Biophysics-based simulation of virtual human model interactions in 3D virtual scenes

Risvas, Konstantinos; Pavlou, Michail; Zacharaki, Evangelia I.; Μουστάκας, Κωνσταντίνος

doi:10.1109/vrw50115.2020.00026

Cited by 4 publications

(3 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In computer graphics research on the other hand, such approaches may facilitate the creation of more realistic human movements in video games, adjusted to the estimated energy expenditure [119] and the character's long-term fatigue induced by selected actions [120]. Therefore, they open the path for modeling temporally evolving, ergonomic effects [121], which may allow in the future to synthesize fatigue-driven motion, and thereby produce more empathic computer graphics characters' animation.…”

Section: Challenges and Research Aimsmentioning

confidence: 99%

Machine Learning Approaches for 3D Motion Synthesis and Musculoskeletal Dynamics Estimation: A Survey

Loi,

Zacharaki,

Moustakas

2024

IEEE Trans. Visual. Comput. Graphics

Self Cite

View full text Add to dashboard Cite

The inference of 3D motion and dynamics of the human musculoskeletal system has traditionally been solved using physics-based methods that exploit physical parameters to provide realistic simulations. Yet, such methods suffer from computational complexity and reduced stability, hindering their use in computer graphics applications that require real-time performance. With the recent explosion of data capture (mocap, video) machine learning (ML) has started to become popular as it is able to create surrogate models harnessing the huge amount of data stemming from various sources, minimizing computational time (instead of resource usage), and most importantly, approximate real-time solutions. The main purpose of this paper is to provide a review and classification of the most recent works regarding motion prediction, motion synthesis as well as musculoskeletal dynamics estimation problems using ML techniques, in order to offer sufficient insight into the state-of-the-art and draw new research directions. While the study of motion may appear distinct to musculoskeletal dynamics, these application domains provide jointly the link for more natural computer graphics character animation, since ML-based musculoskeletal dynamics estimation enables modeling of more long-term, temporally evolving, ergonomic effects, while offering automated and fast solutions. Overall, our review offers an in-depth presentation and classification of ML applications in human motion analysis, unlike previous survey articles focusing on specific aspects of motion prediction.

show abstract

Section: Challenges and Research Aimsmentioning

confidence: 99%

Machine Learning Approaches for 3D Motion Synthesis and Musculoskeletal Dynamics Estimation: A Survey

Loi,

Zacharaki,

Moustakas

2024

IEEE Trans. Visual. Comput. Graphics

Self Cite

View full text Add to dashboard Cite

show abstract

“…Lifelong learning tools can help the worker adapt to changes in the working environment through corresponding ICT-empowered training processes. These tools consist of components that support the creation and execution of a tutorial process in virtual environments [7,9]. The software implementation was performed in the Unity3D real time development platform, so the tutorial environment can be encoded in Unity Asset Bundles which are archive files that contain platformspecific assets (such as models, textures, audio clips) that can be loaded by Unity at run time.…”

Section: Vr and Ar Based Lifelong Learning Toolsmentioning

confidence: 99%

A User Evaluation Study of Augmented and Virtual Reality Tools for Training and Knowledge Transfer

Zacharaki

Triantafyllidis

Carreton³

et al. 2022

Universal Access in Human-Computer Interaction. User and Context Diversity

Self Cite

View full text Add to dashboard Cite

Modern augmented and virtual reality (AR/VR) technologyopen multiple new capabilities in the way people interact, collaborate and deliver or receive information via digital interfaces. Industry workers and operators may especially benefit from such solutions that allow them to get trained, onsite or remotely, using digital copies of the workplace environment. This paper presents the development of AR/VR-based collaborative and telepresence tools, along with a web-based platform for knowledge exchange and interaction, as part of the Ageing@Work project, that enable easy transfer of know-how from experienced (possibly older) to novice workers. The remote collaboration tools facilitate variability in location and working hours, and thus promote age-neutralizing means of participation and cooperation, whereas the knowledge transfer tools support the ageing worker's leadership characteristics within the workplace community, allowing the company or work site to capitalize on her/his experience and expertise gained through the years. The tools were developed in accordance to a user-centred design process and were evaluated by 126 participants in total through online surveys in two pilot sites with regard to core Industry 4.0 processes of mining and machines production, as well as through off-pilot studies. This paper presents analytic outcomes of the assessment of knowledge transfer tools illustrating very positive results on the level of technology acceptance, and the overall potential of the developed solutions to support healthy and productive ageing of workers with enhanced workability.

show abstract

“…Building upon our previous work (Risvas et al, 2020), we perform biomechanical analysis using the open source software platform OpenSim (Seth et al, 2018), that is suitable for modeling and simulation of the musculoskeletal system of humans, animals and robots. In the confines of this work, a standard OpenSim workflow was implemented, that includes the Scale, Inverse Kinematics, Inverse Dynamics and Kinematic Analysis tools.…”

Section: Ergonomics Evaluation Through Musculoskeletal Modelingmentioning

confidence: 99%

XRSISE: An XR Training System for Interactive Simulation and Ergonomics Assessment

Pavlou

Laskos

Zacharaki

et al. 2021

Front. Virtual Real.

Self Cite

View full text Add to dashboard Cite

The use of virtual reality (VR) techniques for industrial training provides a safe and cost effective solution that contributes to increased engagement and knowledge retention levels. However, the process of experiential learning in a virtual world without biophysical constraints might contribute to muscle strain and discomfort, if ergonomic risk factors are not considered in advance. Under this scope, we have developed a digital platform which employs extended reality (XR) technologies for the creation and delivery of industrial training programs, by taking into account the users and workplace specificities through the adaptation of the 3D virtual world to the real environment. Our conceptual framework is composed of several inter-related modules: 1) the XR tutorial creation module, for automatic recognition of the sequence of actions composing a complex scenario while this is demonstrated by the educator in VR, 2) the XR tutorial execution module, for the delivery of visually guided and personalized XR training experiences, 3) the digital human model (DHM) based simulation module for creation and demonstration of job task simulations avoiding the need of an actual user and 4) the biophysics assessment module for ergonomics analysis given the input received from the other modules. Three-dimensional reconstruction and aligned projection of the objects situated in the real scene facilitated the imposition of inherent physical constraints, thereby allowed to seamlessly blend the virtual with the real world without losing the sense of presence.

show abstract

Biophysics-based simulation of virtual human model interactions in 3D virtual scenes

Cited by 4 publications

References 21 publications

Machine Learning Approaches for 3D Motion Synthesis and Musculoskeletal Dynamics Estimation: A Survey

Machine Learning Approaches for 3D Motion Synthesis and Musculoskeletal Dynamics Estimation: A Survey

A User Evaluation Study of Augmented and Virtual Reality Tools for Training and Knowledge Transfer

XRSISE: An XR Training System for Interactive Simulation and Ergonomics Assessment

Contact Info

Product

Resources

About