Tesla Driving AV Development with Neural Nets
May 22, 2020—Full Self Driving has been foundational to Tesla's development and the company aims to achieve a solution capable of fully autonomous driving, reported CleanTechnica.
Tesla has leveraged its deployed fleet in a way that is not immediately intuitive in order to train its Autopilot neural net. According to the report, the company has tasked vehicles driving around the real world with finding examples of stop signs or likely stop signs. The vehicles then send the resulting data surrounding the encounter back to the Tesla headquarters.
Tesla analyzes the images and uses them to train the autonomous driver neural net for its vehicles. Tesla instructs vehicles to do this for other cases, including street lights and lane markings. The more potential situations the model trains on, the more abstract scenarios the car will be able to handle.
The automaker also extrapolates 2D video images into 3D to build a dynamic world that can be used for navigation.