Self-driving is capability- and context-dependent; “self-driving” lacks a single standardized definition and may be used differently in marketing.
A self-driving car (also called an autonomous, driverless, robotic, or robo-car) is a vehicle that can operate with reduced or no human input. The term “self-driving” does not have a single universally agreed definition and is often influenced by vendor branding. In practice, most systems rely on advanced driver-assistance technologies (ADAS) and a combination of sensors (commonly LiDAR and cameras/visual sensors), software, mapping, and supporting technologies such as GPS and artificial intelligence to drive safely within specific operating limits. Because capabilities vary widely, terminology is organized around concepts like the operational design domain (ODD), which describes where and under what conditions automation is intended to work. Definitions also distinguish between autonomy and automation: autonomy implies the system is controlled by the vehicle rather than the driver, while automation is typically function-specific and may still leave broader decision-making to the human. Standards and classifications—especially SAE International’s automation levels (0–5)—describe responsibility for driving tasks (direction/speed, monitoring, and fallback) rather than listing every possible feature. Additional terminology frameworks include Mobileye’s “eyes-on/hands-on,” “eyes-on/hands-off,” “eyes-off/hands-off,” and “no driver,” which describe driver attention and control expectations. Testing and safety discussions further depend on these definitions, since terms like “disengagement” and “autonomous” can be interpreted differently by companies and regulators, affecting how performance and reliability are reported.
Self-driving is capability- and context-dependent; “self-driving” lacks a single standardized definition and may be used differently in marketing.
Key terminology centers on ODD (where the system is intended to work), and on distinctions between autonomy vs automation and between ADAS and higher-level automated driving systems.
SAE International’s 0–5 automation levels classify systems by driver responsibility and fallback behavior, while Mobileye uses attention/control categories (eyes/hands/no driver).
Terminology affects safety reporting and testing metrics (e.g., disengagement definitions), which can vary across vendors and standards bodies.
A vehicle capable of operating with reduced or no human input, using sensors and software to control, navigate, and drive.
The specific conditions and environment in which an automated system is intended to operate safely.
Systems that automate specific driving functions (e.g., collision warning or lane keeping) while requiring the human driver to handle unsupported tasks.
A system that performs driving automation at higher SAE levels (typically Level 3 or above) with defined driver responsibilities.
Autonomy means the vehicle system is under vehicle control rather than the driver, while automation is usually function-specific and may leave broader decisions to the driver.
A classification scheme describing how driving responsibility is shared between the system and the human driver, including monitoring and fallback expectations.
A category where the driver must both keep hands on the wheel and monitor the driving environment.
A category where the driver does not need to keep hands on the wheel but must monitor the driving environment.
A category where the driver is not expected to monitor the environment and does not need to keep hands on the wheel.
A category indicating the system is intended to operate without a human driver for the relevant conditions.
An event where a company-defined automated driving mode is exited, with reporting definitions that can vary over time and by vendor.
“Can you explain what "Self-driving is capability- and context-dependent; “self-driving” lacks a single standardized definition and may be used differently in marketing." means in simple terms?”