Self-Driving Autonomous Cars

Google Self Driving Car

The Ultimate Information Guide to Understand Self-Driving Autonomous Cars

It is estimated that by the year 2030, there will be approximately 380 million semi, highly or fully autonomous vehicles on the roads. These vehicles are no longer a matter of if, rather a matter of when. The founder of Tesla Motors, Elon Musk, claims that within a decade, self-driving autonomous cars will be as common as elevators. Below, we explore what this new technology is, how it works, as well as the pros-and-cons.

What Are Self-Driving Cars?


Self-Driving Autonomous Car Definition

Self driving autonomous cars are vehicles designed to travel between destinations without the need for a human driver to constantly monitor the roadway. To technically qualify as "fully autonomous", a vehicle must be able to navigate without human intervention to a predetermined destination over roads that have not been adapted for its use.


Self-Driving Autonomous Cars Explained

Self driving cars (also called driverless cars, autonomous cars, automated cars, or robotic cars) are vehicles that can maneuver themselves without human interaction. Driverless car technology, such as Google's "Self Driving Autonomous Car Project" are already logging more physical hours of testing on American roads than the typical American driver will do in a year.

Autonomous car technology aims to achieve:

  • The benefits of technology by processing large amounts of data and using it to make intelligent decisions.
  • The human ability to be adapt in known or unknown environments.
Autonomy still implies personal ownership. Looking into the future, some believe that steering wheels will disappear completely and the vehicle will do all the driving using the same system of sensors, radar and GPS mapping that today's driverless cars employ. This will be somthing that is ultimately up to the self-driving car companies currently building the future of this technology.

Google Self-Driving Car Project
Google Self-Driving Project

Self-Driving Car History

Since the dawn of driving, the human imagination has always pushed the barrier of what is possible, including the fascination of cars that can drive themselves. Although the concept of self driving cars may seem new, there have been several publicly documented experiments to automate cars since at least the 1920s.

First driverless car 'American Wonder'

The very first car to publicly demonstrate the ability to drive itself is often credited to the ‘American Wonder’ built by the Houdina Radio Control Co. The car was built by the company’s founder, Francis P Houdina, who was an electrical engineer in the U.S. Army. Houdina equipped a 1925 Chandler Metropolitan Sedan with a transmitting antenna on an openly exposed back area of the car. He then operated the American Wonder from a second car that followed it with a transmitter. The radio signals operated small electric motors that directed every movement of the car. That year he publicly demonstrated this in New York City streets, traveling up Broadway and down Fifth Avenue through thick traffic.

Mercedes-Benz F 015 Autonomous Vehicle

Since then, nearly every subsequent decade led to a major advancement in the push to bring self-driving cars to the masses. Recent developments this century have brought this technology closer than ever before to be within feasible attainment for the general consumer. With both global technology giants (e.g. Google Self-Driving Car Project and Baidu Auto Brain System) and the world’s largest automotive manufacturers (e.g. Mercedes-Benz F 015 and BMW i NEXT Autonomous Vehicle) racing to be first to market with prototype demonstrations and working in conjunction with lawmakers to bring these cars to public roads, it is safe to say that world is only several years away from being able to purchase a truly self driving car.

Levels of Autonomous Vehicle Automation

What does "autonomous driving" really mean? Is there a difference between "autonomous" and "driverless"? Why is “driverless” a more advanced stage of “autonomous”? Questions such as these from both the general public and policy makers has prompted the U.S. Department of Transportation's National Highway Traffic Safety Administration (NHTSA) to specify the various official levels of automation when it comes to self-driving autonomous vehicle technology.

The NHTSA has defined these levels of autonomous vehicle automation as follows:

  • Level 0: No-Automation
    The driver is in complete and sole control of the primary vehicle controls – brake, steering, throttle, and motive power – at all times.

  • Level 1: Function-specific Automation
    Automation at this level involves one or more specific control functions. Examples include electronic stability control or pre-charged brakes, where the vehicle automatically assists with braking to enable the driver to regain control of the vehicle or stop faster than possible by acting alone.

  • Level 2: Combined Function Automation
    This level involves automation of at least two primary control functions designed to work in unison to relieve the driver of control of those functions. An example of combined functions enabling a Level 2 system is adaptive cruise control in combination with lane centering.

  • Level 3: Limited Self-Driving Automation
    Vehicles at this level of automation enable the driver to cede full control of all safety-critical functions under certain traffic or environmental conditions and in those conditions to rely heavily on the vehicle to monitor for changes in those conditions requiring transition back to driver control. The driver is expected to be available for occasional control, but with sufficiently comfortable transition time. The Google car is an example of limited self-driving automation.

  • Level 4: Full Self-Driving Automation
    The vehicle is designed to perform all safety-critical driving functions and monitor roadway conditions for an entire trip. Such a design anticipates that the driver will provide destination or navigation input, but is not expected to be available for control at any time during the trip. This includes both occupied and unoccupied vehicles.

How Do Self-Driving Cars Work?

Self driving autonomous cars use various automotive technologies to provide an effortless mode of transportation. Providing this type of transportation requires a harmonious sychronization of advanced sensors gathering information about the surrounding environments, sophisticated algorithms processing that data and controlling the vehicles, and computational power processing it all in real time.

How do self-driving autonomous cars work diagram?
The following technologies are core components to self driving cars:

  1. Radar sensors (Where are you?) - Autonomous cars typically have bumper-mounted radar sensor units (two in the front and two in the back). These help the vehicle detect road dynamics such as detours, traffic delays, vehicle collisons, and other obstacles, by sending a signal to the on-board processor to apply the brakes and/or move out of the way. This technology works in conjunction with other features on the car such as inertial measurement units, gyroscopes, and a wheel encoder to send accurate signals to the processing unit (i.e. brain) of the vehicle.

  2. Optics (High-powered Cameras) - All autonomous cars utilize some form of camera technology, but the actual camera technology and setup on each driverless car varies. The cameras are used to identify road markings and traffic signals. Some self-driving cars can operate using just a single camera embedded in the windshield. Other autonomous car cameras require several cameras mounted to the vehicle's exterior with slight separation in order to give an overlapping view of the car's surroundings. The goal of a driverless car camera is to help the car's computer build up a composite picture of the surrounding world in order to drive safely. The technolgoy behind these cameras function similar to the human eye, which provides overlapping images to the vehicle's computer before determining things like depth of field, peripheral movement, and dimensionality of objects.

  3. LIDAR (Laser Illuminating Detection and Ranging) - The LIDAR unit, which looks like a spinning siren light, provides driverless cars with highly accurate long range detection, with ranges of up to 100 meters. As it is spins, it continuously scans the world around the car and builds a 3D omni-directional view to allow the car to see potential hazards by bouncing a laser beam off of surfaces surrounding the car in order to accurately determine the identity and distance of the object. The rotating LIDAR units are normally mounted to the top of the car, providing an unobstructed 360-degree view. This unit generates raw information about the world, which is then sent to the car's brain to process; just like a human driver would.

    How Autonomous Car LIDAR Units Work:
    1. The laser emitter inside the the LIDAR unit, generates and sends a laser beam outside of the rotating cylindrical housing.
    2. After the laser beam bounces off an object, the laser light returns back to inside of the housing.
    3. The gathered light is bounced downward to the reciever, which interprets it.
    4. The car's computer then takes this data and generates a map of it's surroundings.

  4. GPS (Global Positioning Software) - The GPS in driverless cars is not much more different than Google Maps' navigational software. While having a GPS may seem like a no-brainer, it’s actually a vital part of a self-driving car’s technology. The major difference is that driverless cars require GPS to navigate the car, while human driven cars do not. It looks at all the roads, chooses the best path, and is often better than people at doing it. GPS software is important because it defines the "mission" of the autonomous vehicle by setting a start and end point of the drive. However, GPS alone does not drive the vehicle. The GPS works in conjunction with radars, sensors, LIDAR and Deep learning HD mapping software to safely maneuver the vehicle to its final destination.

  5. Processors - Autonomous cars have mini-computers on board to make sense of all of the cars instruments, with some cars running more than 20 different processors. Computer processor giants such as Intel have already taken note of the increased computing requirements of self-driving vehicles, and have already taken the first steps at synergistically integrating automotive and technology companies. All of the data generated by the cameras and sensors mentioned above, is processed in real-time, as well as modeled behavioral dynamics of other drivers, pedestrians, and objects around the vehicle. While some data is hard-coded into the car, such as stopping at red lights, other responses can be learned based on previous driving experiences through machine learning. For example, actions such as steering, accelerating, and hitting the brakes are all controlled by the processed information.

Self-Driving Car Pros and Cons


  • Mobility for those unable to drive - Disabled individuals, who have to rely on public transportation or assistance from others to get around, could reap the benefits of self-driving cars with new freedom and enhanced mobility.

  • Reduced human induced vehicle collisions - In comparison to the myriad of bad behaviors human drivers might exhibit behind the wheel, a computer is actually an ideal motorist. It is estimated that 81% of car crashes are the result of human error. Computer controlled vehicles would take the danger of this equation entirely.

  • Time savings - When a computer takes over the driving responsibilites, drivers can use this new found time do other things, such as reading or work related activities, all without having to worry about road safety.

  • Smaller roads and lesser congestion - Driverless cars require less road space as they are programmed to follow directional instructions with only centimeters of variation. Smaller roads and more accurate driving also equate to reduced road congestion.

  • Reduced parking strain - Self driving cars could drop passengers off and park themselves in a safe and distant location, increasing owners's quality of life and reducing the need for parking structures.


  • Initial purchase price - The cost of this new technology is significantly above budget of most Americans average vehicle budget. Currently, the engineering, hardware, and software components of an autonomous car add up to more than approximately $100,000.

  • Sensitive data mining and hacking - In order for a computer to operate an autonomous vehicle, large amounts of information have to be collected. Concerns lie in the opportunity for an unauthorized user to gain access to the personal data stored in the cars built-in computer.

  • Unemployment implications - Self driving cars would theoretically eliminate many jobs in the transportation sector, especially in the freight and taxi sector. A related industry that is at risk of becoming extinct is drivers education.

  • Accountability and adaptability - If other technology fails, such as a traffic signal, there is currently no accounting for human traffic signals. For example, if there were an accident and a police officer was directing traffic, could the autonomous vehicle interpret human directional signals?

  • Reliance on technology - The reliance on technology could mean that over time drivers are no longer equipped with the skills to operate cars. In the event of a glitch or recall, drivers might be helpless to operate a vehicle, having been "out of practice" in the driving world for some time.