Waymo, the autonomous driving subsidiary of Alphabet, announced this week that its self-driving cars have driven more than 10 million miles on the road since 2009. Waymo also announced that their software is now driving the same distance every 24 hours inside of a simulation of the real world, where engineers are able to train the software using test scenarios that might be too dangerous to run in the real world. Waymo has clocked more than 6 billion miles in this virtual simulation of the real world and became the first company last October to remove safety drivers from inside some of their self-driving vehicles.
Autonomous cars rely on data rather than knowledge of the real world like human drivers so it is essential to provide the machine learning systems with vast amounts of training data. Waymo uses "fuzzing," which adds random variations to the same simulation to test and train the machine learning system's response to confusing situations. There are currently close to 400 people using Waymo's autonomous vehicles as taxis in Arizona.
There is a big gap however, between the driving environment in Phoenix, Arizona and cities like San Fransisco or Boston. Being able to address the unexpected situations that arise from more chaotic or less temperate places is the next hurdle for Waymo and other autonomous driving companies.
Click here to read the full article.
A2D Digital Feed
Acompanhe as principais novidades sobre transformação digital.