A Computational Framework For Robotic Quality Assessment and Management In Construction

—As an integrated process in construction projects, quality assessment and management (QA&M) can be important to prevent failures during construction. The existing QA&M practice such as the evaluation of the geometric tolerance and surface qualities is mostly performed manually which can be labor-intensive and tedious. This study proposes a computational framework for a robot to perform automatic QA&M in unknown environments. The framework is composed of three parts: (1) motion planning; (2) defect detection; and (3) defect registration. The motion planning component generates efficient robotic path for autonomous exploration and surface inspection. The defect detection component quantifies surface anomalies within a user-defined area of interests through multiple sensor measurements. The defect registration component localizes the detected defects and registers the defects to a site model. To demonstrate the feasibility of the proposed framework, we present a user case for assessing geometric tolerance and surface quality of a 1500 mm (L) x 745 mm (W) x 1980 mm interior wall mockup. The result of the case study shows that the proposed framework has the potential to provide reliable geometric measurement and defect detection for gypsum wall panels in a lab environment.