S4-DISC3-4 - A Study on the Impact of a Statics Sketch-Based Tutoring System Through a Truss Design Problem1. Innovative Practice Full Paper
1 Georgia Institute of Technology
2 Texas A&M University
Providing opportunities for students to exercise their creative skills in large, entry engineering classes challenges most faculty. This paper presents a study of a large statics class provided with a homework problem that asks them to design a truss structure. Automatic grading was done by Mechanix, an AI tutor-based software package that can automatically recognize a free-body diagram or a planar, 2d, statically determinate truss structure. The paper presents a study done in two different semesters, comparing the students using Mechanix to a control (problem on paper). To ease grading, the control group's trusses were analyzed by Mechanix after submission. No mean homework grade differences were observed, but students in the Mechanix group produced trusses that could withstand higher loads. This is despite the fact the only guidance or feedback Mechanix provides was if the students' calculated max load was correct, and if it was not, which member failed. This study occurred in Fall 2019 and Spring 2020. Students also submitted more attempts in Mechanix than the control. It may be students in the control group only submitted correct answers despite being asked to submit all attempts. Future work will provide more incentive for students to submit all attempts on paper. Mechanix automatically records all attempts. During high stress (Covid-19), more students in the Mechanix group submitted the assignment indicating that students may find this system less mentally taxing to use, less stressful, or something else led to this difference. It will be explored with focus groups in the future. AI tools have the potential to provide automatic grading for open-ended, creativity required, design problems, and to engage students more, allowing universities to develop more innovative engineers while also deepening their knowledge.