Oier Mees - Autonomous Intelligent Systems (original) (raw)

Info Albert-Ludwigs-Universität Freiburg Technische Fakultät Autonome Intelligente Systeme Georges-Köhler-Allee 080 D-79110 Freiburg i. Br., Germany Office: Building 80, Room 00-023 meeso@informatik.uni-freiburg.de Phone: +49 761 203-8023 Personal Website About me 10/2022 -03/2023: Research Intern, NVIDIA AI Robotics Research Lab. 01/2017 - 05/2023: Working at the Autonomous Intelligent Systems group headed by Prof. Dr. Wolfram Burgard as Ph.D. student 10/2013 - 10/2016: Master o.Sc. in Computer Science, University of Freiburg 2007 - 2013: Diploma in Computer Science, University of Basque Country, Spain Research Interests Robot Learning Self-Supervised/Unsupervised Learning Language Grounding Publications Preprints Chenguang Huang, Oier Mees, Andy Zeng, Wolfram Burgard NEW: Audio Visual Language Maps for Robot Navigation arXiv:2303.07522, 2023 Download BibTeX @article{huang23avlmaps, title={Audio Visual Language Maps for Robot Navigation}, author={Chenguang Huang and Oier Mees and Andy Zeng and Wolfram Burgard}, journal={arXiv preprint arXiv:2303.07522}, year={2023} } } Project Page Journal and Conference Papers Chenguang Huang, Oier Mees, Andy Zeng, Wolfram Burgard NEW: Visual Language Maps for Robot Navigation IEEE International Conference on Robotics and Automation (ICRA), London, UK, 2023 Download BibTeX @inproceedings{huang23vlmaps, title={Visual Language Maps for Robot Navigation}, author={Chenguang Huang and Oier Mees and Andy Zeng and Wolfram Burgard}, booktitle = {Proceedings of the IEEE International Conference on Robotics and Automation (ICRA)}, year={2023}, address = {London, UK} } Project Page Code Oier Mees*, Jessica Borja-Diaz*, Wolfram Burgard NEW: Grounding Language with Visual Affordances over Unstructured Data IEEE International Conference on Robotics and Automation (ICRA), London, UK, 2023 Finalist for the Best Paper Award in Robot Learning Download Code BibTeX @inproceedings{mees23hulc2, title={Grounding Language with Visual Affordances over Unstructured Data}, author={Oier Mees and Jessica Borja-Diaz and Wolfram Burgard}, booktitle = {Proceedings of the IEEE International Conference on Robotics and Automation (ICRA)}, year={2023}, address = {London, UK} } Project Page Dataset Erick Rosete-Beas*, Oier Mees*, Gabriel Kalweit, Joschka Boedecker, Wolfram Burgard NEW: Latent Plans for Task Agnostic Offline Reinforcement Learning Conference on Robot Learning (CoRL), Auckland, New Zealand, 2022 Download BibTeX Project Page Dataset Code Video @INPROCEEDINGS{rosete2022corl, author = {Erick Rosete-Beas and Oier Mees and Gabriel Kalweit and Joschka Boedecker and Wolfram Burgard}, title = {Latent Plans for Task Agnostic Offline Reinforcement Learning}, booktitle = {Proceedings of the 6th Conference on Robot Learning (CoRL)}, year = {2022}, address = {Auckland, New Zealand}, } Oier Mees*, Lukas Hermann*, Wolfram Burgard What Matters in Language Conditioned Robotic Imitation Learning over Unstructured Data IEEE Robotics and Automation Letters (RAL), 2022 Download BibTeX @article{mees2022hulc, author={Oier Mees and Lukas Hermann and Wolfram Burgard}, title = {What Matters in Language Conditioned Robotic Imitation Learning Over Unstructured Data}, journal={IEEE Robotics and Automation Letters (RA-L)}, volume={7}, number={4}, pages={11205-11212}, year={2022} } Project Page Dataset Code Oier Mees*, Lukas Hermann*, Erick Rosete-Beas, Wolfram Burgard CALVIN: A Benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Tasks IEEE Robotics and Automation Letters (RAL), 2022 2022 IEEE Robotics and Automation Letters Best Paper Award Download BibTeX @article{mees22calvin, author = {Oier Mees and Lukas Hermann and Erick Rosete-Beas and Wolfram Burgard}, title = {CALVIN - A Benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Tasks}, journal={IEEE Robotics and Automation Letters (RA-L)}, volume={7}, number={3}, pages={7327-7334}, year={2022} } Project Page Dataset Code Video Jessica Borja-Diaz*, Oier Mees*, Gabriel Kalweit, Lukas Hermann, Joschka Boedecker, Wolfram Burgard Affordance Learning from Play for Sample-Efficient Policy Learning IEEE International Conference on Robotics and Automation (ICRA), Philadelphia, USA, 2022 Download BibTeX Project Page Code Video @inproceedings{borja22icra, author = {Jessica Borja-Diaz and Oier Mees and Gabriel Kalweit and Lukas Hermann and Joschka Boedecker and Wolfram Burgard}, title = {Affordance Learning from Play for Sample-Efficient Policy Learning}, booktitle = {Proceedings of the IEEE International Conference on Robotics and Automation (ICRA)}, year = 2022, address = {Philadelphia, USA} } Oier Mees, Wolfram Burgard Composing Pick-and-Place Tasks By Grounding Language International Symposium on Experimental Robotics (ISER), La Valletta, Malta, 2021 Download BibTeX Project Page @inproceedings{mees21iser, author = {Oier Mees and Wolfram Burgard}, title = {Composing Pick-and-Place Tasks By Grounding Language}, booktitle = {Proceedings of the International Symposium on Experimental Robotics (ISER)}, url = {http://ais.informatik.uni-freiburg.de/publications/papers/mees21iser.pdf}, year = 2021, address = {La Valletta, Malta} } Iman Nematollahi, Oier Mees, Lukas Hermann, Wolfram Burgard Hindsight for Foresight: Unsupervised Structured Dynamics Models from Physical Interaction IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Las Vegas, USA, 2020 Download BibTeX Project Page Dataset Video Talk @inproceedings{nematoli20iros, author = {Iman Nematollahi and Oier Mees and Lukas Hermann and Wolfram Burgard}, title = {Hindsight for Foresight: Unsupervised Structured Dynamics Models from Physical Interaction}, booktitle = {Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)}, year = 2020, url = {http://ais.informatik.uni-freiburg.de/publications/papers/nematoli20iros.pdf}, address = {Las Vegas, USA} } Oier Mees*, Markus Merklinger*, Gabriel Kalweit, Wolfram Burgard Adversarial Skill Networks: Unsupervised Robot Skill Learning from Video IEEE International Conference on Robotics and Automation (ICRA), Paris, France, 2020 Finalist for the Best Paper Award in Cognitive Robotics Download BibTeX Project Page Dataset Code Video Talk @INPROCEEDINGS{mees20icra_asn, author = {Oier Mees and Markus Merklinger and Gabriel Kalweit and Wolfram Burgard}, title = {Adversarial Skill Networks: Unsupervised Robot Skill Learning from Videos}, booktitle = {Proceedings of the IEEE International Conference on Robotics and Automation (ICRA)}, year = 2020, url = {http://ais.informatik.uni-freiburg.de/publications/papers/mees20icra\_a.pdf} address = {Paris, France} } Oier Mees*, Alp Emek*, Johan Vertens, Wolfram Burgard Learning Object Placements For Relational Instructions by Hallucinating Scene Representations IEEE International Conference on Robotics and Automation (ICRA), Paris, France, 2020 Download BibTeX Project Page Dataset Video Talk @INPROCEEDINGS{mees20icra_placements, author = {Oier Mees and Alp Emek and Johan Vertens and Wolfram Burgard}, title = {Learning Object Placements For Relational Instructions by Hallucinating Scene Representations}, booktitle = {Proceedings of the IEEE International Conference on Robotics and Automation (ICRA)}, year = 2020, url = {http://ais.informatik.uni-freiburg.de/publications/papers/mees20icra\_b.pdf} address = {Paris, France} } Oier Mees, Maxim Tatarchenko, Thomas Brox, Wolfram Burgard Self-supervised 3D Shape and Viewpoint Estimation from Single Images for Robotics IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Macao, China, 2019 Download BibTeX Code Video @INPROCEEDINGS{mees19iros, author = {Oier Mees and Maxim Tatarchenko and Thomas Brox and Wolfram Burgard}, title = {Self-supervised 3D Shape and Viewpoint Estimation from Single Images for Robotics}, booktitle = {Proceedings of the International Conference on Intelligent Robots and Systems (IROS)}, year = 2019, address = {Macao, China} } Wolfram Burgard,Abhinav Valada,Noha Radwan,Tayyab Naseer,Jingwei Zhang,Johan Vertens,Oier Mees,Andreas Eitel,Gabriel Oliveira Perspectives on Deep Multimodel Robot Learning Proceedings of the International Symposium on Robotics Research (ISRR), Puerto Varas, Chile, 2017. Download BibTeX @INPROCEEDINGS{Burgard_2017_isrr, author = Wolfram Burgard, Abhinav Valada, Noha Radwan, Tayyab Naseer, Jingwei Zhang, Johan Vertens, Oier Mees, Andreas Eitel, and Gabriel Oliveira, title = Perspectives on Deep Multimodel Robot Learning, booktitle = Proceedings of the International Symposium on Robotics Research (ISRR), month = December, year = 2017, } Oier Mees, Nichola Abdo, Mladen Mazuran, Wolfram Burgard Metric Learning for Generalizing Spatial Relations to New Objects IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Vancouver, Canada, 2017 Download BibTeX Project Page Dataset Code Video @INPROCEEDINGS{mees17iros, author = {Oier Mees and Nichola Abdo and Mladen Mazuran and Wolfram Burgard}, title = {Metric Learning for Generalizing Spatial Relations to New Objects}, booktitle = {Proceedings of the International Conference on Intelligent Robots and Systems (IROS)}, year = 2017, address = {Vancouver, Canada}, url = {http://ais.informatik.uni-freiburg.de/publications/papers/mees17iros.pdf}, } Oier Mees, Andreas Eitel, Wolfram Burgard Choosing Smartly: Adaptive Multimodal Fusion for Object Detection in Changing Environments IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Deajeon, South Korea, 2016 Download BibTeX Project Page Demo Dataset Code @INPROCEEDINGS{mees16iros, author = {Oier Mees and Andreas Eitel and Wolfram Burgard}, title = {Choosing Smartly: Adaptive Multimodal Fusion for Object Detection in Changing Environments}, booktitle = {Proceedings of the International Conference on Intelligent Robots and Systems (IROS)}, year = 2016, address = {Daejeon, South Korea}, url = {http://ais.informatik.uni-freiburg.de/publications/papers/mees16iros.pdf}, _} Workshop Papers Oier Mees*, Lukas Hermann*, Wolfram Burgard What Matters in Language Conditioned Robotic Imitation Learning over Unstructured Data Workshop on Overlooked Aspects of Imitation Learning: Systems, Data, Tasks, and Beyond at RSS, 2022 Download BibTeX @inproceedings{hulc22, author = {Oier Mees and Lukas Hermann and Wolfram Burgard}, title = {What Matters in Language Conditioned Robotic Imitation Learning over Unstructured Data}, booktitle = {Workshop on Overlooked Aspects of Imitation Learning: Systems, Data, Tasks, and Beyond at RSS}, year = {2022}, } Project Page Code Oier Mees and Wolfram Burgard Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Tasks RSS Pioneers at Robotics: Science and Systems (RSS), New York, USA, 2022 Download BibTeX @INPROCEEDINGS{mees22rsspi, author = {Oier Mees and Wolfram Burgard}, title = {Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Tasks}, booktitle = {Proc.~of RSS Pioneers at Robotics: Science and Systems (RSS)}, year = 2022, address = {New York, USA} } Jessica Borja-Diaz*, Oier Mees*, Gabriel Kalweit, Lukas Hermann, Joschka Boedecker, Wolfram Burgard Affordance Learning from Play for Sample-Efficient Policy Learning Workshop on Robot Learning: Self-Supervised and Lifelong Learning at NeurIPS, 2021 Download BibTeX Project Page @INPROCEEDINGS{borja21neurips, author = {Jessica Borja-Diaz and Oier Mees and Gabriel Kalweit and Lukas Hermann and Joschka Boedecker and Wolfram Burgard}, title = {Affordance Learning from Play for Sample-Efficient Policy Learning}, booktitle = {Workshop on Robot Learning: Self-Supervised and Lifelong Learning at NeurIPS}, year = 2021, address = {Virtual} } Oier Mees*, Markus Merklinger*, Gabriel Kalweit, Wolfram Burgard Adversarial Skill Networks: Unsupervised Robot Skill Learning from Video Workshop on Learning from Unlabeled Videos at IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, USA, 2020 Download BibTeX @INPROCEEDINGS{mees20icra_asn, author = {Oier Mees and Markus Merklinger and Gabriel Kalweit and Wolfram Burgard}, title = {Adversarial Skill Networks: Unsupervised Robot Skill Learning from Videos}, booktitle = {Proceedings of the IEEE International Conference on Robotics and Automation (ICRA)}, year = 2020, address = {Paris, France} } Workshop on Combining Learning and Reasoning – Towards Human-Level Robot Intelligence at Robotics: Science and Systems (RSS), Freiburg, Germany, 2019 Download BibTeX @INPROCEEDINGS{mees19rss, author = {Markus Merklinger and Oier Mees and Gabriel Kalweit and Wolfram Burgard}, title = {Adversarial Skill Networks: Unsupervised Skill Learning from Video}, booktitle = {Workshop on Combining Learning and Reasoning – Towards Human-Level Robot Intelligence at Robotics: Science and Systems (RSS)}, year = 2019, address = {Freiburg, Germany}, } Iman Nematollahi, Oier Mees, Lukas Hermann, Wolfram Burgard Hindsight for Foresight: Unsupervised Structured Dynamics Models from Physical Interaction Workshop on Structured Approaches to Robot Learning for Improved Generalization at Robotics: Science and Systems (RSS), 2020 Download BibTeX @INPROCEEDINGS{nematoli20rss, author = {Iman Nematollahi and Oier Mees and Lukas Hermann and Wolfram Burgard}, title = {Hindsight for Foresight: Unsupervised Structured Dynamics Models from Physical Interaction}, booktitle = {Workshop on Structured Approaches to Robot Learning for Improved Generalization at Robotics: Science and Systems (RSS)}, year = {2020} } Workshop on Machine Learning in Planning and Control of Robot Motion at IEEE International Conference on Robotics and Automation (ICRA), Paris, France, 2020 Download BibTeX @INPROCEEDINGS{nematoli20icra, author = {Iman Nematollahi and Oier Mees and Lukas Hermann and Wolfram Burgard}, title = {Hindsight for Foresight: Unsupervised Structured Dynamics Models from Physical Interaction}, booktitle = {Workshop on Machine Learning in Planning and Control of Robot Motion at IEEE International Conference on Robotics and Automation (ICRA)}, year = {2020}, address = {Paris, France} } Oier Mees, Andreas Eitel, Wolfram Burgard Adaptive Sensor Fusion for RGB-D Object Detection Deutsche Gesselschaft für Robotik - Tage 2016 (DGR-Tage 2016), Leipzig, Germany, 2016 Download BibTeX Project Page Demo Dataset Code @INPROCEEDINGS{mees16dgr, author = {Oier Mees and Andreas Eitel and Wolfram Burgard}, title = {Adaptive Sensor Fusion for RGB-D Object Detection}, booktitle = {Proceedings of the Deutsche Gesellschaft für Robotik - Tage 2016}, year = 2016, address = {Leipzig, Germany}, } Courses International Computer Vision Summer School (ICVSS) 2018, Sicily, Italy Research Projects OML, Organic Machine Learning STAMINA Demos, Datasets & Code Visual Language Maps for Robot Navigation Grounding Language with Visual Affordances over Unstructured Data Task Agnostic Offline Reinforcement Learning Hierarchical Universal Language Conditioned Policies Visual Affordances for Sample-Efficient Policy Learning Language Conditioned Policy Learning for Long-Horizon Robot Manipulation Tasks Unsupervised Robot Skill Learning from Video Teaching Robots To Generalize Spatial Relations Deep Adaptive Multimodal Fusion Teaching Deep Learning Lab, SS 2021 Deep Learning Lab, SS 2020 Proseminar Robot Navigation, WS 2019 Deep Learning for Autonomous Driving, SS 2018 Proseminar: KI im Alltag, WS 2018 Introduction to Mobile Robotics, SS 2017 Sep 2023 I have joined Prof. Sergey Levine's lab at UC Berkeley as a PostDoc. June 2023 We won the 2022 IEEE Robotics and Automation Letters Best Paper Award for CALVIN: A Benchmark for Language-conditioned Policy Learning for Long-horizon Robot Manipulation Tasks! May 2023 I successfully defended my PhD thesis (summa cum laude)! May 2023 Our paper on Grounding Language with Visual Affordances over Unstructured Data has been nominated for the Best Paper Award in Robot Learning at ICRA 2023! Apr 2023 I have received the 2023 AI Newcomer award by the German Federal Ministry of Education and Research and the German Informatics Society in the Technical and Engineering Sciences category! Mar 2023 New preprint for our latest collaboration with Google Research Audio Visual Language Maps for Robot Navigation. Jan 2023 I have been nominated for the 2023 AI Newcomer award by the German Federal Ministry of Education and Research and the German Informatics Society! If you have time, please support me by voting via http://bit.ly/3XWVaF8 Jan 2023 Two papers accepted for ICRA 2023 Visual Language Maps for Robot Navigation and Grounding Language with Visual Affordances over Unstructured Data. Oct 2022 New preprint for our latest collaboration with Google Research Visual Language Maps for Robot Navigation. Oct 2022 New preprint Grounding Language with Visual Affordances over Unstructured Data. Sep 2022 One new paper on task agnostic offline reinforcement learning accepted at CoRL 2022. Sep 2022 I am co-organizing the Workshop on Language and Robot Learning at CoRL 2022. July 2022 Two new papers accepted for RA-L with IROS 2022 presentation in Kyoto, Japan. CALVIN and HULC. May 2022 I have been selected as part of the 2022 cohort for RSS Pioneers which will be held in conjunction with Robotics: Science and Systems 2022 April 2022 New preprint What Matters in Language Conditioned Robotic Imitation Learning. February 2022 I am co-organizing an ICRA workshop on Scaling Robot Learning together with Andy Zeng, Raia Hadsell, Roberto Calandra, Danica Kragic, Serena Ivaldi and Wolfram Burgard. The submission deadline will be in April 2022! February 2022 One new paper accepted for ICRA 2022. December 2021 New preprint CALVIN: A Benchmark for Language-conditioned Policy Learning for Long-horizon Robot Manipulation Tasks. November 2021 Our work on leveraging visual affordances for efficient policy learning has been accepted for NeurIPS 2021 workshop on Robot Learning. March 2021 I am happy to co-organize an ICRA workshop on Semantic Representations for Robotics through Continuous Interaction and Incremental Learning together with Tamim Asfour and Wolfram Burgard. November 2020 One new paper accepted for ISER 2021. August 2020 One new paper accepted for IROS 2020. May 2020 Our paper on unsupervised skill learning from video has been nominated for the Best Paper Award in Cognitive Robotics at ICRA! March 2020 I am co-organizing an RSS workshop on Self-supervised Robot Learning together with Wolfram Burgard, Anelia Angelova, Joschka Boedecker and Abhinav Valada. The submission deadline will be in April 2020! February 2020 Our work on hallucinating scene representations to enable a robot to place objects from speech instructions has been featured on TechXplore. February 2020 Two new papers accepted for ICRA 2020.