Driving license tests just got smarter in India with Microsoft’s AI project

An American giant may have figured out a way to simplify the tedious procedure of issuing driver’s licenses. And an early sneak peek of this solution is now live in parts of India.

Hundreds of people who have taken the driver’s license test in Dehradun, the capital of Indian state Uttarakhand near the Himalayan foothills, in recent weeks haven’t had to sit next to an instructor.

Instead, their cars were affixed with a smartphone that was running HAMS, an AI project developed by Microsoft Research team. HAMS uses a smartphone’s front and rear cameras and other sensors to monitor the driver (their gaze), and the road ahead of them. Microsoft Research team said for driver tests, they customized HAMS to enable precise tracking of a vehicle’s trajectory during test manoeuvres such as parallel parking or negotiating a roundabout.

This AI technology can determine whether the driver performed any action — such as stopping in the middle of a test or course correcting by rolling forward or backward more times than they were allowed — during the test, the team said. Additionally, it also checks things like whether a driver scanned their mirrors before changing the lane.

Shri Shailesh Bagauli, IAS, Secretary of Government of Uttarakhand, said the deployment of HAMS-based driver license testing at the Dehradun RTO is a “significant step towards the Transport Department’s goal of providing efficient, world-leading services to the citizens of Uttarakhand. We are proud to be among the pioneers of the application of AI to enhance road safety.”

HAMS, short for Harnessing AutoMobiles for Safety, was originally developed to monitor drivers and their driving to improve road safety. “Driver training and testing are foundational to this goal, and so the project naturally veered in the direction of helping evaluate drivers during their driving test,” the team said.

Automation is slowly making its way to driver testing across the world, but they still require deployment of extensive infrastructure such as pole-mounted video cameras along the test track. Microsoft’s team said HAMS can bring down the cost of automation while improving test coverage by including a view within the vehicle.

Some surveys (PDF) have shown that a significant number of applicants don’t even show up to give a test to obtain their license because of the “burden” they would have to go through. “Automation using HAMS technology can not only help relieve evaluators of the burden but also make the process objective and transparent for candidates,” says Venkat Padmanabhan, Deputy Managing Director, Microsoft Research India, who started the HAMS project in 2016.

The test venue of this project should not come as a surprise. American technology companies are increasingly expanding their presence in India, one of the last great growth markets with several unique local challenges.

Microsoft, Google, and Amazon have used India a a test bed to build solutions for the local market, some of which eventually make it to other countries. Microsoft has previously developed tools to help farmers in India increase their crop yields and worked with hospitals to prevent avoidable blindness. Last year, the company partnered with Apollo Hospitalls to create an AI-powered API customized to predict risk of heart diseases in India.

Last year, the company also worked with cricket legend Anil Kumble to develop a tracking device that helps youngsters analyze their batting performance. Microsoft has also tied up with insurance firm ICICI Lombard to help it process customers’ repair claims and renew lapsed policies using an AI system.

Google has also developed a range of services and tools for India. The company last year launched a tool to help publishers easily bring stories written in local languages to the web. This year, the Android-maker unveiled improvements it has made to its flood prediction tool. And of course, several popular apps such as YouTube Go, and Google Station started as India-only services.



from TechCrunch https://ift.tt/2N1R0dz
via gqrds