Optimal active particle navigation meets machine learning

Abstract

The question of how "smart" active agents, like insects, microorganisms, or future colloidal robots need to steer to optimally reach or discover a target, such as an odor source, food, or a cancer cell in a complex environment has recently attracted great interest. Here, we provide an overview of recent developments, regarding such optimal navigation problems, from the micro- to the macroscale, and give a perspective by discussing some of the challenges which are ahead of us. Besides exemplifying an elementary approach to optimal navigation problems, the article focuses on works utilizing machine learning-based methods. Such learning-based approaches can uncover highly efficient navigation strategies even for problems that involve e.g. chaotic, high-dimensional, or unknown environments and are hardly solvable based on conventional analytical or simulation methods.

arXiv comment7 pages, 3 figures

References in corpus (42)

• A Brief Survey of Deep Reinforcement Learning
• Active Particles in Complex and Crowded Environments
• Motility-Induced Phase Separation
• Physics of Microswimmers - Single Particle Motion and Collective Behavior
• An Introduction to Deep Reinforcement Learning
• Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model
• Lévy walks
• Perseus: Randomized Point-based Value Iteration for POMDPs
• Phototaxis of synthetic microswimmers in optical landscapes
• Tuned, driven, and active soft matter
• Chemotaxis and auto-chemotaxis of self-propelling artificial droplet swimmers
• Self-Propelled Rods: Insights and Perspectives for Active Matter
• Unstable fronts and stable "critters" formed by microrollers
• Persistent Robotic Tasks: Monitoring and Sweeping in Changing Environments
• Flow Navigation by Smart Microswimmers via Reinforcement Learning
• Active colloidal suspensions: Clustering and phase behavior
• An active approach to colloidal self-assembly
• Active colloids in complex fluids
• Active Particles Bound by Information Flows
• Zermelo's problem: Optimal point-to-point navigation in 2D turbulent flows using Reinforcement Learning
• Feedback-Controlled Active Brownian Colloids with Space-Dependent Rotational Dynamics
• The topography of the environment alters the optimal search strategy for active particles
• Viscotaxis: microswimmer navigation in viscosity gradients
• Machine learning strategies for path-planning microswimmers in turbulent flows
• Optimal steering of a smart active particle
• Finding Efficient Swimming Strategies in a Three Dimensional Chaotic Flow by Reinforcement Learning
• Self-learning how to swim at low Reynolds number
• Microswimmers learning chemotaxis with genetic algorithms
• Hydrodynamics can Determine the Optimal Route for Microswimmer Navigation
• Intrinsically motivated collective motion
• Searching for a source without gradients: how good is infotaxis and how to beat it
• Smart Inertial Particles
• Optimal search strategies of run-and-tumble walks
• Reinforcement learning of optimal active particle navigation
• Reinforcement learning for pursuit and evasion of microswimmers at low Reynolds number
• Independent Control and Path Planning of Microswimmers with a Uniform Magnetic Field
• Optimising low-Reynolds-number predation via optimal control and reinforcement learning
• Optimal navigation strategy of active Brownian particles in target-search problems
• Target search of active agents crossing high energy barriers
• Optimal navigation of microswimmers in complex and noisy environments
• Optimal navigation strategies for microswimmers on curved manifolds
• Unraveling Modular Microswimmers: From Self-Assembly to Ion-Exchange Driven Motors

Cited by in corpus (11)

• A review of active matter reviews
• Optimal tracking strategies in a turbulent flow
• Energetic cost of microswimmer navigation: the role of body shape
• Dynamics of switching processes: general results and applications to intermittent active motion
• Neuroevolution of Decentralized Decision-Making in N-Bead Swimmers Leads to Scalable and Robust Collective Locomotion
• Optimal Control in Soft and Active Matter
• Kinetic theory of decentralized learning for smart active matter
• Reinforcement Learning for Active Matter
• Tailoring the overlap distribution in driven mean-field spin models
• A Hitchhiker's Guide To Active Motion
• Optimal navigation in two-dimensional flows: Control theory and reinforcement learning