Whole-Brain Connectomic Graph Model Enables Whole-Body Locomotion Control in Fruit Fly
This work demonstrates that static brain connectomes can be transformed into effective neural policies for embodied learning, potentially advancing bio-inspired robotics and neuroscience.
The authors tackled the problem of using the exact neural architecture of a fruit fly's brain for whole-body locomotion control by developing FlyGM, a connectomic graph model that achieved stable control across diverse tasks with higher sample efficiency and superior performance compared to baseline models.
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.