Towards Fault-Tolerant AGV Task Scheduling in Flexible Manufacturing Systems Using a Tree-Based Max-Plus Predictive Approach
Sensors · 19.06.2026 · 26 (12) · 3898
DOI: 10.3390/s26123898 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 19.06.2026. Verfasst von Dominik Zaborniak und 3 weiteren Autor:innen. Beteiligte Einrichtung: Institute of Control and Computation Engineering, University of Zielona Góra, ul. Prof. Z. Szafrana 2, 65-516 Zielona Góra, Poland. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 26 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Efficient task assignment for mobile robots is a crucial challenge in modern intralogistics. This paper presents an integrated cyber-physical framework combining predictive tree search on switching max-plus linear systems with a physical IoT-based dispatch interface. The scheduling problem is modelled as a discrete event system, where standard max-plus algebra captures robot synchronization, and a switching mechanism represents alternative resource assignments. To address real-world operational disturbances, the predictive model is enhanced with a fault-tolerant control (FTC) mechanism that dynamically estimates and adapts to non-stationary transport delays. The resulting decision space, which grows exponentially with the prediction horizon, is explored via a predictive tree search algorithm utilizing a quadratic cost function to penalize excessive and uneven transport times. The physical dispatch layer is realized using KIS.BOX IoT devices acting as operator-controlled stations, communicating with the central controller via a WebSocket/STOMP event stream and a lightweight REST API. Simulation results obtained in a Blender 3D environment demonstrate that the proposed FTC predictive strategy significantly reduces the variance of task completion times under fault conditions compared to a baseline First-In-First-Out approach. Furthermore, the IoT integration successfully simulates and validates the feasibility of human-in-the-loop task injection within a realistic, stochastic scenario.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Institute of Control and Computation Engineering, University of Zielona Góra, ul. Prof. Z. Szafrana 2, 65-516 Zielona Góra, Poland.
- Doctoral School of Exact and Technical Sciences, University of Zielona Góra, ul. Prof. Z. Szafrana 2, 65-516 Zielona Góra, Poland.
ORCID-Profile: Dominik Zaborniak, Paweł Kasza, Marcin Pazera, Marcin Witczak
Zitieren
APA
Zaborniak, D., Kasza, P., Pazera, M., & Witczak, M. (2026). Towards Fault-Tolerant AGV Task Scheduling in Flexible Manufacturing Systems Using a Tree-Based Max-Plus Predictive Approach. Sensors, 26(12), 3898. https://doi.org/10.3390/s26123898
Vancouver
Zaborniak D, Kasza P, Pazera M, Witczak M. Towards Fault-Tolerant AGV Task Scheduling in Flexible Manufacturing Systems Using a Tree-Based Max-Plus Predictive Approach. Sensors. 2026;26(12):3898. doi:10.3390/s26123898
BibTeX
@article{Zaborniak2026,
author = {Zaborniak, Dominik and Kasza, Paweł and Pazera, Marcin and Witczak, Marcin},
title = {Towards Fault-Tolerant AGV Task Scheduling in Flexible Manufacturing Systems Using a Tree-Based Max-Plus Predictive Approach},
journal = {Sensors},
year = {2026},
volume = {26},
number = {12},
pages = {3898},
doi = {10.3390/s26123898}
}
EUVIMED