TY - GEN
T1 - Do what I want, not what I did
T2 - 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2016
AU - Paxton, Chris
AU - Jonathan, Felix
AU - Kobilarov, Marin
AU - Hager, Gregory D.
N1 - Funding Information:
This work was supported by NSF NRI 1227277.
Publisher Copyright:
© 2016 IEEE.
PY - 2016/11/28
Y1 - 2016/11/28
N2 - We propose a learning-from-demonstration approach for grounding actions from expert data and an algorithm for using these actions to perform a task in new environments. Our approach is based on an application of sampling-based motion planning to search through the tree of discrete, high-level actions constructed from a symbolic representation of a task. Recursive sampling-based planning is used to explore the space of possible continuous-space instantiations of these actions. We demonstrate the utility of our approach with a magnetic structure assembly task, showing that the robot can intelligently select a sequence of actions in different parts of the workspace and in the presence of obstacles. This approach can better adapt to new environments by selecting the correct high-level actions for the particular environment while taking human preferences into account.
AB - We propose a learning-from-demonstration approach for grounding actions from expert data and an algorithm for using these actions to perform a task in new environments. Our approach is based on an application of sampling-based motion planning to search through the tree of discrete, high-level actions constructed from a symbolic representation of a task. Recursive sampling-based planning is used to explore the space of possible continuous-space instantiations of these actions. We demonstrate the utility of our approach with a magnetic structure assembly task, showing that the robot can intelligently select a sequence of actions in different parts of the workspace and in the presence of obstacles. This approach can better adapt to new environments by selecting the correct high-level actions for the particular environment while taking human preferences into account.
UR - http://www.scopus.com/inward/record.url?scp=85006507589&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85006507589&partnerID=8YFLogxK
U2 - 10.1109/IROS.2016.7759556
DO - 10.1109/IROS.2016.7759556
M3 - Conference contribution
AN - SCOPUS:85006507589
T3 - IEEE International Conference on Intelligent Robots and Systems
SP - 3778
EP - 3785
BT - IROS 2016 - 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 9 October 2016 through 14 October 2016
ER -