Rezumat articol ediţie STUDIA UNIVERSITATIS BABEŞ-BOLYAI

În partea de jos este prezentat rezumatul articolului selectat. Pentru revenire la cuprinsul ediţiei din care face parte acest articol, se accesează linkul din titlu. Pentru vizualizarea tuturor articolelor din arhivă la care este autor/coautor unul din autorii de mai jos, se accesează linkul din numele autorului.

 
       
         
    STUDIA THEOLOGIA REFORMATA TRANSYLVANICA - Ediţia nr.2 din 2022  
         
  Articol:   CONSECINȚELE UNEI ANALIZE FOLOSIND ANALOGII BIBLICE PENTRU PROIECTAREA CONTROLULUI AUTOMAT AL VEHICULELOR * CONSEQUENCES OF AN ANALYSIS USING BIBLICAL ANALOGIES FOR AUTOMATED VEHICLE CONTROL DESIGN * EGY BIBLIAI ANALÓGIÁKAT HASZNÁLÓ ELEMZÉS KÖVETKEZMÉNYEI AZ AUTOMATIZÁLT JÁRMŰVEZÉRLŐ TERVEZÉSHEZ.

Autori:  NÉMETH BALÁZS.
 
       
         
  Rezumat:  
DOI: 10.24193/subbtref.67.2.02

Published Online: 2022-12-29
Published Print: 2022-12-30
pp. 29-56

VIEW PDF

FULL PDF

Abstract: The paper proposes an analysis of learning-based approaches for automated vehicle control systems from an ethical viewpoint. An analysis using analogies between selected biblical texts and operation concepts of learning-based approaches is performed. Thus, analogies for supervised, unsupervised, and reinforcement learning-based approaches are created. Through the analogies, the root of the automatic control design problems, i.e. forming objective functions, on a theological level is explored. The analysis leads to three consequences, which are related to the difficulty of forming control objective, the difficulty of considering human objectives in control, and the necessity of viewing systems in all their complexity. The paper proposes the application of the consequences in an illustrative route selection vehicle control example. A multi-layer control concept involving the consequences of the analysis is proposed, with which some ethical challenges of the selected control problem can be handled.

Keywords: biblical analogies, automated vehicle control, ethical challenges, machine learning
 
         
     
         
         
      Revenire la pagina precedentă