What inspired us
Our team wanted to create something that would make recycling more engaging and impactful. We were inspired by how small actions can lead to big changes, especially when everyone gets involved. Recycling can feel like a chore, so we wanted to find a way to combine technology with real-world impact. This led us to create Recycle Buddy.
What it does
The website allows users to scan recyclables using their webcam, and through AI, it recognizes common recyclable items and awards points based on what you recycle. It’s a simple way to make recycling feel more rewarding. We also added bonus challenges that users can complete for extra points, and a profile page to track all the points and items they’ve recycled. The analytics section shows progress, so you can see the direct impact of your efforts over time.
How we built it
We built the AI model using Teachable Machine to train an AI model to recognize recyclable materials. After that, we integrated it with a webcam feature on the website. We focused on making the design user-friendly, with sections for scanning items, completing challenges, and viewing stats. For the challenges and analytics, we used algorithms to generate and track progress.
Challenges we ran into
One of the biggest challenges we faced was getting the AI model to accurately detect recyclable items. It wasn’t perfect at first, and there were lots of trial and error moments where the model detected items incorrectly. We also had to make sure the user experience was smooth, with efficient and fast loading times.
Accomplishments that we're proud of
We’re proud of how we managed to integrate the AI with the user experience. It feels like an actual game yet it leads to a meaningful impact. We also love how the challenges add competitiveness and make recycling more fun. We are also proud of the live analytics page because it gives users a visual representation of their progress.
What we learned
Through this project, we learned how to work with AI models, specifically training them to recognize objects. We also learned a lot about web development, from user interface design to ensuring everything runs smoothly for the best user experience. Combining tech and sustainability in a fun way taught us that even small innovations can make a big difference.
What's next for Untitled
Next, we plan to improve the AI model, making it more accurate and capable of detecting a wider range of recyclable materials. We also want to add more challenges and rewards to keep users engaged. We also hope to work with environmental organizations to get more people involved in recycling. We want to make recycling engaging rather than like a chore.
Log in or sign up for Devpost to join the conversation.