NeuroCopter is a joint project of the Biorobotics Lab and the Neuroinformatics group at Free University Berlin. Our goal is to control an autonomously flying robot with a brain simulation. We want to develop the neural control architecture for “high-level” tasks such as learning, memory and navigation. The design of this neural architecture will follow an insect model, the honey bee.
The robot will learn to navigate in previously unknown terrain by relying on sensory modalities of bees, i.e. measurements of stereoscopic optical flow, polarization of the sky, color and geometrical terrain features and odor detection. The central brain of the robot is equipped with a spiking neural network of deep architecture where learning is expressed locally by different forms of synaptic plasticity and metaplasticity, reinforced through external and internal rewards. The central network will compute behavioral decisions that drive low level motor plans.
The first version of the robot will rely on simulated neural circuitry; the final version will be equipped with neuromorphic electronics running a network of spiking neurons in hardware structures.