Levels of autonomous vehicles

Autonomous vehicles are cars capable of navigating and perceiving their surroundings without human intervention. A technological model that aspires to become the future of driving; Meanwhile, proposals such as Movistar Car bring analog cars closer to the new era by making them smarter.

In any case, and for autonomous cars to be a reality, they must be able to imitate our driving, control, environment evaluation and decision-making capabilities. But do you know how they work?

The 6 levels of autonomous vehicles

Autonomous driving has been classified into six levels by the Society of Automotive Engineers (SAE). The most recent update is the J3016 standard.

Level 0: No automation

The level 0 of autonomous vehicles that applies to the most common cars today, the driver’s actions are not automated.

  • Features: The driver performs all tasks and maneuvers. The vehicle may include sensors or radars that notify the driver of events and nearby objects.
  • Limitations: Cars at this level do not include any type of autonomous control.

Level 1: Driver assistance

Level 1 autonomous vehicles include systems that control steering, speed and braking. Many models available today include features of this level, including:

* Adaptive autopilot (cruise control).
* Lane control system.
* Parking assistance.
* Distance control and collision avoidance.
* Automatic emergency braking system.
  • Features: Autonomous assistance in steering or speed systems. The driver continues to control most of the functions of the car. Hands must be kept on the wheel.
  • Limitations: There is only autonomous assistance in one system at a time. Assistance in steering or speed, but not both simultaneously.

Level 2: Partial automation

Level 2 autonomous vehicles are capable of taking control of some systems, although the driver must be alert in case their intervention is needed. Real examples are: the Nissan ProPilot models and the Mercedes-Benz E-Class.

  • Features: At least two functions are automated at the same time. The self-driving car stays in lane and at a safe distance from other elements on the road. The driver is allowed to stop controlling the steering wheel and accelerator (hands-free driving). These autonomous vehicles detect the limits of the lane and the road. Even without the need for lines or signage on the pavement.
  • Limitations: The car takes control for short periods of time, only of some functions and under certain conditions. The driver must be alert to take control if necessary.

Level 3: Conditional automation

In this level 3, autonomous vehicles begin to analyze their environment and are capable of making decisions. They use LIDAR sensors to record what is happening around them. These sensors combine computer vision, cameras, radar and location.

Level 3 autonomous vehicles are: the Tesla Model S, with the autopilot system, and the Audi A8. They are already available in China and the United States, and are expected to arrive in Europe by the end of 2020.

  • Features: Cars are capable of controlling critical driving functions on a highway, overtaking a car or taking an exit. The vehicle automatically activates safety settings when it detects certain traffic, road or environmental situations. The driver can stop supervising the car for extended periods of time.
  • Limitations: The driver is allowed to let go of the steering wheel, but only on sections with slow traffic, less than 60 km/h. The driver is required to be behind the wheel of these autonomous vehicles if driving on public roads. In many countries, the legal framework has not yet been defined or updated, limiting its use. In Spain, work is being done to modify the legislative framework affecting autonomous vehicles.

Level 4: High automation

Level 4 autonomous vehicles are driven without the need for driver intervention. They use AI algorithms to train themselves in different driving conditions and scenarios. There is a WiFi connection in the car.

Tesla has a variant of the Model S, Google the Waymo Project and Audi the Elaine Concept. Meanwhile, Ford and Volvo announce level 4 models for 2021.

  • Features: The car can control all critical driving functions. Level 4 autonomous vehicles modify their response based on external conditions. If conditions are adverse, it looks for an appropriate place and stops. There is no longer a driver, only passengers, who can travel asleep.
  • Limitations: They are expected to be available between 2021 and 2030. Initially they will be operational under supervision (not driving) and in specific scenarios.

Level 5:Complete Automation

At this level, robotic vehicles do not require any type of driving control (no steering wheel or pedals). There is no longer a driver and instructions are given by voice command or through mobile applications.

Cars at levels 4 and 5 work by exchanging information with their environment. They take advantage of sharing and using the data generated by the telecommunications of smart cities and the IOT. The Audi Aicon is an example of a level 5 concept car that is only possible with 5G technology. The European Parliament expects these autonomous vehicles to be available by 2030.


  • No human interaction required: Level 5 autonomous vehicles are designed to operate without any human intervention. This means that there is no need for a driver, and the vehicle can handle all aspects of driving, from navigation to obstacle avoidance.
  • Electric vehicles: Many level 5 prototypes are electric vehicles. This is because electric motors are more efficient and quieter than gasoline engines, which is important for a vehicle that will be operating in close proximity to pedestrians and other vehicles.
  • 360° recognition: Level 5 vehicles use a variety of sensors, including cameras, radar, and lidar, to achieve 360° perception of their surroundings. This allows them to see and understand the world around them in a way that is far beyond the capabilities of a human driver.


  • Legal framework: There is currently no clear legal framework for the operation of level 5 autonomous vehicles. This is a major hurdle that will need to be overcome before these vehicles can be widely deployed.
  • Infrastructure: The current infrastructure is not designed for autonomous vehicles. Roads will need to be upgraded with sensors and other infrastructure to support the safe operation of these vehicles.


The evolution of autonomous vehicles has been fascinating to watch. The progress that has been made in recent years is truly impressive. However, there are still a number of challenges that need to be overcome before these vehicles can become a reality. With continued investment and research, we can expect to see level 5 autonomous vehicles on the road in the next decade.