people:agostini
Differences
This shows you the differences between two versions of the page.
| Both sides previous revision Previous revision Next revision | Previous revision | ||
|
people:agostini [2022/04/19 12:42] Alejandro Agostini |
people:agostini [2024/09/21 11:12] (current) Alejandro Agostini |
||
|---|---|---|---|
| Line 2: | Line 2: | ||
| ===== Alejandro Agostini ===== | ===== Alejandro Agostini ===== | ||
| - | ==== Senior Postdoc - PI Austrian Science Fund (FWF) project ==== | + | ==== PI Austrian Science Fund (FWF) project ==== |
| Office: T12 (ICT) 3N07\\ | Office: T12 (ICT) 3N07\\ | ||
| Line 12: | Line 12: | ||
| === Short Biography === | === Short Biography === | ||
| - | + | * Since 2019. Principal Investigator. Austrian Science Fund (FWF) projects. University of Innsbruck, Austria. | |
| - | * Since 2019. Principal Investigator. Austrian Science Fund (FWF) project. University of Innsbruck, Austria. | + | |
| * 2019-2021. Group Leader. Department of Electrical and Computer Engineering, Technical University of Munich, Germany. | * 2019-2021. Group Leader. Department of Electrical and Computer Engineering, Technical University of Munich, Germany. | ||
| * 2011-2018. Group Leader. Bernstein Center for Computational Neuroscience, University of Göttingen, Germany. | * 2011-2018. Group Leader. Bernstein Center for Computational Neuroscience, University of Göttingen, Germany. | ||
| Line 27: | Line 26: | ||
| === Research Interests === | === Research Interests === | ||
| - | My current field of research covers machine learning in robotics, robotic perception and manipulation, task and motion planning, reinforcement learning, and robotic cognitive architectures. | + | My current field of research covers machine learning in robotics, combined task and motion planning, reinforcement learning, and cognitive systems for life science applications. |
| === Projects === | === Projects === | ||
| - | + | * **ABSTRACTRON** (EUREGIO Project). Conceptual Abstraction in Humans and Robots. 2024 - 2027. | |
| - | * **SEAROCO** (Lise Meitner FWF Project). Seamless Levels of Abstraction for Robot Cognition. 2019 - 2023. | + | * [[https://doi.org/10.55776/P36965|PURSUIT]] (Principal Investigator FWF Project). Purposeful Signal-symbol Relations for Manipulation Planning. 2023 - 2026. |
| + | * [[https://doi.org/10.55776/M2659|SEAROCO]] (Lise Meitner FWF Project). Seamless Levels of Abstraction for Robot Cognition. 2019 - 2023. | ||
| * **ALAIVE** (Innovation Project - SNIC). Automatic Control of Living Systems using Artificial Intelligence and Advanced Sensing. 2018 - 2019. | * **ALAIVE** (Innovation Project - SNIC). Automatic Control of Living Systems using Artificial Intelligence and Advanced Sensing. 2018 - 2019. | ||
| * **RECONCELL** (FoF EU Project). A Reconfigurable Robot Work-cell for Fast Set-up of Automated Assembly Processes in SMEs. 2015 - 2019. | * **RECONCELL** (FoF EU Project). A Reconfigurable Robot Work-cell for Fast Set-up of Automated Assembly Processes in SMEs. 2015 - 2019. | ||
| Line 48: | Line 48: | ||
| * Advanced Seminar Autonomous System. Technical University of Munich. WS 2019-2020. SoSe 2020. | * Advanced Seminar Autonomous System. Technical University of Munich. WS 2019-2020. SoSe 2020. | ||
| * Project Laboratory Human-centered Robotics. Technical University of Munich. WS 2019-2020. | * Project Laboratory Human-centered Robotics. Technical University of Munich. WS 2019-2020. | ||
| + | * Mathematics II. National University of Entre Ríos, Argentina. SoSe and WS 1997. | ||
| Line 54: | Line 55: | ||
| **Journal Articles** | **Journal Articles** | ||
| + | - Paulius*, D., Agostini*, A., Lee, D. (2023). [[https://arxiv.org/pdf/2207.05800.pdf|Long-Horizon Task and Motion Planning with Functional Object-Oriented Networks.]] (*) Co-first author. IEEE Robotics and Automation Letters, 8(8), 4513-4520. DOI: 10.1109/LRA.2023.3285510. | ||
| - Agostini, A., Saveriano, M., Lee, D., Piater, J. (2020). [[https://mediatum.ub.tum.de/1550910?show_id=1576183|Manipulation Planning Using Object-Centered Predicates and Hierarchical Decomposition of Contextual Actions.]] IEEE Robotics and Automation Letters, 5(4), 5629-5636. DOI: 10.1109/LRA.2020.3009063. | - Agostini, A., Saveriano, M., Lee, D., Piater, J. (2020). [[https://mediatum.ub.tum.de/1550910?show_id=1576183|Manipulation Planning Using Object-Centered Predicates and Hierarchical Decomposition of Contextual Actions.]] IEEE Robotics and Automation Letters, 5(4), 5629-5636. DOI: 10.1109/LRA.2020.3009063. | ||
| - Lüddecke, T., Agostini, A., Fauth, M., Tamosiunaite, M., Wörgötter, F. (2019). [[https://doi.org/10.1016/j.artint.2018.12.009|Distributional Semantics of Objects in Visual Scenes in Comparison to Text.]] Artificial Intelligence, 274, 44-65. DOI:10.1016/j.artint.2018.12.009. Elsevier. | - Lüddecke, T., Agostini, A., Fauth, M., Tamosiunaite, M., Wörgötter, F. (2019). [[https://doi.org/10.1016/j.artint.2018.12.009|Distributional Semantics of Objects in Visual Scenes in Comparison to Text.]] Artificial Intelligence, 274, 44-65. DOI:10.1016/j.artint.2018.12.009. Elsevier. | ||
| Line 67: | Line 69: | ||
| **Refereed Conference Papers** | **Refereed Conference Papers** | ||
| - | - Orbik, J., Agostini, A., and Lee, D (2021). [[https://mediatum.ub.tum.de/doc/1632205/1632205.pdf|Inverse Reinforcement Learning for Dexterous Hand Manipulation.]] In: IEEE International Conference on Development and Learning (ICDL). pp. 1-7. | + | - Orbik, J., Agostini, A., and Lee, D (2021). [[https://mediatum.ub.tum.de/doc/1632205/1632205.pdf|Inverse Reinforcement Learning for Dexterous Hand Manipulation.]] In: IEEE International Conference on Development and Learning (ICDL). pp. 1-7. DOI: 10.1109/ICDL49984.2021.9515637. IEEE. |
| - | - Urbaniak, D., Agostini, A., and Lee, D (2021). [[https://mediatum.ub.tum.de/doc/1621721/1621721.pdf|Combining Task and Motion Planning using Policy Improvement with Path Integrals.]] In: IEEE International Conference on Humanoid Robots (HUMANOIDS). pp. 149-155. | + | - Urbaniak, D., Agostini, A., and Lee, D (2021). [[https://mediatum.ub.tum.de/doc/1621721/1621721.pdf|Combining Task and Motion Planning using Policy Improvement with Path Integrals.]] In: IEEE International Conference on Humanoid Robots (HUMANOIDS). pp. 149-155. DOI: 10.1109/HUMANOIDS47582.2021.9555684. IEEE. |
| - Paulius, D., Agostini, A., Sun, Y., and Lee, D. (2021). [[https://arxiv.org/pdf/2106.00158.pdf|A Road-map to Robot Task Execution with the Functional Object-Oriented Network.]] International Conference on Ubiquitous Robots (UR). WIP. | - Paulius, D., Agostini, A., Sun, Y., and Lee, D. (2021). [[https://arxiv.org/pdf/2106.00158.pdf|A Road-map to Robot Task Execution with the Functional Object-Oriented Network.]] International Conference on Ubiquitous Robots (UR). WIP. | ||
| - Agostini, A., Wörgötter, F. (2019). [[http://vm19030.virt.gwdg.de/aagostini/Publications_files/ECPA2019_poster_abstract_30190_agostini.pdf|Automatic Control of the Growth of Plants using Artificial Intelligence and Internet Technology.]] In: Poster Proceedings of the 12th European Conference on Precision Agriculture (ECPA). pp. 12-13. SupAgro Montpellier. ISBN 978-2-900792-49-0. | - Agostini, A., Wörgötter, F. (2019). [[http://vm19030.virt.gwdg.de/aagostini/Publications_files/ECPA2019_poster_abstract_30190_agostini.pdf|Automatic Control of the Growth of Plants using Artificial Intelligence and Internet Technology.]] In: Poster Proceedings of the 12th European Conference on Precision Agriculture (ECPA). pp. 12-13. SupAgro Montpellier. ISBN 978-2-900792-49-0. | ||
| Line 94: | Line 96: | ||
| - Agostini, A., & Lee, D. (2020). [[https://arxiv.org/abs/2007.08251|Efficient state abstraction using object-centered predicates for manipulation planning.]] arXiv preprint arXiv:2007.08251. | - Agostini, A., & Lee, D. (2020). [[https://arxiv.org/abs/2007.08251|Efficient state abstraction using object-centered predicates for manipulation planning.]] arXiv preprint arXiv:2007.08251. | ||
| - | - Agostini, A. PLANTAR: Automatic control of the growth of plants using artificial intelligence and Internet Technology (2018). URL: http://vm19030.virt.gwdg.de/alaive/alaive/Agriculture.html. Accessed: 2020-09-01. Technology transference prototype. ALAIVE, Südniedersachsen Innovations Campus (SNIC). | + | - Agostini, A. PLANTAR: Automatic control of the growth of plants using artificial intelligence and Internet Technology (2018). URL: https://alaive.github.io/agriculture.html. Accessed: 2022-11-01. Technology transference prototype. ALAIVE, Südniedersachsen Innovations Campus (SNIC). |
| - | - Agostini, A. HRV2: Internet Platform for the Intelligent Monitoring of Cardiovascular Patients using Wearable Technology (2015). URL: http://vm19030.virt.gwdg.de/alaive/alaive/Health_Care.html. Accessed: 2020-09-01. Technology transference prototype. ALAIVE, Südniedersachsen Innovations Campus (SNIC). | + | - Agostini, A. HRV2: Internet Platform for the Intelligent Monitoring of Cardiovascular Patients using Wearable Technology (2015). URL: https://alaive.github.io/healthcare.html. Accessed: 2022-11-01. Technology transference prototype. ALAIVE, Südniedersachsen Innovations Campus (SNIC). |
| - Agostini, A. and Celaya, E. (2014). [[https://upcommons.upc.edu/handle/2117/28454|Competitive function approximation for reinforcement learning.]] Technical report, IRI-TR-14-05. Institut de Robtica i Informtica Industrial. UPC-CSIC. (Barcelona, Spain). | - Agostini, A. and Celaya, E. (2014). [[https://upcommons.upc.edu/handle/2117/28454|Competitive function approximation for reinforcement learning.]] Technical report, IRI-TR-14-05. Institut de Robtica i Informtica Industrial. UPC-CSIC. (Barcelona, Spain). | ||
| - Agostini, A., Wörgötter, F., Celaya, E., and Torras, C. (2008). [[https://upcommons.upc.edu/bitstream/handle/2117/2694/doc1.pdf|On-line learning of macro planning operators using probabilistic estimations of cause-effects.]] Technical report, IRI-TR 05/2008. Institut de Robtica i Informtica Industrial. UPC-CSIC. (Barcelona, Spain). | - Agostini, A., Wörgötter, F., Celaya, E., and Torras, C. (2008). [[https://upcommons.upc.edu/bitstream/handle/2117/2694/doc1.pdf|On-line learning of macro planning operators using probabilistic estimations of cause-effects.]] Technical report, IRI-TR 05/2008. Institut de Robtica i Informtica Industrial. UPC-CSIC. (Barcelona, Spain). | ||
| Line 101: | Line 103: | ||
| **Theses** | **Theses** | ||
| - | - Agostini, A. (2011). [[http://vm19030.virt.gwdg.de/aagostini/Publications_Skill_Learning_files/PhD_thesis_Alejandro_Agostini.pdf|Q-Learning with a Degenerate Function Approximation.]] Polytechnic University of Catalonia (UPC), Spain. PhD Thesis. | + | - Agostini, A. (2011). [[https://alejandroagostini.github.io/publications/PhD_thesis_Alejandro_Agostini.pdf|Q-Learning with a Degenerate Function Approximation.]] Polytechnic University of Catalonia (UPC), Spain. PhD Thesis. |
| - | - Agostini, A. (1999). [[http://vm19030.virt.gwdg.de/aagostini/Publications_files/bioeng_degree_thesis_alejandro_agostini.pdf|Mathematical Analysis of the Heart Rate Variability and Its Clinical Implications]] (in Spanish). National University of Entre Ríos. Eng. Degree Thesis. | + | - Agostini, A. (1999). [[https://alejandroagostini.github.io/publications/bioeng_degree_thesis_alejandro_agostini.pdf|Mathematical Analysis of the Heart Rate Variability and Its Clinical Implications]] (in Spanish). National University of Entre Ríos. Eng. Degree Thesis. |
people/agostini.1650364920.txt.gz · Last modified: 2022/04/19 12:42 by Alejandro Agostini