--- res: bibo_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.@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: Alexander foaf_name: Amini, Alexander foaf_surname: Amini - foaf_Person: foaf_givenName: Thomas A foaf_name: Henzinger, Thomas A foaf_surname: Henzinger foaf_workInfoHomepage: http://www.librecat.org/personId=40876CD8-F248-11E8-B48F-1D18A9856A87 orcid: 0000-0002-2985-7724 - 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: 10.1038/s42256-020-00237-3 bibo_volume: 2 dct_date: 2020^xs_gYear dct_identifier: - UT:000583337200011 dct_isPartOf: - http://id.crossref.org/issn/2522-5839 dct_language: eng dct_publisher: Springer Nature@ dct_title: Neural circuit policies enabling auditable autonomy@ ...