Robot learning of container-emptying skills through haptic demonstration

Technical Report (2009)

IRI code



Download the digital copy of the doc pdf document


Locally weighted learning algorithms are suitable strategies for trajectory learning and skill acquisition, in the context of programming by demonstration. Input streams other than visual information, as used in most applications up to date, reveal themselves as quite useful in trajectory learning experiments where visual sources are not available. In this work we have used force/torque feedback through a haptic device for teaching a teleoperated robot to empty a rigid container. Structure vibrations and container inertia appeared to considerably disrupt the sensing process, so a filtering algorithm had to be devised. Then, memory-based LWPLS (locally weighted partial least squares) and non-memory-based LWPR (locally weighted projection regression) algorithms were implemented, their comparison leading to very similar results, with the same pattern as regards to both the involved robot joints and the different initial experimental conditions. Tests where the teacher was instructed to follow a strategy compared to others where he was not lead to useful conclusions that permit devising the new research stages, where the taught motion will be refined by autonomous robot rehearsal through reinforcement learning.


intelligent robots, manipulators, robot programming, telerobotics.

Author keywords

learning by demonstration, locally weighted learning, manipulation skills

Scientific reference

L. Rozo, P. Jiménez and C. Torras. Robot learning of container-emptying skills through haptic demonstration. Technical Report IRI-TR-09-05, Institut de Robòtica i Informàtica Industrial, CSIC-UPC, 2009.