Autonomous Droplet Navigation via Model-Based Reinforcement Learning
Summary
This paper presents a model-based reinforcement learning approach for autonomous droplet navigation in microfluidic platforms, achieving reliable navigation through complex geometries with zero-shot transfer from simpler paths.
View Cached Full Text
Cached at: 09/16/26, 08:49 AM
# Autonomous Droplet Navigation via Model-Based Reinforcement Learning Source: [https://arxiv.org/abs/2609.16369](https://arxiv.org/abs/2609.16369) [View PDF](https://arxiv.org/pdf/2609.16369) > 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\. ## Submission history From: Rajneesh Anand \[[view email](https://arxiv.org/show-email/ec35ee4e/2609.16369)\] **\[v1\]**Mon, 14 Sep 2026 21:31:28 UTC \(7,158 KB\)
Similar Articles
Offline Reinforcement Learning for Fluid Controls: Data-based Multi-observational Policy Extraction
This paper proposes a novel offline reinforcement learning framework for active flow control that uses a sensor position-conditioned architecture with Point Attention layers to handle varying sensor configurations, enabling data-driven policy extraction without costly online interactions.
Geometry-free prediction of inertial lift forces in microfluidic devices using deep learning
This paper presents a novel deep learning approach to predict inertial lift forces in microfluidic devices without explicit geometric parameters, enabling better generalization to unseen channel cross-sections compared to previous models.
Generative-Model Predictive Planning for Navigation in Partially Observable Environments
This paper introduces BeliefDiffusion, a framework combining diffusion models to represent multimodal belief distributions and Model Predictive Control for planning in partially observable environments, achieving better navigation success and path efficiency than baselines.
Implementation of reinforcement learning in chemical reaction networks: application to phototaxis as curiosity-driven exploration
This paper proposes a framework linking partially observable Markov decision processes (POMDPs) with biochemical reaction dynamics to model phototaxis in unicellular algae, using inverse reinforcement learning to infer behavioral objectives from experimental trajectories.
ReflectDrive-2: Reinforcement-Learning-Aligned Self-Editing for Discrete Diffusion Driving
ReflectDrive-2 is a new discrete diffusion planner for autonomous driving that uses reinforcement learning to enable self-editing of trajectory tokens, achieving high performance and low latency on the NAVSIM benchmark.