Perception-driven adaptive CPG-based locomotion for hexapod robots

Abstract

According to neurobiological studies, rhythmic motion in animals is controlled by neural circuits known as central pattern generators (CPGs), which are robust against transient perturbations. Yet, CPGs can integrate sensory feedback that potentially enables adaptive locomotion solutions. Despite previous works, the construction of practical embedded neuromorphic locomotion systems exhibiting similar properties and organization observed in CPGs is still reduced. In this paper a CPG-based control strategy able to modulate motion speed and manage smoothly gait transitions in hexapod robots according to visual information is proposed. Fuzzy logic and finite state machines are the base of the proposed integration mechanism used to map perception into locomotion parameters according to a sensed situation. A vision sensor is integrated in the CPG-based control loop to provide feedback in obstacle avoidance and target tracking behaviors within simplified experimental environments. Experimental results using an hexapod robot confirm both the effectiveness of the proposed control strategy and its use as an experimental embedded platform to investigate further adaptive locomotion, particularly about ways that biological systems fuse information from visual cues to adapt locomotion.