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.
Also known as: HRI, human-robot interaction, human robot interaction
Updated
Interaction requires an exchange
ISO 8373:2021 defines human–robot interaction through information and action exchanges between a person and a robot to perform a task by means of a user interface. Speech, gesture, touch, displays, controls and robot motion can all carry part of that exchange.
Mere co-location is not enough to describe the interaction. A person visible in a robot’s camera may be a bystander rather than a participant. An HRI record should identify who communicated what, through which channel, and how the robot’s subsequent behaviour depended on it.
HRI spans remote, proximate and shared-control settings
The foundational Goodrich and Schultz survey frames HRI as the study of understanding, designing and evaluating robotic systems for use by or with humans. It includes remote teleoperation and supervisory control as well as co-located assistance, collaboration, physical interaction and social behaviour.
The allocation of control can change during one task. A person may choose a goal, the robot may navigate autonomously, and the person may intervene for an unfamiliar manipulation. Describing that sequence is more informative than labelling the entire system either manual or autonomous.
HRI data carries human context and risk
Useful records can combine robot state, commands, dialogue, gaze, gestures, contact, task outcomes and intervention events. They should preserve timing and participant roles without implying that proximity, eye direction or speech automatically proves intent.
Human recordings can contain faces, voices, locations and behavioural signals. Collection therefore needs consent, privacy controls and documented access conditions. Safety events, near misses and operator overrides should remain visible rather than being removed as failed demonstrations.
ISO uses “HRI” for human–robot interaction and advises against using the same abbreviation for the interface itself. Keeping the interaction, interface and participants distinct prevents ambiguous dataset labels.
Sources
Related terms
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
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.
Data & collection
Human–object interaction
Human–object interaction is the physical and semantic relationship between a person and an object while the person observes, reaches, grasps, moves, uses, or otherwise acts on it. In robotics datasets, the term often refers to recordings and annotations that connect human body or hand motion with object identity, pose, contact, action, and task context.
Data & collection
Demonstration
A demonstration is a recorded example of how an intended task or behaviour is performed, usually represented as a time-aligned sequence of observations, states and actions. For humanoid robot learning, demonstrations may come from teleoperation, kinaesthetic guidance, motion capture or autonomous experts and provide targets for imitation.
Data & collection
Language annotation
A language annotation is natural-language metadata attached to a robot-data sample, segment, or episode. It may state the instruction given before execution, describe what happened afterward, name a task or subtask, identify objects, record a correction, or explain an outcome. These annotation types are not interchangeable because they contain different information and may be available at different times.