ART of PIV: Agentic Real-Time Particle Image Velocimetry for Active Flow Control
Abstract
Particle image velocimetry (PIV) measures fluid motion from images of tracer particles, but its accuracy depends on choices throughout the estimation pipeline, including image preprocessing, flow estimation, and postprocessing. These choices are typically left to expert tuning, and a fixed configuration can become less accurate as conditions change. This matters especially when PIV supplies feedback for real-time control, where measurements must be both accurate and fast, and flow conditions vary. We introduce ART of PIV -- short for Agentic Real-Time and also a nod to the art of tuning a PIV pipeline -- which automates pipeline choice for each image pair. A learned agent selects a configuration according to a chosen measurement objective from a library assembled for a specified speed budget. Across cross-correlation, classical optical-flow, and learning-based estimators, ART of PIV reduces average end-point error (AEPE) by 12.2-22.4 % relative to the best single estimator at matched speed, with gains extending to 1000-4000 image pair/s. In a simulated local velocity regulation task, it reduces mean normalized closed-loop cost by 13.24-13.59 percentage points relative to a tuned fixed estimator, with the same classical controller in both cases. In a tabletop water channel, we illustrate two ways to tune ART of PIV for a fluidic pinball of three rotating cylinders: selecting between complementary optical-flow tunings for accuracy, and selecting regions of interest with coherent rotation or shear using a common flow estimator. For the first variant, we train a DreamerV3 reinforcement learning controller directly in the physical world and demonstrate tracking of a prescribed flow field in the wake of a fluidic pinball.
Related
- Dual Laser and Shadow Particle Image Velocimetry for Multiscale Fluid-Structure Interactions
- Direct Trajectory Reconstruction for Fast 3D X-ray Particle Tracking Velocimetry in Porous Media
- Bayesian inference in active microrheology with wall and particle-particle interactions
- Work to insert a particle into an active fluid
- Unsteady and inertial dynamics of a small active particle in a fluid
BibTeX
@misc{terpin2026agentic,
title = {{ART of PIV: Agentic Real-Time Particle Image Velocimetry for Active Flow Control}},
author = {Antonio Terpin and Francesco Banelli and Alan Bonomi and Raffaello D'Andrea},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.41304},
eprint = {2610.41304},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.41304},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - ART of PIV: Agentic Real-Time Particle Image Velocimetry for Active Flow Control
AU - Antonio Terpin
AU - Francesco Banelli
AU - Alan Bonomi
AU - Raffaello D'Andrea
PY - 2026
DA - 2026/10/30
PB - arXiv
DO - 10.48550/arxiv.2610.41304
UR - https://arxiv.org/abs/2610.41304
AB - Particle image velocimetry (PIV) measures fluid motion from images of tracer particles, but its accuracy depends on choices throughout the estimation pipeline, including image preprocessing, flow estimation, and postprocessing. These choices are typically left to expert tuning, and a fixed configuration can become less accurate as conditions change. This matters especially when PIV supplies feedback for real-time control, where measurements must be both accurate and fast, and flow conditions vary. We introduce ART of PIV -- short for Agentic Real-Time and also a nod to the art of tuning a PIV pipeline -- which automates pipeline choice for each image pair. A learned agent selects a configuration according to a chosen measurement objective from a library assembled for a specified speed budget. Across cross-correlation, classical optical-flow, and learning-based estimators, ART of PIV reduces average end-point error (AEPE) by 12.2-22.4 % relative to the best single estimator at matched speed, with gains extending to 1000-4000 image pair/s. In a simulated local velocity regulation task, it reduces mean normalized closed-loop cost by 13.24-13.59 percentage points relative to a tuned fixed estimator, with the same classical controller in both cases. In a tabletop water channel, we illustrate two ways to tune ART of PIV for a fluidic pinball of three rotating cylinders: selecting between complementary optical-flow tunings for accuracy, and selecting regions of interest with coherent rotation or shear using a common flow estimator. For the first variant, we train a DreamerV3 reinforcement learning controller directly in the physical world and demonstrate tracking of a prescribed flow field in the wake of a fluidic pinball.
ER -