Gershgorin loss stabilizes the recurrent neural network compartment of an end-to-end robot learning scheme

M. Lechner, R. Hasani, D. Rus, R. Grosu, in:, Proceedings - IEEE International Conference on Robotics and Automation, IEEE, 2020, pp. 5446–5452.

Download
OA 2020_ICRA_Lechner.pdf 1.07 MB

Conference Paper | Published | English

Scopus indexed
Author
Lechner, MathiasIST Austria; Hasani, Ramin; Rus, Daniela; Grosu, Radu
Department
Series Title
ICRA
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.
Publishing Year
Date Published
2020-05-01
Proceedings Title
Proceedings - IEEE International Conference on Robotics and Automation
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.
Page
5446-5452
Conference
ICRA: International Conference on Robotics and Automation
Conference Location
Paris, France
Conference Date
2020-05-31 – 2020-08-31
ISSN
IST-REx-ID

Cite this

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: Proceedings - IEEE International Conference on Robotics and Automation. IEEE; 2020:5446-5452. doi:10.1109/ICRA40945.2020.9196608
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. In Proceedings - IEEE International Conference on Robotics and Automation (pp. 5446–5452). Paris, France: IEEE. https://doi.org/10.1109/ICRA40945.2020.9196608
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 Proceedings - IEEE International Conference on Robotics and Automation, 5446–52. IEEE, 2020. https://doi.org/10.1109/ICRA40945.2020.9196608.
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 Proceedings - IEEE International Conference on Robotics and Automation, Paris, France, 2020, pp. 5446–5452.
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.
Lechner, Mathias, et al. “Gershgorin Loss Stabilizes the Recurrent Neural Network Compartment of an End-to-End Robot Learning Scheme.” Proceedings - IEEE International Conference on Robotics and Automation, IEEE, 2020, pp. 5446–52, doi:10.1109/ICRA40945.2020.9196608.
All files available under the following license(s):
Copyright Statement:
This Item is protected by copyright and/or related rights. [...]
Main File(s)
File Name
Access Level
OA Open Access
Date Uploaded
2020-11-06
MD5 Checksum
fccf7b986ac78046918a298cc6849a50


Export

Marked Publications

Open Data IST Research Explorer

Search this title in

Google Scholar
ISBN Search