≪ Back to Blog

A.I. for Cycling Navigation

I recently had the pleasure of presenting my first session at Esri DevSummit 2019 in Palm Springs, CA. It was also my first time in Palm Springs, and we were greeted with warm and sunny, if a little windy, weather. Along with my colleague and mentor, Christopher Moravec, we showcased a side project our company has been working on, A.I. Navigation for Cycling Safety and Inclusion, as a User Presentation.

Our goal with this project is to inspire others to bike more often. Our data begins focused on Portland, OR as that is where we work and cycle. We’ve seen the city grow over the past few years and would like to offer safer routing options that learn with the cyclist and are always ready to improve.

comic depicting a joke about biking like salmon swim

This project is currently separated into two parts: the chatbot interface and the navigation. We built our initial chat interface using the Azure Bot Service. Microsoft offers this neat little tool where even early career developers like me can build a friendly and fun, interactive chatbot. Our eventual goal is to create a voice-based interface that will update a chosen route via voice command while on the go.

The navigation piece is much more involved. Portland is an awesome city and one way they prove that is by making their bike infrastructure data available to the public. We combined the Portland bike data and OpenStreetMaps. With the help of good friends, we were able to transform and improve that data and the results turned out very nicely. Along the way, we discovered weird bugs where bikes were being routed into heavy traffic because the routing mechanism (or really the data) was thinking like a car and not like a bike. This is an example of what we aim to improve.

We broke the roads down into seven useable categories. The eighth category, highways, were not included as viable options for cyclers of any level. Our three levels were: Level One novice cyclers (or those new to city biking), Level Two intermediate cyclers, and Level Three hard core daily commute and more cyclers. Depending on the rider’s level of comfort, more or less intense routes are suggested.

comic depicting a joke about ai

We welcome you to view our A.I. Navigation for Cycling Safety and Inclusion slides and find out for what’s next to come.

We’d love your help beta testing the cycling navigation app.

≪ Back to Blog