The paper presents a robotic platform that enables closed‑loop autonomous navigation of liquid droplets on an open surface using model‑based reinforcement learning. A two‑axis tilting board with a silicone oil film moves the droplet while an overhead camera supplies real‑time feedback, and a policy is trained in only 50–150 physical episodes without simulation or analytical models. The system demonstrates zero‑shot transfer to unseen geometries, autonomously discovers an oscillatory depinning strategy to release stuck droplets, and completes the full training pipeline in under 90 minutes.
arXiv:2609.16369v1 Announce Type: new Abstract: Precise manipulation of liquid droplets underpins lab-on-a-chip platforms for diagnostics, chemical synthesis, and biological assays. Yet autonomous dr...
arXiv:2512. 17534v2 Announce Type: replace-cross Abstract: Modeling and controlling fluids is critical across science and engineering.
arXiv:2606. 26154v1 Announce Type: cross Abstract: Autonomous microrobots navigating biological vasculature could enable targeted drug delivery and thrombolysis, yet training control policies for realistic environments remains an open challenge.
The article discusses how glass-box deep reinforcement learning (DRL) can discover actuation strategies for high‑speed, nonlinear, unsteady flows without explicit models, potentially revealing mechanisms beyond classical control. It highlights the challenges of applying DRL to real high‑speed flows, including simulation cost, data efficiency, sensing in extreme environments, reward design, explainability, and generalization across Mach and Reynolds numbers. The authors argue that overcoming these constraints will require physics‑aware learning, robust real‑time operation, and extensive validation to translate DRL capabilities into reliable, certified technology.
arXiv:2511. 06667v2 Announce Type: replace-cross Abstract: With the explosive growth of rigid-body simulators, policy learning in simulation has become the de facto standard for most rigid morphologies.
arXiv:2606. 08405v1 Announce Type: new Abstract: While data-intensive deep reinforcement learning can optimize complex control policies, scientific discovery in physical systems fundamentally requires an interpretable chain of reasoning that connects physical evidence to structured control architectures.
Vision-language-action (VLA) models can learn manipulation skills from demonstrations, but their capabilities are bounded by the skills in the training data. We present InSight, a framework that unlocks autonomous skill acquisition by rendering VLAs steerable at the primitive-action level (e.
arXiv:2606. 24884v1 Announce Type: cross Abstract: Vision-language-action (VLA) models can learn manipulation skills from demonstrations, but their capabilities are bounded by the skills in the training data.
arXiv:2608. 07870v1 Announce Type: new Abstract: Improving sample efficiency remains a core challenge in reinforcement learning (RL), especially in real-world settings like robotics, where data collection is costly.
arXiv:2605. 31286v2 Announce Type: replace-cross Abstract: Real-world household robots require Vision-Language-Action (VLA) foundation models that can acquire reusable manipulation skills across diverse objects, task conditions, and household environments.
The paper presents a method where self‑evolving scientific agents design explicit, neural‑network‑free white‑box controllers for fluid dynamics tasks. By iteratively interpreting simulation data, the agents accumulate control knowledge and refine controller code, ultimately achieving robust control of an underactuated two‑joint swimmer in unsteady flows. The resulting controllers generalize across varying target positions, wake geometries, cylinder counts, and inflow speeds, and 2D control priors successfully transfer to accelerate 3D adaptation.
The paper introduces a self‑evolving scientific agent that uses large language models and iterative code generation to build interpretable, physically‑reasoned white‑box controllers for complex systems. The agent deploys candidate controllers in simulations, diagnoses dynamic behavior from multimodal evidence, and refines source code until a robust policy is achieved. Applied to a nonlinear fluid‑structure interaction problem—a two‑joint dogfish swimmer navigating an unsteady wake—the agent autonomously designs a controller that consistently reaches targets across a wide range of conditions without retraining.