Reinforcement learning of optimal active particle navigation

Abstract

The development of self-propelled particles at the micro- and the nanoscale has sparked a huge potential for future applications in active matter physics, microsurgery, and targeted drug delivery. However, while the latter applications provoke the quest on how to optimally navigate towards a target, such as e.g. a cancer cell, there is still no simple way known to determine the optimal route in sufficiently complex environments. Here we develop a machine learning-based approach that allows us, for the first time, to determine the asymptotically optimal path of a self-propelled agent which can freely steer in complex environments. Our method hinges on policy gradient-based deep reinforcement learning techniques and, crucially, does not require any reward shaping or heuristics. The presented method provides a powerful alternative to current analytical methods to calculate optimal trajectories and opens a route towards a universal path planner for future intelligent active particles.

References in corpus (7)

• Geometric capture and escape of a microswimmer colliding with an obstacle
• Bacteria display optimal transport near surfaces -- bacteria as intermittent active chiral particles: trapped by hydrodynamics, escaping by adhesion
• Microswimmers learning chemotaxis with genetic algorithms
• Hydrodynamics can Determine the Optimal Route for Microswimmer Navigation
• Optimal navigation strategies for microswimmers on curved manifolds
• Hunting active Brownian particles: Learning optimal behavior
• Particle motion nearby rough surfaces

Cited by in corpus (13)

• Optimal active particle navigation meets machine learning
• Optimising low-Reynolds-number predation via optimal control and reinforcement learning
• Jeffery's orbits and microswimmers in flows: A theoretical review
• Predator-prey survival pressure is sufficient to evolve swarming behaviors
• Efficient control protocols for an active Ornstein-Uhlenbeck particle
• Energetic cost of microswimmer navigation: the role of body shape
• Optimal Navigation in Microfluidics via the Optimization of a Discrete Loss
• Learning to swim efficiently in a nonuniform flow field
• Dynamic control of self-assembly of quasicrystalline structures through reinforcement learning
• Reinforcement Learning for Active Matter
• Run-and-Tumble Particles Learning Chemotaxis
• Optimal navigation in two-dimensional flows: Control theory and reinforcement learning
• Learning to traverse convective flows at moderate to high Rayleigh numbers