KSRTC likely to mount AI system in 1044 buses to avoid collisions

CIOReviewIndia Team | Wednesday, 09 June 2021, 06:21 IST

KSRTC likely to mount AI system in 1044 buses to avoid collisionsIn an attempt to reduce accidents and increase the safety of passengers and bus crew, the Karnataka State Road Transport Corporation (KSRTC) is planning to use Artificial Intelligence(AI)-based technology.

The corporation had recently floated a tender for the implementation of AI-powered Collision Warning System (CWS) and Driver Drowsiness System (DDS) in 1,044 buses.

CWS will offer features like Forward Looking Collision Warning (FLCW), Lane Departure Warning (LDW) and Virtual Bumper and also provide alerts. The tender is likely to be finalised by the end of this month.

This is perhaps for the first time in the country a state-run bus corporation is using technology on a large-scale to reduce accidents. Sources said other state-run bus corporations are also waiting to adopt this system.

Of the 1,044 buses, 400 are non-AC night-service ones and the remaining are premium AC services. KSRTC officials said the FLCW system will identify an impending collision and inform the driver that he has entered the unsafe distance zone.

“This helps the driver prepare to take necessary action to avoid collision. The system will provide real-time alerts to warn the driver against impending collisions. AI-based camera sensors will provide detection of the vehicle for sufficient range of at least 150m at any speed, for vehicle detection, so that it can effectively warn the driver,” an official said.

It will provide an alert (when the minimum safe distance is not maintained) based on a calculation of the Time-To-Collision (TTC) with the vehicle ahead (including 2/3 wheelers, pedestrians and cyclists).

“The alarm will be initiated at a TTC of up to 2.5-3 seconds. It will also be operational at a vehicle speed range of up to at least 120kmph. It will provide both visual and audible alarm,” said a KSRTC official.

The system will provide audible and visual alert when the vehicle unintentionally departs from the driving lane. It will also notify the driver when lane marks are not available. VB provides an alert before a possible collision with the vehicle in front in extremely low speed situations, for example, traffic lights, jams and parking scenarios.

“The VB distance sensitivity level is to be adjustable from 1m to 4m and also when the vehicle speed is lower than 5kmph,” he said. DDS will check its drivers from dozing off at the wheel. It will monitor the driver’s eye movements and sound a warning alarm in case he appears sleepy.

“There have been several instances of drivers tending to ignore drowsiness and causing accidents. AI-based tech will keep watching the facial behaviour of the driver. It will also give an alert to the KSRTC central control room if the alert to the driver is ignored. This will be helpful for night services,” said an official.