Adaptable Pouring: Teaching Robots Not to Spill using Fast but Approximate Fluid Simulation
- Submitting institution
-
Heriot-Watt University
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 16545792
- Type
- E - Conference contribution
- DOI
-
-
- Title of conference / published proceedings
- Proceedings of Machine Learning Research: Conference on Robot Learning, 13-15 November 2017
- First page
- 77
- Volume
- 78
- Issue
- -
- ISSN
- 2640-3498
- Open access status
- Out of scope for open access requirements
- Month of publication
- November
- Year of publication
- 2017
- URL
-
-
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
4
- Research group(s)
-
-
- Citation count
- -
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- Those tasks which appear to require the least thought in humans are frequently the most difficult to achieve with robots. Pouring of liquids is a task which humans are able to perform intuitively, gauging viscosity and trajectory as they undertake the task, often with little prior knowledge with which to calibrate their actions. Pouring is a task that a robotic care assistant will be expected to perform. This paper presents an approximate simulation approach which enables fast calibration and execution of pouring tasks. This work was well received at the inaugural Conference on Robot Learning.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -
