On the Impact of the Rules on Autonomous Drive Learning

Sie sind hier: Homepage > Suche

On the Impact of the Rules on Autonomous Drive Learning

Freier Zugriff

Talamini, Jacopo / Bartoli, Alberto / De Lorenzo, Andrea De / Medvet, Eric

Autonomous vehicles raise many ethical and moral issues that are not easy to deal with and that, if not addressed correctly, might be an obstacle to the advent of such a technological revolution. These issues are critical because autonomous vehicles will interact with human road users in new ways and current traffic rules might not be suitable for the resulting environment. We consider the problem of learning optimal behavior for autonomous vehicles using Reinforcement Learning in a simple road graph environment. In particular, we investigate the impact of traffic rules on the learned behaviors and consider a scenario where drivers are punished when they are not compliant with the rules, i.e., a scenario in which violation of traffic rules cannot be fully prevented. We perform an extensive experimental campaign, in a simulated environment, in which drivers are trained with and without rules, and assess the learned behaviors in terms of efficiency and safety. The results show that drivers trained with rules enforcement are willing to reduce their efficiency in exchange for being compliant to the rules, thus leading to more overall safety.

Zugriff

Download

Exportieren, teilen und zitieren

Dokumentinformationen

Titel :

On the Impact of the Rules on Autonomous Drive Learning

Beteiligte:

Talamini, Jacopo (Autor:in) / Bartoli, Alberto (Autor:in) / De Lorenzo, Andrea De (Autor:in) / Medvet, Eric (Autor:in) / Talamini, Jacopo / Bartoli, Alberto / De Lorenzo, Andrea De / Medvet, Eric

Erscheinungsdatum :

2020-01-01

DOI :

https://doi.org/10.3390/app10072394

Medientyp :

Aufsatz (Zeitschrift)

Format :

Elektronische Ressource

Sprache :

Englisch

Schlagwörter :

Reinforcement Learning , Self-driving Vehicle , Traffic Rules