Reference
Humanoid Robotics Glossary
Clear, source-backed definitions of humanoid robotics, embodied AI, robot learning, training data, control, and simulation terms.
A
Models & learning
Action chunking
Action chunking is a policy design in which one observation is used to predict a sequence of several future robot actions rather than a single next action. The chunk can capture short-term motion structure and reduce the effective number of sequential predictions, while its execution and replanning schedule determine how quickly the robot can react to new observations.
Models & learning
Action space
An action space is the set and representation of commands that an agent or robot policy is allowed to choose. In robotics, actions may be discrete choices or continuous values such as joint targets, motor torques, end-effector pose changes, base velocities, or gripper commands. The action space defines what the policy outputs, not necessarily the motion the hardware ultimately executes.
Hardware & control
Actuator
An actuator is a robot’s power mechanism that converts electrical, hydraulic, pneumatic or other supplied energy into controlled mechanical force, torque or motion. In a humanoid, actuators drive joints, often through transmissions; they are distinct from the joints and sensors, and their arrangement need not correspond one-to-one with the robot’s degrees of freedom.
Models & learning
Asynchronous inference
Asynchronous inference is a deployment pattern that overlaps robot action execution with prediction of a later action chunk. A robot client consumes queued actions while a policy process or server evaluates a newer observation, then merges or replaces the remaining queue when the new chunk arrives. The pattern reduces idle inference gaps but does not remove latency, stale observations or safety constraints.
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.
B
Models & learning
Behaviour cloning
Behaviour cloning is a form of imitation learning that fits a policy to expert observation–action pairs as a supervised prediction problem. For humanoid robots, the training examples typically align camera or proprioceptive observations with commands recorded during demonstrations, so the learned policy can reproduce similar behaviour without an explicit reward model.
Hardware & control
Bimanual manipulation
Bimanual manipulation is the use of two hands or robot manipulators to carry out one manipulation task with spatial, temporal, or force coordination between them. The two sides may play symmetric roles, such as lifting a large object together, or asymmetric roles, such as one hand holding an object while the other operates a tool.
Hardware & control
Biped robot
A biped robot is a legged mobile robot that travels using two legs. Biped describes the locomotion structure, not the robot’s overall resemblance to a person: a biped can lack arms or a head, while a robot described as humanoid may use wheels instead of two-legged locomotion.
C
Hardware & control
Centre of mass
The centre of mass is the mass-weighted average position of a body or multibody system. For a humanoid, the whole-robot centre of mass changes as its joints move or its payload changes, and its position and acceleration are central variables in balance, locomotion and whole-body control.
Hardware & control
Centre of pressure
The centre of pressure is the point on a support surface at which the resultant of a distributed contact pressure or ground-reaction force can be represented as acting. In legged robotics it summarises how load is applied through one foot or across coplanar contacts and is commonly estimated from a measured contact wrench.
Hardware & control
Control frequency
Control frequency is the rate, usually expressed in hertz, at which a robot control loop reads state, updates its controller or policy, and issues commands. A robot can contain several nested loops at different rates, so policy frequency, actuator-control frequency, sensor sampling rate, and dataset frame rate should not be assumed to be identical.
Hardware & control
Control latency
Control latency is the elapsed time between a relevant event or observation and the physical effect of the resulting robot command. It can include sensor exposure and transport, preprocessing, policy inference, network transfer, controller scheduling, actuator response, and communication back to a human operator. The measured boundary must be stated because each component has a different latency.
Hardware & control
Coordinate frame
A coordinate frame is a defined origin and set of oriented axes used to express positions, orientations, motions, forces, or other spatial quantities. A value has no complete geometric meaning until its frame and convention are known. Transformations relate measurements expressed in frames such as world, robot base, camera, end effector, object, or sensor.
Data & collection
Cross-embodiment data
Cross-embodiment data is robot training data drawn from multiple physical embodiments, such as arms, mobile manipulators, quadrupeds or humanoids with different kinematics, sensors and action spaces. The datasets are aligned or packaged so models can learn jointly from experience produced by different robots, although shared formatting does not make their observations or controls physically equivalent.
D
Data & collection
Data synchronisation
Data synchronisation is the process of placing sensor, state, action, annotation, and outcome records on a common timeline so samples that describe the same physical instant or transition can be matched. It requires trustworthy timestamps or trigger relationships and an explicit rule for handling streams with different rates, delays, dropped samples, and clock offsets.
Hardware & control
Degree of freedom
A degree of freedom (DoF) is one independent parameter needed to specify a robot’s configuration; equivalently, a robot’s DoF is the dimension of its configuration space. It describes possible motion, not the number of motors. Joint constraints, closed kinematic chains and environmental contacts can make joint count, actuator count and controllable motion differ.
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
Depth data
Depth data records the distance associated with image locations or sensor rays, usually as a depth image in which each pixel stores a metric value relative to a camera. The exact geometry, units, invalid-value convention, and coordinate frame depend on the sensor and encoding. RGB-D data pairs depth with colour imagery; a point cloud is a separate 3D representation derived from or aligned with such measurements.
Hardware & control
Dexterous manipulation
Dexterous manipulation is the controlled, skillful reconfiguration of an object through coordinated motion and contact, often using multiple fingers. It can involve changing an object's pose within a hand, regrasping, sliding, rolling, finger gaiting, or making precise contact with the environment. The term describes capability, not a fixed minimum number of fingers or joints.
Models & learning
Diffusion policy
A diffusion policy is a learned robot policy that generates an action or action sequence through iterative denoising conditioned on observations and, where applicable, a task goal. This formulation can represent several plausible behaviours for the same scene and is commonly trained by imitation on time-aligned trajectories of observations and expert actions.
Simulation & transfer
Digital twin
A digital twin is a fit-for-purpose digital representation of a specific physical robot, asset or process that is kept synchronised with its real counterpart through operational data. It may contain geometry, dynamics and simulation models, but the maintained link to an identified real system distinguishes it from an ordinary, standalone simulator.
Simulation & transfer
Domain randomisation
Domain randomisation is a simulation-training technique that varies selected visual, physical or sensor parameters across generated examples or episodes. By exposing a model or policy to a distribution of environments rather than one calibrated scene, it aims to make real conditions fall within the learned variation and improve sim-to-real transfer.
E
Data & collection
Egocentric data
Egocentric data is sensor data recorded from the viewpoint of the person or robot performing an activity, most commonly with a head- or body-mounted camera. It can also include audio, gaze, depth or inertial signals. For humanoid learning, it shows hands, objects and actions from an actor-centred perspective.
Models & learning
Embodied AI
Embodied AI is artificial intelligence that perceives and acts through a body in an environment, so its actions change the observations available to it next. The body may be a physical robot or, in common research usage, an agent situated in a persistent simulated world. Embodied AI emphasises the coupled loop between morphology, perception, action, learning, and the environment.
Models & learning
Embodied reasoning
Embodied reasoning is reasoning grounded in an agent's body, sensors, tools, and physical environment so that it can plan, select, or revise real-world actions. The term is broad and not standardised; in robotics it can include spatial understanding, task decomposition, grasp or trajectory reasoning, success detection, and replanning.
Hardware & control
End effector
An end effector is a task-specific device attached to a robot manipulator’s mechanical interface so the robot can act on its environment, such as a gripper, hand or welding tool. It is distinct from the wrist or mounting flange, and from the tool centre point, which is only a coordinate frame used to plan the device’s motion.
F
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.
Hardware & control
Floating base
A floating-base model represents a robot’s root body with six unconstrained spatial degrees of freedom—three for translation and three for rotation—instead of fixing it to the world. Those base coordinates are not directly actuated; a legged robot changes them through joint motion and external contact forces.
Models & learning
Flow matching
Flow matching is a generative-model training method that learns a time-dependent vector field transporting samples from a simple prior distribution to a data distribution. Training regresses the vector field along chosen probability paths without solving the flow during each update; generation starts from the prior and numerically integrates the learned ordinary differential equation.
Hardware & control
Force closure
Force closure is a property of a set of contacts whose admissible forces can collectively generate a wrench opposing any external disturbance wrench under the chosen contact model. It describes directional force and moment capability without, by itself, accounting for finite actuator strength, object damage or uncertainty in the contacts.
Hardware & control
Force–torque sensing
Force–torque sensing is the measurement of forces and rotational moments transmitted through a robot interface, commonly with a six-axis sensor reporting three force components and three torque components. The combined quantity is a wrench expressed at a specified origin and in a specified coordinate frame. It measures the resultant load at the sensor, not a spatial pressure map across every contact.
Hardware & control
Friction cone
A friction cone is the set of contact-force vectors allowed by a Coulomb friction model: the normal force is nonnegative and the tangential force magnitude cannot exceed the friction coefficient times that normal force. It represents a force constraint at a contact, not a physical cone or a guarantee that the robot will not slip.
G
Hardware & control
Gait
A gait is a recurring pattern of leg motion and contact phases used for legged locomotion. For a biped, it describes how left and right stance, swing, double-support and any flight phases repeat over a cycle; gait is narrower than locomotion, which also includes starts, stops, turns, transitions and recovery.
Hardware & control
Gripper
A gripper is a robot end effector designed to seize and hold an object. It may use fingers, jaws, suction, magnetism, adhesion, or another grasping mechanism. A gripper can open and close with one command or expose several independently controlled joints, but it is not synonymous with every end effector or with a complete robot hand.
H
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
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.
Hardware & control
Humanoid robot
A humanoid robot is a robot whose body is modelled on the human form, typically with a torso, head and limbs, so it can move through human spaces or use human-scale tools and interfaces. The term describes morphology, not intelligence or autonomy; wheeled, partial-body and simplified-hand designs are also sometimes classed as humanoids, so the robot's actual configuration should be stated.
I
Models & learning
Imitation learning
Imitation learning is a family of methods that learns a policy from examples of expert behaviour rather than specifying every control rule by hand. In robotics, demonstrations pair observations or states with actions, trajectories or inferred objectives. Behaviour cloning is one imitation-learning method; interactive and inverse approaches address different supervision and distribution-shift problems.
Hardware & control
Impedance control
Impedance control regulates the dynamic relationship between a robot’s motion error and the force or torque it exerts, usually by giving the robot virtual stiffness, damping and sometimes inertia. It lets an end effector or limb yield predictably during contact instead of trying to hold an exact position regardless of interaction forces.
Hardware & control
Inverse kinematics
Inverse kinematics (IK) finds robot configurations that satisfy a desired position, orientation or other geometric constraints. It reverses the question asked by forward kinematics: instead of computing where a hand or foot is from the joint values, it searches for joint values that place it at a target. A target can have multiple solutions or no feasible solution.
K
L
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.
Data & collection
LeRobot dataset
A LeRobot dataset is a robot-learning dataset organised for the LeRobot data model and loaders. LeRobot v3 stores low-dimensional state, action and timestamp fields in Parquet, camera streams in MP4, and schema, task, statistics and episode metadata under a coordinated directory layout.
Hardware & control
Loco-manipulation
Loco-manipulation is the integrated performance of locomotion and object manipulation, in which a robot moves its own body while reaching, carrying, pushing, pulling, or otherwise controlling something in the environment. In humanoids and other legged robots, the task couples contact planning, balance, whole-body motion, and manipulation rather than treating walking and arm control as independent stages.
Hardware & control
Locomotion
Robot locomotion is the process by which a robot transports its body from one place to another through physical interaction with its environment. Robots may walk, roll, crawl, hop, fly, or swim. For a humanoid, locomotion usually means coordinated legged movement such as walking, turning, stepping, climbing, or recovering balance.
Models & learning
Long-horizon task
A long-horizon task is a temporally extended robot task whose success depends on maintaining reliable behaviour across many actions, phases, or dependent subtasks. The term has no universal step-count threshold: it usually signals sequential dependencies, accumulating execution error, delayed outcomes, changing object state, or information that must be remembered beyond the current observation.
M
Hardware & control
Manipulability
Manipulability describes how readily a robot can produce task-space velocities in different directions at a particular configuration, given a specified bound on joint velocities. It is often represented by a Jacobian-derived ellipsoid or scalar measure; it is not a general score for grasp quality, payload capacity or task success.
Models & learning
Markov decision process
A Markov decision process is a mathematical model of sequential decision-making defined by states, actions, transition probabilities and rewards. After an agent chooses an action, the current state and action determine the distribution of the next state and reward. Reinforcement-learning methods use this structure to compare policies by expected cumulative reward.
Data & collection
MCAP
MCAP is an open container format for timestamped robotics and multimodal log messages. It can store heterogeneous serialised messages with schemas, channels, attachments, metadata, optional compression, and indexes, but it does not define whether the recorded sensors, clocks, or robot actions are correct.
Hardware & control
Mobile manipulation
Mobile manipulation is the coordinated use of locomotion and manipulation by a robot that combines a mobile base or body with one or more arms or other manipulators. Mobility expands the robot's reachable workspace, while the manipulator grasps, pushes, operates tools or makes contact; the base and arm may move separately or at the same time.
Hardware & control
Model predictive control
Model predictive control is a feedback-control method that uses a dynamics model to optimise a sequence of future actions, applies the first action or short part of that sequence, and replans from an updated state estimate. In receding-horizon MPC, the planning window moves forward at each update.
Data & collection
Motion capture
Motion capture is the measurement and reconstruction of a person’s or object’s movement over time, commonly as joint positions, orientations or a fitted body model. Optical markers, cameras and inertial sensors can supply the measurements. Humanoid robotics uses the resulting motion sequences for analysis, imitation and retargeting to a robot body.
Simulation & transfer
Motion retargeting
Motion retargeting is the adaptation of a recorded or generated motion from one body to another with different proportions, joints or limits. For humanoid robots, it maps source poses or trajectories into robot configurations while preserving task-relevant relationships such as contacts and end-effector paths and satisfying kinematic, balance, collision and actuator constraints.
O
P
Models & learning
Physical AI
Physical AI is artificial intelligence used in machines that perceive and act in the physical world, including robots, autonomous vehicles, and other autonomous systems. It closes a loop between sensing, decisions, action, and physical consequences. The label is emerging rather than standardised and often overlaps with embodied AI.
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.
Models & learning
Pose estimation
Pose estimation is the process of inferring the position and orientation of a body, object, camera, hand, or robot relative to a specified coordinate frame. In three-dimensional robotics this is often called 6D or 6-DoF pose estimation because the result has three translational and three rotational degrees of freedom, even when orientation is stored with more than three numbers.
Hardware & control
Proprioception
Proprioception is sensing of a robot’s own internal configuration and motion rather than the external scene. For a humanoid it commonly includes joint positions and velocities, actuator effort or torque, and inertial measurements of body rotation and acceleration. These signals support state estimation and feedback control but do not, by themselves, directly describe nearby objects or terrain.
R
Simulation & transfer
Real-to-sim
Real-to-sim is the process of using observations or measurements from a real robot, object or environment to construct or update a simulation-ready representation. Depending on the application, this may recover geometry, articulation, calibration and physical parameters, or translate real demonstrations into simulator state, usually to support later analysis, training or sim-to-real deployment.
Models & learning
Reinforcement learning
Reinforcement learning is a method in which an agent learns a policy by interacting with an environment and optimising cumulative reward. In humanoid robotics, actions change the robot and world, while observations, rewards and episode endings provide experience for improving balance, locomotion or manipulation behaviour.
Models & learning
Reward model
A reward model is a learned function that estimates task progress, success, preference, or another reward signal from robot observations or trajectories. It can replace or supplement a hand-written reward when training or evaluating a policy, but its output is only as reliable as its labels, coverage, and resistance to shortcuts.
Hardware & control
Robot
A robot is a programmed, actuated mechanism with some degree of autonomy that performs locomotion, manipulation or positioning. The term includes the mechanism and its control system, but it does not imply a human-like body, machine learning, general intelligence or fully independent operation.
Hardware & control
Robot dynamics
Robot dynamics describes the relationship between forces and torques acting on a robot and the motion they produce, accounting for mass, inertia, gravity, velocity-dependent effects and external contact. Forward dynamics predicts acceleration from applied forces; inverse dynamics computes forces or torques for a specified motion.
Hardware & control
Robot embodiment
A robot embodiment is the particular body and sensorimotor interface through which a robot perceives and acts. It includes morphology and kinematics, actuators, end effectors, sensors, physical limits, and the observation and action conventions exposed to a controller or learned policy. Two robots can perform the same task while having different embodiments.
Models & learning
Robot foundation model
A robot foundation model is a broadly pretrained model intended to provide a reusable starting point for multiple robot tasks, environments or embodiments. It learns from diverse robotics and sometimes web or human data, then acts directly or is adapted with target-domain data. The term describes a training and reuse strategy, not one fixed architecture.
Hardware & control
Robot Jacobian
A robot Jacobian is a configuration-dependent matrix that maps joint velocities to a specified task velocity, such as the linear and angular velocity of an end effector. It describes instantaneous motion, rather than the end effector's finite displacement or the forces needed to accelerate the robot.
Hardware & control
Robot kinematics
Robot kinematics describes the geometric relationship between a robot’s joint configuration and the position, orientation and velocity of its links or end-effector, without modelling the forces that cause the motion. Forward kinematics computes pose from joint values; inverse kinematics searches for joint values that achieve a requested pose.
Models & learning
Robot learning
Robot learning is the use of data and machine-learning methods to acquire or improve robot perception, prediction, planning or control. A robot may learn from demonstrations, rewards, direct interaction, simulation or previously collected datasets. The field includes reinforcement learning and imitation learning, but neither term is a synonym for robot learning as a whole.
Hardware & control
Robot manipulation
Robot manipulation is a robot's controlled physical interaction with objects or its environment to change or maintain their state. It includes grasping, carrying, pushing, pulling, inserting, wiping, folding, tool use, and other tasks performed through selective contact. Manipulation can use a gripper, hand, tool, arm, or another part of the robot.
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.
Data & collection
Robot training data
Robot training data is recorded experience used to train, fine-tune, or adapt models for robot perception, prediction, planning, or control. It can include sensor observations, robot state, actions, task instructions, rewards or outcomes, demonstrations, failures, and embodiment metadata. Not every dataset contains every field, but their timing and physical meaning must be clear.
S
Data & collection
Sensor calibration
Sensor calibration is the estimation and documentation of parameters that map raw sensor readings into physically meaningful values and known spatial relationships. In robotics it can include scale, bias, distortion, intrinsic camera parameters, sensor-to-sensor or sensor-to-robot transforms, and timing offsets. Calibration does not remove all noise or drift.
Simulation & transfer
Sim-to-real
Sim-to-real is the transfer of a model, policy or behaviour developed wholly or partly in simulation to a physical robot or real environment. The central problem is the reality gap: errors in simulated dynamics, sensing, appearance and timing can make a strategy successful in simulation but unreliable or unsafe on hardware.
Hardware & control
SLAM
Simultaneous localisation and mapping
SLAM is the joint estimation of a moving robot or sensor rig's pose and a map of its environment from sensor observations. It addresses the coupled problem of needing a map to localise while needing pose estimates to build that map.
Hardware & control
State estimation
State estimation is the process of inferring variables that are not known exactly—such as a robot’s base pose, velocity, contact state or sensor bias—from noisy measurements, control inputs and a model of how the system evolves. An estimator should provide both an estimate and, where possible, a representation of its uncertainty.
Hardware & control
Support polygon
The support polygon is the convex hull of a robot’s contact areas on a declared support surface. For a biped on level ground it is formed by the loaded parts of one or both feet; it changes when contacts are added, removed or reduced to an edge or toe.
Simulation & transfer
Synthetic data
Synthetic data is training or evaluation data produced computationally rather than measured directly from the target real-world event. In robotics it can include rendered sensor observations, automatically generated labels, reconstructed or generated scenes, and simulated trajectories. A simulated rollout is one subtype: a temporally linked trajectory produced by executing a controller or policy in a simulator.
Simulation & transfer
System identification
System identification is the process of estimating a dynamical model from measured inputs and outputs. In robotics it can fit parameters of a known mechanical model or learn a model structure that predicts how a robot or environment responds to actions.
T
Hardware & control
Tactile sensing
Tactile sensing is the detection and measurement of physical contact properties at a robot's surface or contact interface. Depending on the sensor, it can report pressure or force distribution, contact location, shear, vibration, slip, texture, temperature, or deformation. Tactile data complements vision by measuring interactions that may be hidden at the point of contact.
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
Torque control
Torque control is a control mode in which desired joint torques, or equivalent linear forces, are the command variables sent to a robot’s low-level actuators. Unlike position control, it does not directly command where each joint should be. Motion and contact instead emerge from the applied efforts, robot dynamics, feedback, constraints and any higher-level controller.
Data & collection
Trajectory
A trajectory is a time-ordered sequence of states or observations, actions and, where applicable, rewards generated as an agent or robot evolves. A complete episode or policy rollout often yields a trajectory, but the terms are not universally identical: trajectories may be partial, while episodes have dataset- or environment-defined boundaries.
U
V
Models & learning
Vision-language-action model
A vision-language-action model is a robot policy that conditions on visual observations and natural-language instructions to predict executable actions. It adapts a pretrained vision-language model, or a similar multimodal backbone, using robot trajectories so that semantic knowledge is connected to an embodiment’s action space. The action representation may use discrete tokens or continuous values.
Data & collection
Visual-inertial odometry
Visual-inertial odometry estimates a moving sensor rig's motion by combining camera observations with inertial measurements from accelerometers and gyroscopes. Its core output is a relative motion or pose estimate over time, not an independently measured ground-truth trajectory or necessarily a reusable global map.
W
Hardware & control
Whole-body control
Whole-body control coordinates a humanoid’s full multibody state, actuated joints and environmental contacts to pursue several motion or force objectives while respecting constraints such as balance, joint limits and friction. It is a family of hierarchical or optimisation-based methods, not one algorithm; implementations may output joint positions, accelerations or torques.
Models & learning
World model
A world model is a learned predictive model of how an environment changes, often conditioned on a robot’s current state and candidate actions. It may forecast pixels, latent states, rewards or other task-relevant quantities. A policy or planner can use those predictions to compare possible futures before commanding the physical robot.
Models & learning
World-action model
A world-action model is an emerging, non-standardised name for a robot model that couples prediction of future world states with generation of executable actions, often by adapting a video or world-model backbone as a policy. It differs from an action-conditioned world model that only predicts consequences of supplied actions, and from Barrett’s WAM, the Whole Arm Manipulator.