SKYNET coming? Self-driving cars will now learn from experiences to tackle unknown circumstances!

To develop a more flexible, responsive control system, the researchers built a neural network -- a type of artificially intelligent computing system -- that integrates data from past driving experiences.

By: | Published: March 28, 2019 1:03 PM
self driving cars stanford Shelley, Stanford’s autonomous Audi TTS, at Thunderhill Raceway Park (Photo: Stanford News)

Autonomous cars will now get smarter and learn from their previous experiences to perform more safely in extreme and unknown circumstances, thanks to new research conducted by Stanford scientists. The research involved testing the new tech on two self-driving cars - Niki and Shelley - which drove around a racetrack. The researchers say that the new system performed as well as existing autonomous control systems and an experienced racecar driver. Nathan Spielberg, a graduate student at Stanford University in the US, said that the prime motivation for this new tech comes from making autonomous cars safer.

"Our work is motivated by safety, and we want autonomous vehicles to work in many scenarios, from normal driving on high-friction asphalt to fast, low-friction driving in ice and snow," Spielberg said, adding: "We want our algorithms to be as good as the best-skilled drivers -- and, hopefully, better."

While current autonomous cars might rely on in-the-moment evaluations of their environment, the control system these researchers designed incorporates data from recent maneuvers and past driving experiences -- including trips Niki took around an icy test track near the Arctic Circle.

Its ability to learn from the past could prove particularly powerful, given the abundance of autonomous car data researchers are producing in the process of developing these vehicles. Control systems for autonomous cars need access to information about the available road-tire friction. This information dictates the limits of how hard the car can brake, accelerate and steer in order to stay on the road in critical emergency scenarios.

If engineers want to safely push an autonomous car to its limits, such as having it plan an emergency maneuver on the ice, they have to provide it with details, like the road-tire friction, in advance. This is difficult in the real world where friction is variable and often is difficult to predict.

To develop a more flexible, responsive control system, the researchers built a neural network -- a type of artificially intelligent computing system -- that integrates data from past driving experiences and a winter test facility with foundational knowledge provided by 200,000 physics-based trajectories.

"With the techniques available today, you often have to choose between data-driven methods and approaches grounded in fundamental physics," said J Christian Gerdes, a professor at Stanford.

"We think the path forward is to blend these approaches in order to harness their individual strengths. Physics can provide insight into structuring and validating neural network models that, in turn, can leverage massive amounts of data," said Gerdes.

Gallery: Meet Robocar, a self-driving race car that could give Lewis Hamilton a run for his money

The group ran comparison tests for their new system. Shelley sped around controlled by the physics-based autonomous system, pre-loaded with set information about the course and conditions. When compared on the same course during 10 consecutive trials, Shelley and a skilled amateur driver generated comparable lap times.

Researchers loaded Niki with their new neural network system. The car performed similarly running both the learned and physics-based systems, even though the neural network lacked explicit information about road friction.

In simulated tests, the neural network system outperformed the physics-based system in both high-friction and low-friction scenarios. It did particularly well in scenarios that mixed those two conditions.

The results were encouraging, but the researchers stress that their neural network system does not perform well in conditions outside the ones it has experienced. They say as autonomous cars generate additional data to train their network, the cars should be able to handle a wider range of conditions

Do you know What is Automated Manual Transmission (AMT), Electronic Brakeforce Distribution (EBD), Anti-Lock Braking System, Power Steering? FE Knowledge Desk explains each of these and more in detail at Financial Express Explained. Also get Live BSE/NSE Stock Prices, latest NAV of Mutual Funds, Best equity funds, Top Gainers, Top Losers on Financial Express. Don’t forget to try our free Income Tax Calculator tool.

Get the latest cars price and upcoming bikes price in India exclusively at Financial Express. Stay tuned for new cars and bikes reviews, follow us on twitter, Facebook and subscribe us on YouTube for latest auto news.

Next Stories
1GoZero Mobility launches e-bikes: 60 km range at Rs 32,999
2Citroen India launch on 3rd April: C5 Aircross could be French carmaker’s first car for India
3EXCLUSIVE: Massive Rs 75,000 discount on Mahindra Mojo: About to go extinct?