Integrative Object and Pose to Task Detection for an Augmented-Reality-based Human Assistance System using Neural Networks

Kästner, Linh; Eversberg, Leon; Mursa, Marina; Lambrecht, Jens

doi:10.1109/icce48956.2021.9352121

Cited by 6 publications

(3 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The task completion time is a measurement of speed or performance and is used in different fields (such as industrial processes (Kastner et al, 2021), medical services (Bavafa & Jónasson, 2021)). To recall, a worker accumulates fatigue and stress when performing a task and recovers from both over a break (Ferjani et al, 2017) (Mansour, 2016a).…”

Section: Completion Timementioning

confidence: 99%

Human Performance Modelling and Mission Planning Optimisation incorporating Human Performance

Asadayoobi

2024

Preprint

View full text Add to dashboard Cite

Factors related to workers and tasks have a combined effect on system performance. Management tends to make effective decisions by understanding the dynamics of the workers' performance over time, affected by their time-varying learning, fatigue, and stress levels. Such managerial decisions could improve system productivity and ensure workforce safety. Despite the importance of the problem, the literature did not focus on the performance modelling or task planning framework that includes all the mentioned factors, i.e., learning, fatigue, and stress. This dissertation includes three main contributions with different performance modelling and task allocation/scheduling planning that help managers plan mission operations, characterized as uncertain, dynamic, and time-sensitive. The first contribution (Chapter 3) is a mathematical model that modifies a popular learning curve model from the literature by making its learning exponent dependent on the fatigue level. The results of applying this model to a data set (vs. the other available ones in the literature,) showed an outperformance in terms of efficiency and balance criteria.

show abstract

Section: Completion Timementioning

confidence: 99%

Human Performance Modelling and Mission Planning Optimisation incorporating Human Performance

Asadayoobi

2024

Preprint

View full text Add to dashboard Cite

show abstract

“…To overcome paper-based manuals, AR-based assistance system with instant interaction can be one solution (Chu 2020, Hynes 2019). An AR instruction is of practical use, since it leads to a lower error rate compared to a paper-based instruction though it can have a higher time consumption (Chu 2020, Kästner et. al.…”

Section: Ar For Service and Maintenance Supportmentioning

confidence: 99%

“…2020. Other studies could prove a better time efficiency when using an AR approach (Hynes 2019, Kästner et. al.…”

Section: Ar For Service and Maintenance Supportmentioning

confidence: 99%

Human-Centered Development and Evaluation of an AR-Assistance System to Support Maintenance and Service Operations at LNG Ship Valves

Stern¹,

Leder²,

Lütjen³

2021

Competence Development and Learning Assistance Systems for the Data-Driven Future

View full text Add to dashboard Cite

The use of LNG propulsion in ships has significant environmental benefits but also creates challenges in handling the LNG. Due to the safety regulations, the maintenance of the LNG ship systems is essential and requires a high degree of reliability and accuracy. Here, digital assistance systems, e.g., based on Augment-ed Reality (AR) technology, can support the maintenance and service purposes of LNG ship systems by displaying additional information directly on the objects to be serviced. Thus, this paper deals with the development and evaluation of a digital assistance system using AR technology. The developed assistance system based on an Android smartphone enables users to access maintenance instruc-tions and manuals, simplifies spare parts' ordering, and supports the work pro-cess step by step through context-sensitive virtualizations. Its evaluation was conducted as a combined quantitative and qualitative user study. Overall, the assistance system offers promising potentials for reducing workload and improv-ing processes.

show abstract

Evaluating digital work instructions with augmented reality versus paper-based documents for manual, object-specific repair tasks in a case study with experienced workers

Eversberg

Lambrecht

2023

Int J Adv Manuf Technol

View full text Add to dashboard Cite

Manual repair tasks in the industry of maintenance, repair, and overhaul require experience and object-specific information. Today, many of these repair tasks are still performed and documented with inefficient paper documents. Cognitive assistance systems have the potential to reduce costs, errors, and mental workload by providing all required information digitally. In this case study, we present an assistance system for object-specific repair tasks for turbine blades. The assistance system provides digital work instructions and uses augmented reality to display spatial information. In a user study with ten experienced metalworkers performing a familiar repair task, we compare time to task completion, subjective workload, and system usability of the new assistance system to their established paper-based workflow. All participants stated that they preferred the assistance system over the paper documents. The results of the study show that the manual repair task can be completed 21% faster and with a 26% lower perceived workload using the assistance system.

show abstract

Integrative Object and Pose to Task Detection for an Augmented-Reality-based Human Assistance System using Neural Networks

Cited by 6 publications

References 15 publications

Human Performance Modelling and Mission Planning Optimisation incorporating Human Performance

Human Performance Modelling and Mission Planning Optimisation incorporating Human Performance

Human-Centered Development and Evaluation of an AR-Assistance System to Support Maintenance and Service Operations at LNG Ship Valves

Evaluating digital work instructions with augmented reality versus paper-based documents for manual, object-specific repair tasks in a case study with experienced workers

Contact Info

Product

Resources

About