Abstract
With the rise in classroom populations—in both physical classrooms and online learning environments such as massively open online courses—instructors are struggling to provide relevant and personalized feedback on student work. As a result, many instructors choose to structure their homework assignments and assessments via multiple-choice questions or other more automatable techniques, rather than assign complete problems and diagrams. In this work, we aim to provide a new solution to the instructors of introductory engineering courses. We leveraged the power of sketch-recognition and artificial intelligence to create Mechanix, a sketch-based system that tutors students through drawing and solving free-body diagrams. Mechanix can support problems that have only a single answer, as well as questions for which many answers might apply (i.e. design this vs. solve this).
Over the last 3 years, besides deploying Mechanix in multiple classrooms at three different universities, we have presented the system to over 150 high school and university teachers, where they themselves stepped through the problems as a student would. This paper summarizes the system that was tested by multiple educators during the 2012 ASEE Workshop, the 2014 TAMU Teacher’s Summit, and the You-Try-It Strand during WIPTTE 2014. We found that even physics teachers could use a reminder of the concepts, and by changing our first problem set to be a tutorial of the concepts, the teachers were much happier with the software and able to solve the problems much more quickly.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Atilola, O., Valentine, S., Kim, H.-H., Turner, D., McTigue, E., Hammond, T., & Linsey, J. (2014). Mechanix: A natural sketch interface tool for teaching truss analysis and free-body diagrams. Artificial Intelligence for Engineering Design, Analysis and Manufacturing, 28(02), 169–192.
Callahan, J., Hopkins, D., Weiser, M., & Shneiderman, B. (1988). An empirical comparison of pie vs. linear menus. In Proceedings of the SIGCHI conference on human factors in computing systems, pp. 95–100. New York, NY, USA, ACM.
Field, M., Valentine, S., Linsey, J., & Hammond, T. (2011). Sketch recognition algorithms for comparing complex and unpredictable shapes. In Proceedings of the Twenty-Third International Joint Conference on Artificial Intelligence. Barcelona, Spain.
Kebodeaux, K., Field, M., & Hammond, T. (2011). Defining precise measurements with sketched annotations. In Proceedings of the Eighth Eurographics Symposium on Sketch-Based Interfaces and Modeling. SBIM ’11. ACM, New York, NY, USA, pp. 79–86.
Kozma, R. B. (1994). Will media influence learning reframing the debate? Educational Technology, 42, 7–19.
Lee, W., de Silva, R., Peterson, E. J., Calfee, R. C., & Stahovich, T. F. (2008). Newton’s pen: A pen-based tutoring system for statics. Computers & Graphics, 32(5):511–524.
McGraw Hill. (2011). McGraw Hill connect. http://connect.customer.mheducation.com/. Accessed: 1 Sept 2012.
Roselli, R. J., Howard, L., Cinnamon, B., Brophy, S., Norris, P., Rothney, M., & Eggers, D. (2003). Integration of an interactive free body diagram assistant with a courseware authoring package and an experimental learning management system. In Proceedings of the American Society for Engineering Education.
Rosser, S. V. (2007). InTEL: Interactive toolkit for engineering learning. http://intel.gatech.edu/index.php. Accessed 24 Feb 2010.
Valentine, S., Vides, F., Lucchese, G., Turner, D., Kim, H., Li, W., Linsey J., & Hammond, T. (2012). Mechanix: A sketch-based tutoring system for statics courses. In Proceedings of AAAI.
Valentine, S., Vides, F., Lucchese, G., Turner, D., Hong-Hoe, K., Wenzhe, L., Linsey, J., & Hammond, T. (2013). Mechanix: A sketch-based tutoring and grading system for free-body diagrams. AI Magazine, 34(1), 55–66.
Vanlehn, K., Lynch, C., Schulze, K., Shapiro, J. A., Shelby, R., Taylor, L., Treacy, D., Weinstein, A., & Wintersgill, M. (2005). The Andes physics tutoring system: Lessons learned. International Journal of Artificial Intelligence in Education, 15(3), 147–204
Varley, P. & Company, P. (2008). Automated sketching and engineering culture. VL/HCC Workshop: Sketch Tools for Diagramming September, pp. 83–92.
Yin, P., Forbus, K. D., Usher, J., Sageman, B., & Jee, B. (2010). Sketch worksheets: A sketch-based educational software system. In Proceedings of the 22nd AAAI Conference on Innovative Applications of Artificial Intelligence. Menlo Park, CA: AAAI Press.
Acknowledgments
The authors thank the many other contributors to Mechanix, specifically Hong-Hoe Kim, David Turner, Chris Aikens, Kourtney Kebodeaux, Francisco Vides, and Martin Field, as well as other members of the Sketch Recognition Lab and the IDREEM Lab (Innovation, Design Reasoning, Engineering Education and Methods Lab). This research is funded in part by Google and the National Science Foundation under Grant Nos. 0935219, 0942400 and 1129525.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this chapter
Cite this chapter
Valentine, S., Lara-Garduno, R., Linsey, J., Hammond, T. (2015). Mechanix: A Sketch-Based Tutoring System that Automatically Corrects Hand-Sketched Statics Homework. In: Hammond, T., Valentine, S., Adler, A., Payton, M. (eds) The Impact of Pen and Touch Technology on Education. Human–Computer Interaction Series. Springer, Cham. https://doi.org/10.1007/978-3-319-15594-4_9
Download citation
DOI: https://doi.org/10.1007/978-3-319-15594-4_9
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-15593-7
Online ISBN: 978-3-319-15594-4
eBook Packages: Computer ScienceComputer Science (R0)