Controller parameter tuning based on neural network gradient

A wheeled mobile mechanism with a passive and/or active linkage mechanism for rough terrain environment is developed and evaluated. In our previous research, we developed a switching controller system for wheeled mobile robots in rough terrain. This system consists of two sub-systems: an environment recognition system using self-organizing map (SOM) and an adjustable control system using neural network. In this paper, we focus on the decision of controller parameters using hyperplane of adjusted neural network. Our proposed controller shows almost same performance of adjusted neural network controller in the experiments of the climbing over the stairs. And also, that controller shows better performance than well-tuned PID controller.