Optimization of Machine Learning Models Applied to Robot Localization in the RobotAtFactory 4.0 Competition DOI
Luan C. Klein, João Mendes, João Braun

и другие.

Communications in computer and information science, Год журнала: 2024, Номер unknown, С. 112 - 125

Опубликована: Янв. 1, 2024

Язык: Английский

Machine learning-based multi-sensor fusion for warehouse robot in GPS-denied environment DOI
Abhilasha Singh, V. Kalaichelvi, R. Karthikeyan

и другие.

Multimedia Tools and Applications, Год журнала: 2023, Номер 83(18), С. 56229 - 56246

Опубликована: Дек. 11, 2023

Язык: Английский

Процитировано

2

Fast 50 Hz Updated Static Infrared Positioning System Based on Triangulation Method DOI Open Access
Maciej Ciężkowski, Rafał Kociszewski

Опубликована: Фев. 2, 2024

One of the important issues being explored in Industry 4.0 is a collaborative mobile robots. This collaboration requires precise navigation systems, especially indoor systems where GNSS (Global Navigation Satellite System) cannot be used. To enable localization robots, different variations are developed, mainly based on trilateration and triangulation methods. Triangulation distinguished by fact that they allow determination an object’s orientation, which for An feature positioning frequency position updates measurements. For most it 10-20 Hz. In our work, we propose high-speed 50 Hz system method with infrared transmitters receivers. addition, completely static, i.e. has no moving/rotating measurement sensors, makes more resistant to disturbances (caused vibrations, wear tear components, etc.). this paper describe principle as well its design. Finally, present tests built system, show centimeter accuracy update

Язык: Английский

Процитировано

0

Extended Kalman Filter Algorithm for Accurate State-of-Charge Estimation in Lithium Batteries DOI Open Access
Gen Li, Qian Mao, Fan Yang

и другие.

Processes, Год журнала: 2024, Номер 12(8), С. 1560 - 1560

Опубликована: Июль 25, 2024

With the continuous development of industrial and energy industries, new vehicles is entering a period rapid one hot research directions today. Due to needs different working environments, demand for mobile power sources in automobiles increasing, which means that battery design system management (BMS) determine their work efficiency. How enable users accurately real-time understand usage status electric vehicle batteries very important thing, it also an challenge faced process vehicles. This article proposes state-of-charge (SOC) estimation method based on extended Kalman filter algorithm (EKF) core areas BMS–battery (SOC). According guidance direction Industry 4.0 Germany, we hope address some aforementioned challenges automotive robotics products while developing our industry. Therefore, made innovative explorations this direction. In study, was found can adjust parameters achieve better convergence. The final results indicate had high accuracy robustness meet current vehicles, providing safety control BMS. long run, will change situation monitoring using sources. At same time, provided effective practical implementation template production estimation, has certain heuristic effect future estimation.

Язык: Английский

Процитировано

0

A Cable-driven Parallel Robot for High-rack Logistics Automation DOI
Seunggyun Ha, Seongwoo Woo,

Min-Cheol Kim

и другие.

International Journal of Control Automation and Systems, Год журнала: 2024, Номер 22(11), С. 3329 - 3340

Опубликована: Ноя. 1, 2024

Язык: Английский

Процитировано

0

Indoor Positioning Systems in Logistics: A Review DOI Creative Commons

Laura Vaccari,

Antonio Maria Coruzzolo, Francesco Lolli

и другие.

Logistics, Год журнала: 2024, Номер 8(4), С. 126 - 126

Опубликована: Дек. 4, 2024

Background: Indoor Positioning Systems (IPS) have gained increasing relevance in logistics, offering solutions for safety enhancement, intralogistics management, and material flow control across various environments such as industrial facilities, offices, hospitals, supermarkets. This study aims to evaluate IPS technologies’ performance applicability guide practitioners selecting systems suited specific contexts. Methods: The systematically reviews key technologies, positioning methods, data types, filtering hybrid alongside real-world examples of applications testing environments. Results: Our findings reveal that radio-based Radio Frequency Identification (RFID), Ultra-wideband (UWB), Wi-Fi, Bluetooth (BLE), are the most commonly used, with UWB highest accuracy settings. Geometric particularly multilateration, proved be effective supported by advanced techniques like Extended Kalman Filter machine learning models Convolutional Neural Networks. Overall, approaches integrate multiple technologies demonstrated enhanced reliability, effectively mitigating environmental interferences signal attenuation. Conclusions: provides valuable insights logistics practitioners, emphasizing importance operational contexts, where precision reliability critical success.

Язык: Английский

Процитировано

0

Kabsch Marker Estimation Algorithm—A Multi-Robot Marker-Based Localization Algorithm Within the Industry 4.0 Context DOI Creative Commons
João Braun, José Lima, Ana I. Pereira

и другие.

IEEE Access, Год журнала: 2024, Номер 12, С. 68711 - 68729

Опубликована: Янв. 1, 2024

This paper introduces the Kabsch Marker Estimation Algorithm (KMEA), a new, robust multi-marker localization method designed for Autonomous Mobile Robots (AMRs) within Industry 4.0 (I4.0) settings. By integrating Algorithm, our approach significantly enhances robustness by aligning detected fiducial markers with their known positions. Unlike conventional methods that rely on limited subset of visible markers, KMEA uses all available without requiring camera's extrinsic parameters, thereby improving robustness. The algorithm was validated in an I4.0 automated warehouse mockup, four-stage methodology compared to previously established marker estimation reference. On one hand, results have demonstrated KMEA's similar performance standard controlled scenarios, millimetric precision across set error metrics and mean relative (MRE) less than 1%. other KMEA, when faced challenging test scenarios outliers, showed superior baseline algorithm, where it maintained centimetric scale metrics, whereas suffered extreme degradation. emphasized average reduced from 86.9% 92% Parts III IV methodology, respectively. These were achieved using low-cost hardware, indicating possibility even greater accuracy advanced equipment. details algorithm's development, theoretical framework, comparative advantages over existing methods, discusses results, concludes comments regarding its potential industrial commercial applications scalability reliability.

Язык: Английский

Процитировано

0

Optimization of Machine Learning Models Applied to Robot Localization in the RobotAtFactory 4.0 Competition DOI
Luan C. Klein, João Mendes, João Braun

и другие.

Communications in computer and information science, Год журнала: 2024, Номер unknown, С. 112 - 125

Опубликована: Янв. 1, 2024

Язык: Английский

Процитировано

0