autonomous cars are inevitable in the automotive industry. Most carmakers say they are able to launch autonomous cars in 2020, Tesla, confident that the company can do it earlier, in 2018. So, what exactly is the autonomous car and what makes it so special?
autonomous cars are divided in five types:
Level 0 :. This is the type of cars that are bought before 2011 that pilots must be in complete control at all times
Level 1: This is the type of car that functions such as controller speed, automatic braking and holding the path can be done automatically, however, the functions work by itself. The drivers are always in complete control, which means that his hands and feet still need to be on the steering wheel and pedals all the time. Level 1 cars can be found in most cars on the road today
Level 2 :. This is the type of cars that some functions are already able to work together. Drivers are allowed to keep their hands and feet on the steering wheel and pedals. However, drivers must always be alert all the time. Tesla Autopilot is classified in this level of self driving cars
Level 3 :. This is the type of cars that most functions are enough for cars to be able to lead automatically. Volvo Intellisafe Autopilot belongs at this level of self driving cars
Level 4 :. This is the type of cars that all functions of the car are sufficient to operate the cars. Drivers should not be alert all the time. In addition, this design is suitable for occupied and unoccupied vehicles. cars Tesla and Google cars to reach that level.
There are certainly challenges that automakers and technology companies face in that autonomous cars to be able to launch and use on public roads. One of the challenges is in the legal obstacles and insurance regulation. Last December, Department of Motor Vehicles in California issued a draft regulation that require drivers to sit behind the steering wheels and also require that the vehicle be equipped with steering wheels and pedals too. Google, on the other hand, plans to design auto Car driving without a steering wheel that aligned with authority.
The insurance is also becoming a challenge for self driving cars. For example, if the autonomous car led to a blocked road on a one way street and the only way out is by u-turn and unfortunately it causes accidents. Therefore, who is responsible, the owner or the car manufacturer? Therefore, unless these challenges were resolved, while autonomous cars are not ready to take to the streets.
Another challenge is more on technical challenge of how to make autonomous cars to be able to handle all kinds of scenarios without interference from the human pilot. One way is by equipping autonomous cars with advanced technology such as deep learning and advanced equipment such as sensors or cameras for them to be able to do things they are designed to do.
deep learning is an algorithm in which the system is able to learn and manage new scenarios that never met before in the testing phase . Therefore, on the basis of data collected from sensors and cameras, the system is able to find models, predicts the next thing that will happen and find the best way to handle the scenario. Everything is done without interference of human operator.
To develop a learning algorithm in depth, the major automakers are working together with another technology company, Mobileye. The company has developed smart cameras that are able to detect the area, calculated the possibilities of a collision and stop occur. Mobileye has worked with Hyundai and Tesla among other automakers to develop assistant systems of the advanced driver-related vision.
learning algorithm in depth requires enormous processing power that normally known as supercomputers. These supercomputers are no longer as large bulky machines. They are more likely that the construction of an electronic chip. Nvidia is one company that has experience in their development.
Therefore supercomputers should be able to collect large data collected from cameras, sensors or lidar systems, analyze data in real time and make decisions based on it. All must be done in the shortest time possible. The input can be as large as multi-terabyte size. He should be able to handle the input jack when the car rolls on a six-lane highway with thousands of cars that travel around it and at different speeds. He should be able to handle thousands of objects on the roads.
Hopefully the authorities and automakers find way to solve the problems so that we can experience the advantage of having auto car driving on our roads.
0 Komentar