The body of an animal influences how its nervous system generates behavior1. Accurately modeling the neural control of sensorimotor behavior requires an anatomically detailed biomechanical representation of the body. Here, we introduce a whole-body model of the fruit fly Drosophila melanogaster in a physics simulator. Designed as a general-purpose framework, our model enables the simulation of diverse fly behaviors, including both terrestrial and aerial locomotion. We validate its versatility by replicating realistic walking and flight behaviors. To support these behaviors, we develop new phenomenological models for fluid and adhesion forces. Using data-driven, end-to-end reinforcement learning we train neural network controllers capable of generating naturalistic locomotion along complex trajectories in response to high-level steering commands. Additionally, we show the use of visual sensors and hierarchical motor control, training a high-level controller to reuse a pre-trained low-level flight controller to perform visually guided flight tasks. Our model serves as an open-source platform for studying the neural control of sensorimotor behavior in an embodied context.

Preprint: www.biorxiv.org/content/early/2024/03/14/2024.03.11.584515

The body of an animal influences how the nervous system produces behavior. Therefore, detailed modeling of the neural control of sensorimotor behavior requires a detailed model of the body. Here we contribute an anatomically-detailed biomechanical whole-body model of the fruit fly Drosophila melanogaster in the MuJoCo physics engine. Our model is general-purpose, enabling the simulation of diverse fly behaviors, both on land and in the air. We demonstrate the generality of our model by simulating realistic locomotion, both flight and walking. To support these behaviors, we have extended MuJoCo with phenomenological models of fluid forces and adhesion forces. Through data-driven end-to-end reinforcement learning, we demonstrate that these advances enable the training of neural network controllers capable of realistic locomotion along complex trajectories based on high-level steering control signals. We demonstrate the use of visual sensors and the re-use of a pre-trained general-purpose flight controller by training the model to perform visually guided flight tasks. Our project is an open-source platform for modeling neural control of sensorimotor behavior in an embodied context.Competing Interest StatementThe authors have declared no competing interest.

What can we learn from a connectome? We constructed a simplified model of the first two stages of the fly visual system, the lamina and medulla. The resulting hexagonal lattice convolutional network was trained using backpropagation through time to perform object tracking in natural scene videos. Networks initialized with weights from connectome reconstructions automatically discovered well-known orientation and direction selectivity properties in T4 neurons and their inputs, while networks initialized at random did not. Our work is the first demonstration, that knowledge of the connectome can enable in silico predictions of the functional properties of individual neurons in a circuit, leading to an understanding of circuit function from structure alone.