The issue of waste management is something that many people view as trivial yet is one of the fundamental factors that will decide the liveability of the world. Yet even in Canada, a developed country, only 9% of plastics are recycled, meaning that the equivalent of 24 CN towers of recyclable plastic enters our landfills each year. In developing nations, this is an even more serious issue that can have profound impacts on quality of life.

What it does

Detritus AI is a smart garbage can that is able to detect and categorize waste into the respective containers and transmit essential information that allows for the optimization of garbage routes. DetritusAI tracks the quantity of waste that is in each container and communicates with the client-side applications used by garbage truck drivers to determine how full each container is. Based on the capacity of each garbage can and its location, DetritusAI calculates the optimal route for garbage trucks to collect garbage while minimizing distance and time, even taking into account traffic.

How we built it

When users place an object near the garbage can, a time of flight sensor detects the object and triggers an image classification algorithm that identifies the category of the waste. A message is sent via Solace, which instructs the garbage can to open the appropriate lid.

Within the garbage cans, the time of flight sensors continuously determines the capacity of the bin and communicates that information via Solace to the client-side application.

Using the Google Directions API, the optimal route for garbage collection is determined by factoring in traffic, distance, and the capacity of each bin. An optimal route is displayed on the dashboard, along with turn by turn directions.

Challenges I ran into

An issue we had was that we wanted to display a visual representation of the optimal route; however, we did not have enough time to figure out how to visually display the directions of the optimal route that we calculated.

Accomplishments that I'm proud of

We're proud of how we were able to integrate the hardware, classification algorithm, and the dashboard into a seamless solution for waste management -- especially given the tight time constraint.

What I learned

Communication between different components often takes more time than one might imagine. Thankfully, Solace is a very powerful tool that has resolved this issue.

What's next for DetritusAI

  1. Visually display the optimized route on the dashboard for the user
  2. Add a compost category because the environment is cool.
  3. Incorporate a social aspect that encourages people to recycle such as incentives or leaderboards

Built With

  • google
  • imageclassification
  • iot
  • nodemcu
  • react
  • solace
  • tensorflow
  • tofsensors
Share this project: