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.

On the Impact of the Rules on Autonomous Drive Learning

Talamini, Jacopo;Bartoli, Alberto;De Lorenzo, Andrea De;Medvet, Eric
2020-01-01

Abstract

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.
File in questo prodotto:
File Dimensione Formato  
2020-AppSci-LearningToDriveWithRules.pdf

accesso aperto

Tipologia: Bozza finale post-referaggio (post-print)
Licenza: Creative commons
Dimensione 314.76 kB
Formato Adobe PDF
314.76 kB Adobe PDF Visualizza/Apri
applsci-10-02394-v2.pdf

accesso aperto

Tipologia: Documento in Versione Editoriale
Licenza: Creative commons
Dimensione 314.14 kB
Formato Adobe PDF
314.14 kB Adobe PDF Visualizza/Apri
Pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11368/2961655
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 14
  • ???jsp.display-item.citation.isi??? 8
social impact