Learning swimming escape patterns for larval fish under energy constraints

TL;DR

This paper uses reinforcement learning to discover energy-efficient escape patterns in larval fish, including the C-start, revealing principles for optimal swimming under energy constraints and potential robotic applications.

Contribution

It introduces a data-efficient reinforcement learning approach to identify larval fish escape patterns under energy constraints, expanding beyond previous flow simulation methods.

Findings

Identified C-start and efficient escape patterns via reinforcement learning.

Short bursts of acceleration combined with gliding optimize distance under energy limits.

Method can be applied to control energy-constrained aquatic robots.

Abstract

Swimming organisms can escape their predators by creating and harnessing unsteady flow fields through their body motions. Stochastic optimization and flow simulations have identified escape patterns that are consistent with those observed in natural larval swimmers. However, these patterns have been limited by the specification of a particular cost function and depend on a prescribed functional form of the body motion. Here, we deploy reinforcement learning to discover swimmer escape patterns for larval fish under energy constraints. The identified patterns include the C-start mechanism, in addition to more energetically efficient escapes. We find that maximizing distance with limited energy requires swimming via short bursts of accelerating motion interlinked with phases of gliding. The present, data efficient, reinforcement learning algorithm results in an array of patterns that reveal practical flow optimization principles for efficient swimming and the methodology can be transferred to the control of aquatic robotic devices operating under energy constraints.