Waymo and Tesla’s self-driving data differences

Waymo and Tesla are both in the process of creating self-driving vehicles – but in different ways

In order for both companies to succeed in this technological revolution, they need to develop a strategy to produce, collect and analyse driverless-vehicle data.

Unlike Google’s self-driving project Waymo, Tesla vehicles use Autopilot to collect its data, which has the ability to log instances where the Autopilot software is taken an action. Its data will eventually get uploaded back to the company as it has the ability to simulate full Autopilot data across billions of miles that will be eventually driven.

Tesla explained in a blog post: “Enhanced Autopilot adds these new capabilities to the Tesla Autopilot driving experience. Your Tesla will match speed to traffic conditions, keep within a lane, automatically change lanes without requiring driver input, transition from one freeway to another, exit the freeway when your destination is near, self-park when near a parking spot and be summoned to and from your garage.

Autopilot software

“Tesla’s Enhanced Autopilot software has begun rolling out and features will continue to be introduced as validation is completed, subject to regulatory approval. Every driver is responsible for remaining alert and active when using Autopilot, and must be prepared to take action at any time.”

Similarly, Waymo is working on its data, but not through Autopilot. Instead, it’s using LIDAR data – an optical remote-sensing technique that implements laser light to sample the surface of the earth, which produces “highly accurate” x,y,z measurements; as well as sensors, five radar sensors, and eight cameras.

Waymo wrote in a blog post: “We’re building a safer driver that is always alert and never distracted. Our fully self-driving technology will handle all the driving so you can go from door to door without taking the wheel. This will deliver the biggest impact on improving road safety and mobility for everyone.

“Our vehicles have sensors and software that are designed to detect pedestrians, cyclists, vehicles, road work and more from up to three football fields away in all 360 degrees.”

Ultrasonic sensors

Tesla is also “highly kitted out”, but instead of using LIDAR, it implements eight surround cameras which provide 360 degrees of visibility around the car at up to 250 meters of range; twelve updated ultrasonic sensors complement this vision, allowing for detection of both hard and soft objects at nearly twice the distance of the prior system; and a forward-facing radar which provides additional data about the world on a redundant wavelength.

Tesla is said to be the low-cost option and its goal is to automate 90% of driving within the next two years. Waymo created the 90% solution years ago, so is currently focusing on solving big issues within the driverless-vehicle industry, and a monopolistic advantage for the future.

Tesla also noted in a blog post that, “to make sense of all of this data, a new onboard computer with over forty times the computing power of the previous generation runs the new Tesla-developed neural net for vision, sonar and radar processing software.”

I’m sure we can all agree that it will be interesting to see Waymo and Tesla’s driverless-vehicle results by 2022.

Written by Leah Alger