Posture prediction models in digital human modeling for ergonomic design: A systematic review

Area of Science:

• Ergonomics and Human Factors
• Computer Science
• Biomechanical Engineering

Background:

• Posture prediction models are crucial for ergonomic design in Digital Human Modeling (DHM).
• A systematic review is needed to assess current posture prediction models.
• Understanding model development, validation, and application is key.

Purpose of the Study:

• To systematically review and critically assess posture prediction models in DHM.
• To categorize models into data-driven and optimization-based approaches.
• To identify limitations and future research directions.

Main Methods:

• Systematic literature search across nine academic databases following PRISMA guidelines.
• Inclusion of 24 studies, categorized into data-driven (n=12) and optimization-based (n=12) models.
• Analysis of model development, validation, applications, and limitations.

Main Results:

• Data-driven models (e.g., neural networks) show high accuracy but limited generalizability.
• Optimization-based models offer biomechanical fidelity but face computational and CAD integration challenges.
• Most models lack ergonomic evaluation and real-time usability, with insufficient diverse datasets and real-world validation.

Conclusions:

• Hybrid strategies combining learning-based inference and biomechanical simulation are promising.
• Future research should focus on scalable motion data using computer vision for improved posture prediction.
• Enhancing model generalizability, computational efficiency, and real-world validation is essential for DHM applications.