Dozens of projects by student designers and creators of three Cornell Department Information Science courses Ann S. Bowers College took to the Duffield Hall atrium on Thursday, December 9 as part of a joint end-of-year showcase. semester. Showcasing robotics and wearable devices of all kinds, the showcase included projects from three courses from the Department of Information Sciences: Rapid Prototyping and Physical Computing, Robot Redesign and Ubiquitous Computing.
INFO 4120/6120 – Ubiquitous Computing
In Ubiquitous Computing, student teams draw on their education to understand how technology can inform intelligent solutions to today’s challenges using hands-on machine learning and hardware prototyping. Twelve demonstrations of student teams stationed along the hallway of the Duffield Atrium focused primarily on portable devices, including a portable golf swing analyzer, and two devices to help maneuver the social intricacies of wearing masks in the days of COVID-19.
Recognizing the inability to read facial expressions in conversations with masked friends, Christopher Chandra and Jackie Woo built “Behind the Mask”, a mask equipped with sensors and an LED screen to read and display four facial expressions – neutral , surprise, a smile, and a frown.
Classmates Rishik Zaparde and Sunil Sabnis also used the math to discuss another aspect of wearing the mask: how to wear one correctly and consistently. “SmartMask” is a portable mask with four capacitive sensors to detect if it is correctly positioned. When the mask is worn on the nose, for example, the mask vibrates and the connection software displays a surprised emoji. When the mask is worn correctly, the interface displays a green check mark and a smiling emoji.
Fall 2021 was the first time that Cheng Zhang taught this course, and for students, INFO 4120 is a first for them too, said the assistant professor of information science.
“Many students did not have both computer hardware and machine learning experience prior to taking this course,” Zhang said. “The students learned about the entire development pipeline of an Ubicomp [ubiquitous computing] project, from the design of hardware prototypes to the collection of data in real environments, to the development of applied machine learning methods, to the processing and analysis of data.
Each of the 12 student teams was successful, he said, citing the “SmartMask” duo of Zaparde and Sabnis as an example.
“They creatively used capacitive sensing and machine learning learned in the classroom to address a timely challenge of the pandemic,” he said.
INFO 4410/6420 – Redesign of robots
Re-Designing Robots is an introductory human-robot interaction (HRI) course. The intention of this semester’s projects was not to design and build a robot from scratch, but to improve on the automation that exists right here on the Cornell campus, particularly at the Statler Hotel, said Malte Jung, Associate Professor of Information Science, Nancy H. ’62 and Philip M. ’62 Faculty 150th Anniversary Youth Scholar and INFO 4410 instructor.
“Students have spent time this semester going to the Statler and observing the automation used in the kitchen, laundry room, and room service,” Jung said. “The goal is to take existing automation and redesign it taking into account HRI principles. “
One of four class projects, FineLine was built with Taverna Banfi in mind, the hotel’s restaurant. Developed by Jenny Fu, Hancheng Zhang, and Nnamdi Nwagwu, Fineline is a mobile ticket and print interface design system that aims to alleviate some of the mental workload associated with tracking food orders and progress.
INFO 4320 – Introduction to Rapid Prototyping and Physical Computing
A popular course among information science students, Introduction to Rapid Prototyping challenges students to apply creativity and iterative design skills to build working prototypes. This is where students learn to conceptualize and build a prototype using techniques such as laser cutting, 3D printing, and microcontroller programming.
The student team of Ben Shen, Katie Go and Will Spencer built the Beer Pong robot, a clean assembly of laser-cut plywood, an assortment of 3D printed parts, a DC motor and a switch, all channeled towards the goal with a good grade, above all, and perhaps by defeating the most seasoned beer pong enemies. The robot worked very well. The other students were having fun with it too, and it was very rewarding for Go.
“In the last 96 hours, we weren’t sure it would all turn out,” she said with a laugh.
“It was mostly running at 6:30 am last night,” Spencer added, “and was running fully about half an hour before. [this demonstration]. “
Across the atrium, Kevin Sun, Victoria Lu, Lucy Wang and Nandan Aggarwal had built “Knitpicking: Automated String Art,” a mechanical threading arm that loops the thread on a rotating wooden platform, creating a spiral work of art in about 25 minutes. Nearby, Kari Si, Mina Barakatain and Zenas Lim have created “Le Pour Barista”, a barista robot designed to serve the perfect latte.
“The aim of the course is to know how to transform an idea into a physical concept that people can demonstrate to others”, declared François Guimbretière, professor of information sciences and lecturer INFO 4320. “The project did not no need to be perfect. What is important is that it conveys the main principles behind the idea. The emphasis is on fast iteration, where you discover your mistake very quickly and move forward as you learn.
Louis DiPietro is a writer at Cornell Ann S. Bowers College of Computing and Information Science.