Abstract
Humans manipulate fluids intuitively using intuitive approximations of the underlying physical model. In this paper, we explore a general methodology
that robots may use to develop and improve strategies for overcoming manipulation tasks associated with appropriately defined loss functions. We focus on the specific task of pouring a liquid from a container (pourer) to another container (receiver) while minimizing the mass of liquid that spills outside the receiver. We present a solution, based on guidance from approximate simulation, that is fast, flexible and adaptable to novel containers as long as their shapes can be sensed. Our key idea is to decouple the optimization of the parameter space of the simulator from the optimization over action space for determining robot control actions. We perform the former in a training (calibration) stage and the latter during run-time (deployment). For the purpose of this paper we use pouring in both stages, even though separate actions could be chosen. We compare four different strategies for
calibration and three different strategies for deployment. Our results demonstrate that fast fluid simulations are effective, even if they are only approximate, in guiding automatic strategies for pouring liquids.
that robots may use to develop and improve strategies for overcoming manipulation tasks associated with appropriately defined loss functions. We focus on the specific task of pouring a liquid from a container (pourer) to another container (receiver) while minimizing the mass of liquid that spills outside the receiver. We present a solution, based on guidance from approximate simulation, that is fast, flexible and adaptable to novel containers as long as their shapes can be sensed. Our key idea is to decouple the optimization of the parameter space of the simulator from the optimization over action space for determining robot control actions. We perform the former in a training (calibration) stage and the latter during run-time (deployment). For the purpose of this paper we use pouring in both stages, even though separate actions could be chosen. We compare four different strategies for
calibration and three different strategies for deployment. Our results demonstrate that fast fluid simulations are effective, even if they are only approximate, in guiding automatic strategies for pouring liquids.
Original language | English |
---|---|
Title of host publication | Proceedings of Machine Learning Research: Conference on Robot Learning, 13-15 November 2017 |
Editors | Sergey Levine, Vincent Vanhoucke, Ken Goldberg |
Pages | 77-86 |
Number of pages | 10 |
Volume | 78 |
Publication status | Published - 13 Nov 2017 |
Event | 1st Conference on Robot Learning 2017 - Mountain View, United States Duration: 13 Nov 2017 → 15 Nov 2017 http://www.robot-learning.org/ |
Publication series
Name | Proceedings of Machine Learning Research |
---|---|
Volume | 78 |
ISSN (Electronic) | 2640-3498 |
Conference
Conference | 1st Conference on Robot Learning 2017 |
---|---|
Abbreviated title | CoRL 2017 |
Country/Territory | United States |
City | Mountain View |
Period | 13/11/17 → 15/11/17 |
Internet address |
Keywords
- Fluid simulation
- Pouring