IEEE Compute | The Blog


Official Blog of IEEE Compute


Autonomous Cars

.

I remember the time when I used to read the Batman Comics, with my mouth gaping open in awe at the stunts Batman pulled off with his Batmobile. How at the press of a button, the car would leave his home on its own and reach his location never failed to fascinate me. Like me, I’m sure many others must have fantasized seeing driverless cars on roads. These dreams might have seemed too good to be true as it was always overshadowed by skepticism about its feasibility in our lifetime. Thanks to Google, our doubts can now be dismissed without a second thought.

800px Hands free Driving.jpg

An autonomous car is a vehicle that is capable of sensing its environment and navigation without human input. Autonomous cars can detect surroundings using a variety of techniques such as radar, LIDAR, GPS, odometry, and computer vision. Advanced control systems interpret sensory information to identify appropriate navigation paths, as well as obstacles and relevant signage. Autonomous cars are operated via control systems that are capable of analyzing sensory data to distinguish between different cars on the road, which is very useful in route planning to a desired destination. Some of the advantages of introducing driverless cars include fewer fatal accidents, reduced greenhouse gas emissions, lower road infrastructure costs, and the arrival of a convenient and hassle free mode of travel for the blind, disabled and the elderly. Though the concept of autonomous cars has been around for a while, it was only recently in 2011, that some states in the United States passed the legislation to allow the operation of driverless cars, after Google lobbied for robotic car laws. In May 2014, Google announced plans to create a driverless car that had neither a steering wheel nor pedals, and unveiled a fully functioning prototype in December that year, which they planned to test in 2015. The project team at Google has equipped a number of different types of cars with the self-driving equipment, including the Toyota Prius, Audi TT, and Lexus RX450h. Google has also developed their own custom vehicle assembled by Roush Enterprises and uses equipment from Bosch, ZF Lenksysteme, LG, and Continental. Google’s robotic cars have about $150,000 in equipment including a $70,000 LIDAR system. The range finder mounted on the top is a Velodyne 64-beam laser which allows the vehicle to generate a detailed 3D map of its environment. The car then takes these generated maps and combines them with real high-resolution maps of the world, producing different types of data models that allow it to drive itself. As of June 2014, the system works with a very high definition inch-precision map of the area the vehicle is expected to use, including how high the traffic lights are. In addition to the on-board systems, some computations are performed on remote computer farms as well. While testing their autonomous vehicles on public roads, Google always has test drivers ready to take over if the car is not driving itself safely or smoothly enough. In August 2016, their cars traveled a "total of 170,000 miles of which 126,000 miles was driven autonomously (i.e. the car was fully in control)." As of June 2016, Google had test driven their fleet of vehicles, in autonomous mode, a total of 1,725,911 miles (2,777,585 km). There are, however, quite a few limitations to this idea. According to “Computer World” ,Google’s self-driving cars were in fact unable to use about 99% of US roads. As of the same date, the latest prototype had not been tested in heavy rain or snow due to safety concerns. As the cars rely primarily on pre-programmed route data, they do not obey temporary traffic lights and, in some situations, revert to a slower "extra cautious" mode in complex unmapped intersections. The vehicle faces difficulty identifying when objects, such as trash and light debris, are harmless, causing the vehicle to veer unnecessarily, leading to reduced fuel efficiency and time wastage. Additionally, the LIDAR technology cannot spot some potholes or discern when humans, such as a police officer, signaling the car to stop. To ensure safety of passengers and pedestrians, the Californian DMV suggested imposing strict regulations on the use of such vehicles stating that there must be a steering wheel and pedals on each car and a minimum of one occupant in each car while in transit. Also, the occupant would be held responsible in a situation where there are damages, irrespective of whether they were at the wheel or not. Google however, projects to overcome these shortcomings and come out with a commercially viable product by 2020 which will be made available to the general public. So it won’t be much longer until you see driverless taxis, buses and private vehicles transporting goods and products on the roads near you. The vehicles of the future are here.

comments powered by Disqus