-
Front-end 1 (State map, light mode)
-
Front-end 2 (RoadSense interface, dark mode)
-
ML Training 1
-
ML Training 2
-
ML Training 3
Inspiration
Driving has become second nature to most people, and it is easy to forget how much danger is on the road each time a person gets behind the wheel. Our product, Toyota RoadSense - Done Driving Dangerously, optimizes the average driver's experience in a hands-on approach to show the user Weather data, Speed + Location, Speed + Weather, and Traffic Data that could potentially affect their travel and allows them to re-route to their destination should they choose to.
What it does
- Weather data - shows impacts of weather on the route the user plans to utilize
- Speed + Location - highlights the range of speeding drivers in a particular location
- Speed + Weather - recommends speed to the user based on the weather for a particular location
Traffic data - shows route hazards due to traffic
Data obtained would be from Toyota's current user vehicle data
How we built it
AWS Cloud (SageMaker, Lambda, Jupyter, API Gateway, etc.), React.js, Node.js, JavaScript
Challenges we ran into
- Training the dataset with ML
- UI format challenges
Accomplishments that we're proud of
- Learning and implementing AWS Cloud services for the first time
- Creating a minimal viable product (MVP)
What we learned
- How to train a particular dataset using ML
- AWS Cloud services
- React.js/Node.js UI implementation
What's next for Toyota RoadSense - Done Driving Dangerously
- Expanding implementation into individual state counties
Log in or sign up for Devpost to join the conversation.