10.1109/IROS40897.2019.8967996
https://zenodo.org/records/5599666
oai:zenodo.org:5599666
Silvério, João
João
Silvério
Idiap Research Institute, Martigny, Switzerland
Huang, Yanlong
Yanlong
Huang
Department of Advanced Robotics, Istituto Italiano di Tecnologia, Genova, Italy
Abu-Dakka, Fares J.
Fares J.
Abu-Dakka
Department of Advanced Robotics, Istituto Italiano di Tecnologia, Genova, Italy
Rozo, Leonel
Leonel
Rozo
Bosch Center for Artificial Intelligence, Renningen, Germany
Caldwell, Darwin G.
Darwin G.
Caldwell
Department of Advanced Robotics, Istituto Italiano di Tecnologia, Genova, Italy
Uncertainty-Aware Imitation Learning using Kernelized Movement Primitives
Zenodo
2019
2019-10-20
eng
https://zenodo.org/communities/collaborate_project
https://zenodo.org/communities/eu
Creative Commons Attribution 4.0 International
During the past few years, probabilistic approaches to imitation learning have earned a relevant place in the robotics literature. One of their most prominent features is that, in addition to extracting a mean trajectory from task demonstrations, they provide a variance estimation. The intuitive meaning of this variance, however, changes across different techniques, indicating either variability or uncertainty. In this paper we leverage kernelized movement primitives (KMP) to provide a new perspective on imitation learning by predicting variability, correlations and uncertainty using a single model. This rich set of information is used in combination with the fusion of optimal controllers to learn robot actions from data, with two main advantages: i) robots become safe when uncertain about their actions and ii) they are able to leverage partial demonstrations, given as elementary sub-tasks, to optimally perform a higher level, more complex task. We showcase our approach in a painting task, where a human user and a KUKA robot collaborate to paint a wooden board. The task is divided into two sub-tasks and we show that the robot becomes compliant (hence safe) outside the training regions and executes the two sub-tasks with optimal gains otherwise.
European Commission
10.13039/501100000780
820767
Co-production CeLL performing Human-Robot Collaborative AssEmbly