Seamless Autonomous Mobility: The ultimate Nissan Intelligent Integration
Advances in artificial intelligence are making vehicles smarter, more responsive, and better at making decisions in a variety of driving environments. But we are still not at a point where we can trust our vehicles to make all the right choices, or know exactly what to do in unpredictable situations. This is one of the roadblocks to realizing a fully autonomous future for driving.
Developed from NASA technology, Nissan’s “Seamless Autonomous Mobility,” or SAM, will ensure a seamless mobility system in which millions of autonomous cars can be on the roads together without problems. SAM provides a secure means of navigating unforeseen situations that occur on city streets, such as accidents, obstacles in the road, or other environments that an autonomous vehicle may not immediately recognize.
Here’s how it works: imagine an autonomous vehicle is moving through city streets and comes across an accident, with police using hand signals to direct traffic, possibly across double yellow lines and against traffic lights. The vehicle cannot, should not, reliably judge what to do by itself.
Vehicle sensors (lidar, cameras, radars) can tell it where obstacles are, the traffic light state and maybe even recognize some hand gestures, human judgment is required to understand what other road users are doing and decide on the appropriate course of action.
With SAM, the autonomous vehicles is smart enough to know when it should not attempt to negotiate the problem by itself, as in this instance. It brings itself to a safe stop and requests help from the command center. The request is routed to the first available mobility manager, who uses vehicle images and sensor data (streamed over the wireless network) to assess the situation and decide on the correct action – in this case to take an off nominal path around the obstruction when signaled by the policemen (and ignoring the traffic lights). The mobility manager does this by “painting” a virtual lane for the vehicle to drive itself through. When she/he sees the policemen wave the vehicle past, she/he releases it to continue on by itself along the designated route. Once clear of the area the vehicle resumes fully autonomous operations and the mobility manager is free to assist other vehicles calling for assistance.
When a supervised vehicle encounters a problem, the location and solution stored in cloud and distributed to the entire fleet, so that other autonomous vehicles can either re-route around the problem, or require less assistance if they decide to drive through it.
At the current time, one trained mobility manager can safely supervise at least 10 vehicles. As the system learns from experience, and autonomous technology improves, vehicles will require less assistance and each mobility manager can assist a greater number of vehicles at once. There are several factors that will determine how many managers are necessary: for example, how busy the zone is, and what service the vehicle is providing, whether it’s for robo-taxis, robo-shuttle, or a robo-delivery vehicle.
NASA VERVE software, used to visualize and supervise these robots, was the starting point for Nissan’s SAM platform. NASA’s robots use autonomous technology to avoid obstacles and calculate safe driving paths through unpredictable and uncertain environments. Where the environment makes autonomous decision-making difficult, NASA supervisors draw the desired route and send to the robot for execution.
“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,” said Eugene Tu, Center Director, NASA Ames Research Center.
Back on Earth, SAM is not for just Nissan vehicles, but for all vehicles. "Our goal is to change the transportation infrastructure," said Liam Pedersen, leader for autonomous vehicles at Nissan Silicon Valley (and former NASA scientist). "We want to reduce fatalities, we want to ease congestion. We need 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."
The backbone of SAM is human/machine teaming. The goal is not to remove the human from the system, but rather to use the human intelligence more strategically to support a larger system of autonomous mobility – and to help improve the artificial intelligence of the vehicles in real-time.
"Show me an autonomous system without humans in the loop and I will show you a useless system," said Maarten Sierhuis, former NASA engineer and director of the Nissan Ames Research Center in Silicon Valley. “Vehicles will have to interact with other human beings and to do that well, and to do that in any situation flawlessly, we believe that a system like SAM will create this seamless integration into human society."
SAM makes it possible for our society to reap the benefits of the mass introduction of autonomous vehicles. In any single day, autonomous vehicles will encounter thousands of situations that should not be resolved autonomously. Without SAM, these vehicles will be stranded, causing traffic congestion, creating a public nuisance and failing to reach their destinations. SAM permits autonomous vehicles to seamless integrate into our existing transportation infrastructure and society.
But it’s more than a luxury – SAM is a necessary component of any system with autonomous vehicles. Without a technology like SAM, the full integration of autonomous vehicles into society will be difficult.
SAM will also benefit companies that wish to deploy fleets of commercial autonomous vehicles, including delivery companies, taxi services and transportation systems.
