skip to main content

Sketch Recognition Lab
Director: Dr. Tracy Anne Hammond

Mechanix

Free Body Diagram and Truss Analysis Sketch Workbook


About

Introductory engineering courses within large universities often have annual enrolments exceeding several hundreds of students, while MOOCS and online classes have even larger classes. It is very challenging to achieve differentiated instruction in classrooms with class sizes and student diversity of such great magnitude. In such classes, professors can only assess whether students have mastered a concept by using multiple-choice questions. However, in a multiple choice scenario, students only have to identify the answer rather than create the answer, and the feedback received is only of a binary nature (right or wrong). Additionally, a growing concern among engineering educators is that students are losing both the critical skill of sketched diagrams and the ability to take a real system and reduce it to an accurate but simplified free-body diagram (FBD).

Mechanix is a sketch-based deployed tutoring system for engineering students enrolled in statics courses. Mechanix not only allows students to hand-draw solutions with planar truss and free body diagrams, just as they would with pencil and paper, but it also checks the student’s work against a hand-drawn answer entered by the instructor. It uses sketch recognition to determine both the component shapes and features of the sketched diagram and the relationships between those shapes and features. Mechanix then uses those relationships to determine whether a student’s work is correct and why it is incorrect, enabling Mechanix to return immediate personalized feedback to the student otherwise not possible in large classes. Additionally, because sketching is the preferred mode of problem solving for many professional engineers, producing a tool that utilizes sketching should increase the transfer of skills from the classroom to the real world. Finally, the iterative correction process facilitates student learning. Preliminary results suggest that Mechanix increases homework motivation in struggling students, and have shown that Mechanix is as effective as paper-and-pencil-based homework for teaching method of joints truss analysis. Focus groups have revealed that students believe Mechanix enhances their learning and that they are highly engaged while using it.

Currently, Mechanix can correct three different types of static homework problems: 1) Standard truss problems requiring calculations of method of joints, 2) Free-form free body diagrams, and 3) Creative Design problems. In creative design mode, the student must think creatively to create a viable truss that abides by the constraints. Creative design mode offers an infinite number of possible solutions for the student, and thus presents an interesting recognition problem. Additionally Mechanix contains three different interfaces: 1) the student interface, where the student answers the problem, 2) the instructor question creation interface, where the instructor enters the problem, and 3) the instructor review mode, where the instructor reviews the existing solutions (Figure 5 shows a mockup). To add questions, the instructor simply types the question, uploads an image, draws the answer, and types in the numerical answers. The drawn answer is then compared to the student’s answer for correction. Because the student needs to know where he or she is wrong, Mechanix performs sophisticated analysis on the student’s solution in an attempt to determine where the student has gone wrong. In the case of creative design mode, no solution is drawn, instead only constraints are specified, and Mechanix then uses these constraints to grade the student’s solution. Two types of feedback are given, that of a simple dropdown box, and that of a complete checklist for them to follow. We provide two types of feedback so that the instructor can provide more feedback on initial problems and less later, scaffolding the feedback.

Download & Try It!

User: studentTest / Pass: studentTest User: adminTest / Pass: adminTest

Download the Tutorial!

In this project we develop and adapt the state-of-the-art in free-sketch recognition to create and evaluate an educational tool for improving student learning of free-body diagrams.This tool has been deployed in first-year Fundamentals of Engineering and Statics curricula, creating collaboration between experts in Civil Engineering, Computer Science, and Engineering Education. The main goal of this project is to build a sketch recognition-based learning system that allows learners to draw free-body diagrams as they would naturally, in an unconstrained manner. Free-body diagrams are graphical representations of the forces acting on the components of physical systems, and are applicable to every field of engineering dealing with such systems. This work includes several significant advances in engineering mechanics-based education and in the field of sketch recognition. The learning system has been developed based on user and usability data collected from students and professors who participate in the first-year Fundamentals of Engineering and Statics curricula.The tool has been refined based on user feedback and evaluated in a classroom setting.

Instructor Mode

The instructor can enter answers by drawing the truss or free body diagram and forces. The instructor writes the problem text and can enter a picture related to the problem. There are equation boxes for entering the necessary equations for the answer, and there are panels for entering values of reaction forces, member forces, other input/output forces, and any other extra answers that might not be part of the diagram. The instructor can create multiple assignments and multiple problems per assignment.

Student Mode

Once a student logs in, he or she can select an assignment and begin working. The student will read the problem and proceed to draw the corresponding diagram. The student can then use the pullout notepad to do scratch work in order to obtain the necessary equations and answer values. Then the student will enter the answers into the appropriate answer boxes.

General Recognition

As the user clicks and drags the mouse or tablet pen across the screen, a series of points are registered that form strokes. The program will recognize trusses, arrows, double-ended arrows, axes, and the letters x and y. The power set of all the strokes on the screen are analyzed to determine if any particular combination of strokes forms one of the recognizable shapes. If a shape is recognized, it will become highlighted when the user pans the mouse over it.

Truss Recognition

A truss is a complex shape that can be constructed from a combination of polygons that share common sides. Recognition of trusses is more complicated than recognition of the other shapes handled by the program. Instead of analyzing combinations of strokes, recognition is based on the detection of intersection points. A shortest path algorithm is used to find the smallest possible polygons that can be formed by a set of intersection points. If any of these polygons share an edge with another polygon, they are combined into a truss.

Answer Checking

At any point in time, the student can check his answer by pressing the large check button. The program will compare the student's diagram to the instructor's answer diagram and state anything the student is missing or has wrong. It will also compare the equations and the other answers by comparing the value and units of each answer.

Use Mechanix in YOUR Classroom

To obtain usernames and passwords for you and your students, email us at mechanix_support@googlegroups.com.

Resources and links

Mechanix a how to.mp4
NSF TUES PI conference.pptx
mechanix-with-instructormode.mp4


People

 SRLMemberImage SRLMemberImage SRLMemberImage SRLMemberImage SRLMemberImage SRLMemberImage SRLMemberImage SRLMemberImage SRLMemberImage SRLMemberImage SRLMemberImage SRLMemberImage SRLMemberImage SRLMemberImage SRLMemberImage SRLMemberImage SRLMemberImage SRLMemberImage SRLMemberImage SRLMemberImage SRLMemberImage SRLMemberImage SRLMemberImage SRLMemberImage SRLMemberImage SRLMemberImage SRLMemberImage SRLMemberImage SRLMemberImage SRLMemberImage SRLMemberImage SRLMemberImage SRLMemberImage SRLMemberImage SRLMemberImage SRLMemberImage SRLMemberImage SRLMemberImage SRLMemberImage SRLMemberImage SRLMemberImage SRLMemberImage SRLMemberImage SRLMemberImage SRLMemberImage SRLMemberImage SRLMemberImage SRLMemberImage SRLMemberImage
Chris Aikens; Dr. Funmi Atilola; Dr. Richard Berman; Christopher Blanchard; Eric Botello; Randy Brooks; Federico Burch; Dr. Anthony Cahill; Sabyasachi Chakraborty; Alexis Chuck; Martin Field; Anurag Garg; Dr. Matthew Green; Dr. Tracy Hammond; Nicholas Hanemann; Dr. Michael Helms; Maria Isokpunwu; Siddhartha Karthik; Kourtney Kebodeaux; Dr. Hong-Hoe (Ayden) Kim; Andrew King III; Jung In Koh; Travis Kosarek; Raniero Lara Garduno; Jusung Lee; Dewanna Lewis; Wenzhe Li; Dr. Julie Linsey; George Lucchese; Rhiannon Martinez; Dr. Donald Maxwell; Dr. Erin McTigue; Laura Murphy; Alyssa Nabors; Trevor Nelligan; Cheryl Osterman; Dr. Joshua Peschel; Seth Polsley; Larry Powell; Dr. Manoj Prasad; Jaideep Ray; Alexandra Reynolds; Matthew Runyon; Murat Russell; Paul Taele; David Turner; Dr. Stephanie Valentine; Francisco Vides; Aaron Wolin;

News

 TAMU   2012-07-13
Sketch Recognition Lab researchers honored at IAAI in Toronto:
Researchers in the Sketch Recognition Lab in the Department of Computer Science and Engineering at Texas A&M University will be honored at the 24th Conference on Innovative Applications of Artificial Intelligence (IAAI) in Toronto July 22-26. The researchers received the IAAI Innovation Award for the paper, "Mechanix: A Sketch-Based Tutoring System for Statics Course."
NewsImage   Link
PDF  
 TAMU   2013-06-06
Computer Science and Engineering students earn honorable mention from CRA:
Sketch Recognition Lab Junior, David Turner, earns CRA Honorable Mention for the Undergraduate Researcher Award. CRA cited Turner for his work on "Mechanix - Free Body Diagram and Truss Analysis Sketch Workbook," a Sketch Recognition Lab (SRL) team project.
NewsImage   Link
PDF  
 TAMU   2014-01-14
David Turner named 2014 CRA Undergraduate Research Finalist:
David Turner, computer engineering senior in the Department of Computer Science and Engineering at Texas A&M University, is a Finalist in the Computing Research Association's Outstanding Undergraduate Research Awards for 2014.
NewsImage   Link
PDF  
 TAMU   2014-01-31
Dr. Tracy Hammond presents Sketching at Teacher Summit:
Associate Professor Dr. Tracy Hammond, director of the Sketch Recognition Lab in the Department of Computer Science and Engineering at Texas A&M, is hosting a workshop session entitled, "Interactive Sketching with Intelligent Educational Applications." "Sketching plays an important part in the learning process for a variety of subjects ranging from science to language," said Dr. Hammond.
NewsImage   Link
PDF  
 TAMU   2014-03-10
WIPTTE 2014 starts March 12:
The Workshop on the Impact of Pen and Touch Technology in Education (WIPTTE), coordinated by the Sketch Recognition Lab and the Department of Computer Science and Engineering (CSE) at Texas A&M University, will be hosted on the Texas A&M Campus March 12-15, 2014.
NewsImage   Link
PDF  
 TAMU   2014-04-17
CSE students present MECHANIX project:
Raniero Lara-Garduo, a computer engineering Ph.D. student, and Larry Powell, a senior in computer science, both students in the Sketch Recognition Lab in the Department of Computer Science and Engineering (CSE), were 2nd place winners in two graduate student categories at Student Research Week 2014. They presented their poster, "Enhancing Mechanix - Interface and Algorithms," in Engineering/Architecture and in the Sigma Xi Award for Interdisciplinary Research categories.
NewsImage   Link
PDF  
 TAMU   2015-03-30
Sketch Recognition Lab Presents to Texas A&M Computing Society:
On Tuesday, February 24, 2015, Sketch Recognition Lab members Raniero Lara-Garduno, Seth Polsley, Larry Powell, Paul Taele, and David Turner were on hand to present and discuss several of the lab's latest on-going research projects in front of a room-filled audience of students from the Texas A&M Computing Society (TACS), the representative undergraduate student organization for the Department of Computer Science & Engineering. The Sketch Recognition Lab, directed by Dr.Tracy Hammond, was invited by TACS to present to the undergraduate students as part of a series of guest talks and workshops to improve and broaden students' understanding of opportunities that exist in the computing field.
NewsImage   Link
PDF  
 TAMU   2015-03-31
Two Summer Research Experience for Teachers (RET) Opportunities with the Sketch Recognition Lab:
Two Research Experience for Teachers (RET) will be available for summer 2015 in the Sketch Recognition Lab, mentored by lab director Dr. Tracy Hammond. The two teachers will contribute to the ongoing NSF EEC project 1129525, titled Collaborative Research: Enabling Instructors to Teach Statics Actively, (PIs Tracy Hammond, Julie Linsey, Erin McTigue, Matthew Green) working with the Mechanix software project in the Computer Science Department at Texas A&M University. Mechanix is a sketch recognition system that automatically corrects students hand-drawn homework assignments for trusses and free body diagrams. The Mechanix software for testing as well as a video tutorial can be downloaded from http://sketchmechanix.com. Applications are dues April 1, 2015.
NewsImage   Link
PDF  
 TAMU   2015-07-09
SRL Graduate Students Also Awarded 5 Times in Medicine, Education, and CS at 2015 TAMU Student Research Week!:
The 2015 Student Research Week (SRW) at Texas A&M University began on March 24 and ended with an awards ceremony on March 27. Many students of the Sketch Recognition Lab, directed by Dr. Tracy Hammond, participated. SRL students won 10 awards; 5 awards went to undergraduates (see prior post) and 5 went to graduate researchers. This post describes the graduate awards.
NewsImage   Link
PDF  

Awards

 2015 logoBest Poster at 2015 ACM International conference on intelligent user interface
Dr. Tracy Hammond, Dr. Michael Helms, Dr. Julie Linsey, Trevor Nelligan, Seth Polsley, Jaideep Ray, Mechanix: A Sketch-Based Educational Interface
tracyhammondmichaelhelmsjulielinseytrevornelligansethpolsleyjaideepray
 2014 logoCRA Outstanding Undergraduate Researcher Award Finalist
David Turner, NSF Computing Research Association
davidturner
 2014 logo2nd Place TAMU Student Research Week Graduate Research Poster in Engineering/Architecture
Raniero Lara Garduno, Larry Powell, Enhancing Mechanix - Interface and Algorithms
ranierolaragardunolarrypowell
 2014 logo2nd Place TAMU Student Research Week Graduate Sigma Xi Award for Interdisciplinary Research
Raniero Lara Garduno, Larry Powell, Enhancing Mechanix - Interface and Algorithms
ranierolaragardunolarrypowell
 2013 logoCRA Outstanding Undergraduate Researcher Honorable Mention
David Turner, NSF Computing Research Association
davidturner
 2013 logo1st Place TAMU Student Research Week (SRW) Graduate Research Poster in Computational Sciences
Dr. Stephanie Valentine, Mechanix - A Sketch-Based Tutoring System for Statics Courses
stephanievalentine
 2012 logoIAAI Innovative Applications of AI Deployed Application Award
Dr. Tracy Hammond, Dr. Hong-Hoe (Ayden) Kim, Wenzhe Li, George Lucchese, Dr. Stephanie Valentine, Mechanix: A Sketch-Based Tutoring System for Statics Course
tracyhammondhonghoekimwenzheligeorgelucchesestephanievalentine
 2012 logo1st Place TAMu Student Research Week Undergraduate Research Oral in Computational Sciences
David Turner, Creative Design in Mechanix (award: $300)
davidturner

Publications

2012 
PublicationImagePublicationImage
 Lucchese, George. Sketch Recognition on Mobile Devices. Texas A&M University (TAMU) MS Master's Thesis. Advisor: Tracy Hammond. 54 pages. Texas A&M University (TAMU), College Station, TX, USA. December, 2012. First Position: IBM. Link
Show Abstract:

Sketch recognition allows computers to understand and model hand drawn sketches and diagrams. Traditionally sketch recognition systems required a pen based PC interface, but powerful mobile devices such as tablets and smartphones can provide a new platform for sketch recognition systems. We describe a new sketch recognition library, Strontium (SrL) that combines several existing sketch recognition libraries modified to run on both personal computers and on the Android platform. We analyzed the recognition speed and accuracy implications of performing low-level shape recognition on smartphones with touch screens. We found that there is a large gap in recognition speed on mobile devices between recognizing simple shapes and more complex ones, suggesting that mobile sketch interface designers limit the complexity of their sketch domains. We also found that a low sampling rate on mobile devices can affect recognition accuracy of complex and curved shapes. Despite this, we found no evidence to suggest that using a finger as an input implement leads to a decrease in simple shape recognition accuracy. These results show that the same geometric shape recognizers developed for pen applications can be used in mobile applications, provided that developers keep shape domains simple and ensure that input sampling rate is kept as high as possible.

Show BibTex

@mastersthesis{georgelucchese2012MS,
type = {{MS Master's Thesis}},
author = {Lucchese, George},
title = {Sketch Recognition on Mobile Devices},
school = {Texas A\&M University (TAMU)},
year = {2012},
month = {December},
address = {College Station, TX, USA},
note = {Advisor: Tracy Hammond. 54 pages.}
}
2011 
PublicationImagePublicationImage
 Valentine, Stephanie. A Shape Comparison Technique for Use in Sketch-based Tutoring Systems. St. Mary's University of Minnesota Undergraduate Honors Thesis. Advisor: Ann Smith & Tracy Hammond. St. Mary's University of Minnesota, Winona, MN, USA. May, 2011. First Position: TAMU PhD Student. Link
Show Abstract:

To Be Entered

Show BibTex

@mastersthesis{stephanievalentine2011BS,
type = {{Undergraduate Honors Thesis}},
author = {Valentine, Stephanie},
title = {A Shape Comparison Technique for Use in Sketch-based Tutoring Systems},
school = {St. Mary's University of Minnesota},
year = {2011},
month = {May},
address = {Winona, MN, USA},
note = {Advisor: Ann Smith \& Tracy Hammond. }
}
2016 
PublicationImage
 Hammond, Tracy; Valentine, Stephanie; Adler, Aaron; Payton, Mark. Revolutionizing Education with digital Ink: The Impact of Pen and Touch Technology on Education. Human-Computer Interaction Series. pp. 350 pages. Springer, April , 2016. Link
Show Abstract:
Derived from contributions to the Workshop on Pen and Touch Technology on Education (WIPTTE) in 2015, this edited volume highlights recent developments for pen and tablet research within the education system with a particular focus on hardware and software developments, comprising the perspectives of teachers, school and university administrators, and researchers for educators at every level. Split into six distinct parts, the book explores topics like how classrooms are increasingly using sketch-based videos, created by teachers and students alike, and how the teaching of key skills such as literacy, languages, math, and art via pen and touch technologies within the classroom are leading to improvements in engagement, learning, and retention levels amongst students. Future perspectives of digital learning, as envisioned by current high school students, are also explored.

Show BibTex
@book{Hammond:2016,
 author = {Hammond, Tracy and Valentine, Stephanie and Adler, Aaron},
 title = {Revolutionizing Education with digital Ink: The Impact of Pen and Touch Technology on Education},
 year = {2016},
 isbn = {9783319311913},
 edition = {1st},
 publisher = {Springer Publishing Company, Incorporated},
} 
2015 
PublicationImage
 Hammond, Tracy; Valentine, Stephanie; Adler, Aaron; Payton, Mark. The Impact of Pen and Touch Technology on Education. Human-Computer Interaction Series. pp. 387 pages. Springer, August 15, 2015. Link
Show Abstract:

Show BibTex
@book{Hammond:2015:IPT:2815658,
 author = {Hammond, Tracy and Valentine, Stephanie and Adler, Aaron and Payton, Mark},
 title = {The Impact of Pen and Touch Technology on Education},
 year = {2015},
 isbn = {3319155938, 9783319155937},
 edition = {1st},
 publisher = {Springer Publishing Company, Incorporated}
} 
2015 
PublicationImage
 Matthew Green, Benjamin Caldwell, Michael Helms, Julie Linsey, Tracy Hammond. Using Natural Sketch Recognition Software to Provide Instant Feedback on Statics Homework (Truss Free Body Diagrams): Assessment of a Classroom Pilot. 2015 ASEE Annual Conference and Exposition. pp. 26.1671.1 - 26.1671.12. Seattle, WA. ASEE, June 14, 2015. Link
Show Abstract:
Using Natural Sketch Recognition Software to Provide Instant Feedback on Statics Homework: Assessment of a Classroom PilotDespite the importance of hand-sketched Free Body Diagrams for engineering education and practice, large class sizes often prevent detailed feedback on such diagrams. Relatively recently computing technology has become powerful enough to enable rapid and plentiful feedback on hand-sketched engineering diagrams. Researchers have recently developed the free “Mechanix”sketch recognition tutoring system for free body diagrams (FBDs) and trusses which provides intelligent and immediate feedback.This paper will describe the process and results of piloting this software at a primarily undergraduate university with approximately 40 students enrolled in a Statics class, contrasted with a control group. Results will include attitudes towards technology, online homework scores, test scores, and self-reported perceptions of the effectiveness of the sketch-recognition software. Preliminary results look very positive, and the full paper will include a detailed data analysis of both quantitative learning outcomes and qualitative comments from users.

Show BibTex
@INPROCEEDINGS{GreenASEE2015,
 author = {Green, Matthew G. and Caldwell, Benjamin W. and Helms, Michael and Linsey, Julie S. and Hammond, Tracy Anne},
 title = {Using Natural Sketch Recognition Software to Provide Instant Feedback on Statics Homework (Truss
   Free Body Diagrams): Assessment of a Classroom Pilot},
 booktitle = {2015 ASEE Annual Conference and Exposition},
 year = {2015},
 month = {June},
 address = {Seattle, Washington},
 publisher = {ASEE Conferences},
 note = {https://peer.asee.org/25007},
 number = {10.18260/p.25007}
}
2015 
PublicationImage
 Nelligan, Trevor; Polsley, Seth; Ray, Jaideep; Helms, Michael; Linsey, Julie; Hammond, Tracy. Mechanix: A Sketch-Based Educational Interface. Proceedings of the 2015 ACM International Conference on Intelligent User Interfaces (IUI 2015). pp. 53-56. Atlanta, Georgia. ACM, March 29-1, 2015. Link
Show Abstract:
At the university level, high enrollment numbers in classes can be overwhelming for professors and teaching assistants to manage. Grading assignments and tests for hundreds of students is time consuming and has led towards a push for software-based learning in large university classes. Unfortunately, traditional quantitative question-and-answer mechanisms are often not sufficient for STEM courses, where there is a focus on problem-solving techniques over finding the right answers. Working through problems by hand can be important in memory retention, so in order for software learning systems to be effective in STEM courses, they should be able to intelligently understand students sketches. Mechanix is a sketch-based system that allows students to step through problems designed by their instructors with personalized feedback and optimized interface controls. Optimizations like color-coding, menu bar simplification, and tool consolidation are recent improvements in Mechanix that further the aim to engage and motivate students in learning.

Show BibTex
@inproceedings{Nelligan:2015:MSE:2732158.2732194,
 author = {Nelligan, Trevor and Polsley, Seth and Ray, Jaideep and Helms, Michael and Linsey, Julie and Hammond, Tracy},
 title = {Mechanix: A Sketch-Based Educational Interface},
 booktitle = {Proceedings of the 20th International Conference on Intelligent User Interfaces Companion},
 series = {IUI Companion '15},
 year = {2015},
 isbn = {978-1-4503-3308-5},
 location = {Atlanta, Georgia, USA},
 pages = {53--56},
 numpages = {4},
 url = {http://doi.acm.org/10.1145/2732158.2732194},
 doi = {10.1145/2732158.2732194},
 acmid = {2732194},
 publisher = {ACM},
 address = {New York, NY, USA},
 keywords = {computer-assisted instruction (cai), graphical user interfaces (gui), guides, interaction styles, user-centered design}
} 
2015 
PublicationImage
 Valentine, Stephanie; Lara-Garduno, Raniero; Linsey, Julie; Hammond, Tracy. Mechanix: A Sketch-Based Tutoring System that Automatically Corrects Hand-Sketched Statics Homework. In: T. Hammond, S. Valentine, A. Adler, and M. Payton, editors, The Impact of Pen and Touch Technology on Education.. Volume 3, Number 9, pp. 91-105. New York, NY. Springer, August, 2015. Link
Show Abstract:

Show BibTex
@incollection{Valentine2015Mechanix,
 title = {Mechanix: A Sketch-Based Tutoring System that Automatically Corrects Hand-Sketched Statics Homework}, 
 author = {Valentine, Stephanie and Lara-Garduno, Raniero and Linsey, Julie and Hammond, Tracy},
 booktitle = {The Impact of Pen and Touch Technology on Education}, 
 editor = {Hammond, Tracy and Valentine, Stephanie and Adler, Aaron and Payton, Mark}, 
 pages = {91--105},
 year = {2015},
 isbn = {3319155938, 9783319155937},
 edition = {1st},
 publisher = {Springer Publishing Company, Incorporated}
}
2014 
PublicationImage
 Atilola, Olufunmilola; Valentine, Stephanie; Kim, Hong-Hoe; Turner, David; McTigue, Erin; Hammond, Tracy; Linsey, Julie. Mechanix: A natural sketch interface tool for teaching truss analysis and free-body diagrams. Artificial Intelligence for Engineering Design, Analysis and Manufacturing (AIEDAM). Volume 28, Number 2, pp. 169-192. Cambridge University Press, May, 2014. Link
Show Abstract:
Massive open online courses, online tutoring systems, and other computer homework systems are rapidly changing engineering education by providing increased student feedback and capitalizing upon online systems’ scalability. While online homework systems provide great benefits, a growing concern among engineering educators is that students are losing both the critical art of sketching and the ability to take a real system and reduce it to an accurate but simplified free-body diagram (FBD). For example, some online systems allow the drag and drop of forces onto FBDs, but they do not allow the user to sketch the FBDs, which is a vital part of the learning process. In this paper, we discuss Mechanix, a sketch recognition tool that provides an efficient means for engineering students to learn how to draw truss FBDs and solve truss problems. The system allows students to sketch FBDs into a tablet computer or by using a mouse and a standard computer monitor. Using artificial intelligence, Mechanix can determine not only the component shapes and features of the diagram but also the relationships between those shapes and features. Because Mechanix is domain specific, it can use those relationships to determine not only whether a student’s work is correct but also why it is incorrect. Mechanix is then able to provide immediate, constructive feedback to students without providing final answers. Within this manuscript, we document the inner workings of Mechanix, including the artificial intelligence behind the scenes, and present studies of the effects on student learning. The evaluations have shown that Mechanix is as effective as paper-and-pencil-based homework for teaching method of joints truss analysis; focus groups with students who used the program have revealed that they believe Mechanix enhances their learning and that they are highly engaged while using it.

Show BibTex
@article{Atilola2014AIE,
 author = {Atilola, Olufunmilola and Valentine, Stephanie and Kim, Hong-Hoe and Turner, David and McTigue, Erin and Hammond,Tracy and Linsey, Julie},
 title = {Mechanix: A natural sketch interface tool for teaching truss analysis and free-body diagrams},
 journal = {Artificial Intelligence for Engineering Design, Analysis and Manufacturing},
 volume = {null},
 issue = {Special Issue 02},
 month = {5},
 year = {2014},
 issn = {1469-1760},
 pages = {169--192},
 numpages = {24},
 doi = {10.1017/S0890060414000079},
 URL = {http://journals.cambridge.org/article_S0890060414000079}
}
2013 
PublicationImage
 Atilola, Olufumilola; McTigue, Erin M.; Hammond, Tracy; Linsey, Julie. Mechanix: Evaluating the Effectiveness of a Sketch Recognition Truss Tutorin Program Against Other Truss Programs. 120th American Society for Engineering Education Annual Conference & Exposition (ASEE). pp. 15 pages. Atlanta, GA. ASEE, June 23-26, 2013. Link
Show Abstract:
Mechanix is a sketch recognition program that was developed at Texas A&M University. Mechanix provides an efficient and effective means for engineering students to learn how to draw truss free-body diagrams (FBDs) and solve truss problems. The Mechanix interface allows for students to sketch these FBDs, as they normally would by hand, into a tablet computer; a mouse can also be used with a regular computer monitor. Mechanix is able to provide immediate and intelligent feedback to the students, and it tells them if they are missing any components of the FBD. The program is also able to tell students whether their solved reaction forces or member forces are correct or not without actually providing the answers. A recent and exciting feature of Mechanix is the creative design mode which allows students to solve open-ended truss problems; an instructor can give their students specific minimum requirements for a truss/bridge, and the student uses Mechanix to solve and create this truss. The creative design feature of Mechanix can check if the students’ truss is structurally sound, and if it meets the minimum requirements stated by the instructor. This paper presents a study to evaluate the effectiveness and advantages of using Mechanix in the classroom as a supplement to traditional teaching and learning methods. Mechanix is also tested alongside an established and popular truss program, WinTruss, to see how learning gains differ and what advantages Mechanix offers over other truss analysis software. Freshman engineering classes were recruited for this experiment and were divided into three conditions: a control condition (students who were not exposed to Mechanix or WinTruss and did their assignments on paper), a Mechanix condition (students who used Mechanix in class and for their assignments, and a WinTruss condition (students who used the WinTruss program for their assignments). The learning gains among these three groups were evaluated using a series of quantitative formal assessments which include a statics concepts inventory, homework sets, quizzes, exam grades and truss/bridge creative design solutions. Qualitative data was also collected through focus groups for all three conditions to gather the students’ impressions of the programs for the experimental group and general teaching styles for the control group. Results from previous evaluations show Mechanix highly engages students and helps them learn basic truss mechanics. This evaluation will be compared with previous evaluations to show that Mechanix continues to be a great tool for enhancing student learning.

Show BibTex
@inproceedings{Atilola2013ASEE,
 title = {Mechanix: Evaluating the Effectiveness of a Sketch Recognition Truss Tutorin Program Against Other Truss Programs},
 author = {Atilola, Olufumilola and McTigue, Erin M. and Hammond, Tracy and Linsey, Julie},
 booktitle = {120th American Society for Engineering Education Annual Conference & Exposition (ASEE). June 23-26},
 year = 2013,
 address = {Atlanta, GA},
 month = 6,
 organization = {ASEE},
 note = {15 pages}
}
2013 
PublicationImage
 Valentine, Stephanie; Vides, Francisco; Lucchese, George; Turner, David; Kim, Hong-hoe; Li, Wenzhe; Linsey, Julie; Hammond, Tracy. Mechanix: A Sketch-Based Tutoring and Grading System for Free-Body Diagrams. AI Magazine. Volume 34, Number 1, pp. 55-66. AAAI, January, 2013. Link
Show Abstract:
Introductory engineering courses within large universities often have annual enrollments that can reach up to a thousand students. In this article, we introduce Mechanix, a sketch-based deployed tutoring system for engineering students enrolled in statics courses. Our system not only allows students to enter planar trussand free-body diagrams into the system, just as they would with pencil and paper, but our system also checks the student’s work against a hand-drawn answer entered by the instructor, and then returns immediate and detailed feedback to the student. Students are allowed to correct any errors in their work and resubmit until the entire content is correct and thus all of the objectives are learned. Since Mechanix facilitates the grading and feedback processes, instructors are now able to assign more free-response questions, increasing teacher’s knowledge of student comprehension. Furthermore, the iterative correction process allows students to learn during a test, rather than simply display memorized information.

Show BibTex
@article{Valentine2013Mechanix,
 author = {Valentine, Stephanie and Vides, Francisco and Lucchese, George and Turner, David and Kim, Hong-hoe
   and Li, Wenzhe and Linsey, Julie and Hammond, Tracy},
 title = {Mechanix: A Sketch-Based Tutoring and Grading System for Free-Body Diagrams},
 journal = {AI Magazine},
 year = {2013},
 volume = {34},
 number = {1},
 pages = {55–66}
}
2012 
PublicationImage
 Atilola, Olufunmilola; Vides, Francisco; Mctigue, Erin M; Linsey, Julie S; Hammond, Tracy Anne. Automatic Identification of Student Misconceptions and Errors for Truss Analysis. 119th American Society for Engineering Education Annual Conference & Exposition (ASEE). pp. 13 pages. San Antonio, TX. ASEE, June 10-13, 2012. Link
Show Abstract:
Mechanix is a sketch recognition program that was developed at Texas A&M University. Mechanix provides an efficient and effective means for engineering students to learn how to draw truss free-body diagrams (FBDs) and solve truss problems. The Mechanix interface allows for students to sketch these FBDs, as they normally would by hand, into a tablet computer; a mouse can also be used with a regular computer monitor. Mechanix is able to provide immediate and intelligent feedback to the students, and it tells them if they are missing any components of the FBD. The program is also able to tell students whether their solved reaction forces or member forces are correct or not without actually providing the answers. A recent and exciting feature of Mechanix is the creative design mode which allows students to solve open-ended truss problems; an instructor can give their students specific minimum requirements for a truss/bridge, and the student uses Mechanix to solve and create this truss. The creative design feature of Mechanix can check if the students’ truss is structurally sound, and if it meets the minimum requirements stated by the instructor. This paper presents a study to evaluate the effectiveness and advantages of using Mechanix in the classroom as a supplement to traditional teaching and learning methods. Mechanix is also tested alongside an established and popular truss program, WinTruss, to see how learning gains differ and what advantages Mechanix offers over other truss analysis software. Freshman engineering classes were recruited for this experiment and were divided into three conditions: a control condition (students who were not exposed to Mechanix or WinTruss and did their assignments on paper), a Mechanix condition (students who used Mechanix in class and for their assignments, and a WinTruss condition (students who used the WinTruss program for their assignments). The learning gains among these three groups were evaluated using a series of quantitative formal assessments which include a statics concepts inventory, homework sets, quizzes, exam grades and truss/bridge creative design solutions. Qualitative data was also collected through focus groups for all three conditions to gather the students’ impressions of the programs for the experimental group and general teaching styles for the control group. Results from previous evaluations show Mechanix highly engages students and helps them learn basic truss mechanics. This evaluation will be compared with previous evaluations to show that Mechanix continues to be a great tool for enhancing student learning.

Show BibTex
@inproceedings{Atilola2012ASEE,
 title = {Automatic Identification of Student Misconceptions and Errors for Truss Analysis},
 author = {Atilola, Olufunmilola and Vides, Francisco and Mctigue, Erin M and Linsey, Julie S and Hammond, Tracy Anne},
 booktitle = {119th American Society for Engineering Education Annual Conference & Exposition (ASEE). June 10–13},
 year = 2012,
 address = {San Antonio, TX},
 month = 6,
 organization = {ASEE},
 note = {13 pages}
}
2012 
PublicationImage
 Li, Wenzhe; Hammond, Tracy. Using Scribble Gestures to Enhance Editing Behaviors of Sketch Recognition Systems. CHI'12 Extended Abstracts on Human Factors in Computing Systems (CHI). pp. 2213-2218. Austin, TX. ACM, May 5-10, 2012. Link
Show Abstract:
Mechanix is a computer-assisted tutoring system for engineering students. It uses recognition of freehand sketches to provide instant, detailed, and formative feedback as a student progresses through each homework problem. By using recognition algorithms, the system allows students to solve free-body diagrams and truss problems as if they were using a pen and paper. However, the system currently provides little support for students to edit their drawings by using free hand sketches. Specifically, students may wish to delete part or the whole of a line or shape, and the natural response is to scribble that part of shape out. We developed a new method for integrating scribble gestures into a sketch recognition system. The algorithm automatically identifies and distinguishes scribble gestures from regular drawing input using three features. If the stroke is classified as a scribble, then the algorithm further decides which shape or which part of shape to be deleted. Instead of using slower brute-force methods, we use geometric-based linear-time algorithms which efficiently detect a scribble gesture and remove the intended shapes in real-time.

Show BibTex
@inproceedings{Li:2012:USG:2212776.2223778,
 author = {Li, Wenzhe and Hammond, Tracy},
 title = {Using Scribble Gestures to Enhance Editing Behaviors of Sketch Recognition Systems},
 booktitle = {CHI '12 Extended Abstracts on Human Factors in Computing Systems},
 series = {CHI EA '12},
 year = {2012},
 isbn = {978-1-4503-1016-1},
 location = {Austin, Texas, USA},
 pages = {2213--2218},
 numpages = {6},
 url = {http://doi.acm.org/10.1145/2212776.2223778},
 doi = {10.1145/2212776.2223778},
 acmid = {2223778},
 publisher = {ACM},
 address = {New York, NY, USA},
 keywords = {editing, gesture recognition, pen-input computing, sketch recognition}
} 
2012 
PublicationImage
 Prasad, Manoj; Hammond, Tracy. Observational Study on Teaching Artifacts Created Using Tablet PC. CHI'12 Extended Abstracts on Human Factors in Computing Systems (CHI). pp. 301-316. Austin, TX. ACM, May 5-10, 2012. Link
Show Abstract:
Teaching typically involves communication of knowledge in multiple modalities. The ubiquity of pen-enabled technologies in teaching has made the accurate capture of user ink data possible, alongside technologies to recognize voice data. When annotating on a white board or other presentation surface, teachers often have a specific style of structuring contents taught in a lecture. The availability of sketch data and voice data can enable researchers to analyze trends followed by teachers in writing and annotating notes. Using ethnographic methods, we have observed the structure that teachers use while presenting lectures on mathematics. We have observed the practices followed by teachers in writing and speaking the lecture content, and have derived models that would help computer scientists identify the structure of the content. This observational study motivates the idea that we can use speech and color change events to distinguish between strokes meant for drawing versus those meant for attention marks.

Show BibTex
@inproceedings{Prasad:2012:OST:2212776.2212809,
 author = {Prasad, Manoj and Hammond, Tracy},
 title = {Observational Study on Teaching Artifacts Created Using Tablet PC},
 booktitle = {CHI '12 Extended Abstracts on Human Factors in Computing Systems},
 series = {CHI EA '12},
 year = {2012},
 isbn = {978-1-4503-1016-1},
 location = {Austin, Texas, USA},
 pages = {301--316},
 numpages = {16},
 url = {http://doi.acm.org/10.1145/2212776.2212809},
 doi = {10.1145/2212776.2212809},
 acmid = {2212809},
 publisher = {ACM},
 address = {New York, NY, USA},
 keywords = {ethnography, multimodal, pen enabled technologies, sketch recognition, sketching, tablet pc}
} 
2012 
PublicationImage
 Valentine, Stephanie; Vides, Francisco; Lucchese, George; Turner, David; Kim, Hong-hoe; Li, Wenzhe; Linsey, Julie; Hammond, Tracy. Mechanix: A Sketch-Based Tutoring System for Statics Courses. Proceedings of the Twenty-Fourth Innovative Applications of Artificial Intelligence Conference (IAAI). pp. 2253-2260. Toronto, Canada. AAAI, July 22-26, 2012. Link
Show Abstract:
Introductory engineering courses within large universities often have annual enrollments which can reach up to a thousand students. It is very challenging to achieve differentiated instruction in classrooms with class sizes and student diversity of such great magnitude. Professors can only assess whether students have mastered a concept by using multiple choice questions, while detailed homework assignments, such as planar truss diagrams, are rarely assigned because professors and teaching assistants would be too overburdened with grading to return assignments with valuable feedback in a timely manner. In this paper, we introduce Mechanix, a sketch-based deployed tutoring system for engineer- ing students enrolled in statics courses. Our system not only allows students to enter planar truss and free body diagrams into the system just as they would with pen- cil and paper, but our system checks the student’s work against a hand-drawn answer entered by the instructor, and then returns immediate and detailed feedback to the student. Students are allowed to correct any errors in their work and resubmit until the entire con- tent is correct and thus all of the objectives are learned. Since Mechanix facilitates the grading and feedback processes, instructors are now able to assign free response questions, increasing teacher’s knowledge of student comprehension. Furthermore, the iterative correction process allows students to learn during a test, rather than simply displaying memorized information.

Show BibTex
@inproceedings{valentine2012mechanix,
 title = {Mechanix: A Sketch-Based Tutoring System for Statics Courses.},
 author = {Valentine, Stephanie and Vides, Francisco and Lucchese, George and Turner, David and
   Kim, Hong-hoe and Li, Wenzhe and Linsey, Julie and Hammond, Tracy},
 booktitle = {Proceedings of the Twenty-Fourth Innovative Applications of Artificial Intelligence Conference (IAAI)},
 year = {2012},
 address = {Toronto, Canada},
 month = {July},
 organization = {AAAI},
 pages = {2253–2260}
}
2011 
PublicationImage
 Atilola, Olufunmilola; Field, Martin; McTigue, Erin; Hammond, Tracy; Linsey, Julie. Mechanix: A Sketch Recognition Truss Tutoring System. American Society of Mechanical Engineers (ASME) 2011 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference, Volume 7: 5th International Conference on Micro- and Nanosystems; 8th International Conference on Design and Design Education; 21st Reliability, Stress Analysis, and Failure Prevention Conference.. Volume 7, pp. 645-654. Washington, DC. ASME, August 28-30, 2011. Link
Show Abstract:

Show BibTex
@INPROCEEDINGS{atilola2011asme,
 author = {Atilola, Olufunmilola and Field, Martin and McTigue, Erin and Hammond, Tracy and Linsey, Julie},
 booktitle= {American Society of Mechanical Engineers (ASME) 2011 International Design Engineering Technical 
   Conferences and Computers and Information in Engineering Conference, Volume 7: 5th International Conference
   on Micro- and Nanosystems; 8th International Conference on Design and Design Education; 21st Reliability, 
   Stress Analysis, and Failure Prevention Conference},
 title = {Mechanix: A Sketch Recognition Truss Tutoring System},
 year = {2011},
 volume= {7},
 pages = {645–654},
 month = {August 28–30},
 address = {Washington, DC},
 publisher = {ASME}
}
2011 
PublicationImage
 Atilola, Olufunmilola; Field, Martin; McTigue, Erin; Hammond, Tracy; Linsey, Julie. Evaluation of a Natural Sketch Interface for Truss FBDs and Analysis. Frontiers in Education Conference (FIE). pp. S2E-1 - S2E-6. Rapid City, SD. IEEE, October 12-15, 2011. Link
Show Abstract:

Show BibTex
@inproceedings{Atilola:2011:ENS:2192607.2193253,
 author = {Atilola, Olufunmilola and Field, Martin and McTigue, Erin and Hammond, Tracy and Linsey, Julie},
 title = {Evaluation of a Natural Sketch Interface for Truss FBDs and Analysis},
 booktitle = {Proceedings of the 2011 Frontiers in Education Conference},
 series = {FIE '11},
 year = {2011},
 isbn = {978-1-61284-468-8},
 pages = {S2E-1--1-S2E-6},
 url = {http://dx.doi.org/10.1109/FIE.2011.6142959},
 doi = {10.1109/FIE.2011.6142959},
 acmid = {2193253},
 publisher = {IEEE Computer Society},
 address = {Washington, DC, USA}
} 
2011 
PublicationImage
 Field, Martin; Valentine, Stephanie; Linsey, Julie; Hammond, Tracy. Sketch Recognition Algorithms for Comparing Complex and Unpredictable Shapes. Proceedings of the Twenty-Second international Joint Conference on Artificial Intelligence (IJCAI). Volume 3, pp. 2436-2441. Barcelona, Spain. AAAI Press, July 16-22, 2011. Link
Show Abstract:

Show BibTex
@inproceedings{Field:2011:SRA:2283696.2283803,
 author = {Field, Martin and Valentine, Stephanie and Linsey, Julie and Hammond, Tracy},
 title = {Sketch Recognition Algorithms for Comparing Complex and Unpredictable Shapes},
 booktitle = {Proceedings of the Twenty-Second International Joint Conference on Artificial Intelligence - Volume Three},
 series = {IJCAI'11},
 year = {2011},
 isbn = {978-1-57735-515-1},
 location = {Barcelona, Catalonia, Spain},
 pages = {2436--2441},
 numpages = {6},
 url = {http://dx.doi.org/10.5591/978-1-57735-516-8/IJCAI11-406},
 doi = {10.5591/978-1-57735-516-8/IJCAI11-406},
 acmid = {2283803},
 publisher = {AAAI Press}
} 
2011 
PublicationImage
 Valentine, Stephanie; Field, Martin; Smith, A; Hammond, T. A Shape Comparison Technique for Use in Sketch-Based Tutoring Systems. Proceedings of the 2011 Intelligent User Interfaces Workshop on Sketch Recognition (Palo Alto, CA, USA, 2011) . Volume 11, Number 5, pp. 4 pages. Palo Alto, CA. IUI, February 13, 2011. Link
Show Abstract:

Show BibTex
@INPROCEEDINGS{valentine2011shape,
 author = {Valentine, Stephanie and Field, Martin and Smith, A and Hammond, T},
 title = {A Shape Comparison Technique for Use in Sketch-Based Tutoring Systems},
 booktitle = {Proceedings of the 2011 Intelligent User Interfaces Workshop on Sketch Recognition (Palo Alto, CA, USA, 2011)},
 year = {2011},
 month = {February 13},
 address = {Palo Alto, CA},
 publisher = {ASEE Conferences},
 note = {4 pages}
}
2008 
PublicationImage
 Peschel, Joshua M; Hammond, Tracy Anne. STRAT: A Sketched-Truss Recognition and Analysis Tool. 2008 International Workshop on Visual Languages and Computing (VLC) at the 14th International Conference on distributed Multimedia Systems (DMS). pp. 282-287. Boston, MA. Knowledge Systems Instistute, September 4-6, 2008. Link
Show Abstract:
The statically-determinate, pin-connected truss is a basic structural element used by engineers to create larger and more complex systems. Truss analysis and design are topics that virtually all students who study engineering mechanics are required to master, many of whom may experience difficulty with initial understanding. The mathematics used to analyze truss systems typically requires lengthy hand calculations or the assistance of proprietary computer-aided design (CAD) programs. To expedite work in this domain, we propose: STRAT (Sketched-Truss Recognition and Analysis Tool), a freehand sketch recognition system for solving truss problems. The STRAT system allows users to rapidly determine all of the unknown forces in a truss, using only a hand-drawn sketch of the truss itself. The focus of this article covers the design methodology and implementation of the STRAT system. Results from a preliminary user study are also presented.

Show BibTex
@inproceedings{peschel2008STRAT,
 title = {STRAT: A Sketched-Truss Recognition and Analysis Tool},
 author = {Peschel, Joshua M and Hammond, Tracy Anne},
 booktitle = {2008 International Workshop on Visual Languages and Computing (VLC) at the 14th International 
   Conference on distributed Multimedia Systems (DMS)},
 year = {2008},
 address = {Boston, MA},
 month = 9,
 organization = {Knowledge Systems Instistute},
 pages = {282–287}
}

Sponsors

SponsorImage
NSF EEC 1129525: Collaborative Research: Enabling Instructors to Teach Statics Actively
NSF EEC
2011-09-01 - 2017-08-31, $540,970
PI: Tracy Hammond, CoPIs: Julie Linsey, Erin McTigue
SponsorImage
Sketch and Gesture Recognition for Collaborative and Design Interfaces on the Surface Hub
Microsoft Surface Hub
2015-07-01 - 2016-06-30, $45,000
PI: Tracy Hammond
SponsorImage
I-Corps: Evaluating the Market Potential of the Mechanix Sketch Recognition Software
NSF IIP
2015-07-01 - 2015-12-31, $50,000
PI: Tracy Hammond
SponsorImage
NSF DUE/CCLI 0942400, Sketched-Truss Recognition Tutoring System
NSF DUE
2010-03-01 - 2013-02-28, $199,769
PI: Julie Linsey, CoPIs: Tracy Hammond and Erin McTigue
SponsorImage
NSF EEC 0935219, Civil Engineering Sketch Workbook
NSF EEC
2009-10-01 - 2012-09-30, $400,000
PI: Tracy Hammond, CoPIs: Anthony Cahill
SponsorImage
Sketch Recognition: Algorithms, Interfaces, and a Platform for Engineering Education and Beyond
Google Research
2010-01-01 - 2011-12-31, $50,000
PI: Tracy Hammond
SponsorImage
REU support for the Mechanix project
NSF CRA
2010-09-01 - 2011-08-31, $25,500
PI: Tracy Hammond
SponsorImage
Creative IT 0757557, Pilot: Let Your Notes Come Alive: The SkRUI Classroom Sketchbook
NSF CreativeIT CHS
2008-06-01 - 2011-05-31, $247,000
PI: Tracy Hammond, CoPI: Donald Maxwell