Now showing1 - 4 of 4
- Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: without files , Hierarchical reinforcement learning for fleet control in multilayer container storage systemsPublicationtype: Journal Article10 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: without files , Aulis - A modular and agent-based fleet management system for mobile robots(IEEE, 2026-10-16); ; ; Modern intralogistics require flexible automation, yet traditional fleet management system (FMS) architectures are often monolithic and lack the interoperability needed for heterogeneous robot fleets. To address this, we present Aulis, an open-source, modular, and agent-based FMS designed for the vendor-agnostic coordination of mobile robots. Unlike existing closed-source solutions, Aulis decomposes core fleet-management functionalities into lightweight agents and services that communicate via the VDA 5050 standard. This architecture follows cyber-physical system principles by decoupling task allocation, routing, and optimization, thereby enhancing system scalability and maintainability. The framework's extensibility is validated through a matrix-production use case, demonstrating the seamless integration of specialized zone and parking services without altering the core system. Experimental results with heterogeneous fleets confirm the system's ability to optimize makespan and manage traffic density in dynamic environments. Consequently, Aulis provides a research-oriented platform that bridges the gap between modular flexibility and industrial realism for cyber-physical production systems.Publicationtype: Conference Paper14 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: without files , Simulation-only training for real-world localization integrity monitoring(IEEE, 2026-09); ; ; ; Reliable self-localization is a prerequisite for the safe operation of autonomous mobile robots. Particle-filter-based methods such as adaptive Monte Carlo localization (AMCL) may silently fail under dynamic disturbances, map ambiguities, or motion uncertainty. This paper presents a data-driven localization monitoring framework that detects localization failures using Light Detection and Ranging (LiDAR) scans, occupancy maps, and particle filter statistics. The monitoring model is trained exclusively in simulation using randomized environments, without real-world training data. Gradient-boosting models are employed to capture nonlinear consistency relations, and temporal feature aggregation is introduced to model failure dynamics over time. Experiments in simulation and on real robotic platforms demonstrate reliable failure detection and generalization to unseen environments and motion uncertainty levels. Cross-platform transfer to a different robot is evaluated and identified as a limitation. Simulation-only training with domain randomization achieves an F1 score of 0.86 on real-world data.Publicationtype: Conference Paper10 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: without files , Teleoperating mobile robots via VDA 5050 - a first middleware evaluation within open industrial networksTeleoperation is a practical fallback for mobile robots in intralogistics when rare but safety- and throughputcritical edge cases exceed autonomous capabilities. While Fleet Management Systems (FMSs) increasingly rely on vendor-neutral interfaces such as VDA 5050 to coordinate heterogeneous robots, teleoperation is not natively represented in the standard and is typically implemented as an ad hoc, robot-specific add-on. This paper closes this gap by proposing a VDA 5050 teleoperation extension that enables human-in-the-loop control as part of the same interface used for autonomous task and route coordination. To facilitate reproducible evaluation, we further contribute a configurable VDA 5050 traffic generator that reproduces realistic message patterns for middleware-based FMS communication. Employing the Open Radio Access Network (Open RAN) concept, cellular 5G and future 6G networks can be flexibly deployed in industrial environments to provide reliable, low-latency wireless connectivity for mobile robot teleoperation. Using an end-to-end stack consisting of VDA 5050 messaging, middleware transport, and Open RAN wireless link, we evaluate latency and communication overhead to characterize the performance implications of standardized teleoperation integration.Publicationtype: Conference Paper19