Journal
COMPUTATIONAL MECHANICS
Volume 72, Issue 3, Pages 577-591Publisher
SPRINGER
DOI: 10.1007/s00466-023-02279-x
Keywords
Physics-informed incremental learning; GENERIC; Liquid simulation; Dynamic data driven application; Hybrid twins
Ask authors/readers for more resources
Learning and reasoning about physical phenomena is a challenge in robotics, and computational sciences play a key role in finding accurate methods for explaining past events and predicting future situations. This paper proposes a thermodynamics-informed active learning strategy for fluid perception and reasoning from observations. The method demonstrates the importance of physics and knowledge in data-driven modeling and adaptation to low-data regimes.
Learning and reasoning about physical phenomena is still a challenge in robotics development, and computational sciences play a capital role in the search for accurate methods able to provide explanations for past events and rigorous forecasts of future situations. We propose a thermodynamics-informed active learning strategy for fluid perception and reasoning from observations. As a model problem, we take the sloshing phenomena of different fluids contained in a glass. Starting from full-field and high-resolution synthetic data for a particular fluid, we develop a method for the tracking (perception) and simulation (reasoning) of any previously unseen liquid whose free surface is observed with a commodity camera. This approach demonstrates the importance of physics and knowledge not only in data-driven (gray-box) modeling but also in real-physics adaptation in low-data regimes and partial observations of the dynamics. The presented method is extensible to other domains such as the development of cognitive digital twins able to learn from observation of phenomena for which they have not been trained explicitly.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available