Cloud-Based Hierarchical Imitation Learning for Scalable Transfer of Construction Skills from Human Workers to Assisting Robots DOI Creative Commons

Hongrui Yu,

Vineet R. Kamat, Carol C. Menassa

и другие.

arXiv (Cornell University), Год журнала: 2023, Номер unknown

Опубликована: Янв. 1, 2023

Assigning repetitive and physically-demanding construction tasks to robots can alleviate human workers's exposure occupational injuries. Transferring necessary dexterous adaptive artisanal craft skills from workers is crucial for the successful delegation of achieving high-quality robot-constructed work. Predefined motion planning scripts tend generate rigid collision-prone robotic behaviors in unstructured site environments. In contrast, Imitation Learning (IL) offers a more robust flexible skill transfer scheme. However, majority IL algorithms rely on repeatedly demonstrate task performance at full scale, which be counterproductive infeasible case To address this concern, paper proposes an immersive, cloud robotics-based virtual demonstration framework that serves two primary purposes. First, it digitalizes process, eliminating need physical manipulation heavy objects. Second, employs federated collection reusable demonstrations are transferable similar future thus reduce requirement illustration by agents. Additionally, enhance trustworthiness, explainability, ethical soundness robot training, utilizes Hierarchical (HIL) model decompose into sequential reactive sub-skills. These layers represented deep generative models, enabling control actions. By delegating strains work human-trained robots, promotes inclusion with diverse capabilities educational backgrounds within industry.

Язык: Английский

Dynamic Modeling and Simulation of Mobile Robot Under Disturbances and Obstacles in an Environment DOI Open Access
Vesna Knights,

Olivera Petrovska

Journal of Applied Mathematics and Computation, Год журнала: 2024, Номер 8(1), С. 59 - 67

Опубликована: Апрель 26, 2024

This paper aims to develop a mathematical model of mobile robot, utilizing deductive approach create versatile applicable various tasks and adjusted for specific scenarios.The study employed dynamic modeling simulation analysis investigate the posture stabilization humanoid upperbody robot amidst diverse disturbances cart movements.Control strategies were implemented, simulations conducted using MATLAB assess robot's stability performance under findings demonstrate successful navigation through obstacle configurations, albeit encountering challenges at higher speeds.The emphasizes relevance robots in human-centered environments, underscoring importance balance, stability, accuracy functioning.This research provides new insights directions future studies field robotics.It highlights practical implications developing capable navigating complex contributing advancements service robotics.By simulating wheeled this offers original contributions literature.It underscores significance addressing related posture, robustness, avoidance enhancing functionality real-world applications

Язык: Английский

Процитировано

4

Medical and Surgical Emergencies in Occupational Medicine: A Comprehensive Review DOI Open Access

Joshua A Jogie,

Jeremy Jogie,

Amrita P Ramharacksingh

и другие.

Cureus, Год журнала: 2025, Номер unknown

Опубликована: Янв. 6, 2025

This review aims to provide a general resource for occupational health stakeholders. It also serves as clinical guide frontline providers and policy framework employers regulators. Medical surgical emergencies in settings can cause serious harm if not identified managed early. covers trauma, chemical exposures, thermal injuries, respiratory distress, infectious hazards. We outline signs, diagnostic steps, initial care, follow-up plans. discuss preventive strategies such hazard assessments safety protocols. Evidence-based guidelines practical methods lower injury death rates. Our objective is help stakeholders recognize risks, respond fast, improve outcomes. Future studies should monitor examine new threats, novel industrial processes evolving pathogens, optimize workplace safety.

Язык: Английский

Процитировано

0

Human–robot interaction in industry: a tertiary study DOI Open Access
Marta Rinaldi, Valentina Di Pasquale,

Paola Farina

и другие.

Procedia Computer Science, Год журнала: 2025, Номер 253, С. 1691 - 1701

Опубликована: Янв. 1, 2025

Язык: Английский

Процитировано

0

Large Language Models for topic analysis: insights from robotic accident narratives DOI Open Access
Francesco Costantino, Nicolò Sabetta

Procedia Computer Science, Год журнала: 2025, Номер 253, С. 1462 - 1472

Опубликована: Янв. 1, 2025

Язык: Английский

Процитировано

0

A Literature Review on Safety Perception and Trust during Human–Robot Interaction with Autonomous Mobile Robots That Apply to Industrial Environments DOI
Justin M. Haney, Ci-Jyun Liang

IISE Transactions on Occupational Ergonomics and Human Factors, Год журнала: 2024, Номер 12(1-2), С. 6 - 27

Опубликована: Янв. 8, 2024

Autonomous mobile robots are used in manufacturing and warehousing industries, to transport material across the facility deliver parts work cells. Human workers might encounter or interact with these aisle ways at their workstation. It is important consider factors that impact worker safety trust when implementing autonomous workplace. This paper reviews prior research aims improve of human-robot interaction identifies needs for future research. Researchers a variety questionnaires behavioral assessment methods measure perceived safety. Factors such as robot appearance, approach speed, direction, significantly affect Additionally, projection signals on floor, turn signals, haptic communication devices, can predictability overall navigation.

Язык: Английский

Процитировано

2

Applications of existing and emerging construction safety technologies DOI
Omar Maali, Chien–Ho Ko, Phuong H. D. Nguyen

и другие.

Automation in Construction, Год журнала: 2023, Номер 158, С. 105231 - 105231

Опубликована: Дек. 9, 2023

Язык: Английский

Процитировано

6

Exploring three pillars of construction robotics via dual-track quantitative analysis DOI Creative Commons
Yuming Liu,

Aidi Hizami bin Alias,

Nuzul Azam Haron

и другие.

Automation in Construction, Год журнала: 2024, Номер 162, С. 105391 - 105391

Опубликована: Март 23, 2024

Construction robotics has emerged as a leading technology in the construction industry. This paper conducts an innovative dual-track quantitative comprehensive method to analyze current literature and assess future trends. First, bibliometric review of 955 journal articles published between 1974 2023 was performed, exploring keywords, journals, countries, clusters. Furthermore, neural topic model based on BERTopic addresses modeling repetition issues. The study identifies building information (BIM), human–robot collaboration (HRC), deep reinforcement learning (DRL) "three pillars" field. Additionally, we systematically reviewed relevant nested symbiotic relationships. outcome this is twofold: first, findings provide qualitative scientific guidance for research trends; second, analysis methodology simultaneously stimulates critical thinking about other similarly trending topics characterized avoid high degree homogeneity corpus overlap.

Язык: Английский

Процитировано

2

Catalysing Construction Safety: A Comparative Analysis of Technological Advancements across High-Risk Industries DOI Creative Commons
Adeeb Sidani, João Poças Martins, Alfredo Soeiro

и другие.

Buildings, Год журнала: 2023, Номер 13(11), С. 2885 - 2885

Опубликована: Ноя. 19, 2023

This article presents a comprehensive review of the safety status and technological development in high-risk industries, with focus on construction, mining, agriculture, transportation, healthcare, energy sectors. The objective is to analyse compare current practices, challenges, advancements these industries identify common trends, knowledge gaps, potential areas for improvement. explores incidence accidents, associated costs, traditional methods, limitations, emerging technologies employed enhance across multiple industries. aims provide insights lessons that can be applied practices construction industry. findings highlight critical role mitigating risks fostering culture diverse

Язык: Английский

Процитировано

4

Enhancing Human Safety in Production Environments Within the Scope of Industry 5.0 DOI
Serra Aksoy, Pınar Demircioğlu, İsmail Böğrekçi

и другие.

Lecture notes in mechanical engineering, Год журнала: 2024, Номер unknown, С. 200 - 212

Опубликована: Янв. 1, 2024

Язык: Английский

Процитировано

1

Cloud-Based Hierarchical Imitation Learning for Scalable Transfer of Construction Skills from Human Workers to Assisting Robots DOI

Hongrui Yu,

Vineet R. Kamat, Carol C. Menassa

и другие.

Journal of Computing in Civil Engineering, Год журнала: 2024, Номер 38(4)

Опубликована: Апрель 17, 2024

Assigning repetitive and physically demanding construction tasks to robots can alleviate human workers' exposure occupational injuries, which often result in significant downtime or premature retirement. However, the successful delegation of achievement high-quality robot-constructed work requires transferring necessary dexterous adaptive craft skills from workers robots. Predefined motion planning scripts tend generate rigid collision-prone robotic behaviors unstructured site environments. In contrast, imitation learning (IL) offers a more robust flexible skill transfer scheme. majority IL algorithms rely on repeatedly demonstrating task performance at full scale, be counterproductive infeasible case work. To address this concern, paper, we propose an immersive Cloud Robotics-based virtual demonstration framework that serves two primary purposes. First, it digitalizes process, eliminating need for physical manipulation heavy objects. Second, employs federated collection reusable demonstrations are transferable similar future can, consequently, reduce requirement illustration by agents. addition, enhance trustworthiness, explainability, ethical soundness robot training, utilizes hierarchical (HIL) model decompose into sequential reactive subskills. These layers represented deep generative models; these models enable control action. The proposed has potential mitigate technical adoption barriers facilitate practical deployment full-scale perform variety with supervision. By delegating strains human-trained robots, promotes inclusion diverse capabilities educational backgrounds within industry.

Язык: Английский

Процитировано

1