CAD-AG: A Webapp for CAD-Tool-Independent Autograding of Two-Dimensional CAD Drawings

Manual grading of engineering drawing assignments is often time-consuming, inconsistent, and error-prone, particularly in large-scale engineering education. To address these challenges, we present “CAD-AG”, an automated grading system designed to evaluate two-dimensional engineering drawings exported from any CAD tool in DXF format. The system streamlines the grading process by comparing student submissions with a reference solution through geometric feature extraction and rule-based error detection. Key criteria assessed include shape accuracy, scale, alignment, and element completeness. Developed in Python and deployed via a web-based platform, CAD-AG enhances accessibility and usability. In testing with over 1000 student submissions, the system achieved 100% grading accuracy and significantly reduced average grading time. These results demonstrate the potential of automated grading to improve efficiency and consistency in engineering education, providing timely and objective feedback to support both instructors and learners.

Duke Scholars

Author Rabih Younes Pierre R. Lamond Department of Electrical and Computer Engin ...