In a blog post published today, Lyft announced that they plan to start using their rideshare platform’s drivers to help accelerate autonomous vehicle technology. While AV tech has come a long way, self-driving cars are still making deadly mistakes when faced with unplanned scenarios. If autonomous vehicles are to become mainstream then they need to be able to make real-time assessments of every scenario possible.
Lyft is now equipping a subset of cars on their driver network with low-cost camera sensors to capture how human drivers react to numerous different situations on a daily basis. This will allow Lyft to not only see how a human driver reacts to a pothole or another car running a red light but it will also enable their engineers to find and tackle new challenges that were not considered before.
Another benefit of tapping into their rideshare driver network, is Lyft will be able to more accurately build 3D models of our cities infrastructure which is vital information for AV’s to be able to properly navigate. According to Lyft, “3D maps for AVs must also contain context about the environment in which the self-driving car will operate, such as information on lanes and traffic lights. Lyft generates this information from our rideshare data by using a combination of 3D computer vision and machine learning to automatically identify traffic objects. The situational data we get from this — like where lanes are and which traffic light drivers must follow — gives us the context we need to understand how drivers handle risky situations, like a driver running a particular red light.”
Lastly, another benefit of using their rideshare drivers as outlined by Lyft is it will help their team to find the best “path” for AV’s. For example, while common sense may suggest that staying perfectly centered in a lane is the safest, Lyft believes this assumption is not always true. They have found that human driving is much more nuanced than that due to features that may be undetectable to AVs, such as parked cars, pieces of debris, or potholes. By gathering data on human drivers, Lyft will better be able to plot the safest trajectory for their autonomous vehicles.
As a driver, would you be open to Lyft installing a camera in your car in order to gain data for AV tech?