A Proposal of Continuous Time Recurrent Neural Networks with Neuromodulatory Bias for Adaptation to Un-experienced Environments

Regardless of complex, unknown, and dynamically-changing environments, living creatures can recognize situated environments and behave adaptively in real-time. However it is impossible to prepare optimal motion trajectories with respect to every possible situations in advance. The key concept for realizing the environmental cognition and motor adaptation is a context-based elicitation of constraints which are canalizing well-suited sensorimotor coordination. For this aim, in this study, we propose a polymorphic neural networks model called CTRNN+NM (CTRNN with neuromodulatory bias). The proposed model is applied to two dimensional arm-reaching movement control under various viscous force fields. Simulation results indicate that the proposed model inherits high robustness even though it is situated in unexperienced environments, which have similar rotation, but different size of viscous force, because it evolved "how to adapt" instead of "how to move."