Hardware & control
Autonomy
Robot autonomy is the ability to perform an intended task from the robot’s current state and sensor information without human intervention during that task. Autonomy is contextual and can differ by function, environment and operating phase; it is not a single permanent capability level for the whole robot.
Also known as: robot autonomy, robotic autonomy
Updated
Autonomy belongs to a task and context
ISO 8373:2021 defines autonomy around performing intended tasks from current state and sensing without human intervention. That makes the unit of analysis important. A humanoid may walk autonomously while a person selects goals, recover balance autonomously while its arms are teleoperated, or complete one warehouse task without being able to handle an unfamiliar exception.
“Autonomous robot” should therefore not be read as “independent in every situation”. A useful description names the task, operating environment, information supplied by people and conditions that trigger assistance or shutdown.
Degree of autonomy is not one universal ladder
The NIST ALFUS framework characterises autonomy through mission complexity, environmental complexity and human independence, which it treats as complementary to human–robot interaction. Those dimensions explain why two systems given the same label can require very different levels of supervision.
Autonomy also does not imply machine learning, general intelligence or online adaptation. A conventional planner and controller can operate without intervention inside a defined domain, while a learned policy may still depend on continuous human approval. Automation and autonomy overlap in everyday usage, so technical claims should state the actual allocation of decisions between person and robot.
What autonomy data should record
Logs should identify the active operating mode, task boundaries, goals supplied by people, interventions, controller transitions, safety stops and fallback behaviour. A success completed after hidden operator correction is not evidence of the same autonomy as an uninterrupted run.
Evaluation should report the environment and failure conditions as well as task success. Intervention rate, time between interventions and the kinds of decisions delegated to the robot often reveal more than an unsupported autonomy-level label.
Sources
Related terms
Data & collection
Robot state
Robot state is the set of variables used to describe a robot at a particular time, such as joint positions and velocities, base pose, end-effector pose, gripper state, actuator measurements, or estimated motion. In control theory, a complete state contains enough information to predict future evolution given an action; in robot datasets, “state” often means only the measured or estimated subset that was logged.
Models & learning
Policy
A policy is the decision rule that maps a robot’s current observations or estimated state, and sometimes a task instruction, to an action or probability distribution over actions. It can be hand-designed or learned from demonstrations, rewards or both. In humanoid robotics, its outputs may be joint targets, torques, end-effector changes or higher-level skills.
Data & collection
Teleoperation
Teleoperation is real-time human control of a robot from a remote or mediated interface. For humanoid training-data collection, the operator’s inputs are mapped to robot motions while cameras, proprioception, commands and outcomes are recorded, producing embodied demonstrations in the robot’s own observation and action spaces.
Hardware & control
Feedback control
Feedback control is a closed-loop control method that measures a system’s current output or state, compares it with a target and adjusts the command using the resulting error. In robotics, feedback can correct joint, end-effector, balance or force errors as new sensor measurements arrive.
Data & collection
Human–robot interaction
Human–robot interaction is the exchange of information and actions between people and robots while performing a task, and the field that studies how such systems are designed and evaluated. It includes remote operation, supervision, collaboration, physical interaction and social communication rather than only face-to-face conversation.