aiqbench analysis
This study applies model-based reinforcement learning to solve the complex control problem of navigating liquid droplets through non-linear microfluidic geometries without relying on traditional analytical models or extensive simulation. By leveraging offline-trained policies that generalize zero-shot to unseen paths, the research demonstrates a significant advancement in autonomous lab-on-a-chip systems where classical controllers fail due to partial observability and fluid dynamics constraints.
Autonomous Droplet Navigation via Model-Based Reinforcement Learning
arXiv:2609.16369v1 Announce Type: cross Abstract: Precise manipulation of liquid droplets underpins lab-on-a-chip platforms for diagnostics, chemical synthesis, and biological assays. Yet autonomous droplet transport through confined geometries of varying complexity remains an open challenge. Droplets exhibit contact-angle hysteresis, deformability, and capillary pinning, which make their response to actuation nonlinear and history dependent, that classical controllers and pre-programmed trajectories cannot cope in multi-turn environments. Here we demonstrate autonomous navigation of a liquid droplet through geometries of increasing complexity on a gravity driven (Labyrinth) platform using model-based reinforcement learning. A thin silicone oil film reduces contact-line pinning while two-axis tilt supplies the gravitational driving force, and an overhead camera tracks the droplet in real time. An offline-trained policy discovers effective tilt strategies from limited physical interaction data, without simulation or analytical droplet models. The system operates under partial observability, as oil-film thickness, instantaneous contact angle, and droplet deformation state remain hidden from the controller. Despite these challenges, the learned policy achieves reliable navigation across straight, right-angle, and curved-arc paths, including outside-corner geometries. We further demonstrate that a policy trained on a simpler geometry transfers to complex ones, succeeding zero-shot on right-angle and staircase paths and reaching full success on a curved arc with a fifth of the training data. The findings suggest promising avenues for enabling droplet based microfluidic systems to serve as intelligent chemical laboratories.
Abstract:Precise manipulation of liquid droplets underpins lab-on-a-chip platforms for diagnostics, chemical synthesis, and biological assays. Yet autonomous droplet transport through confined geometries of varying complexity remains an open challenge. Droplets exhibit contact-angle hysteresis, deformability, and capillary pinning, which make their response to actuation nonlinear and history dependent, that classical controllers and pre-programmed trajectories cannot cope in multi-turn environments. Here we demonstrate autonomous navigation of a liquid droplet through geometries of increasing complexity on a gravity driven (Labyrinth) platform using model-based reinforcement learning. A thin silicone oil film reduces contact-line pinning while two-axis tilt supplies the gravitational driving force, and an overhead camera tracks the droplet in real time. An offline-trained policy discovers effective tilt strategies from limited physical interaction data, without simulation or analytical droplet models. The system operates under partial observability, as oil-film thickness, instantaneous contact angle, and droplet deformation state remain hidden from the controller. Despite these challenges, the learned policy achieves reliable navigation across straight, right-angle, and curved-arc paths, including outside-corner geometries. We further demonstrate that a policy trained on a simpler geometry transfers to complex ones, succeeding zero-shot on right-angle and staircase paths and reaching full success on a curved arc with a fifth of the training data. The findings suggest promising avenues for enabling droplet based microfluidic systems to serve as intelligent chemical laboratories.
43 pages, 15 figures, 3 tables including supplementary material. The source code is available via GitHub at this https URL. An archived version of all supplementary movies has also been uploaded to Google Drive: this https URL
Machine Learning (cs.LG); Robotics (cs.RO); Systems and Control (eess.SY); Fluid Dynamics (physics.flu-dyn)
arXiv:2609.16369 [cs.LG]
(or arXiv:2609.16369v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2609.16369 arXiv-issued DOI via DataCite (pending registration)
Full text under the publisher's open licence · 283 words
Related coverage
Autonomous Droplet Navigation via Model-Based Reinforcement Learning: Zero-Shot Transfer and Emergent Dynamics
arXiv · Oct 8, 2026
News
Quantum Computing Report · Jul 25, 2026
Developing Healthcare Robotics with GPU-Native Medical Physics Simulation
NVIDIA · Jul 28, 2026
Introducing Robostral Navigate
Mistral AI · Jul 8, 2026