Nissan joins forces with NASA for autonomous cars

Robots from Mars are helping to solve the traffic challenges of the future.

As autonomous cars get closer to reality, Nissan has partnered with NASA on how to control the vehicles and solve the challenges of integrating artificial intelligence into the real world.

The objective is to allow self-driving cars to make decisions when traffic conditions get chaotic, or unpredictable, or outside the vehicle’s original programming.

Dr Maarten Sierhuis, now the chief technology director at the Nissan Research Centre in Silicon Valley, served 13 years with NASA and is tapping into the remote-control and AI work for the Mars Rovers, Spirit and Opportunity.

But he still says there will be people involved, because of unexpected situations - like roadworks and the need to break road rules - which cannot be pre-programmed.

“This little human interaction … is very difficult for an autonomous system,” he says, speaking at a Nissan Futures gathering in Hong Kong.

Sierhuis talks of a ‘Human in the Loop’ system where self-driving cars can be remotely re-routed or re-programmed for unexpected situations, before their onboard AI updates the core programming so it can adjust automatically if it re-encounters a similar situation.

“Robo-services like self-driving taxis will be the first to turn up. In the next five years. We can have a ‘geo fence', which is easier than having a system that can drive anywhere,” Sierhuis says.

But he still sees an essential need for people in an autonomous world.

“Show me an autonomous system without a human in the loop and I’ll show you a useless system. I’m convinced that is not just for autonomous vehicles, but any autonomous system,” he says.

“We are moving from individual autonomous systems . . . to a system where there is this holistic autonomous system with intelligence on the vehicle, intelligence in the Cloud, and human intelligence working together.

Demonstrating his ideas in action, he forecasts casts that have core programming for basic travel, a human ‘mobility manager’ in a direct link with up to 20 vehicles, and then onboard AI.

“There is still something like 10 per cent of the time where we have an issue where you might need an intervention by a mobility manger.”

Sierhuis says the robocar world is similar to the challenges of guiding the Mars rovers, which had to operate autonomously because of the time delay in communications from Earth, but would receive regular updates from NASA headquarters.

“It was at NASA … that I created much of what I’m putting to work for Nissan today,” he says.

“We started with a simulation language that allowed us to model human behaviour and multiple working together. We were looking at how people might live on Mars and work with people back on Earth, as well as autonomous systems, including robots and smart habitats on Mars.”

“To build the autonomous system for a vehicle on Earth is really like building a robot that drives 80 miles-an-hour very close to other robots. Many issues come up when you think about humans interacting with each other and with robots, because the car needs to be on the road with other people - pedestrians, bicyclists and other cars.”

Nissan's autonomous plans have been most recently promoted with the unveiling of the IMS concept at this year's Detroit motor show.