Testing The Autonomous Vehicle
The impetus toward autonomous driving has endless possibilities…and even more possible potholes. Evaluating the scenarios of everyday driving and trying to program an autonomous response to any one of them—or many of them simultaneously—is the work needed before autonomous driving actually hits the road.
Recently, NI acquired monoDrive, a leader in advanced high-fidelity simulation software for advanced driver-assistance systems (ADAS) and autonomous vehicle development. NI will leverage monoDrive’s signal processing and advanced simulation tech to create high-fidelity driving environments, modeling multiple sensors in thousands of real-time scenarios.
It's a challenge, notes Noah Redding, senior director, Solutions and Offering Management at NI. “You can only recreate a subset of real-world scenarios. Inside this test track, I’m going to do these 100 scenarios, when in reality, when the car is on the road, you’re going to have millions of different situations that it could come across,” said Redding in a new Machine Design article.
“You could be really good in those 100 scenarios, but for the other 999,000, how do you get confidence in those? That’s where we’re going to go out and drive on the road, we’re going to record a bunch of data, and then re-create some scenarios virtually...It’s that type of balance of simulation versus real, and utilization of assets that companies are going through right now.”
Identifying Autonomous Driving Benefits
So where are the benefits of autonomous driving? While the quest for a safe system is a significant factor in its testing, autonomous driving also promises safer roadways by vehicles being aware of traffic and road conditions.
A Machine Design article discusses other benefits, including better traffic management; faster, smoother commutes; and better management of insurance and repair costs for consumers. But while there are many driver-assist sensors in modern cars today, such as lane departure and automatic braking, a fully autonomous fleet of cars is still a long way off.