Project page for CoRL 2018 paper on physically consistent GMM and DS learning.
This project is maintained by nbfigueroa
Following we list all of the code repositories made available for this project, including:
Code for Learning GMM and DS in MATLAB:
Code for Executing Learned DS models in C++:
Code for Executing Learned DS models in ROS:
Code for Executing Manipulation Tasks on a KUKA-LWR 4+/Gazebo (in ROS):
Code for Executing Navigation Tasks on Gazebo (ROS) simulation of Quickie Salsa-M Wheelchair:
Code for Recording Kinesthetic Demonstrations in ROS (arm states, sensors and gripper states):
 Figueroa, N. and Billard, A. (2018) “A Physically-Consistent Bayesian Non-Parametric Mixture Model for Dynamical System Learning”. In Proceedings of the 2nd Conference on Robot Learning (CoRL). [pdf]
Nadia Figueroa (nadia.figueroafernandez AT epfl dot ch)
This work was supported by the EU project Cogimon H2020-ICT-23-2014.