Neural circuit policies enabling auditable autonomy

M. Lechner, R. Hasani, A. Amini, T.A. Henzinger, D. Rus, R. Grosu, Nature Machine Intelligence 2 (2020) 642–652.

Download
No fulltext has been uploaded. References only!

Journal Article | Published | English

Scopus indexed
Author
Lechner, MathiasIST Austria; Hasani, Ramin; Amini, Alexander; Henzinger, Thomas AIST Austria ; Rus, Daniela; Grosu, Radu
Department
Abstract
A central goal of artificial intelligence in high-stakes decision-making applications is to design a single algorithm that simultaneously expresses generalizability by learning coherent representations of their world and interpretable explanations of its dynamics. Here, we combine brain-inspired neural computation principles and scalable deep learning architectures to design compact neural controllers for task-specific compartments of a full-stack autonomous vehicle control system. We discover that a single algorithm with 19 control neurons, connecting 32 encapsulated input features to outputs by 253 synapses, learns to map high-dimensional inputs into steering commands. This system shows superior generalizability, interpretability and robustness compared with orders-of-magnitude larger black-box learning systems. The obtained neural agents enable high-fidelity autonomy for task-specific parts of a complex autonomous system.
Publishing Year
Date Published
2020-10-01
Journal Title
Nature Machine Intelligence
Volume
2
Page
642-652
eISSN
IST-REx-ID

Cite this

Lechner M, Hasani R, Amini A, Henzinger TA, Rus D, Grosu R. Neural circuit policies enabling auditable autonomy. Nature Machine Intelligence. 2020;2:642-652. doi:10.1038/s42256-020-00237-3
Lechner, M., Hasani, R., Amini, A., Henzinger, T. A., Rus, D., & Grosu, R. (2020). Neural circuit policies enabling auditable autonomy. Nature Machine Intelligence, 2, 642–652. https://doi.org/10.1038/s42256-020-00237-3
Lechner, Mathias, Ramin Hasani, Alexander Amini, Thomas A Henzinger, Daniela Rus, and Radu Grosu. “Neural Circuit Policies Enabling Auditable Autonomy.” Nature Machine Intelligence 2 (2020): 642–52. https://doi.org/10.1038/s42256-020-00237-3.
M. Lechner, R. Hasani, A. Amini, T. A. Henzinger, D. Rus, and R. Grosu, “Neural circuit policies enabling auditable autonomy,” Nature Machine Intelligence, vol. 2, pp. 642–652, 2020.
Lechner M, Hasani R, Amini A, Henzinger TA, Rus D, Grosu R. 2020. Neural circuit policies enabling auditable autonomy. Nature Machine Intelligence. 2, 642–652.
Lechner, Mathias, et al. “Neural Circuit Policies Enabling Auditable Autonomy.” Nature Machine Intelligence, vol. 2, Springer Nature, 2020, pp. 642–52, doi:10.1038/s42256-020-00237-3.
External material:
Press Release

Export

Marked Publications

Open Data IST Research Explorer

Search this title in

Google Scholar