Deriving neural network controllers from neuro-biological data: implementation of a single-leg stick insect controller

摘要: This article presents modular recurrent neural network controllers for single legs of a biomimetic six-legged robot equipped with standard DC motors. Following arguments Ekeberg et al. (Arthropod Struct Dev 33:287–300, 2004), completely decentralized and sensori-driven neuro-controllers were derived from neuro-biological data stick-insects. Parameters the either hand-tuned or optimized by an evolutionary algorithm. Employing identical controller structures, qualitatively similar behaviors achieved stick insect simulations. For wide range perturbing conditions, as instance changing ground height up- downhill walking, swing well stance control shown to be robust. Behavioral adaptations, like varying locomotion speeds, could changes in parameters mechanical coupling environment. To large extent simulated walking behavior matched biological data. example, this was case body support force profiles trajectories under heights. The results suggest that single-leg are suitable modules hexapod controllers, they might therefore bridge morphological- behavioral-based approaches control.