96 results
Filters
Settings
Now showing1 - 10 of 96
- 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 Article7 - 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 Paper8 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: without files , Dynamic model inversion of a soft robot using servo-constraintsDue to their flexibility, soft robots offer several advantages over their rigid counterparts in applications such as sensitive manipula-tion and human-machine interaction. However, their use in agile tasks is currently limited because dynamic control of soft robots is usually dif-ficult due to large elastic deformations, underactuation, and redundant actuation. The piecewise constant curvature (PCC) model is commonly used for dynamic forward modeling of soft robots. However, analytical inversion of forward dynamics is typically infeasible due to the model’s complexity. For control purposes, though, inverse models are necessary. In this work, we propose obtaining t he inverse dynamic model of a soft robot from the forward dynamic PCC model using the servo-constraint approach. We analyze the system’s internal stability and validate the model using a physical soft robot. Experimental results demonstrate the effectiveness of our approach indynamictrajectorytracking.Publicationtype: Conference Paper83 - 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 Paper6 - 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 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: without files , Development of a library of modular components to accelerate material flow simulation in the aviation industry(IEEE, 2025-12-07); ; ; ; Aircraft manufacturing presents significant challenges for logistics departments due to the complexity of processes and technology, as well as the high variety of parts that must be handled. To support the development and optimization of these complex logistics processes in the aviation industry, simulation is commonly employed. However, existing simulation models are typically tailored to specific use cases. Reusing or adapting these models for other aircraft-specific applications often requires substantial implementation and validation efforts. As a result, there is a need for flexible and easily adaptable simulation models. This work aims to address this challenge by developing a modular library for logistics processes in aircraft manufacturing. The outcome of this work highlights the simplifications introduced by the developed library and its application in a real aviation warehouse.Publicationtype: Conference Paper20 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: without files , Multi-object tracking for apple counting in orchards using stereo visionQuantitative fruit counting at the individual tree level is a fundamental requirement in data-driven precision agriculture and a critical input for yield estimation models. However, achieving consistent tracking and accurate detection of fruits in unstructured outdoor environments remains a challenging task due to factors such as occlusion, varying illumination and sensor noise. Moreover, conventional 2D image-based methods are prone to scale ambiguity and duplicate detections from multiple viewpoints. To overcome these challenges, this work presents a 3D fruit counting framework based on stereo cameras in which each detection is localized within a georeferenced spatial coordinate system using GPS and visual odometry. The fruits are detected using a YOLOv8x model to identify object positions within individual images. To enable tracking across multiple consecutive frames, two state-of-the-art algorithms, OC-SORT and ByteTrack, are benchmarked against each other. OC-SORT, with incorporated optical flow, achieved the best performance on the validation dataset, with HOTA = 0.59, MOTA = 0.52, and IDF1 = 0.67, while the detection model reached a mAP<inf>0.5:0.95</inf> = 0.56. The proposed fruit counting framework demonstrated promising performance on Elstar trees, yielding an estimated total counting error of 20 apples, corresponding to a RMSE of 6.24 % and an R<sup>2</sup> score of 0.96. Given that fruit count is a key parameter to yield prediction, these results support accurate yield mapping and informed precision orchard management.Publicationtype: Conference Paper21 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: without files , Towards semantically-aware few-shot 3D reconstruction(Wissenschaftliche Gesellschaft für Technische Logistik e.V. (WGTL), 2025-09-30); ; ; Acquiring rich object-level information, including shape, texture, and geometry, serves as a fundamental building block across multiple domains. In this context, few-shot reconstruction has become a prominent research field due to the ability to achieve 3D reconstruction from a limited set of input images. By leveraging prior knowledge encoded within a trained neural network, these methods can recover unseen features beyond the information obtained from the recorded sensor data. However, current approaches either model the entire environment without emphasizing specific regions of interest or restrict the process to the target object by completley neglecting the surrounding context in a prepossessing step. One potential approach is to apply object masking in the images and then directly map semantic information from 2D to 3D through deep learning. Nevertheless, this task reflecs highly non-linear properties, and integrating semantic cues remains a significant challenge. In this work-in-progress paper, we explore a pipeline for semantically aware few-shot 3D reconstruction on real-world data.Publicationtype: Journal Article12 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: without files , Comparative analysis of local trajectory planning algorithms in ROS2(IEEE, 2025-04); ; Local path planners are essential for real-time obstacle avoidance, particularly in unpredictable industrial environments. This study compares three ROS 2 local path-planning algorithms: Dynamic Window Approach (DWB), Model Predictive Path Integral (MPPI), and Regulated Pure Pursuit (RPP). These planners are part of the Robot Operating System 2 (ROS 2) navigation stack (Nav2), with DWB and MPPI as built-in controllers, and RPP integrated as a controller option.While previous studies have focused on simulations or simple real-world environments with static obstacles, few have examined dynamic and unpredictable scenarios. To address this, experiments were conducted with a Clearpath Jackal robot in environments with static and dynamic obstacles. Key metrics, including distance to obstacles, frequency of recovery behaviors, and path smoothness, were used to compare the planners performance in both real-world and simulated settings.MPPI offers a strong balance across all metrics, making it ideal for dynamic environments requiring both safety and efficiency. DWB excels in fast navigation, though with closer proximity to obstacles, while RPP produces smooth paths but struggles in highly dynamic environments. These results provide valuable insights for selecting the right local path planner for autonomous robots in industrial applications like manufacturing and warehousing.Publicationtype: Conference Paper1036 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: with files , Endbericht des Forschungsvorhabens TaBuLa-LOGplus(Technische Universität Hamburg, 2025); ; ; ; The TaBuLa-LOGplus project was based on the results of the two previous projects TaBuLa and TaBuLa-LOG in order to significantly advance automation in the interaction between passenger and freight transport. A central goal of the project was the development of a manufacturer- and vehicle-independent smart control centre, which integrates both the automated transport robots further developed by TUHH and the conventional buses used by vhh.mobility. This offers the added value of optimal use of resources by bundling transport and transportation tasks. The control centre also meets the legal requirement that the automated vehicle can be shut down by a human at any time. Data protection and security were always considered and taken into account. In tests, the control centre could be used by both experienced and non-experienced users for order creation and vehicle monitoring. To achieve this high level of automation, the transport robots were further developed to the point where they can get in and out of a conventional bus independently in order to carry out transport tasks transmitted by the control centre. Additionally, the topic of artificial intelligence (AI) was included into the TaBuLa-LOGplus project. To ensure safe operation of the transport robots in complex and dynamic environments, advanced AI methods for environment detection and situational awareness were investigated. The aim was to automatically detect anomalies and potential hazards and respond appropriately. The impact of the transport robots was investigated through accompanying analyses, simulations and assessments regarding traffic, ecological, economic and social effects. The analysis of traffic effects according to Vester showed that the system can be consciously controlled via highly active and active variables and certain causal relationships (e. g. supply and demand) must be considered. Parcel delivery using transport robots on the last mile can offer ecological and economic advantages if they are transported by an electrically powered bus. The additional simulations also lead to the conclusion that the integration of autonomous transport robots into public transport can be safe and cost-efficient. Overall, the TaBuLa-LOGplus project was the successful next step of the previous projects, as it continued, further developed and incorporated new frame-work conditions.Publicationtype: Research Report75 67