Adaptive navigation control for a quadruped robot based on ART and fuzzy logic

An adaptive navigation control problem is presented for a quadruped robot in cluttered environments by incorporating the capability of adaptive resonance theory (ART) in stable category recognition into the fuzzy logic control. An ART-based neural network is introduced as an environment identifier for the purpose of adaptive selection of the adequate rule base for the fuzzy controller. Therefore, the proposed adaptive control scheme for the robot navigation is implemented by the adaptive fuzzy rule base in response to changes of the robot´s environment, which can be fine observed by the proposed environment identifier. Some simulation results are presented to illustrate the effectiveness of the proposed algorithm