CES 2017: How Nissan and NASA solved a HUGE issue with driverless cars

The only reason driverless technology isn’t everywhere in 2017 is because of us. We’re unpredictable, we cause accidents – and our only redeeming quality is the way we can navigate round our own mishaps. However, because we can’t suddenly turn every car autonomous overnight, the first driverless cars will need to be able to share the road with human drivers, and also deal with tricky situations we can cause. At CES 2017, Nissan and NASA have unveiled Seamless Autonomous Mobility – remote, cloud-based technology that could change driverless cars forever.

CES 2017: How Nissan and NASA solved a HUGE issue with driverless cars

Autonomous cars only really go wrong when something unusual happens. When there’s an element of unpredictability, autonomous cars can read the situation wrongly and can cause an accident. Simply put, Seamless Autonomous Mobility (SAM) works by identifying these tricky situations, and handing remote control to a human operator instead.

During CES, Nissan explained the technology with a scenario: a car encounters an accident and a policeman giving traffic signals, and it uses its sensors to realise it’s incapable of safely negotiating the situation. That’s when SAM gets to work. The car stops, and hands control wirelessly to a “mobility manager,” which is essentially like a concierge service for driving. Once the mobility manager has assessed the situation, they “paint” a virtual path for the car to follow. After leaving the problem area, the vehicle will continue to use its own driverless judgement.


Space science

The technology is actually based on NASA’s Visual Environment for Remote Virtual Exploration (VERVE) software. First designed for NASA’s unmanned missions on alien surfaces, the tech enabled autonomous robots to hand over control to technicians when they encountered tricky terrain. But there’s one main difference with Nissan’s tech.  

The new system would share the new path with nearby cars using the cloud – sharing the data with the rest of the traffic. That means that fewer mobility managers will be needed, and you’d be less likely to have to wait for one to help.

“Our goal is to change the transportation infrastructure,” said Maarten Sierhuis, former NASA scientist and director of the Nissan Research Center in Silicon Valley. “We want to reduce fatalities and ease congestion. We need a huge number of vehicles out there. What we are doing at Nissan is finding a way so that we can have this future transportation system not in 20 years or more, but now.”

Dr Eugene Tu, director of the NASA Ames Research Center, added: “This is not only a demonstration of the transfer of space technology to industry, but also the application of their research back to our space technology, with additional uses for our unmanned aircraft systems research. This is a perfect example of technology literally driving exploration and enabling future space missions.”

FINE. If driverless cars look like this, we'll get one.

Machines vs humans

So, has Nissan really solved one of the biggest problems with autonomous driving? The answer is a resounding – sort of. In theory, Nissan has come up with a safe hybrid that manages to incorporate the best of both worlds – SAM brings mechanical error-free driving to our roads, but also adds human intuition when needed.

However, in practice SAM would require a huge amount of infrastructure that simply doesn’t exist. You’d need to hire a huge number of mobility managers, and you’d also have to hope the wireless network used to connect them was safe and reliable.

Mixing Nissan’s SAM technology with manual driving could be a more viable solution. Autonomous cars could use their sensors to drive normally, but when they encounter situations that need human judgement, they could simply offer in-car control to their passengers.

Disclaimer: Some pages on this site may include an affiliate link. This does not effect our editorial in any way.

Todays Highlights
How to See Google Search History
how to download photos from google photos