Tuesday July 16, 2019
Home Lead Story Indian Origin...

Indian Origin Team Develops Model For Safer Self-driving Cars

"When the system is deployed into the real world, it can use learned model to act more cautiously and intelligently," said Ramakrishnan

0
//
Uber began testing self-driving cars in Pittsburgh and is now rolling out the service in San Francisco. (Uber), VOA

A team of Indian American researchers has developed a novel model that uses human inputs to uncover Artificial Intelligence (AI) “blind spots” in self-driving cars, so that the vehicles can avoid dangerous errors in the real world.

The model developed by MIT and Microsoft researchers identifies instances in which autonomous systems have “learned” from training examples that don’t match what’s actually happening in the real world.

Engineers could use this model to improve the safety of AI systems, such as driverless vehicles and autonomous robots.

“The model helps autonomous systems better know what they don’t know,” said first author Ramya Ramakrishnan from Computer Science and Artificial Intelligence Laboratory at MIT.

“Many times, when these systems are deployed, their trained simulations don’t match the real-world setting [and] they could make mistakes, such as getting into accidents.

“The idea is to use humans to bridge that gap between simulation and the real world, in a safe way, so we can reduce some of those errors,” explained Ramakrishnan.

Waymo, driverless cars
Waymo has been giving rides to a group of volunteer passengers in Arizona in driverless cars since last year. Flickr

The AI systems powering driverless cars are trained extensively in virtual simulations to prepare the vehicle for nearly every event on the road.

But sometimes the car makes an unexpected error in the real world because an event occurs that should, but doesn’t, alter the car’s behaviour.

The researchers validated their method using video games, with a simulated human correcting the learned path of an on-screen character.

The next step is to incorporate the model with traditional training and testing approaches for autonomous cars and robots with human feedback.

Also Read- Facebook Restricts External Campaigners From Accessing Political Ads

Co-authors on the papers are Julie Shah, an associate professor in the Department of Aeronautics and Astronautics and head of the CSAIL’s Interactive Robotics Group; and Ece Kamar, Debadeepta Dey, and Eric Horvitz — all from Microsoft Research.

“When the system is deployed into the real world, it can use learned model to act more cautiously and intelligently,” said Ramakrishnan. (IANS)

Next Story

Self-driving Cars Can be a Potential Game-changer for Older Adults: Researchers

It was also found that older drivers tended to exhibit worse takeover quality in terms of operating the steering wheel, the accelerator and the brake, increasing the risk of an accident, Li added

0
Google's self-driving car. Flickr

Self-driving cars can be a potential game-changer for older adults aged above 60 and can help in minimizing the risk of accidents, say, researchers.

“There are several levels of automation, ranging from zero where the driver has complete control, through to level five where the car is in charge… this will allow the driver to be completely disengaged, they can sit back and watch a film, eat, even talk on the phone,” said Shuo Li from the Newcastle University in the UK.

“But, unlike level four or five, there are still some situations where the car would ask the driver to take back control and at that point, they need to be back in driving mode within a few seconds,” Li said.

For the study published in the journal Transportation Research, the researchers examined 76 volunteers, divided into two age groups (20-35 and 60-81), and studied the time it takes for older drivers to take back control of an automated car in different scenarios and also the quality of their driving in these different situations.

They experienced automated driving for a short period and were then asked to take back control of a highly automated car and avoid a stationary vehicle.

Uber, bengaluru
Toyota Motor Corp. recently invested $500 million in working with Uber on self-driving technology for the ride-hailing service.

It was found that in clear conditions, the quality of driving was good but the reaction time of older volunteers was significantly slower than the younger drivers. It took older drivers about 8.3 seconds to negotiate obstacles compared to around 7 seconds for the younger age group.

“At 60mph, that means older drivers would have needed an extra 35m warning distance – that’s equivalent to the length of 10 cars,” said Li.

Also Read: Ease in Local Sourcing Norms Big Boost for Firms Like Apple

It was also found that older drivers tended to exhibit worse takeover quality in terms of operating the steering wheel, the accelerator and the brake, increasing the risk of an accident, Li added.

The researchers concluded that fully automated cars which are unlikely to require a license and could negotiate bad weather and unfamiliar cities under all situations without input from the driver can be a potential game-changer for older adults and help in avoiding accidents. (IANS)