Abstract
Our brains are able to exploit coarse physical models
of fluids to solve complex manipulation tasks. There has been
considerable interest in developing such a capability in robots
so that they can autonomously manipulate fluids adapting to
different conditions. In this paper, we investigate the problem of
adaptation to liquids with different characteristics. We develop a
simple training task (stirring with a stick) that enables rapid inference
of the parameters of the liquid with relatively inexpensive
measurement equipment (standard webcams) that robots may be
assumed to have access to in the wild. We perform the inference
in the space of simulation parameters rather than on physically
accurate parameters. This facilitates prediction and optimization
tasks since the inferred parameters may be fed directly to the
simulator. First, we +demonstrate that our “stirring” learner
performs better than when the robot is trained with pouring
actions. Further, we show that our method is able to infer
properties of three very different liquids – water, glycerin and
gel – and improve spillage with increased training. We present
various experimental results performed by executing stirring and
pouring actions on a UR10. We believe that this decoupling
of the training actions from the goal task is a significant first
step towards simple and autonomous learning of the behavior of
different fluids in unstructured environments.
of fluids to solve complex manipulation tasks. There has been
considerable interest in developing such a capability in robots
so that they can autonomously manipulate fluids adapting to
different conditions. In this paper, we investigate the problem of
adaptation to liquids with different characteristics. We develop a
simple training task (stirring with a stick) that enables rapid inference
of the parameters of the liquid with relatively inexpensive
measurement equipment (standard webcams) that robots may be
assumed to have access to in the wild. We perform the inference
in the space of simulation parameters rather than on physically
accurate parameters. This facilitates prediction and optimization
tasks since the inferred parameters may be fed directly to the
simulator. First, we +demonstrate that our “stirring” learner
performs better than when the robot is trained with pouring
actions. Further, we show that our method is able to infer
properties of three very different liquids – water, glycerin and
gel – and improve spillage with increased training. We present
various experimental results performed by executing stirring and
pouring actions on a UR10. We believe that this decoupling
of the training actions from the goal task is a significant first
step towards simple and autonomous learning of the behavior of
different fluids in unstructured environments.
Original language | English |
---|---|
Number of pages | 5 |
Publication status | Published - 29 Jun 2018 |
Event | Robotics: Science and Systems Workshop on Learning and Inference in Robotics: Integrating Structure, Priors and Models - Pittsburgh, United States Duration: 26 Jun 2018 → 30 Jun 2018 |
Conference
Conference | Robotics: Science and Systems Workshop on Learning and Inference in Robotics |
---|---|
Abbreviated title | RSS 2018-LAIR |
Country | United States |
City | Pittsburgh |
Period | 26/06/18 → 30/06/18 |
Fingerprint Dive into the research topics of 'To Stir or Not to Stir: Online Estimation of Liquid Properties for Pouring Actions'. Together they form a unique fingerprint.
Profiles
-
Nick Taylor
- Research Centres and Themes, Energy Academy - Professor
- School of Mathematical & Computer Sciences - Professor
- School of Mathematical & Computer Sciences, Computer Science - Professor
Person: Academic (Research & Teaching)