Requirements and Barriers for Human-Centered SMEs

Sensors, Год журнала: 2024, Номер 24(14), С. 4681 - 4681

Опубликована: Июль 19, 2024

With the advantages of new technologies and rising demand from customers, it is necessary to improve manufacturing process. This necessity was recognized by industry; therefore, concept Industry 4.0 has been implemented in various areas services. The backbone main aspect digitalization implementation into processes. While this helps manufacturers with modernization optimization many attributes processes, 5.0 takes a step further brings importance human factor industry practice, together sustainability resilience. contributes idea creating sustainable, prosperous, human-friendly environment within companies. focus article analyze existing literature regarding what missing successful centricity namely small medium-sized factories (SMEs). These findings are then presented form requirements barriers for SME factories, which can serve as guidelines implementing human-centered using axiomatic design theory SMEs, roadmap practitioners.

Язык: Английский

---

Mitigating safety challenges in human-robot collaboration: The role of human competence

Technological Forecasting and Social Change, Год журнала: 2025, Номер 213, С. 124022 - 124022

Опубликована: Фев. 13, 2025

Язык: Английский

---

Determination and quantitative representation of three-level dispersion system in asphalt mixture interface area

Materials & Design, Год журнала: 2025, Номер unknown, С. 113879 - 113879

Опубликована: Март 1, 2025

Язык: Английский

---

H2R Bridge: Transferring vision-language models to few-shot intention meta-perception in human robot collaboration

Journal of Manufacturing Systems, Год журнала: 2025, Номер 80, С. 524 - 535

Опубликована: Апрель 7, 2025

Язык: Английский

---

A deep learning-enabled visual-inertial fusion method for human pose estimation in occluded human-robot collaborative assembly scenarios

Robotics and Computer-Integrated Manufacturing, Год журнала: 2024, Номер 93, С. 102906 - 102906

Опубликована: Ноя. 30, 2024

Язык: Английский

---

System Design for Sensing in Manufacturing to Apply AI through Hierarchical Abstraction Levels

Sensors, Год журнала: 2024, Номер 24(14), С. 4508 - 4508

Опубликована: Июль 12, 2024

Activity recognition combined with artificial intelligence is a vital area of research, ranging across diverse domains, from sports and healthcare to smart homes. In the industrial domain, manual assembly lines, emphasis shifts human–machine interaction thus human activity (HAR) within complex operational environments. Developing models methods that can reliably efficiently identify activities, traditionally just categorized as either simple or remains key challenge in field. Limitations existing approaches include their inability consider contextual complexities associated performed activities. Our approach address this create different levels abstractions, which allow for more nuanced comprehension activities define underlying patterns. Specifically, we propose new hierarchical taxonomy abstraction based on context be used HAR. The proposed hierarchy consists five levels, namely atomic, micro, meso, macro, mega. We compare other divide into categories well similar classification schemes provide real-world examples applications demonstrate its efficacy. Regarding advanced technologies like intelligence, our study aims guide optimize procedures, particularly uncontrolled non-laboratory environments, by shaping workflows enable structured data analysis highlighting correlations various throughout progression. addition, it establishes effective communication shared understanding between researchers industry professionals while also providing them essential resources facilitate development systems, sensors, algorithms custom use cases adapt level abstraction.

Язык: Английский

---

Safe and reconfigurable manufacturing: safety aware multi-agent control for Plug & Produce system

The International Journal of Advanced Manufacturing Technology, Год журнала: 2024, Номер 134(1-2), С. 529 - 544

Опубликована: Июль 23, 2024

Abstract Plug & Produce aims to revolutionize manufacturing by enabling seamless machine integration into production processes without extensive programming. This concept, leveraging multi-agent systems (MAS), offers increased flexibility and faster ramp-up times after reconfiguration. As automated moves towards greater human integration, this paper addresses safe operation within the concept. The main safety challenge arises from autonomous decision-making, as agents in MAS lack awareness of risk consequences their behavior. Additionally, difficulty perceiving system’s exact behavior leads implementation overly restrictive measures. limits ability make decisions for efficient production. proposes a method utilizing control conduct automatic analysis reason task allocations avoid risks. method’s benefits are generation actions that comply with requirements during operation, eliminating need measures allowing more effective equipment utilization. benefit is illustrated through scenario two different configurations: one using hazardous other less one. Formal verification model checker NuSMV demonstrated were satisfied both configurations, manual modifications system results specific showed there reachable states (20 states) safer second configuration, compared first configuration (16 states). means presented strategy dynamically adjusts confirm safety. Hence, maintains fixed rules limit operations.

Язык: Английский

---

Centering on Humans - Intersectionality in Vision Systems for Human Order Picking

IFIP advances in information and communication technology, Год журнала: 2024, Номер unknown, С. 421 - 434

Опубликована: Янв. 1, 2024

Язык: Английский

---

Multimodal data extraction and analysis for the implementation of Temporal Action Segmentation models in Manufacturing^*

2022 8th International Conference on Control, Decision and Information Technologies (CoDIT), Год журнала: 2024, Номер unknown, С. 854 - 859

Опубликована: Июль 1, 2024

Язык: Английский

---

Around-Body Versus On-Body Motion Sensing: A Comparison of Efficacy Across a Range of Body Movements and Scales

Bioengineering, Год журнала: 2024, Номер 11(11), С. 1163 - 1163

Опубликована: Ноя. 19, 2024

Motion is vital for life. Currently, the clinical assessment of motion abnormalities largely qualitative. We previously developed methods to quantitatively assess using visual detection systems (around-body) and stretchable electronic sensors (on-body). Here we compare efficacy these across predefined motions, hypothesizing that around-body system detects with similar accuracy as on-body sensors. Six human volunteers performed six defined motions covering three excursion lengths, small, medium, large, which were analyzed via both marker (MoCa version 1.0) (BioStamp 1.0). Data from each was compared extent trackability comparative between systems. Both successfully detected allowing quantitative analysis. Angular displacement had highest agreement efficiency bicep curl body lean motion, 73.24% 65.35%, respectively. The finger pinch an 36.71% chest abduction/adduction 45.55%. Shoulder shoulder flexion/extension lowest efficiencies 24.49% 26.28%, MoCa comparable BioStamp in terms angular displacement, though velocity linear speed output could benefit additional processing. Our findings demonstrate non-contact sensor detection, offers insight best selection specific uses based on use-case desired being analyzed.

Язык: Английский

---