Self-Driving Car

What Is a Self-Driving Car?

A Self-Driving Car is a vehicle that can propel itself autonomously without a human being needing to take control. However, before complete autonomy arrives, there will be successive stages of sophistication as the systems take over more driving tasks and require less human operator attention.

Benefits of Self-Driving Cars

There are two main benefits of a Self-Driving Car. One is safety; the other is driver convenience. Initial levels of self-driving are closely associated with Advanced Driver-Assistance Systems (ADAS), which provide safety functions such as lane centering, adaptive cruise control, automatic emergency braking, and collision avoidance. These reduce the chances of accidents by providing interventions to aid the driver.

As greater autonomy is added, a Self-Driving Car can take over more duties from the operator, enabling a more relaxed journey. At the highest levels of autonomy, the car takes complete control, enabling all occupants to enjoy entertainment or other activities while they travel rather than driving.

A fully Self-Driving Car could also act as a driverless taxi service, reducing journey costs and increasing availability. This could make those unable to drive or use public transport more mobile. Alongside electrification, self-driving taxis could also negate the need for personal vehicles in urban areas, reducing the number of parked cars on residential and commercial streets. This will have positive effects on emissions and air quality in cities.

Levels of Self-Driving Car Technology

The Society of Automotive Engineers defines six levels of Self-Driving Car technology.

Level 0

This base level implies the vehicle has no self-driving capability; the driver performs all steering, acceleration, and braking functions.

Level 1

One vehicle function can be controlled automatically; this generally means the vehicle speed, through automated acceleration and braking, enabling cruise control, which could also be “adaptive,” where a safe distance to the vehicle in front is maintained using radar range finding.

Level 2

This is the level provided by many current vehicles with sophisticated ADAS, where they can control both speed and steering automatically; the driver must still monitor the vehicle and be ready to take control when necessary. Some manufacturers also mention “Level 2+”, which refers to more sophisticated Level 2 autonomous driving implementations with additional features.

Level 3

The vehicle has environmental awareness and can perform most driving tasks automatically, including navigation; however, the driver must still monitor the vehicle and take control when requested. This is the first level where the vehicle is truly self-driving.

Level 4

The vehicle can perform all driving functions within fixed areas, such as the city’s boundaries; a human driver can still override controls if desired, but this is not usually required.

Level 5

The vehicle performs all driving functions in all conditions and places; no driver input is required and may be impossible with some configurations.

How Self-Driving Cars Work

The key enablers of Self-Driving Cars are high-resolution sensors, powerful local computer processing within the vehicle, and sophisticated driving scenario models. The sensors employed include cameras, radar, LiDAR, and ultrasonics. These provide live environmental data and may be combined using sensor fusion to improve accuracy.

The vehicle’s onboard computer will be loaded with a driving model, which requires extensive development and testing with the help of automotive engineering experts such as the BlackBerry QNX Autonomous Vehicle Innovation Center. This model will combine detailed mapping information with behavioral scenarios based on environmental inputs. These inputs could be the motion of other vehicles, cyclists, pedestrians, or animals and objects detected, such as traffic cones or road debris.

The vehicle sensors can read road markings, signage, traffic signals, and other features. Powerful onboard vehicle computing will employ AI inference based on the sensor inputs and self-driving models to generate driving action outputs. For example, the vehicle could steer around a bend, stop at a red traffic signal, or leave a road junction when traffic flow conditions are safe. Based on a navigational destination, the Self-Driving Car can plot a route and transport passengers safely with little or no operational input from a human driver.

Self-Driving Cars vs. ADAS

Although Self-Driving Car technology and ADAS are closely related, ADAS is a subset of self-driving technology. Most safety features ADAS provides are essential for autonomous vehicles and rely on the same sensors. However, some ADAS features, for example, blind-spot detection, are primarily aimed at an active driver, providing extra alerts and information. ADAS, in general, is intended to improve driver safety. The eventual goal of a Self-Driving Car is to remove the need for a human driver entirely, which can improve safety but with additional benefits.
The BlackBerry IVY® platform leverages BlackBerry® QNX®, edge computing, and the cloud to support a future-proof digital ecosystem. It gives developers and automakers a secure, reliable way to share vehicle data, deliver new features and functionality, and fuel both present and future innovation. Backed by BlackBerry expertise, it’s compatible with most OS and cloud platforms, offering advanced personalization and access to our broad development community. 

Check Out Our Other Ultimate Guides

Structural Dependency
Learn about software-defined vehicles, including their benefits and architecture.
Structural Dependency
Covers topics such as embedded systems protection, security exploits and mitigation, and best practices
Structural Dependency
Offers key concepts and information on standards for safe system design
Structural Dependency
Defines autonomous systems and the various levels of autonomy
Read the Guide