Can a Compact Neuronal Circuit Policy be Re-purposed to Learn Simple Robotic Control?
This work addresses the challenge of developing efficient and interpretable control policies for robotics, offering a domain-specific solution that is incremental in its approach.
The authors tackled the problem of robotic control by repurposing a biological neural circuit model, specifically from C. elegans, to create Neuronal Circuit Policies (NCPs) that achieve performance comparable to or better than deep learning models while using significantly fewer parameters and enabling interpretable dynamics.
We propose a neural information processing system which is obtained by re-purposing the function of a biological neural circuit model, to govern simulated and real-world control tasks. Inspired by the structure of the nervous system of the soil-worm, C. elegans, we introduce Neuronal Circuit Policies (NCPs), defined as the model of biological neural circuits reparameterized for the control of an alternative task. We learn instances of NCPs to control a series of robotic tasks, including the autonomous parking of a real-world rover robot. For reconfiguration of the purpose of the neural circuit, we adopt a search-based optimization algorithm. Neuronal circuit policies perform on par and in some cases surpass the performance of contemporary deep learning models with the advantage leveraging significantly fewer learnable parameters and realizing interpretable dynamics at the cell-level.