Microsoft Research AI Project helps Dehradun RTO in automating driver's license testing

Do you know a whopping 59% of respondents to survey conducted by SaveLIFE Foundation admitted that they did not give any test to obtain a driving license. The numbers seems to be correct, given I have personally seen people around me claiming the same.The challenges with this system range from the subjectivity of each evaluator to the burden of evaluation falling solely on human shoulders. A Microsoft Research team under HAMS (Harnessing AutoMobiles for Safety) project is currently enabling the Regional Transport Office (RTO), Dehradun, Uttarakhand to automate the same process.

“The main challenge in the traditional driver’s license test is the burden placed on the human evaluators and the resulting subjectivity that a candidate faces. 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. Padmanabhan developed HAMS along with Akshay Nambi, who joined the project as an intern and is now a Senior Researcher at Microsoft Research India, and Satish Sangameswaran, Principal Program Manager, Microsoft Research India, who helped the team bring HAMS out of the research lab and into the real world through external partnerships.

Microsoft Research’s HAMS project enables the driver’s license testing to be an objective and transparent process that helps grant licenses to well-tested drivers. The system doesn't require an invigilator to be present with the candidate in the car. The system is competent enough to get the final results on the basis of the driver's actions and conditions of the environment just in time. While it may sound like a very IoT kind of project where lot of sensors needs to be at work, the team at Microsoft has utilized a simple smartphone to achieve the goal.

HAMS in essence uses a mounted smartphone on car's windshield which uses rear camera to monitor real time road condition  as well as the driver's gaze using front camera of the phone. On top of it, the team has developed AI models for efficient and robust operation.

For driving tests, HAMS has been customized to include capabilities such as precise tracking of the vehicle’s trajectory during designated test manoeuvres, for instance, parallel parking or negotiating a roundabout. This tracking enables HAMS to determine precisely, for instance, whether the driver stopped in the middle of a manoeuvre for longer than is permitted or tried to course correct by rolling forward and backward alternately more times than allowed. Today, if you take the driver’s license test at the Dehradun RTO, you will be doing so in just the company of a smartphone affixed to your car’s windshield. HAMS, running on the smartphone and on an edge server onsite at the testing track, will do the rest and produce a detailed report shortly after you finish navigating through the test manoeuvres.

“The successful deployment of the 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,” said Shri Shailesh Bagauli, IAS, Secretary, Government of Uttarakhand. “On an average, over 50 candidates take the HAMS-enabled automated license test every day at the Dehradun RTO. Due to the comprehensive nature of testing, just about 50 percent candidates pass the test, ensuring that only qualified drivers are given a driver’s license,” says Nambi.