Toward Adaptive Guidance: Modeling the Variety of User Behaviors in Continuous-Skill-Improving Experiences of Machine Operation Tasks

An adaptive guidance system that supports equipment operators requires a comprehensive model of task and user behavior that considers different skill and knowledge levels as well as diverse situations. In this study, we investigated the relationships between user behaviors and skill levels under operational conditions. We captured sixty samples of two sewing tasks performed by five operators using a head-mounted RGB-d camera and a static gaze tracker. We examined the operators' gaze and head movements, and hand interactions to essential regions (hotspots on machine surface) to determine behavioral differences among continuous skill improving experiences. We modeled the variety of user behaviors to an extensive task model with a two-step automatic approach, baseline model selection and experience integration. The experimental results indicate that some features, such as task execution time and user head movements, are good indexes for skill level and provide valuable information that can be applied to obtain an effective task model. Operators with varying knowledge and operating habits demonstrate different operational features, which can contribute to the design of user-specific guidance.