[{"publisher":"IEEE","project":[{"call_identifier":"H2020","name":"Vigilant Algorithmic Monitoring of Software","grant_number":"101020093","_id":"62781420-2b32-11ec-9570-8d9b63373d4d"}],"isi":1,"user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","publication_status":"published","citation":{"mla":"Lechner, Mathias, et al. “Overparametrization Helps Offline-to-Online Generalization of Closed-Loop Control from Pixels.” <i>Proceedings of the 2024 IEEE International Conference on Robotics and Automation</i>, IEEE, 2024, pp. 2774–82, doi:<a href=\"https://doi.org/10.1109/ICRA57147.2024.10610284\">10.1109/ICRA57147.2024.10610284</a>.","chicago":"Lechner, Mathias, Ramin Hasani, Alexander Amini, Tsun Hsuan Wang, Thomas A Henzinger, and Daniela Rus. “Overparametrization Helps Offline-to-Online Generalization of Closed-Loop Control from Pixels.” In <i>Proceedings of the 2024 IEEE International Conference on Robotics and Automation</i>, 2774–82. IEEE, 2024. <a href=\"https://doi.org/10.1109/ICRA57147.2024.10610284\">https://doi.org/10.1109/ICRA57147.2024.10610284</a>.","ieee":"M. Lechner, R. Hasani, A. Amini, T. H. Wang, T. A. Henzinger, and D. Rus, “Overparametrization helps offline-to-online generalization of closed-loop control from pixels,” in <i>Proceedings of the 2024 IEEE International Conference on Robotics and Automation</i>, Yokohama, Japan, 2024, pp. 2774–2782.","apa":"Lechner, M., Hasani, R., Amini, A., Wang, T. H., Henzinger, T. A., &#38; Rus, D. (2024). Overparametrization helps offline-to-online generalization of closed-loop control from pixels. In <i>Proceedings of the 2024 IEEE International Conference on Robotics and Automation</i> (pp. 2774–2782). Yokohama, Japan: IEEE. <a href=\"https://doi.org/10.1109/ICRA57147.2024.10610284\">https://doi.org/10.1109/ICRA57147.2024.10610284</a>","ista":"Lechner M, Hasani R, Amini A, Wang TH, Henzinger TA, Rus D. 2024. Overparametrization helps offline-to-online generalization of closed-loop control from pixels. Proceedings of the 2024 IEEE International Conference on Robotics and Automation. ICRA: International Conference on Robotics and Automation, 2774–2782.","ama":"Lechner M, Hasani R, Amini A, Wang TH, Henzinger TA, Rus D. Overparametrization helps offline-to-online generalization of closed-loop control from pixels. In: <i>Proceedings of the 2024 IEEE International Conference on Robotics and Automation</i>. IEEE; 2024:2774-2782. doi:<a href=\"https://doi.org/10.1109/ICRA57147.2024.10610284\">10.1109/ICRA57147.2024.10610284</a>","short":"M. Lechner, R. Hasani, A. Amini, T.H. Wang, T.A. Henzinger, D. Rus, in:, Proceedings of the 2024 IEEE International Conference on Robotics and Automation, IEEE, 2024, pp. 2774–2782."},"doi":"10.1109/ICRA57147.2024.10610284","year":"2024","ec_funded":1,"page":"2774-2782","quality_controlled":"1","title":"Overparametrization helps offline-to-online generalization of closed-loop control from pixels","publication_identifier":{"isbn":["9798350384574"],"issn":["1050-4729"]},"date_published":"2024-08-08T00:00:00Z","external_id":{"isi":["001294576202044"]},"scopus_import":"1","publication":"Proceedings of the 2024 IEEE International Conference on Robotics and Automation","author":[{"last_name":"Lechner","id":"3DC22916-F248-11E8-B48F-1D18A9856A87","first_name":"Mathias","full_name":"Lechner, Mathias"},{"first_name":"Ramin","full_name":"Hasani, Ramin","last_name":"Hasani"},{"last_name":"Amini","full_name":"Amini, Alexander","first_name":"Alexander"},{"last_name":"Wang","full_name":"Wang, Tsun Hsuan","first_name":"Tsun Hsuan"},{"orcid":"0000-0002-2985-7724","first_name":"Thomas A","last_name":"Henzinger","full_name":"Henzinger, Thomas A","id":"40876CD8-F248-11E8-B48F-1D18A9856A87"},{"last_name":"Rus","first_name":"Daniela","full_name":"Rus, Daniela"}],"oa_version":"None","conference":{"location":"Yokohama, Japan","name":"ICRA: International Conference on Robotics and Automation","end_date":"2024-05-17","start_date":"2024-05-13"},"acknowledgement":"This work was partially supported in parts by the ERC-2020-AdG 101020093. Additionally, it was partially sponsored by the United States Air Force Research Laboratory and the United States Air Force Artificial Intelligence Accelerator and was accomplished under Cooperative Agreement Number FA8750-19-2-1000. The views and conclusions contained in this document are those of the authors and should not be interpreted as representing the official policies, either expressed or implied, of the United States Air Force or the U.S. Government. The U.S. Government is authorized to reproduce and distribute reprints for Government purposes notwithstanding any copyright notation herein. This work was further supported by The Boeing Company and the Office of Naval Research (ONR) Grant N00014-18-1-2830.","_id":"17898","language":[{"iso":"eng"}],"month":"08","department":[{"_id":"ToHe"}],"status":"public","day":"08","date_updated":"2026-08-12T06:35:50Z","abstract":[{"text":"There is an ever-growing zoo of modern neural network models that can efficiently learn end-to-end control from visual observations. These advanced deep models, ranging from convolutional to Vision Transformers, from small to gigantic networks, have been extensively tested on offline image classification tasks. In this paper, we study these vision models with respect to the open-loop training to closed-loop generalization abilities, i.e., deployment realizes a causal feedback loop that is not present during training. This causality gap typically emerges in robotics applications such as autonomous driving, where a network is trained to imitate the control commands of a human. In this setting, two situations arise: 1) Closed-loop testing in-distribution, where the test environment shares properties with those of offline training data. 2) Closed-loop testing under distribution shifts and out-of-distribution. Contrary to recently reported results, we show that under proper training guidelines, all vision architectures perform indistinguishably well on in-distribution deployment, resolving the causality gap. In situation 2, We observe that scale is the strongest factor in improving closed-loop generalization regardless of the choice of the model architecture. Our results predict the trend that in the future we will see larger and larger models being used in offline-training-online-deployment imitation learning tasks in robotic applications.","lang":"eng"}],"fulldoi":"https://doi.org/10.1109/ICRA57147.2024.10610284","date_created":"2024-09-08T22:01:13Z","article_processing_charge":"No","type":"conference"},{"date_updated":"2025-04-15T07:43:52Z","day":"04","abstract":[{"lang":"eng","text":"3D printing based on continuous deposition of materials, such as filament-based 3D printing, has seen widespread adoption thanks to its versatility in working with a wide range of materials. An important shortcoming of this type of technology is its limited multi-material capabilities. While there are simple hardware designs that enable multi-material printing in principle, the required software is heavily underdeveloped. A typical hardware design fuses together individual materials fed into a single chamber from multiple inlets before they are deposited. This design, however, introduces a time delay between the intended material mixture and its actual deposition. In this work, inspired by diverse path planning research in robotics, we show that this mechanical challenge can be addressed via improved printer control. We propose to formulate the search for optimal multi-material printing policies in a reinforcement\r\nlearning setup. We put forward a simple numerical deposition model that takes into account the non-linear material mixing and delayed material deposition. To validate our system we focus on color fabrication, a problem known for its strict requirements for varying material mixtures at a high spatial frequency. We demonstrate that our learned control policy outperforms state-of-the-art hand-crafted algorithms."}],"fulldoi":"https://doi.org/10.1109/ICRA48891.2023.10160465","month":"07","language":[{"iso":"eng"}],"has_accepted_license":"1","department":[{"_id":"BeBi"}],"status":"public","type":"conference","article_processing_charge":"No","volume":2023,"date_created":"2023-05-16T09:14:09Z","file_date_updated":"2023-05-16T09:12:05Z","date_published":"2023-07-04T00:00:00Z","title":"Learning deposition policies for fused multi-material 3D printing","publication_identifier":{"eisbn":["9798350323658"],"issn":["1050-4729"]},"oa_version":"Submitted Version","conference":{"location":"London, United Kingdom","name":"ICRA: International Conference on Robotics and Automation","end_date":"2023-06-02","start_date":"2023-05-29"},"acknowledgement":"This work is graciously supported by FWF Lise Meitner (Grant M 3319). Kang Liao sincerely thank Emiliano Luci, Chunyu Lin, and Yao Zhao for their huge support.","_id":"12976","external_id":{"isi":["001048371104068"]},"publication":"2023 IEEE International Conference on Robotics and Automation","author":[{"full_name":"Liao, Kang","first_name":"Kang","last_name":"Liao"},{"first_name":"Thibault","full_name":"Tricard, Thibault","last_name":"Tricard"},{"orcid":"0000-0002-5062-4474","first_name":"Michael","last_name":"Piovarci","full_name":"Piovarci, Michael","id":"62E473F4-5C99-11EA-A40E-AF823DDC885E"},{"first_name":"Hans-Peter","full_name":"Seidel, Hans-Peter","last_name":"Seidel"},{"last_name":"Babaei","full_name":"Babaei, Vahid","first_name":"Vahid"}],"scopus_import":"1","publication_status":"published","citation":{"chicago":"Liao, Kang, Thibault Tricard, Michael Piovarci, Hans-Peter Seidel, and Vahid Babaei. “Learning Deposition Policies for Fused Multi-Material 3D Printing.” In <i>2023 IEEE International Conference on Robotics and Automation</i>, 2023:12345–52. IEEE, 2023. <a href=\"https://doi.org/10.1109/ICRA48891.2023.10160465\">https://doi.org/10.1109/ICRA48891.2023.10160465</a>.","mla":"Liao, Kang, et al. “Learning Deposition Policies for Fused Multi-Material 3D Printing.” <i>2023 IEEE International Conference on Robotics and Automation</i>, vol. 2023, IEEE, 2023, pp. 12345–52, doi:<a href=\"https://doi.org/10.1109/ICRA48891.2023.10160465\">10.1109/ICRA48891.2023.10160465</a>.","ista":"Liao K, Tricard T, Piovarci M, Seidel H-P, Babaei V. 2023. Learning deposition policies for fused multi-material 3D printing. 2023 IEEE International Conference on Robotics and Automation. ICRA: International Conference on Robotics and Automation vol. 2023, 12345–12352.","apa":"Liao, K., Tricard, T., Piovarci, M., Seidel, H.-P., &#38; Babaei, V. (2023). Learning deposition policies for fused multi-material 3D printing. In <i>2023 IEEE International Conference on Robotics and Automation</i> (Vol. 2023, pp. 12345–12352). London, United Kingdom: IEEE. <a href=\"https://doi.org/10.1109/ICRA48891.2023.10160465\">https://doi.org/10.1109/ICRA48891.2023.10160465</a>","ieee":"K. Liao, T. Tricard, M. Piovarci, H.-P. Seidel, and V. Babaei, “Learning deposition policies for fused multi-material 3D printing,” in <i>2023 IEEE International Conference on Robotics and Automation</i>, London, United Kingdom, 2023, vol. 2023, pp. 12345–12352.","short":"K. Liao, T. Tricard, M. Piovarci, H.-P. Seidel, V. Babaei, in:, 2023 IEEE International Conference on Robotics and Automation, IEEE, 2023, pp. 12345–12352.","ama":"Liao K, Tricard T, Piovarci M, Seidel H-P, Babaei V. Learning deposition policies for fused multi-material 3D printing. In: <i>2023 IEEE International Conference on Robotics and Automation</i>. Vol 2023. IEEE; 2023:12345-12352. doi:<a href=\"https://doi.org/10.1109/ICRA48891.2023.10160465\">10.1109/ICRA48891.2023.10160465</a>"},"user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","ddc":["004"],"quality_controlled":"1","doi":"10.1109/ICRA48891.2023.10160465","year":"2023","page":"12345-12352","file":[{"content_type":"application/pdf","file_size":5367986,"relation":"main_file","date_created":"2023-05-16T09:12:05Z","file_name":"Liao2023.pdf","date_updated":"2023-05-16T09:12:05Z","checksum":"daeaa67124777d88487f933ea3f77164","file_id":"12977","success":1,"access_level":"open_access","creator":"mpiovarc"}],"keyword":["reinforcement learning","deposition","control","color","multi-filament"],"intvolume":"      2023","publisher":"IEEE","project":[{"name":"Perception-Aware Appearance Fabrication","_id":"eb901961-77a9-11ec-83b8-f5c883a62027","grant_number":"M03319"}],"oa":1,"isi":1},{"user_id":"317138e5-6ab7-11ef-aa6d-ffef3953e345","publication_status":"published","citation":{"mla":"Brunnbauer, Axel, et al. “Latent Imagination Facilitates Zero-Shot Transfer in Autonomous Racing.” <i>2022 International Conference on Robotics and Automation</i>, IEEE, 2022, pp. 7513–20, doi:<a href=\"https://doi.org/10.1109/ICRA46639.2022.9811650\">10.1109/ICRA46639.2022.9811650</a>.","chicago":"Brunnbauer, Axel, Luigi Berducci, Andreas Brandstatter, Mathias Lechner, Ramin Hasani, Daniela Rus, and Radu Grosu. “Latent Imagination Facilitates Zero-Shot Transfer in Autonomous Racing.” In <i>2022 International Conference on Robotics and Automation</i>, 7513–20. IEEE, 2022. <a href=\"https://doi.org/10.1109/ICRA46639.2022.9811650\">https://doi.org/10.1109/ICRA46639.2022.9811650</a>.","ieee":"A. Brunnbauer <i>et al.</i>, “Latent imagination facilitates zero-shot transfer in autonomous racing,” in <i>2022 International Conference on Robotics and Automation</i>, Philadelphia, PA, United States, 2022, pp. 7513–7520.","apa":"Brunnbauer, A., Berducci, L., Brandstatter, A., Lechner, M., Hasani, R., Rus, D., &#38; Grosu, R. (2022). Latent imagination facilitates zero-shot transfer in autonomous racing. In <i>2022 International Conference on Robotics and Automation</i> (pp. 7513–7520). Philadelphia, PA, United States: IEEE. <a href=\"https://doi.org/10.1109/ICRA46639.2022.9811650\">https://doi.org/10.1109/ICRA46639.2022.9811650</a>","ista":"Brunnbauer A, Berducci L, Brandstatter A, Lechner M, Hasani R, Rus D, Grosu R. 2022. Latent imagination facilitates zero-shot transfer in autonomous racing. 2022 International Conference on Robotics and Automation. ICRA: International Conference on Robotics and Automation, 7513–7520.","short":"A. Brunnbauer, L. Berducci, A. Brandstatter, M. Lechner, R. Hasani, D. Rus, R. Grosu, in:, 2022 International Conference on Robotics and Automation, IEEE, 2022, pp. 7513–7520.","ama":"Brunnbauer A, Berducci L, Brandstatter A, et al. Latent imagination facilitates zero-shot transfer in autonomous racing. In: <i>2022 International Conference on Robotics and Automation</i>. IEEE; 2022:7513-7520. doi:<a href=\"https://doi.org/10.1109/ICRA46639.2022.9811650\">10.1109/ICRA46639.2022.9811650</a>"},"year":"2022","doi":"10.1109/ICRA46639.2022.9811650","page":"7513-7520","ec_funded":1,"quality_controlled":"1","publisher":"IEEE","oa":1,"project":[{"call_identifier":"H2020","name":"Vigilant Algorithmic Monitoring of Software","_id":"62781420-2b32-11ec-9570-8d9b63373d4d","grant_number":"101020093"},{"call_identifier":"FWF","name":"Formal methods for the design and analysis of complex systems","_id":"25F42A32-B435-11E9-9278-68D0E5697425","grant_number":"Z211"}],"isi":1,"language":[{"iso":"eng"}],"month":"07","department":[{"_id":"ToHe"}],"status":"public","date_updated":"2025-09-10T09:39:53Z","day":"12","abstract":[{"lang":"eng","text":"World models learn behaviors in a latent imagination space to enhance the sample-efficiency of deep reinforcement learning (RL) algorithms. While learning world models for high-dimensional observations (e.g., pixel inputs) has become practicable on standard RL benchmarks and some games, their effectiveness in real-world robotics applications has not been explored. In this paper, we investigate how such agents generalize to real-world autonomous vehicle control tasks, where advanced model-free deep RL algorithms fail. In particular, we set up a series of time-lap tasks for an F1TENTH racing robot, equipped with a high-dimensional LiDAR sensor, on a set of test tracks with a gradual increase in their complexity. In this continuous-control setting, we show that model-based agents capable of learning in imagination substantially outperform model-free agents with respect to performance, sample efficiency, successful task completion, and generalization. Moreover, we show that the generalization ability of model-based agents strongly depends on the choice of their observation model. We provide extensive empirical evidence for the effectiveness of world models provided with long enough memory horizons in sim2real tasks."}],"fulldoi":"https://doi.org/10.1109/ICRA46639.2022.9811650","date_created":"2022-09-04T22:02:02Z","type":"conference","article_processing_charge":"No","title":"Latent imagination facilitates zero-shot transfer in autonomous racing","publication_identifier":{"issn":["1050-4729"],"isbn":["9781728196817"]},"arxiv":1,"date_published":"2022-07-12T00:00:00Z","external_id":{"arxiv":["2103.04909"],"isi":["000941277600124"]},"publication":"2022 International Conference on Robotics and Automation","scopus_import":"1","author":[{"last_name":"Brunnbauer","full_name":"Brunnbauer, Axel","first_name":"Axel"},{"full_name":"Berducci, Luigi","last_name":"Berducci","first_name":"Luigi"},{"last_name":"Brandstatter","first_name":"Andreas","full_name":"Brandstatter, Andreas"},{"id":"3DC22916-F248-11E8-B48F-1D18A9856A87","full_name":"Lechner, Mathias","last_name":"Lechner","first_name":"Mathias"},{"full_name":"Hasani, Ramin","first_name":"Ramin","last_name":"Hasani"},{"full_name":"Rus, Daniela","first_name":"Daniela","last_name":"Rus"},{"full_name":"Grosu, Radu","first_name":"Radu","last_name":"Grosu"}],"main_file_link":[{"open_access":"1","url":"https://doi.org/10.48550/arXiv.2103.04909"}],"oa_version":"Preprint","conference":{"name":"ICRA: International Conference on Robotics and Automation","location":"Philadelphia, PA, United States","start_date":"2022-05-23","end_date":"2022-05-27"},"acknowledgement":"L.B. was supported by the Doctoral College Resilient Embedded Systems. M.L. was supported in part by the ERC2020-AdG 101020093 and the Austrian Science Fund (FWF) under grant Z211-N23 (Wittgenstein Award). R.H. and D.R. were supported by The Boeing Company and the Office of Naval Research (ONR) Grant N00014-18-1-2830. R.G. was partially supported by the Horizon-2020 ECSEL Project grant No. 783163 (iDev40) and A.B. by FFG Project ADEX.","_id":"12010"},{"title":"Adversarial training is not ready for robot learning","publication_identifier":{"isbn":["978-1-7281-9078-5"],"issn":["1050-4729"],"eissn":["2577-087X"],"eisbn":["978-1-7281-9077-8"]},"arxiv":1,"date_published":"2021-06-01T00:00:00Z","external_id":{"isi":["000765738803040"],"arxiv":["2103.08187"]},"publication":"2021 IEEE International Conference on Robotics and Automation","scopus_import":"1","author":[{"first_name":"Mathias","last_name":"Lechner","id":"3DC22916-F248-11E8-B48F-1D18A9856A87","full_name":"Lechner, Mathias"},{"first_name":"Ramin","full_name":"Hasani, Ramin","last_name":"Hasani"},{"last_name":"Grosu","full_name":"Grosu, Radu","first_name":"Radu"},{"full_name":"Rus, Daniela","first_name":"Daniela","last_name":"Rus"},{"orcid":"0000-0002-2985-7724","id":"40876CD8-F248-11E8-B48F-1D18A9856A87","full_name":"Henzinger, Thomas A","first_name":"Thomas A","last_name":"Henzinger"}],"oa_version":"Preprint","main_file_link":[{"url":"https://arxiv.org/abs/2103.08187","open_access":"1"}],"conference":{"end_date":"2021-06-05","start_date":"2021-05-30","location":"Xi'an, China","name":"ICRA: International Conference on Robotics and Automation"},"acknowledgement":"M.L. and T.A.H. are supported in part by the Austrian Science Fund (FWF) under grant Z211-N23 (Wittgenstein Award). R.H. and D.R. are supported by Boeing and R.G. by Horizon-2020 ECSEL Project grant no. 783163 (iDev40).","_id":"10666","language":[{"iso":"eng"}],"month":"06","has_accepted_license":"1","status":"public","department":[{"_id":"GradSch"},{"_id":"ToHe"}],"date_updated":"2026-07-07T06:20:35Z","day":"01","abstract":[{"lang":"eng","text":"Adversarial training is an effective method to train deep learning models that are resilient to norm-bounded perturbations, with the cost of nominal performance drop. While adversarial training appears to enhance the robustness and safety of a deep model deployed in open-world decision-critical applications, counterintuitively, it induces undesired behaviors in robot learning settings. In this paper, we show theoretically and experimentally that neural controllers obtained via adversarial training are subjected to three types of defects, namely transient, systematic, and conditional errors. We first generalize adversarial training to a safety-domain optimization scheme allowing for more generic specifications. We then prove that such a learning process tends to cause certain error profiles. We support our theoretical results by a thorough experimental safety analysis in a robot-learning task. Our results suggest that adversarial training is not yet ready for robot learning."}],"fulldoi":"https://doi.org/10.1109/ICRA48506.2021.9561036","date_created":"2022-01-25T15:44:54Z","type":"conference","tmp":{"short":"CC BY-NC-ND (3.0)","name":"Creative Commons Attribution-NonCommercial-NoDerivs 3.0 Unported (CC BY-NC-ND 3.0)","image":"/images/cc_by_nc_nd.png","legal_code_url":"https://creativecommons.org/licenses/by-nc-nd/3.0/legalcode"},"article_processing_charge":"No","OA_type":"green","publisher":"IEEE","project":[{"grant_number":"Z211","_id":"25F42A32-B435-11E9-9278-68D0E5697425","name":"Formal methods for the design and analysis of complex systems","call_identifier":"FWF"}],"oa":1,"related_material":{"record":[{"id":"11362","relation":"dissertation_contains","status":"public"}]},"das_tickbox":"1","OA_place":"repository","isi":1,"user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","publication_status":"published","citation":{"short":"M. Lechner, R. Hasani, R. Grosu, D. Rus, T.A. Henzinger, in:, 2021 IEEE International Conference on Robotics and Automation, IEEE, 2021, pp. 4140–4147.","ama":"Lechner M, Hasani R, Grosu R, Rus D, Henzinger TA. Adversarial training is not ready for robot learning. In: <i>2021 IEEE International Conference on Robotics and Automation</i>. IEEE; 2021:4140-4147. doi:<a href=\"https://doi.org/10.1109/ICRA48506.2021.9561036\">10.1109/ICRA48506.2021.9561036</a>","ista":"Lechner M, Hasani R, Grosu R, Rus D, Henzinger TA. 2021. Adversarial training is not ready for robot learning. 2021 IEEE International Conference on Robotics and Automation. ICRA: International Conference on Robotics and Automation, 4140–4147.","apa":"Lechner, M., Hasani, R., Grosu, R., Rus, D., &#38; Henzinger, T. A. (2021). Adversarial training is not ready for robot learning. In <i>2021 IEEE International Conference on Robotics and Automation</i> (pp. 4140–4147). Xi’an, China: IEEE. <a href=\"https://doi.org/10.1109/ICRA48506.2021.9561036\">https://doi.org/10.1109/ICRA48506.2021.9561036</a>","ieee":"M. Lechner, R. Hasani, R. Grosu, D. Rus, and T. A. Henzinger, “Adversarial training is not ready for robot learning,” in <i>2021 IEEE International Conference on Robotics and Automation</i>, Xi’an, China, 2021, pp. 4140–4147.","chicago":"Lechner, Mathias, Ramin Hasani, Radu Grosu, Daniela Rus, and Thomas A Henzinger. “Adversarial Training Is Not Ready for Robot Learning.” In <i>2021 IEEE International Conference on Robotics and Automation</i>, 4140–47. IEEE, 2021. <a href=\"https://doi.org/10.1109/ICRA48506.2021.9561036\">https://doi.org/10.1109/ICRA48506.2021.9561036</a>.","mla":"Lechner, Mathias, et al. “Adversarial Training Is Not Ready for Robot Learning.” <i>2021 IEEE International Conference on Robotics and Automation</i>, IEEE, 2021, pp. 4140–47, doi:<a href=\"https://doi.org/10.1109/ICRA48506.2021.9561036\">10.1109/ICRA48506.2021.9561036</a>."},"year":"2021","doi":"10.1109/ICRA48506.2021.9561036","page":"4140-4147","ddc":["000"],"quality_controlled":"1"},{"publication_identifier":{"issn":["1050-4729"],"isbn":["9781728173955"]},"title":"Gershgorin loss stabilizes the recurrent neural network compartment of an end-to-end robot learning scheme","date_published":"2020-05-01T00:00:00Z","file_date_updated":"2020-11-06T10:58:49Z","scopus_import":"1","publication":"Proceedings - IEEE International Conference on Robotics and Automation","author":[{"first_name":"Mathias","full_name":"Lechner, Mathias","id":"3DC22916-F248-11E8-B48F-1D18A9856A87","last_name":"Lechner"},{"first_name":"Ramin","full_name":"Hasani, Ramin","last_name":"Hasani"},{"full_name":"Rus, Daniela","first_name":"Daniela","last_name":"Rus"},{"last_name":"Grosu","full_name":"Grosu, Radu","first_name":"Radu"}],"external_id":{"isi":["000712319503110"]},"conference":{"start_date":"2020-05-31","end_date":"2020-08-31","name":"ICRA: International Conference on Robotics and Automation","location":"Paris, France"},"oa_version":"Submitted Version","_id":"8704","acknowledgement":"M.L. is supported in parts by the Austrian Science Fund (FWF) under grant Z211-N23 (Wittgenstein Award). R.H., and R.G. are partially supported by the Horizon-2020 ECSELProject grant No. 783163 (iDev40), and the Austrian Research Promotion Agency (FFG), Project No. 860424. R.H. and D.R. is partially supported by the Boeing Company.","has_accepted_license":"1","language":[{"iso":"eng"}],"month":"05","status":"public","department":[{"_id":"ToHe"}],"date_updated":"2025-07-10T12:01:21Z","day":"01","fulldoi":"https://doi.org/10.1109/ICRA40945.2020.9196608","abstract":[{"lang":"eng","text":"Traditional robotic control suits require profound task-specific knowledge for designing, building and testing control software. The rise of Deep Learning has enabled end-to-end solutions to be learned entirely from data, requiring minimal knowledge about the application area. We design a learning scheme to train end-to-end linear dynamical systems (LDS)s by gradient descent in imitation learning robotic domains. We introduce a new regularization loss component together with a learning algorithm that improves the stability of the learned autonomous system, by forcing the eigenvalues of the internal state updates of an LDS to be negative reals. We evaluate our approach on a series of real-life and simulated robotic experiments, in comparison to linear and nonlinear Recurrent Neural Network (RNN) architectures. Our results show that our stabilizing method significantly improves test performance of LDS, enabling such linear models to match the performance of contemporary nonlinear RNN architectures. A video of the obstacle avoidance performance of our method on a mobile robot, in unseen environments, compared to other methods can be viewed at https://youtu.be/mhEsCoNao5E."}],"date_created":"2020-10-25T23:01:19Z","article_processing_charge":"No","type":"conference","publisher":"IEEE","file":[{"date_created":"2020-11-06T10:58:49Z","content_type":"application/pdf","file_size":1070010,"relation":"main_file","checksum":"fccf7b986ac78046918a298cc6849a50","file_id":"8733","success":1,"access_level":"open_access","creator":"dernst","file_name":"2020_ICRA_Lechner.pdf","date_updated":"2020-11-06T10:58:49Z"}],"alternative_title":["ICRA"],"oa":1,"project":[{"_id":"25F42A32-B435-11E9-9278-68D0E5697425","grant_number":"Z211","name":"Formal methods for the design and analysis of complex systems","call_identifier":"FWF"}],"isi":1,"user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","citation":{"chicago":"Lechner, Mathias, Ramin Hasani, Daniela Rus, and Radu Grosu. “Gershgorin Loss Stabilizes the Recurrent Neural Network Compartment of an End-to-End Robot Learning Scheme.” In <i>Proceedings - IEEE International Conference on Robotics and Automation</i>, 5446–52. IEEE, 2020. <a href=\"https://doi.org/10.1109/ICRA40945.2020.9196608\">https://doi.org/10.1109/ICRA40945.2020.9196608</a>.","mla":"Lechner, Mathias, et al. “Gershgorin Loss Stabilizes the Recurrent Neural Network Compartment of an End-to-End Robot Learning Scheme.” <i>Proceedings - IEEE International Conference on Robotics and Automation</i>, IEEE, 2020, pp. 5446–52, doi:<a href=\"https://doi.org/10.1109/ICRA40945.2020.9196608\">10.1109/ICRA40945.2020.9196608</a>.","ista":"Lechner M, Hasani R, Rus D, Grosu R. 2020. Gershgorin loss stabilizes the recurrent neural network compartment of an end-to-end robot learning scheme. Proceedings - IEEE International Conference on Robotics and Automation. ICRA: International Conference on Robotics and Automation, ICRA, , 5446–5452.","ieee":"M. Lechner, R. Hasani, D. Rus, and R. Grosu, “Gershgorin loss stabilizes the recurrent neural network compartment of an end-to-end robot learning scheme,” in <i>Proceedings - IEEE International Conference on Robotics and Automation</i>, Paris, France, 2020, pp. 5446–5452.","apa":"Lechner, M., Hasani, R., Rus, D., &#38; Grosu, R. (2020). Gershgorin loss stabilizes the recurrent neural network compartment of an end-to-end robot learning scheme. In <i>Proceedings - IEEE International Conference on Robotics and Automation</i> (pp. 5446–5452). Paris, France: IEEE. <a href=\"https://doi.org/10.1109/ICRA40945.2020.9196608\">https://doi.org/10.1109/ICRA40945.2020.9196608</a>","short":"M. Lechner, R. Hasani, D. Rus, R. Grosu, in:, Proceedings - IEEE International Conference on Robotics and Automation, IEEE, 2020, pp. 5446–5452.","ama":"Lechner M, Hasani R, Rus D, Grosu R. Gershgorin loss stabilizes the recurrent neural network compartment of an end-to-end robot learning scheme. In: <i>Proceedings - IEEE International Conference on Robotics and Automation</i>. IEEE; 2020:5446-5452. doi:<a href=\"https://doi.org/10.1109/ICRA40945.2020.9196608\">10.1109/ICRA40945.2020.9196608</a>"},"publication_status":"published","page":"5446-5452","year":"2020","doi":"10.1109/ICRA40945.2020.9196608","quality_controlled":"1","ddc":["000"]}]