dataset -
Learning to Singulate Objects using a Push Proposal Network
Andreas Eitel, Nico Hauff, Wolfram Burgard
International Symposium on Robotics Research (ISRR), Puerto Varas, Chile, 2017
Preprint BibTeX Project Page -
From Plants to Landmarks: Time-invariant Plant Localization that uses Deep Pose Regression in Agricultural Fields
Florian Kraemer, Alexander Schaefer, Andreas Eitel, Johan Vertens, Wolfram Burgard
Workshop on Agri-Food Robotics, IEEE/RSJ Int. Conf. on Intelligent Robots and Systems (IROS), Vancouver, Canada, 2017
Download BibTeX Dataset -
Deep Detection of People and their Mobility Aids for a Hospital Robot
Andres Vasquez, Marina Kollmitz, Andreas Eitel, Wolfram Burgard
The European Conference on Mobile Robotics (ECMR), Paris, France, 2017
Preprint BibTeX Dataset -
The Freiburg Groceries Dataset
Philipp Jund, Nichola Abdo, Andreas Eitel, Wolfram Burgard
arXiv CoRR, 2016
Preprint BibTeX Dataset -
Choosing Smartly: Adaptive Multimodal Fusion for Object Detection in Changing Environments
Oier Mees, Andreas Eitel, Wolfram Burgard
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Deajeon, South Korea, 2016
Download BibTeX Project Page Dataset -
Multimodal Deep Learning for Robust RGB-D Object Recognition
Andreas Eitel, Jost Tobias Springenberg, Luciano Spinello, Martin Riedmiller, Wolfram Burgard
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Hamburg, Germany, 2015
Download arXiv BibTeX Code
Current Research Projects
- ALROMA- Autonomous Active Object Learning Through Robot Manipulation
Students (Co-)Supervised
- People Detection in RGB-D Data Using a Mixture of Deep Network Experts. 2015, Master's Project, Oier Mees (together with Luciano Spinello) Project page
- Hand Orientation Estimation Using Deep Neural Networks. 2015, Bachelor's Thesis, Lukas Hermann
- Body Part Segmentation using Fully Convolutional Neural Networks. 2015, Bachelor's Thesis, Claas Bollen (together with Daniel Kuhner and Gabriel Oliveira)
- Strategien für das Platzieren von Objekten auf der Basis einer Formklassifikation. 2015, Bachelor's Thesis, Nico Hauff (together with Christian Dornhege)
- 3D Object Recognition for Conveyor Systems 2016, Bachelor's Thesis, David Luibrand (at Sick AG )
- Real-Time People Perception for a Mobile Hospital Robot 2017, Master's Thesis, Andres Vasquez (together with Marina Kollmitz)
- Generalizing Spatial Relations with End-to-End Metric Learning 2017, Master's Project, Philipp Jund (together with Nichola Abdo and Tobias Springenberg)
- Semi-Supervised Learning for Real-World Object Recognition using Adversarial Autoencoders 2017, Master's Thesis, Sudhanshu Mittal (together with Maxim Tatarchenko)
- Policy Learning with Natural Gradient for Robot Manipulation 2018, Master's Project, Lukas Hermann
- Adaptive Curriculum Generation from Demonstrations 2019, Master's Thesis, Lukas Hermann (together with Max Argus and Artemij Amiranashvili)
Updates
- November 2020: I successfully defended my thesis and left the group to start working as a machine learning engineer at Geospin GmbH in Freiburg.
- July 2019: Our work on self-supervised instance segmentation learning through physical interaction got accepted for IROS'2019.
- June 2018: We received the Best Paper Award in Robot Vision at ICRA'2018 for our paper on spatial relations.
- December 2018: Our work on object singulation via pushing got accepted for ISRR'2017.
- November 2016: We made the Freiburg Groceries Dataset publicly available and published the corresponding article on arXiv.
- July 2016: Our work on adaptive sensor fusion for object detection got accepted for IROS'2016.
- Dezember 2015: Our work on RGB-D object recognition has been featured on CIO.com.
- July 2015: Our paper about RGB-D object recognition using deep convolutional neural networks got accepted for IROS'2015.
- November 2014: I will co-organize the new seminar Robot Learning which aims to combine the field of Robotics and Machine Learning, together with Wolfram, Nichola and Ayush.
- October 2014: I wil co-organize the lecture Robot Mapping together with Wolfram, Diego, Luciano and Mladen.