Tesla Introduces Self-Driving Features With Software Upgrade

A new report published today by Israel’s Globes suggests that Elon Musk visited Israel-based tech firm Mobileye to test a new system for the next generation Tesla Autopilot.

According to Globes, Musk visited Mobileye’s Israel operations earlier this month for a “demonstration of several breakthrough developments by Mobileye in [automated driving technology] installed on a trial Tesla Model S vehicle.”

The report suggests that Mobileye is testing its automated driving technology in two Tesla Model S test vehicles. Independently, a Model S being tested with a fully-autonomous hardware suite was recently spotted in California.

Mobileye is already a supplier in Tesla’s Autopilot program and last year the automaker committed to keep using the firm’s technology in future iterations of its self-driving and assisted-driving programs.

The Globes described the tech in the demo Musk reportedly witnessed:

“Among the technologies are a system called DNN (digital neural network), which enables the vehicle to “learn” by gathering data on the move, and even to identify different kinds of road surface; free-space, which enables the automatic vehicle’s systems to identify areas without defined objects such as hard shoulders of roads, sidewalks, and so on, and avoid collisions and deviations from the road; a “holistic path prediction”, which enables a vehicle to select the correct path – on an open road, for example – even when there are no visual hints in the environment; and a sign identification system that can identify over 1,000 signs and road markings in use around the world.”

The current version of Tesla’s Autopilot is believed to already have self-learning capacity, similar to the “DNN” described above, built on top of Mobileye’s system. Tesla also recently hired a few machine learning experts to improve its system.

Tesla is expected to release more features through over-the-air updates utilizing the same hardware, but the system, which consists of a forward-looking camera, a radar, and 360 degree sonar sensors, is limited and not expected to achieve fully autonomous driving.

Last year, Mobileye’s CEO Ziv Aviram confirmed that his company is working a new system which he described as a  “more sophisticated” and that could allow fully autonomous driving. He also confirmed that one OEM is already implementing it in a vehicle:

“Today we are already preparing with one of the OEM, a first vehicle based on 8 cameras, one radar and ultrasonic around the vehicle. So this is much wider implementation of the first introduction of semi-autonomous driving and the trifocal is going to be here as we planned, but additional 4 cameras around the vehicle and one camera looking back. The system will run on 5 EyeQ3 chips and all of them will be connected.”

Aviram didn’t disclose which automaker is testing the system, but he said during a recent conference that Tesla is willing to push the envelope “faster and more aggressively than any other OEM”. He also hinted that the new system could find its way into a commercial product within a year and we know that Tesla has been testing a similar hardware suite with more cameras.

Both Musk and Aviram agree that a fully autonomous system could be developed using only camera sensors and radar, without the need for LiDAR technology.

Featured Image: Photographer David Paul Morris/Bloomberg via Getty Images.

Subscribe to Electrek on YouTube for exclusive videos and subscribe to the podcast.

About the Author