Whole-Brain Connectomic Graph Model Enables Whole-Body Locomotion Control in Fruit Fly

TL;DR

This paper introduces FlyGM, a biologically inspired neural network model based on the complete connectome of a fruit fly's brain, enabling effective whole-body locomotion control in a simulated environment.

Contribution

It develops a connectome-based graph model for locomotion control, demonstrating its effectiveness over other neural network architectures in embodied reinforcement learning.

Findings

FlyGM achieves stable locomotion control across diverse tasks.

Connectome-based model outperforms rewired, random, and MLP graphs.

Higher sample efficiency and performance with FlyGM.

Abstract

Whole-brain biological neural networks naturally support the learning and control of whole-body movements. However, the use of brain connectomes as neural network controllers in embodied reinforcement learning remains unexplored. We investigate using the exact neural architecture of an adult fruit fly's brain for the control of its body movement. We develop Fly-connectomic Graph Model (FlyGM), whose static structure is identical to the complete connectome of an adult Drosophila for whole-body locomotion control. To perform dynamical control, FlyGM represents the static connectome as a directed message-passing graph to impose a biologically grounded information flow from sensory inputs to motor outputs. Integrated with a biomechanical fruit fly model, our method achieves stable control across diverse locomotion tasks without task-specific architectural tuning. To verify the structural advantages of the connectome-based model, we compare it against a degree-preserving rewired graph, a random graph, and multilayer perceptrons, showing that FlyGM yields higher sample efficiency and superior performance. This work demonstrates that static brain connectomes can be transformed to instantiate effective neural policy for embodied learning of movement control.