Fostering Computational Thinking for an Adaptive Construction Workforce: Experimental Study of VR-Based Human–Robot Interaction

Abstract

Construction work is becoming increasingly technology-intensive, requiring transferable skills that enable effective human–robot interaction (HRI). We designed and evaluated a virtual-reality (VR) training environment that pedagogically integrates computational thinking (CT) elements (i.e., decomposition, pattern recognition, abstraction, and algorithm design) within HRI tasks relevant to construction. In this study, CT is conceptualized as a structured problem-solving competency that supports task formulation, decision-making, and interaction with automated systems in construction environments. Participants completed a progression of pick-and-place missions using a six-axis robotic arm on a Mecanum mobility platform across three settings: a warehouse (training), along with realistic construction and unfamiliar extraterrestrial construction (testing) environments. In a proof-of-concept, exploratory study with 14 undergraduate construction students, the CT-integrated training environment was compared with a baseline configuration featuring similar HRI tasks without explicit pedagogical CT integration. Outcomes included knowledge–skill–attitude measures and task performance indexed by accuracy–speed–energy–safety metrics. Relative to the control group, the experimental group (trained in the CT-integrated environment) demonstrated larger gains in CT knowledge and attitudes and achieved superior post-training performance in the realistic construction site scenario, with significant multivariate group differences favoring CT integration. Group differences were insignificant in the extraterrestrial construction site scenario, suggesting that near-term transfer is constrained by contextual factors under unfamiliar conditions. Across groups, pattern recognition and algorithm design were the most consistent predictors of efficient and safe task execution. These findings provide preliminary evidence that integrating CT within immersive VR-based HRI training can strengthen computational competencies and structured task performance in construction-relevant environments, while highlighting the need for expanded instructional designs to better support transfer to unfamiliar, high-complexity contexts.