Self-driving cars can easily mimic human drivers

  • The processing system is specifically a convolutional neural network, which is mirrored on the brain's visual cortex.
FILE PHOTO: A self-driving vehicle, based on Nissan Leaf electric vehicle (EV), for Easy Ride service. (REUTERS)
FILE PHOTO: A self-driving vehicle, based on Nissan Leaf electric vehicle (EV), for Easy Ride service.

With the help of an improved sight-correcting system, self-driving cars could learn just by observing human operators complete the same task, researchers have found.

The team implemented imitation learning, also called learning from demonstration.

In this, a human operator drives a vehicle outfitted with three cameras, observing the environment from the front and each side of the car.

Also check these Cars

Find more Cars
Hyundai Kona Electric 2024 (HT Auto photo)
UPCOMING
BatteryCapacity Icon64.8 kWh Range Icon418 Km
₹ 25 Lakhs
Alert Me When Launched
Hyundai Kona Electric (HT Auto photo)
BatteryCapacity Icon39.2 kWh Range Icon452 km
₹ 23.79 Lakhs
Compare
View Offers
Mg Zs Ev (HT Auto photo)
BatteryCapacity Icon50.3 kWh Range Icon419 Km
₹ 21 Lakhs
Compare
View Offers
Mg Erx5 (HT Auto photo)
UPCOMING
BatteryCapacity Icon48.3 kWh Range Icon425 Km
₹ 25 Lakhs
Alert Me When Launched
Hyundai Creta (HT Auto photo)
Engine Icon1497 cc FuelType IconMultiple
₹ 11 Lakhs
Compare
View Offers
Mahindra Thar (HT Auto photo)
Engine Icon2184 cc FuelType IconMultiple
₹ 11.25 Lakhs
Compare
View Offers

The data is then processed through a neural network -- a computer system based on how the brain's neurons interact to process information -- that allows the vehicles to make decisions based on what it learned from watching the human make similar decisions.

"Having a reliable and robust vision is a mandatory requirement in autonomous vehicles, and convolutional neural networks are one of the most successful deep neural networks for image processing applications," explained Saeid Nahavandi, Chair of engineering and director for the Institute for Intelligent Systems Research and Innovation at Deakin University.

The processing system is specifically a convolutional neural network, which is mirrored on the brain's visual cortex.

By reducing the visual information, the network can quickly process changes in the environment: a shift of dots appearing ahead could indicate an obstacle in the road.

This, combined with the knowledge gained from observing the human operator, means that the algorithm knows that a sudden obstacle in the road should trigger the vehicle to fully stop to avoid an accident.

"The expectation of this process is to generate a model solely from the images taken by the cameras. The generated model is then expected to drive the car autonomously," said Nahavandi in a paper published in the journal IEEE/CAA Journal of Automatica Sinica.

He noted a couple of drawbacks, however.

One is that imitation learning speeds up the training process while reducing the amount of training data required to produce a good model.

"The researchers plan to study more intelligent and efficient techniques, including genetic and evolutionary algorithms to obtain the optimum set of parameters to better produce a self-learning, self-driving vehicle," said the study.

First Published Date: 09 Mar 2020, 08:59 AM IST
NEXT ARTICLE BEGINS

Check Latest Offers

Please provide your details to get Personalized Offers

Choose city
+91 | Choose city
Choose city
Select a dealer

Want to get the best price for your existing car?

Powered by: Spinny Logo
By clicking "View Offers" you Agree to our Terms and Privacy Policy
Dear Name

Please verify your mobile number.

+91 | Choose city
Couldn't verify the OTP.
It's either expired or it's incorrect.