Based on kinematics characteristic of two wheeled robot and response characteristic of fact motor drive system,every subsystem of fact robot was analyzed.

Combining with the advantages of good protection of global robot,of self equilibrium and easy control of two wheeled robot,of strong obstacle surmounting ability of jumping robot,a throw-able robot that possesses three kinds of basic modalities of global,two wheeled and jumping robots was constructed.

This paper present a novel method to control the balance of a two-wheeled robot by using reinforcement learning and fuzzy neural networks which can guarantees the convergence and rapidity when the model of the robot is not available and the agent has no prior knowledge.

Energy optimization strategy of two-wheeled self-balanced robot based on improved genetic algorithm

The filtered model is applied to the two-wheeled self-balanced robot system.

The method is applied to the two-wheeled self-balanced robot and the experiments of the running state recognition are conducted.

Two-wheeled self-balancing robot, composed of main body and two independently driven wheels, is a simple structure of the wheeled mobile robot similar to the inverted pendulum in principle.

And then this paper introduces the principle and method to tune PID parameter based on Fuzzy control,which suits to control the two-wheeled self-balancing robot.

To the nonlinear,strong-coupling and absolutely unstable characteristics of self-balancing two-wheel robot,a hierarchical fuzzy control method is proposed.