Tesla’s patent for “Data Pipeline and Deep Learning System for Autonomous Driving” was published on December 26. The idea behind the patent is to revolutionize and improve upon past deep learning systems that have been used for autonomous driving vehicles. In the past, these systems have used “captured sensor data” to retrieve information.
Tesla recognizes the need for new sensors when data becomes more complex. According to the electric car maker’s patent, there is “a need for a customized data pipeline that can maximize the signal information from the captured sensor data and provide a higher level of signal information to the deep learning network for deep learning analysis.”
The system described in this patent would capture an image using any of the sensors or cameras on the vehicle. In this case, this would describe a high dynamic range camera, camera sensor, radar sensor, or ultrasonic sensor. The image would then be broken down through a “high-pass” or ‘lo-pass” filter and a series of processors would then decipher what the image means.
The flowchart below describes what the process of the vehicle learning the information would look like. “Receive Sensor Data” is the first portion of this process. Then, data will be broken down and pre-processed for the system to then begin its “Deep Learning Analysis.” The results will then be passed along to the vehicle’s Artificial Intelligence Processor to be utilized during vehicle control.
Read more here
Join us February 26-27 for the Property Portal Watch Conference Bangkok 2020.