EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Compensating for Sensing Failures via Delegation in Human–AI Hybrid Systems

Andrew Fuchs iD, Andrea Passarella iD, Marco Conti iD

Sensors · 2023

DOI: 10.3390/s23073409 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, 2023. Verfasst von Andrew Fuchs und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science, Universitá di Pisa, 56124 Pisa, Italy. Hauptthemen laut MEDLINE: Learning, Intelligence. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 44 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: H2020 Humane-AI-Net, CHIST-ERA, European Union under the Italian National Recovery and Resilience Plan (NRRP) of partnership on "Artificial Intelligence: Foundational Aspects".

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Given the increasing prevalence of intelligent systems capable of autonomous actions or augmenting human activities, it is important to consider scenarios in which the human, autonomous system, or both can exhibit failures as a result of one of several contributing factors (e.g., perception). Failures for either humans or autonomous agents can lead to simply a reduced performance level, or a failure can lead to something as severe as injury or death. For our topic, we consider the hybrid human–AI teaming case where a managing agent is tasked with identifying when to perform a delegated assignment and whether the human or autonomous system should gain control. In this context, the manager will estimate its best action based on the likelihood of either (human, autonomous) agent’s failure as a result of their sensing capabilities and possible deficiencies. We model how the environmental context can contribute to, or exacerbate, these sensing deficiencies. These contexts provide cases where the manager must learn to identify agents with capabilities that are suitable for decision-making. As such, we demonstrate how a reinforcement learning manager can correct the context–delegation association and assist the hybrid team of agents in outperforming the behavior of any agent working in isolation.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

LearningIntelligenceHumansArtificial Intelligence

Stichwörter der Autor:innen

delegationentity detectionreinforcement learningsimulated sensing

Autor:innen und Institutionen

  • Department of Computer Science, Universitá di Pisa, 56124 Pisa, Italy.
  • Institute for Informatics and Telematics (IIT), National Research Council (CNR), 56124 Pisa, Italy.

ORCID-Profile: Andrew Fuchs, Andrea Passarella, Marco Conti

Förderung

  • H2020 Humane-AI-Net
  • CHIST-ERA
  • European Union under the Italian National Recovery and Resilience Plan (NRRP) of partnership on "Artificial Intelligence: Foundational Aspects"
  • European Union under the Italian National Recovery and Resilience Plan (NRRP) of partnership on “Artificial Intelligence: Foundational Aspects”

Zitieren

APA

Fuchs, A., Passarella, A., & Conti, M. (2023). Compensating for Sensing Failures via Delegation in Human–AI Hybrid Systems. Sensors. https://doi.org/10.3390/s23073409

Vancouver

Fuchs A, Passarella A, Conti M. Compensating for Sensing Failures via Delegation in Human–AI Hybrid Systems. Sensors. 2023. doi:10.3390/s23073409

BibTeX
@article{Fuchs2023,
  author = {Fuchs, Andrew and Passarella, Andrea and Conti, Marco},
  title = {Compensating for Sensing Failures via Delegation in Human–AI Hybrid Systems},
  journal = {Sensors},
  year = {2023},
  doi = {10.3390/s23073409}
}
Kostenlos starten →