Tesla Testing More Autonomous Driving Features With Secret Upgrades Sent To Cars
Tesla Motors has a system incorporated into all vehicles that allows for “over-the-air” software updates. This means that not only can the company correct problems on all vehicles via wireless updates, but also Tesla can collect data to assist with future technology. Autonomous driving software can be loaded (even privately) in order to test its capabilities in relation to drivers habits and traffic and road conditions. Moreover, Tesla can test it even if it’s not driving the vehicle.
With this unique ability, Tesla can rise to the forefront of other automakers in its goal to assure that autonomous driving technology can become a reality on public roads. With the “real-time” data that Tesla collects, aside from helping the company progress its efforts, it will be easier to persuade government regulators to back autonomous technology. Sterling Anderson, director of Tesla’s Autopilot program said:
“The ability to pull high-resolution data from these vehicles and to update the vehicles over the air is a significant part of what’s allowed us in 18 months to go from very behind the curve to what is today one of the more advanced autonomous or semi-autonomous driving features.”
In 2014, Tesla started this process by installing 12 new ultrasonic sensors into its production vehicles. The sensors were reported to be part of an emergency braking system. However, Tesla was “thinking-forward” and has actually been using the sensors, along with cameras and radars to stream data to the company about how that units are functioning and sensing objects in regards to autonomous driving. Anderson explained:
“We will often install an ‘inert’ feature on all our vehicles worldwide. That allows us to watch over tens of millions of miles how a feature performs.”
“Since introducing this hardware 18 months ago we’ve accrued 780 million miles. We can use all of that data on our servers to look for how people are using our cars and how we can improve things.”
He added that Tesla is receiving about a million miles worth of new data every 10 hours. The data is used to assess the autonomous driving software. Following the assessments, Tesla can use the over the air feature to “secretly” install additional software to be able to watch over how it performs comparatively. Even though the software isn’t detected by the user, and has no bearing or control over the driving experience, it can still aid Tesla in its further development.
Other companies like Google (Alphabet) and Uber are currently testing autonomous driving technology. Unlike Tesla, Google and others are only able to process saved “public” data from prototype fleets. Much of the testing is done in closed areas and only some is achieved on public roads. GM is also testing the technology, but without over the air abilities and model wide internet connections, the data is not much like what Tesla is collecting and utilizing.
Overall, Anderson and Tesla are very excited and optimistic about this situation and its benefits. Understanding drivers’ habits, road and traffic conditions, and regularly assessing the autonomous driving technology’s strengths and weaknesses can only help the process. Anderson was adamant to remind drivers:
“Autopilot is not an autonomous system and should not be treated as one. We ask drivers to keep their hands on [the wheel] and be prepared to take over.”