Generative AI-Driven Ergonomics: A Virtual-Real Hybrid Experiment for Human Factors Engineering

Area of Science:

• Human Factors Engineering
• Cognitive Science
• Artificial Intelligence

Background:

• Traditional ergonomics relies on human experiments, which have limitations in scale and population representation.
• Real-time human-machine tasks face challenges with experiment-modeling-validation-application paths due to inflexible experiment updates.
• Existing cognitive models struggle to adapt to dynamic online systems.

Purpose of the Study:

• To propose generative artificial intelligence (GAI)-driven ergonomics as a novel approach to augment human factors engineering (HFE) research.
• To introduce virtual-real hybrid experiments to enhance cognitive modeling and behavioral learning.
• To improve the generality and robustness of human models in human-machine systems.

Main Methods:

• Integration of generative artificial intelligence (GAI) techniques into ergonomic research.
• Implementation of virtual-real hybrid experiments to supplement traditional human experiments.
• Utilizing GAI to enhance input diversity for cognitive and behavioral modeling.

Main Results:

• GAI-driven ergonomics effectively augments human experiment data.
• Virtual-real hybrid experiments provide more heterogeneous samples for model training.
• Enhanced human models demonstrate improved generality and robustness.

Conclusions:

• Generative artificial intelligence offers a powerful paradigm to advance ergonomics and human factors engineering.
• Hybrid experimental approaches are crucial for developing adaptive and robust human-machine systems.
• GAI-driven ergonomics can overcome limitations of traditional experimental methods in HFE.