Skip to main content

Could unsupervised A.I. enable autonomous cars to learn as they go?

Cortica Automotive

Most autonomous vehicle tech ventures such as Waymo, GM Cruise and Nvidia rack up miles of deep learning experience to build reliably safe systems for self-driving cars. Cortica and Renesas Electronics‘ entirely different approach focuses on helping cars learn on their own.

Cortica, an Israeli company with roots in predictive artificial intelligence based on visual perception, is embedding its latest “Autonomous A.I.” solution on the Renesas R-Car V3H system-on-chip (SoC) solution for self-driving cars.

Related Videos

Referred to by the companies as “unsupervised learning,” Cortica’s autonomous A.I. enables a vehicle to make predictions based on visual data received from forward-facing cameras. According to Cortica, the system uses “‘unsupervised learning’ methodology to mimic the way humans experience and incorporate the world around them.”

The goal is for the car to be able to react to any situation, whether or not the objects or circumstances were previously converted to rules by deep learning A.I. For example, if a mattress flies off the back of a pickup truck in front of you at speed on the highway, would you rather be in an autonomous vehicle managed by a system of rules based on specific experiences or a system that observes and reacts to objects in motion based on how various object classes are likely to move?

According to Cortica, its autonomous A.I. can leverage the system’s relatively low computing demand compared to deep learning systems to achieve greater perception accuracy and performance. Referring to the collaboration with Renesas prior to a demonstration at CES 2019, Cortica stated in a news release:

For the first time, the collaborative effort will introduce a more robust and scalable open-platform perception solution featuring unmatched accuracy and performance rates, faster reaction time, and overall safety upgrades for ADAS. The solution demo by Cortica at CES will demonstrate a new generation of safer, smarter, and more ‘aware’ auto running directly on the Renesas chip with unparalleled execution times. 

One hundred percent predictability is a specious goal for autonomous vehicle systems. Everyone wants error-free performance, but no system will ever have a perfect record. However, as with horseshoes and hand grenades, the closer you get, the greater the result.

Nearly all fatal accidents in the United States involve human error. In the 2016 U.S. Department of Transportation Fatal Traffic Crash Data report, the National Highway Traffic Safety Administration (NHTSA) stated, “NHTSA continues to work closely with its state and local partners, law enforcement agencies, and the more than 350 members of the Road to Zero Coalition to help address the human choices that are linked to 94 percent of serious crashes.”

The NHTSA is an active force in self-driving vehicle development. In September 2016 the agency released its Federal Automated Vehicles Policy.

The DOT fatal crash data report refers to traffic safety goals of autonomous vehicle systems, stating that, “NHTSA also continues to promote vehicle technologies that hold the potential to reduce the number of crashes and save thousands of lives every year, and may eventually help reduce or eliminate human error and the mistakes that drivers make behind the wheel.”

Editors' Recommendations

NASA’s experimental electric plane takes ‘major step’ toward first flight
An illustration of NASA's experimental X-57 electric airplane.

NASA says its experimental electric airplane has taken a "major step" toward its maiden flight after successfully completing thermal testing of its cruise motor controllers.

The space agency has been working on the fully electric X-57 Maxwell aircraft since 2016 with the goal of creating an efficient and quiet flying machine that’s kinder to the environment.

Read more
Aussie authorities still searching for tiny radioactive capsule
A map of Western Australia.

Talk about searching for a needle in a haystack. Australian authorities are currently looking for a tiny radioactive capsule that they believe fell from a truck during a recent journey from a desert mine to a storage facility in the city of Perth.

The problem is that the capsule is just 6 millimeters in diameter and 8 millimeters tall, while the road being searched runs for 870 miles. That’s the distance between Los Angeles and Portland, or, to put it another way, the entire length of Great Britain. According to Google Maps, the route takes more than 12 hours to drive. Walking it, which is probably the pace you'd want to go at if you're looking for something this small, would take around 233 hours.

Read more
Robotaxis have a passenger problem that no one thought of
gm cruise to test fully driverless cars in san francisco

An issue with self-driving cars that apparently no one previously considered has come to light: dozing passengers.

Officials in San Francisco, where Alphabet’s Waymo company and GM-backed Cruise are currently operating robotaxi services as part of ongoing trials, highlighted the problem in a recent letter to the regulator, Wired reported.

Read more