Flow-Aware Navigation of Magnetic Micro-Robots in Complex Fluids via PINN-Based Prediction

Abstract

While magnetic micro-robots have demonstrated significant potential across various applications, including drug delivery and microsurgery, the open issue of precise navigation and control in complex fluid environments is crucial for in vivo implementation. This paper introduces a novel flow-aware navigation and control strategy for magnetic micro-robots that explicitly accounts for the impact of fluid flow on their movement. First, the proposed method employs a Physics-Informed U-Net (PI-UNet) to refine the numerically predicted fluid velocity using local observations. Then, the predicted velocity is incorporated in a flow-aware A* path planning algorithm, ensuring efficient navigation while mitigating flow-induced disturbances. Finally, a control scheme is developed to compensate for the predicted fluid velocity, thereby optimizing the micro-robot's performance. A series of simulation studies and real-world experiments are conducted to validate the efficacy of the proposed approach. This method enhances both planning accuracy and control precision, expanding the potential applications of magnetic micro-robots in fluid-affected environments typical of many medical scenarios.

Figures (11)

• Figure 1: Overview of the proposed framework. The flow velocity is initially predicted and refined using the Finite Volume Method (FVM) and Physics-Informed Neural Networks (PINNs), then leveraged for path planning and disturbance compensation in dynamic microenvironments.
• Figure 2: The flow prediction framework. The velocity prediction is formulated as a PDE problem. The initial velocity map is obtained using the finite volume method (FVM) and then refined by the PI-UNet model, which integrates local observations and PDE residual loss for improved accuracy.
• Figure 3: Example of robot navigation in the flow channel. The background color represents flow velocity, where different paths are chosen in downstream and upstream scenarios to minimize travel time.
• Figure 4: Comparison of different flow prediction methods across two cases. The first column represents the ground truth. Flow velocity is normalized within the range of 0 to 1, with colors transitioning from blue (low velocity) to red (high velocity).
• Figure 5: Evaluation of the path planning with different methods and scenarios. Each bar shows the average path length / time over 10 channels in the dataset, and the values for each channel are also plotted as scattered diamond-shaped points.