© 2025 WGLT
A public service of Illinois State University
Play Live Radio
Next Up:
0:00
0:00
0:00 0:00
Available On Air Stations

Rivian ups its game on hands-free driving and AI

A driver in a car with hands off the steering wheel being driven by AI
Rivian
/
Courtesy
Rivian is broadening its hands-free driving options to more than 3 million miles of road by introducing new software, hardware, and AI learning to its vehicles.

Electric automaker Rivian has unveiled new technology it says will put it at the forefront of autonomous vehicles.

Rivian is making the case it is ready to catch up with and surpass Tesla in self-driving vehicle technology. At a company event Thursday, Senior Vice President of Electrical Hardware Vidya Rajagopalan said vehicles made in Normal will have multiple cameras like most competitors. They will also have five radars for 365-degree vision and Lidar. Lidar uses ultraviolet, or near-infrared waves, to determine ranges to objects. That helps in rotten weather and at night.

A printed circuit board with a Rivian processor in it
Rivian
Rivian's multi-chip autonomous driving processor can handle 800 trillion operations per second, according to the company.

"We have shown that our third-gen autonomy hardware system is capable of processing five billion pixels per second of sensor data," said Rajagopalan.

The idea of Lidar has been around since the 1930s. Archeologists have used big bulky units to map out the remains of ancient cities from the air since the 1960s. Rajagopalan said the technology can now fit seamlessly in a car.

"About 10 years ago, Lidars used to cost in the tens of thousands of dollars. Today, you can get a very good Lidar for several hundreds of dollars. The resolution of Lidars has similarly improved tremendously," said Rajagopalan.

Another potential difference maker is Rivian has made its own computer chips, processors, and AI software. The company said that will let improvements come to market faster. It won't have to work through outside hardware and software vendors to make sure all the parts work together.

Rivian Universal Hands Free

Rivian is billing its new AI driving system as robust by any measure. The multi-chip processor can handle 800 trillion Operations Per Second [TOPS]. It's more energy efficient than something bought from outside the company, said Rajagopalan.

"By building purpose-built silicon, we do not carry the overhead that comes from leveraging a design that was built for some other tasks and repurposed for autonomous driving. We built this silicon so it would do a really good job at autonomous driving and physical AI problems," said Rajagopalan.

Most autonomous vehicle companies have what are called “ground-truthing” vehicles to teach their AIs better and safer driving. Workers drive around in sensor-equipped vehicles and accumulate data on best practices and real-world conditions. Rivian Autonomy and AI vice President James Philbin said Rivian's system is better than the rest.

Side view of an R-2 Rivian equipped with Lidar
Rivian
/
Courtesy
All R2 vehicles Rivian will start selling next year will have a more robust hands-free driving software stack with Lidar to help cope with adverse driving conditions.

"Because they are prototypes, these fleets are typically small, numbering in the tens to 100s. In contrast, with the LIDAR-equipped R-, every vehicle will become a ground truthing vehicle," said Philbin.

The company will begin producing R2 vehicles for sale next year at its plant in Normal.

Most AI is based on large language models. Rivian's is based on what's called a Large Driving Model or LDM. And it has what the company is calling an "apprentice" running in the background, learning from what's going on.

"Imagine this process running millions of times a second across millions of scenarios with a whole database of road rule costs and losses. That's how LDM is trained. We can then distill this model into one that we can run onboard. All of this work results in new models, continuous enhancements, refinements and new features that we can continuously deliver to our customers," said Philbin.

One thing about using human data from drivers in the wild instead of curated drivers following the rules: Ordinary people don't always make the best choices. Take for example approaching a stop sign. A lot of motorists slow to almost a stop and roll right on through. Or they go too far forward.

Philbin said Rivian can sort for data that catches drivers doing what they're supposed to, slow to a stop behind the line, and train the AI to produce the preferred outcome.

Rivian can set its software to filter for certain scenarios and mine that data immediately, said Philbin.

The company has also listened to owners who said they want more road coverage and the latest improvements expand on what had been a relatively small hands-free map of about 100,000 miles of roads.

"Universal hands-free unlocks over 3.5 million miles of hands-free driving on roads across the U.S. and Canada. If there is a painted line and it's clearly marked, you can now drive hands free," said Philbin.

Rivian's dreams include more than point-to-point hands-off driving. Eventually they want eyes-off-the-road driving. Someday, the company hopes, you will be able to ask your car to drop you off at the airport, drive home with no one in it, and then pick you up when you get back.

You may not even have to own the vehicle. The company said its AI opens opportunities in the ridesharing sector.

"The gap between software-defined vehicles and traditional architectures is getting exponentially wider with AI," said Chief Software Officer Wassym Bensaid.

Rivian has also unveiled a digital assistant in its vehicles that's billed as much more than a chatbot.

"The assistant has memory, has context, it remembers the full story — who you are talking to, where you are going, and what you just searched for. And then it puts everything into a perfect message," said Bensaid.

Bensaid says Rivian is positioned to add capabilities as they come on the market.

Rivian CEO RJ Scaringe said all these features will give people back their time.

WGLT Senior Reporter Charlie Schlenker has spent more than three award-winning decades in radio. He lives in Normal with his family.