Learning to serve: an experimental study for a new learning from demonstrations framework

by   Okan Koc, et al.

Learning from demonstrations is an easy and intuitive way to show examples of successful behavior to a robot. However, the fact that humans optimize or take advantage of their body and not of the robot, usually called the embodiment problem in robotics, often prevents industrial robots from executing the task in a straightforward way. The shown movements often do not or cannot utilize the degrees of freedom of the robot efficiently, and moreover suffer from excessive execution errors. In this paper, we explore a variety of solutions that address these shortcomings. In particular, we learn sparse movement primitive parameters from several demonstrations of a successful table tennis serve. The number of parameters learned using our procedure is independent of the degrees of freedom of the robot. Moreover, they can be ranked according to their importance in the regression task. Learning few parameters that are ranked is a desirable feature to combat the curse of dimensionality in Reinforcement Learning. Preliminary real robot experiments on the Barrett WAM for a table tennis serve using the learned movement primitives show that the representation can capture successfully the style of the movement with few parameters.


page 2

page 6


Adaptation and Robust Learning of Probabilistic Movement Primitives

Probabilistic representations of movement primitives open important new ...

Bimanual rope manipulation skill synthesis through context dependent correction policy learning from human demonstration

Learning from demonstration (LfD) provides a convenient means to equip r...

Learning Humanoid Robot Motions Through Deep Neural Networks

Controlling a high degrees of freedom humanoid robot is acknowledged as ...

Human movement augmentation and how to make it a reality

Augmenting the body with artificial limbs controlled concurrently to the...

Residual Robot Learning for Object-Centric Probabilistic Movement Primitives

It is desirable for future robots to quickly learn new tasks and adapt l...

Incremental Learning of Probabilistic Movement Primitives (ProMPs) for Human-Robot Cooperation

For a successful deployment of physical Human-Robot Cooperation (pHRC), ...

Phase Portraits as Movement Primitives for Fast Humanoid Robot Control

Currently, usual approaches for fast robot control are largely reliant o...

Please sign up or login with your details

Forgot password? Click here to reset