Whole-body simulation of realistic fruit fly locomotion with deep reinforcement learning
Vaxenburg, R.; Siwanowicz, I.; Merel, J.; Robie, A. A.; Morrow, C.; Novati, G.; Stefanidi, Z.; Card, G. M.; Reiser, M. B.; Botvinick, M. M.; Branson, K. M.; Tassa, Y.; Turaga, S. C.
Show abstract
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.
Matching journals
The top 4 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Estimating orientation in Natural scenes: A Spiking Neural Network Model of the Insect Central Complex 95%
- Wing structure and neural encoding jointly determine sensing strategies in insect flight 94%
- A unified mechanism for innate and learned visual landmark guidance in the insect central complex 94%
Similar papers in this journal
Similar papers in this journal
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.