--- res: bibo_abstract: - 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.@eng bibo_authorlist: - foaf_Person: foaf_givenName: Mathias foaf_name: Lechner, Mathias foaf_surname: Lechner foaf_workInfoHomepage: http://www.librecat.org/personId=3DC22916-F248-11E8-B48F-1D18A9856A87 - foaf_Person: foaf_givenName: Ramin foaf_name: Hasani, Ramin foaf_surname: Hasani - foaf_Person: foaf_givenName: Daniela foaf_name: Rus, Daniela foaf_surname: Rus - foaf_Person: foaf_givenName: Radu foaf_name: Grosu, Radu foaf_surname: Grosu bibo_doi: 10.1109/ICRA40945.2020.9196608 dct_date: 2020^xs_gYear dct_identifier: - UT:000712319503110 dct_isPartOf: - http://id.crossref.org/issn/10504729 - http://id.crossref.org/issn/9781728173955 dct_language: eng dct_publisher: IEEE@ dct_title: Gershgorin loss stabilizes the recurrent neural network compartment of an end-to-end robot learning scheme@ ...