The American ridesharing company Lyft says it’s using data from its network to improve the performance of its autonomous vehicle systems.

Venturebeat.com reports that the company’s equipped a subset of vehicles with inexpensive camera sensors to capture “challenging scenarios” and solve problems like generating 3D maps and improving simulation tests.

Lyft has told the website the data from drivers’ vehicles will allow it to continuously update “city-scale” 3D maps and create high-definition, centimetre-level maps of roads, buildings, vegetation, and other objects to help the vehicles localise, also providing contextual information like speed limits and the location of traffic lanes and pedestrian crossings.