Do you know that in countries like the United Kingdom, the cost of insurance is really high? Sometimes due to various reasons, the insurance cost rises up so much that it becomes better for owners to scrap their old cars and buy a new one. So what does this have to do with IoT? Well to understand that we should figure out how the insurance premiums are calculated in those countries.
The insurance premiums are actually calculated based on a lot of parameters like vehicle value, how safe is it to drive, age of the driver, location where the vehicle will be parked, etc.,
To give an example, a rear-wheel drive, 400 bhp sports car driven by a youngster and being parked in open parking by the side of the road will fetch a heft insurance premium. Why? Because the insurance companies argue that
- Rear wheel drive is inherently unsafe than FWD or AWD
- 400 bhp is too much and will lead to accidents
- Youngsters are more prone to drive rashly and hence have a higher chance of accidents
- Parking on the side of the road will probably lead the car being stolen or broken into
But then is this the right way of calculating if a driver is safe on the roads? Arent the insurance companies stereotyping based on vehicle make/driver age etc? To put an end to this insurance companies came up with the concept of “Usage-Based Insurance”
UBI – Usage-Based Insurance works by plugging an OBD dongle in the customer vehicles. The OBD dongle is a micro-controller-based device that lets the device read the diagnostics data from the vehicle’s ECU. This data includes information like vehicle speed, gear, engine rpm, throttle position, etc., The dongle also has a built in GPS and accelerometer which measure how the vehicle is being driven – smooth vs sudden acceleration, etc.,
All of this data is bundled and transmitted back to the central servers where a machine learning algorithm builds a user profile for the driver based on their driving pattern. Consider the following profiles
- Engine RPM always below 3000 rpm, vehicle speed never exceeds 80 kmph, accelerometer data is very smooth
- Engine RPMs go up to 7000 rpm, vehicle speed frequently exceeds 140 kmph, acceleration data is sudden ad abrupt
We could possibly classify the first driver as SAFE ad the second driver as RISKY and there could be a whole lot more profiles in between these two. Under the UBI scheme, the machine learning algorithm classifies drivers based on their driving pattern and assigns them a score out of 100. Based o how safe the driver is deemed to be based on his driving patterns, the insurance companies assign discounts to safe drivers as they are less prone to accidents.
This is one of the biggest applications of IoT in the automotive sector right now, but this is by no means the only application. We have just started scratching the surface as far as IoT applications in the automotive sector go and numerous other applications ranging from diagnostics, prognostics, real-time demand calculation ( for EV ), scheduling, etc., are possible when IoT becomes widely used in all automobiles.