1) A (human) teacher demonstrates the task: via kinesthetic guiding of the arm, teleoperation or an observed recording. 2) The system records the demonstrations - trajectories, forces, vision, robot state. 3) A policy/skill is extracted from the demonstrations (e.g. via imitation learning / behavior cloning). 4) The robot reproduces and generalizes the task; optionally it improves further (e.g. via additional corrective demonstrations or reinforcement learning).
Hand-coding a robot for each new task is slow, costly and needs experts. Teaching by demonstration lets a non-technical user 'show' the task, and the robot learns it from examples.
The way the task is shown: kinesthetic guiding, teleoperation or video observation.
Official
Capturing trajectories, forces, vision and robot state during the demo.
Official
Turning demonstrations into a policy/skill (e.g. imitation learning / BC).
Official
The robot reproduces the learned task and generalizes it to new conditions.
Official
A policy learned from demonstrations can drift outside the demo distribution, compounding errors (the behavior-cloning problem).
Different human and robot embodiment/kinematics makes transferring demonstrations hard (especially from observation).
Good demonstrations are labor-intensive; inconsistent or suboptimal demos degrade the learned policy.
Early work on programming robots by demonstration (teleoperation and guiding) in industrial and research robotics.
Argall, Chernova, Veloso, Browning publish the canonical survey 'A survey of robot learning from demonstration', framing the field.
Teleoperation and demonstrations at scale feed robotic foundation models and skill libraries (embodied AI).
Time complexity: Nie dotyczy (paradygmat uczenia/HRI, nie algorytm). Space complexity: Nie dotyczy.
Effectiveness depends primarily on demonstration quality and coverage (data), not raw compute; the bottleneck is costly collection of good demonstrations and out-of-distribution generalization.
Kinesthetic guiding, teleoperation or observation (video).
E.g. behavior cloning, inverse RL, dynamic movement primitives.
How many demos are needed to learn and generalize the task.
This describes the phase of reproducing the learned policy; the teaching paradigm itself is not a compute paradigm.
Demonstration collection is sequential (human), but policy training and multiple demo stations can run in parallel.
A teaching/HRI paradigm - independent of accelerator type; kinesthetic demonstration benefits from back-drivable actuation, and policy training may use GPUs.
