[danpat]

Here at Mapbox we're doing navigation on OSM with traffic data - we collect our own telemetry, and use it to guide OSM-based routing. There are numerous Android/iOS apps using our API that you could use, or you could build one yourself.

[Sir_Cmpwn]

I've been wondering, given that you've made all of the building blocks, why hasn't Mapbox built and released an open source maps app for Android? It looks like you're just weekend's work away from having an open source app which is competetive with Google Maps on F-Droid.

[mberg]

Mapbox has been pretty strategic about not being perceived to compete with it's developers. Besides creating an amazing stack remaining neutral I think is part of their appeal.

[JetSpiegel]

OsmAnd already exists, and it had a metric ton of development time put into it.

[pymai]

I presumed they open sourced it already since the "Maps" app in the fdroid store is the same app just minus some ads or something

[rmc]

The "Maps" app in fdroid[1] is actually a recompilation of Maps.me[2], which is from another company, not Mapbox.

[1] https://f-droid.org/en/packages/com.github.axet.maps/ [2] https://maps.me/

[jakecopp]

I second this, and very interested in doing it myself!

[em3rgent0rdr]

Please elaborate. From where and how do you get the traffic data from, and is it sufficient?

[morganherlocker]

Our traffic data is generated in house using anonymized location telemetry from our SDKs, much like most other traffic providers. The live speed predictions we generate for congestion and ETA models are competitive globally, providing the most accurate ETAs available in many parts of the world. Our accuracy today is particularly strong in the US, when compared to similar services.

[arctux]

Do you know if Mapbox has any plans to work with the World Bank's OpenTraffic[0]?

[0]: http://opentraffic.io

[morganherlocker]

Not at this time. It's an awesome project, but we started developing our traffic engines around the same time and needs quickly diverged. We do try to open source many of the low level pieces of our model as reusable libraries whenever possible, such as our graph normalization algorithms[1]. At the end of the day, much of the core is difficult to decouple from data engineering infrastructure which will be internal to each organization, due to the immense volumes of live data that must be handled to power a modern traffic engine.

Aspects of the model like noise reduction, modality classification, and speed distribution estimation also require lots of fine tuning that is specific to the telemetry being ingested & the usage patterns of the output. For example, our speed models learn and correct from observed errors in various situations over time, which is coupled to our internal metrics data.

[1] https://github.com/mapbox/graph-normalizer