A Kinesthetic Teaching Framework for Tasks With Contact Transitions and Time-Optimized Execution
Nikolas Thelenberg, Christian Ott
AI summary
Problem
Most kinesthetic teaching methods replay recorded motions but ignore contact transitions, causing dangerous force peaks if operators move too quickly into rigid environments.
Approach
The framework augments compliance control with a state-dependent unilateral damping force that gradually slows the robot near rigid surfaces, then uses convex optimization to generate time-optimal execution trajectories that explicitly respect learned contact transitions.
Key results
- Analytical derivation of a smooth, state-dependent damping coefficient for impact-free teaching
- Explicit integration of contact transition points into a convex time-optimal path parameterization
- Experimental validation on a torque-controlled manipulator demonstrating safe teaching and accelerated execution
- Practical implementation strategies to handle numerical singularities and crossed hyperplanes
Why it matters
Enables safe, intuitive manual programming of contact-heavy tasks while maximizing operational speed for industrial and service robotics.
Abstract
In kinesthetic teaching, a robot is manually guided by a human operator to demonstrate a task. Most methods focus on replaying the recorded motion, but are agnostic to contact transitions, which can be critical when interacting with rigid environments. To overcome this limitation, we propose a framework that allows to teach motions in free space as well as in contact while preventing fast unintended contact transitions. This is accomplished by exploiting a projection-based unilateral damping force that increases close to contact. We derive an explicit analytical expression for the damping characteristics to ensure a safe stop before the contact when no further forces act on the robot. Furthermore, after the teaching, the recorded motion data is utilized to generate a time-optimized trajectory based on convex optimization, in which the contact transitions are explicitly considered. We validated our framework in experiments with a torque-controlled manipulator.