Hardware & control
Joint space
Joint space is a coordinate space whose variables describe a robot's joint configuration, such as revolute-joint angles and prismatic-joint displacements. A point represents one configuration subject to the robot model and joint limits; a path or trajectory represents how that configuration changes.
Also known as: configuration space coordinates, joint configuration space
Updated
Coordinates describe configuration, not appearance
Modern Robotics introduces configuration space as the set of possible robot configurations. For a simple serial arm, joint coordinates often provide a direct parameterisation. A humanoid also has a floating base, so a complete configuration may include base position and orientation in addition to internal joints.
Joint-space distance does not directly measure how far a hand or foot moves. The same angular change can produce very different Cartesian displacement depending on link lengths and the current configuration.
Joint-space and task-space commands differ
A joint-space controller tracks desired joint values. A task-space controller instead targets quantities such as hand pose or centre of mass and uses kinematics or dynamics to obtain joint commands.
Multiple joint configurations can realise the same end-effector pose. Conversely, a requested task-space pose may be unreachable or may require passing near a kinematic singularity. Joint limits, self-collision and balance constraints reduce the usable configurations beyond the nominal number of degrees of freedom.
Data needs an explicit joint convention
A joint vector is meaningful only with names, ordering, units, zero references, signs, limits and robot revision. Quaternions or other floating-base coordinates also need a stated component order and frame.
Dataset producers should distinguish measured positions from commanded targets and record velocities or torques separately. When joint subsets are omitted, say whether the missing joints were fixed, uncontrolled or simply unrecorded. An array length is not a sufficient robot description.
Sources
Related terms
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.
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.
Hardware & control
Task space
Task space is a coordinate space used to express quantities directly relevant to a robot task, such as an end-effector pose, centre-of-mass position, gaze direction, contact force, or several objectives together. It describes what should be achieved, while joint space describes the robot configuration used to achieve it.
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.
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.
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.