How Self Driving Cars aren't as Bad as You Think

 

Autonomous vehicle (AV) is mostly referred to as a self driving vehicle or driver-less vehicle. Self-driving Vehicle senses the environment and drives safely with a little or no human input. Long distance vehicles like transport trucks are the main focus for making autonomous vehicles.

The first trial on automated vehicles began in the 1950s.  The first semi-automated car was developed in 1977 by Japan’s Tsukuba Mechanical Engineering Laboratory which ran upto the speed of 30km per hour on a track. This was the first big step towards autonomous vehicles. Since then, many companies have started working on automated vehicles. In 2018, Waymo commercialized a fully AI taxi service in Phoenix in the United state. National transportation safety board chairman said that no autonomous cars were available to consumers in the US till 2020.

Main components for Autonomous vehicle :-

• Computer vision
• Sensor fusion
• Localization
• Path planning
• Control

Let me elaborate :-

1) Computer vision:-

Like humans, computers(Artificial intelligence) also need vision to operate vehicles and to understand the outside environment to perform required action. It identifies the object near the car and takes the programmed action required at that time. This is done by a network known as convolutional neural network.

To read more about this network link is in description.

2) Sensor Fusion :-

The driver is stuck in a lot of traffic. The driver knows this by analyzing the environment. This is equivalent to the idea of sensor fusion: being able to understand the environment in a detailed way. Lots of sensors are equipped on an SDC, we can take all the necessary data and fuse them to provide a richer diagram to our car, thus named sensor fusion.

3) Localization :-

With this component we are able to figure out where our car is  in the real world so that we can make better decisions on how we get from Point A to Point B. But in these situations things get complicated and require complex math algorithms. We can relate, localization is just like the GPS on your phone.

4)Path Planning:-

Now lets understand about path planning. Till now our vehicle is able to identify how it will drive but it doesn’t know where to give that input. Taking an example if a driver wants to go the from point A to point B then if there is human driver he knows a path which he knows in his mind  but computer does not know that path that human knows, what if there is another way to point B and human is driving the path like point A point C and point B. It increases the journey. But then what the computer does is that it eliminates point C and goes from that path which reduces the journey. Using this, the computer saves time and money which is only possible when we have proper path planning.

5) Control

It is the core of the AV as of now we know all the things, how it will locate the vehicle and how to do path planning. Now here we will learn how it will control the wheel. Many companies like Waymo, Tesla, Lyft are trying to make a level 5 vehicle but to steer the wheel like a human is still a big challenge. You must be confused, what a level 5 vehicle is, don’t worry stay with us. It will be covered below.

Component used in AV:-

1) RADAR –

It uses bursts of sound to measure distance by measuring the time it takes for the sound to return to the sensor.

2)LIDAR-

Light Detection and Ranging similar to radar but uses lasers to measure distance instead of sound, with a range of upto 200m.

3)Video Cameras –

It records multiple still shots (frames) to capture a 2 dimensional motion picture.

4)Ultrasonic Range Sensors –

It uses high frequency sound waves to measure distance between objects.

5)Inertial Measuring Unit (IMU) -

IMU is a combination of accelerometers and gyroscopes that determine a vehicle’s linear and angular motion.

6)Global Navigation Satellite System (GNSS) –

It  uses satellites to provide autonomous geo-spatial positioning. Global Positioning System (GPS) is a subset of GNSS.

Level of autonomous vehicle:-

There are 6 levels in autonomous vehicle:

1. Level 0:

At level 0, the car has no control over its operation and the human driver does all of the driving.

2. Level 1:

At level 1, the vehicle’s ADAS (advanced driver assistance system) has the ability to support the driver with either steering or accelerating and braking.

3. Level 2:

At level 2, the ADAS can oversee steering and accelerating and braking in some conditions, although the human driver is required to continue paying complete attention to the driving environment throughout the journey, while also performing the remainder of the necessary tasks.

4. Level 3:

1. At level 3, the ADS (advanced driving system) can perform all parts of the driving task in some conditions, but the human driver is required to be able to regain control when requested to do so by the ADS. In the remaining conditions, the human driver executes the necessary tasks.

5. Level 4:

At level 4, the vehicle’s ADS is able to perform all driving tasks independently in certain conditions in which human attention is not required.

6. Level 5:

At level 5, it involves full automation whereby the vehicle’s ADS is able to perform all tasks in all conditions, and no driving assistance is required from the human driver. This full automation will be enabled by the application of 5G technology. which will allow vehicles to communicate not just with one another, but also with traffic lights, signage and even the roads themselves.

Finally at level 5, we will be able to get autonomous vehicles or driverless vehicles

Advantages of Autonomous vehicle :-

• Decrease the number of accidents.
• Less human death.
• Less number of traffic jam
• Stress free parking
• Accessibility to transportation
• Tension free driving at night.

Disadvantages of Autonomous vehicle :-

• It could be more expensive than a normal vehicle.
• It can be hacked.
• Dysfunction of sensor can cause problems

Future of Autonomous vehicle :-

The future of vehicles tends to be dependent on Autonomous vehicles and is good as many companies are trying to make their own Autonomous vehicle such as Waymo, Tesla and Lyft. Everyone is surely looking forward for this.

~ Thank you for reading this post ~

🙏