Learning performance and physiological feedback-based evaluation for human-robot collaboration.

Area of Science:

• Manufacturing Engineering
• Human-Robot Interaction
• Industrial Psychology

Background:

• Industry 4.0 transforms manufacturing, integrating robots and necessitating human adaptation to new collaborative environments.
• Wearable technologies enable detailed collection of human physiological data for performance evaluation.
• A human-centered approach is crucial for building resilience in manufacturing operations.

Purpose of the Study:

• To develop and apply an assessment approach for human performance in human-robot collaboration.
• To evaluate human perception of collaborative work using workload, performance, and physiological feedback indicators.
• To understand the relationship between learning, physiological responses, and perceived workload in a collaborative setting.

Main Methods:

• Participants were evaluated over a 120-minute period in a human-robot collaboration scenario.
• Human performance was assessed based on task repetitions and learning rate.
• Physiological data and subjective workload perceptions were collected and analyzed.

Main Results:

• Human performance significantly improved with increased task repetitions, achieving a learning performance value of 92%.
• Physiological indicators showed a decreasing trend as human performance improved.
• Perceptions of workload and performance were correlated with physiological feedback.

Conclusions:

• The study provides a method for evaluating human performance in human-robot collaboration using workload, performance, and physiological data.
• Findings indicate that human performance and learning can be enhanced through adaptive work systems.
• This assessment framework supports the development of resilient manufacturing operations adaptable to human capabilities.