AiVibeLead-Through Programming
Lead-through programming, also called hand-guided or kinaesthetic teaching, teaches a robot by physically moving its arm through the required positions or paths while the controller records them, instead of jogging it with a pendant.
The operator holds the arm, or a handle on the tool, and pushes it to each position. The robot either compensates for gravity and follows the applied force using joint torque sensing, or interprets readings from a wrist force/torque sensor as motion commands. Individual points or continuous paths are recorded and then combined with logic and I/O in the program.
Lead-through teaching is widely used on collaborative robots, where joint torque sensing makes it straightforward, and on conventional robots fitted with force/torque sensors for tasks such as polishing or adhesive paths. It lowers the skill barrier for programming and is also used to collect demonstrations for imitation learning.
Taught paths reflect the operator's hand movements and may need smoothing or editing for accuracy. ISO 10218 and ISO/TS 15066 describe hand guiding as a collaborative operation method with its own requirements, and the risk assessment determines whether hand guiding is suitable for a given application, tool and workpiece.
Key points
- The robot is taught by moving the arm physically rather than jogging
- Relies on joint torque sensing or a wrist force/torque sensor
- Common on cobots and for recording demonstrations for imitation learning
- Hand guiding is a collaborative operation method in ISO/TS 15066
Where AiVibe comes in
AiVibe designs and manufactures the AiAmbA AI Factory, whose edge devices and AI agents let people talk to robot controllers in plain language. Robotics perception is an AiAmbA use case, and robot safety functions follow ISO 10218 and never depend on the AI layer.