Autonomous vehicles are self-driving vehicles capable of operating with little or even no human intervention. These vehicles use artificial intelligence (AI) and existing automotive technologies such as adaptive cruise control to automate driving.
Self-driving cars range in complexity from basic systems that must be constantly monitored by the driver, to systems that can operate in all conditions and without human error at all.
Companies such as waymo, already have autonomous cars on the road, and automakers like Tesla, Ford, GM and others have developed their own autonomous car technologies like Tesla Autopilot, Argo AI and GM Cruise.
How do autonomous cars work?
Autonomous cars use a combination of artificial intelligence systems and vehicles based on existing advanced driver assistance systems (ADAS), to create something known as an Automated Driver System (ADS).
The artificial intelligence at the heart of the autonomous car takes data from various sensors built into the car and uses those inputs to create a picture of the outside world. With this image, combined with a map of the area and data global satellite positioning (GPS), an autonomous vehicle can plot a course safely in its environment.
To move from one point to another, AI connects to vehicle systems such as electronic throttle control brake and steering. When a vehicle’s sensors, which can include everything from radar to lasers, detect an object such as a pedestrian or other vehicle, the AI is designed to take immediate corrective action to avoid a crash.
In addition to full AI control, autonomous vehicles are usually designed with full driver control possible. In such vehicles, ADS acts as a very advanced form of cruise control, where the driver can take or leave control at any time.
Some autonomous vehicles are designed to operate without human intervention at all, although legality of cars without a driver varies from one place to another.
Key technologies that allow the car to drive itself
In order for a car to drive itself, it must use a range of technologies that have been in our vehicles for years, and in some cases even decades. A car must support electronic control of every system, from the engine and transmission to the brakes, and it needs some type of artificial intelligence to tie it all together.
Most of the technologies used in autonomous vehicles are known as advanced driver assistance systems because they were designed to make driving more comfortable and less dangerous.
Here are some of the most important technologies that underlie autonomous vehicles:
- Artificial Intelligence: Autonomous machines would not be possible without artificial intelligence. These vehicles are driven by AI programs that are developed and trained through machine learning, to be able to read data from various sensors built into the vehicle and then determine the most appropriate action in any given situation.
- drive-by-wire : These systems have been present in conventional vehicles for many years and they basically replace mechanical connections with electrical connections and controls. This greatly simplifies the built-in AI to control each individual system such as steering, acceleration and braking.
- Preservation traffic lanes. These systems were originally designed to help human drivers avoid shifting their lanes, but autonomous vehicles use many of the same types of sensors and techniques.
- Automatic braking . It was originally developed to prevent accidents by automatically braking in situations where the driver is too slow to act. Autonomous cars use similar technologies on a much larger scale.
- Adaptive cruise control : This is another system that was originally designed to assist drivers, in this case by dynamically increasing and decreasing speed relative to surrounding traffic. Autonomous cars must perform this same basic task in addition to everything a driver would normally do.
Degrees of autonomy: can autonomous cars really be driverless?
The development of autonomous cars was a slow step forward, not a switch someone decided to flip one day. It started in the 1950s with some of the first safety and convenience features that became common over time, such as anti-lock brakes and cruise control, and sped up in the 2000s with ADAS, such as adaptive cruise control. and automatic braking.
Because autonomous cars have gone through such a slow and gradual process, the Society of Automotive Engineers (SAE) has developed a five-level automation scale.
This scale describes everything from the fully manual cars of yesterday to the fully automated cars expected to hit showrooms and highways by 2020.
These are the levels of automation a vehicle can have:
Level 0: No Automation
These are traditional vehicles that require the constant participation of the driver. These cars don’t even have features like anti-lock brakes or cruise control.
Level 1: Driver Assistance
These vehicles are still fully controlled by the driver, but they include some general driver assistance systems. A vehicle at this level usually includes basic features such as cruise control.
Level 2: Partial Automation
At this stage, cars receive some level of automatic control over functions such as acceleration, braking, and steering. The driver is still in full control of the vehicle, and a vehicle at this level cannot drive itself without a human driver.
Such vehicles typically have ADAS, such as automatic braking, adaptive cruise control, and some type of lane keeping system.
Level 3: Conditional Automation
Vehicles at this level include ADS, so they are technically autonomous. These vehicles are capable of moving from one place to another, identifying hazards and responding to them. The presence of a human driver is still required in the event of an emergency and the driver must remain alert and ready to take control.
Every system in vehicles at this level must be automated, and these vehicles also require extensive AI capability to operate safely without human driver involvement.
Level 4: High Automation
At this level, the car is fully automated. It is able to move safely from one place to another in most conditions. Under some conditions, and in some circumstances, the car may still require human intervention.
This type of autonomous vehicle is technically capable of operating without the presence of a human operator, but an option for a human operator may be included.
Level 5: Full Automation
Vehicles at this level of automation are truly autonomous and can operate without a driver in all driving conditions. Depending on the design, a human operator may be able to take over manual control, but these types of vehicles do not require such intervention.
What are the benefits of autonomous cars?
The main benefit of autonomous vehicles and the driving force behind the development of autonomous vehicles is safety. According to the NHTSA, more than 90 percent of all serious accidents are caused by simple human error. The basic idea is that if the human factor can be completely removed from the equation, many lives can be saved.