Optimal Navigation in Microfluidics via the Optimization of a Discrete Loss
arXiv:2506.15902 · doi:10.1103/PhysRevLett.134.044001
Abstract
Optimal path planning and control of microscopic devices navigating in fluid environments is essential for applications ranging from targeted drug delivery to environmental monitoring. These tasks are challenging due to the complexity of microdevice-flow interactions. We introduce a closed-loop control method that optimizes a discrete loss (ODIL) in terms of dynamics and path objectives. In comparison with reinforcement learning, ODIL is more robust, up to three orders faster, and excels in high-dimensional action/state spaces, making it a powerful tool for navigating complex flow environments.
21 pages, 13 figures
References in corpus (10)
- A Simplest Swimmer at Low Reynolds Number: Three Linked Spheres
- Efficient representation and approximation of model predictive control laws via deep learning
- Flow Navigation by Smart Microswimmers via Reinforcement Learning
- Zermelo's problem: Optimal point-to-point navigation in 2D turbulent flows using Reinforcement Learning
- Microswimmers learning chemotaxis with genetic algorithms
- Optimizing a DIscrete Loss (ODIL) to solve forward and inverse problems for partial differential equations using machine learning tools
- Direct Collocation Methods for Trajectory Optimization in Constrained Robotic Systems
- Reinforcement learning of optimal active particle navigation
- Independent Control and Path Planning of Microswimmers with a Uniform Magnetic Field
- Flow reconstruction by multiresolution optimization of a discrete loss with automatic differentiation