An adaptive coordinator for multi-variable controller via dynamic belief assignment

The stability of a humanoid robot is the base of other complex gestures in different and complicated tasks. Each gesture for different joints needs many controllers. To address the outputs from different controller, an adaptive coordinator for multi-variable controller via dynamic basic belief assignment strategy is proposed in this work. The planar inverted pendulum (PIP) platform, which is a very typical, simplify, cheap and an effective system for verification of a multi-variable controller, can generally imitate the stability of a robot as a whole. For each axis of PIP, there are two control variables. One is the angle of the rod, and the other is the displacement for the base cart. We propose an adaptive coordinator for the fuzzy controller in each axis to construct the final output value of control variable from the only motor in different axes. The adaptive coordinator has a dynamic value represented as the belief degree in the framework of belief functions. For different control areas and moment, the coordinator has an adaptive and dynamic basic belief assignment for the corresponding controller. The control strategy for controller design is based on classical and efficient fuzzy control. Simulation experiment verifies the rationality of the adaptive coordinator as well as the effectiveness of the multi-variable controller.