Nissan teams up with Nasa to solve a big issue with autonomous cars

SAM enables humans to remotely interact with driverless cars when they get stuck

We're moving toward an autonomous future. With many new cars featuring ever more sophisticated driver aids. But fully autonomous cars will have a problem - they'll always stick to the rules. 

Say there's an accident blocking the carriageway that means you need to pass on the other side of the road. Or maybe there's a traffic light stuck on red. 

Currently, a human doesn't have a problem resolving this issue. But what about a fully autonomous vehicle that is programmed to never go through a red light? 

To resolve this problem, Nissan has partnered with NASA to use some of its technology within a new system that it has introduced at CES 2017.

Seamless Autonomous Mobility, or SAM, partners in-vehicle artificial intelligence with human support to help autonomous vehicles make decisions in unpredictable situations and build the knowledge of in-vehicle AI.

Vehicle sensors (LIDAR, cameras, radars) can tell the car where obstacles are, the traffic light state, and even recognize some hand gestures, but Nissan believes that human judgment is required to decide on the appropriate course of action when a car is 'stuck'.

When a SAM-enabled vehicle comes across a situation it can't process, a human controller - perhaps hundreds of miles away - can view the information and images from the cameras and sensors on the vehicle and instruct it how to proceed. These situations will probably be rare, but  

"A lot of driverless cars [still] have human interaction, maybe 15, 20 years down the road we can change that," said Nissan CEO Carlos Ghosn at the launch of the technology. "A human knows how to overcome the rules. Having human support is probably the best way forward."

It's thought that the system could be most useful for situations where someone is managing a fleet of driverless vehicles, perhaps for deliveries or for use as taxis.

Nissan believes the system could enable more rapid introductions of fully autonomous vehicles on the road as they'll be more easily able to integrate into existing transportation infrastructure.

"Our goal is to change the transportation infrastructure," said Maarten Sierhuis, former NASA scientist and director of the Nissan Research Center. "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."

Ghosn also said Nissan plans to launch a new version of the Leaf which will feature ProPILOT technology, enabling autonomous driving for single-lane driving on a motorway. Nissan will also bring Cortana, Microsoft's virtual assistant to its vehicles. 

Check out all the latest from CES 2017

ABOUT THE AUTHOR

Dan is the Editor or T3.com and covers the latest in computing, home entertainment and mobile tech. He's the former Deputy Editor of TechRadar and former Editor of Lifehacker UK. Dan has written for numerous computing and lifestyle magazines and has also written a book, too. You'll see him pop up in numerous places, having been quoted in or on The Sun, BBC World Service, BBC News Online, ITN News, BBC Radio 5Live, BBC Radio 4 and Sky News Radio.