View in EDS

Leveraging Performance-Shaping Factors for a human-centric adaptive automation algorithm.

Saved in:
Bibliographic Details
Title: Leveraging Performance-Shaping Factors for a human-centric adaptive automation algorithm.
Authors: Bernabei, Margherita1 (AUTHOR) margherita.bernabei@uniroma1.it
Source: Procedia Computer Science. 2025, Vol. 253, p146-154. 9p.
Subject Terms: Manufacturing processes, Time management, Human error, Well-being, Algorithms
Abstract: Existing algorithms for human-machine activities allocation neglect human-centricity and adaptability. This research innovatively integrates Performance Shaping Factors (PSFs) into an adaptive allocation algorithm to safeguard worker wellbeing and system performance, since it is common knowledge that PSFs influence human status and errors. In the proposed three-phase algorithm, PSFs, together with human health and safety risks, availability of technologies and tools to perform tasks, guide the definition of static and adaptive activities. Performance analyses then define the allocation of adaptive activities, and continuous monitoring of dynamic factors assesses the possible shift of such allocation over time. PSFs models are investigated to identify categories of factors for manufacturing and collaborative contexts. Methodology and algorithm design are detailed, along with practical implementation steps. This research provides insights for human-centric manufacturing systems, addressing human factors and offering avenues for enhanced system performance and worker wellbeing thanks to adaptive manufacturing environments. [ABSTRACT FROM AUTHOR]
Database: Supplemental Index
Description
Abstract:Existing algorithms for human-machine activities allocation neglect human-centricity and adaptability. This research innovatively integrates Performance Shaping Factors (PSFs) into an adaptive allocation algorithm to safeguard worker wellbeing and system performance, since it is common knowledge that PSFs influence human status and errors. In the proposed three-phase algorithm, PSFs, together with human health and safety risks, availability of technologies and tools to perform tasks, guide the definition of static and adaptive activities. Performance analyses then define the allocation of adaptive activities, and continuous monitoring of dynamic factors assesses the possible shift of such allocation over time. PSFs models are investigated to identify categories of factors for manufacturing and collaborative contexts. Methodology and algorithm design are detailed, along with practical implementation steps. This research provides insights for human-centric manufacturing systems, addressing human factors and offering avenues for enhanced system performance and worker wellbeing thanks to adaptive manufacturing environments. [ABSTRACT FROM AUTHOR]
ISSN:18770509
DOI:10.1016/j.procs.2025.01.078