Uber begins autonomous mapping of Washington D.C.
Posted: 27 January 2020 | Sam Mehmet (Intelligent Transport)
Uber Advanced Technologies Group has already performed similar projects in Dallas, Pittsburgh, San Francisco and Toronto.
After its original launch in the region in 2011, Uber has now begun to map Washington, D.C. using its self-driving cars on District roads for data collection. The cars were in manual driving mode, meaning a Mission Specialist (a specially trained vehicle operator) maintained control of the vehicle at all times.
Uber is reportedly using a phased approach to develop and deploy self-driving vehicles, taking the necessary steps to operate safely in every city. Manual data collection is said to be the first step in this development process.
According to a Medium post written by Danielle Burr, Head of Uber Federal Affairs, this manual data collection allows Uber to:
- Develop high-definition maps – the foundational information layer for our self-driving system
- Capture scenarios that might be different from city to city to simulate and incorporate into on-track testing
- Further refine Uber’s expansion methodology, which involves identifying key characteristics within an operational domain in a new city, and then running that data through its autonomy system in simulation and on its test track to verify that the self-driving system performs as intended before it drives on the road.
Uber is looking to use this first round of manually driven data collection to lay the foundation for testing vehicles in self-driving mode in Washington, D.C.. The Medium post stated that Uber remains committed to ensuring that every mile it drives on public roads contributes safe and meaningful learnings to inform development work in the future.