What is the problem you’re solving? According to USA Today and research conducted by the American College Counselling Association, up to one-third of college students report serious symptoms of depression, with up to 80% of students reporting overwhelming feelings of hopelessness or stress. Along with the stress of school, the stress of having to care for oneself can be daunting. Our task was to try and alleviate some of the sadness on college campuses through the creation of Winston, the Efficient Diplomacy Technician. Who are users and/or customers? Users and customers are college campuses, as they have a vested interest in the mental health and well-being of their students. What’s currently missing that they need and which your solution provides? Currently, there is not an automated implementation for a system that identifies at-risk individuals who exhibit troubling symptoms. Our solution automates the task of both identifying these individuals and cheering them up.
Inspiration
Our team proposed two questions that governed our hacking process: what makes people happy, and what if we could automate that process? The answers: free stuff and yes, yes we can. We chose to automate the act of cheering people up by creating an artificial person that can perform this task.
What it does
Winston, the Efficient Diplomacy Technician, moves freely around, collects data from human faces to measure their facial expressions and associated emotions, and determines whether or not it is appropriate to dispense candy.
How I built it
There are three main elements to the design of this hack, the first of which being the enclosure and the elements which it encloses (the dispenser and its hardware). The dispenser was built using an Arduino Uno and an ATtiny to control the motion of a repurposed cat food feeder. The second main element was the actual facial recognition software and camera, which was sourced from Microsoft Cognitive Services and then rewritten to capture a limited number of frames, accept and reference either a URL or a file path as the image source, and dispense candy based on the measured happiness and sadness levels. The third and final main element is the rover, mainly consisting of a four wheel framework, a battery, and a Raspberry pi. In addition to these main elements, a user interface was developed using Firebase.
Challenges I ran into
As with the nature of hardware hacks, numerous obstacles were overcome in the process of building Winston, the Efficient Diplomacy Technician. Challenges included: mounting the enclosure to the rover given the rover's low power and limited mobility and mounting the dispenser to the enclosure itself; the inconsistent dispensing of candy via the dispenser, which required recreating a previous working design after a refined and soldered design failed to dispense candy as required by the design; and configuring the Wifi on the Raspberry Pi.
Accomplishments that I'm proud of
We're proud of the fact that we successfully got a hardware hack connected to Microsoft Cognitive Services.
What I learned
We spent hours learning about the temperamental nature of circuits and how best to minimize the damage incurred by malfunctions, as well as how to optimize the mobility of a rover operating in a low-friction and hard-floor environment when its performance is best understood on a thin, firm carpet environment.
What's next for Winston, the Efficient Diplomacy Technician
Winston's work will never be done so long as there are stressed college students there to demand his help! Winston hopes to distribute other free goods or perform verbal acts of kindness (like singing a song or giving complements) to impact the mood of students on college campuses.
Built With
- attiny
- firebase
- microsoft-emotion-api
- python
- raspberry-pi
- webcam
Log in or sign up for Devpost to join the conversation.