A Thermodynamics-informed Active Learning Approach to Perception and Reasoning about Fluids
This work addresses the problem of fluid perception and reasoning in robotics and computational sciences, offering an extensible approach for applications like cognitive digital twins, though it appears incremental as it builds on existing physics-informed methods.
The authors tackled the challenge of learning and reasoning about fluid dynamics from observations by proposing a thermodynamics-informed active learning strategy, achieving a method that can track and analyze previously unseen liquids using only a commodity camera.
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 analysis (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 (grey box) modeling but also in the correction for real physics adaptation in low data regimes and partial observations of the dynamics. The method presented 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.