An analysis of a riding control algorithm for two wheeled vehicles with a neural network modeling.

This paper discusses the control algorithm of two wheeled vehicle rider based on a sensitivity analysis using the constructed model with neural network system. The main conclusions are: (1) The structured model has a capability of sufficiently representing the control motion of the rider which includes non-linear properties; (2) It is shown that the sensitivity analysis is able to analyze the control algorithm of a driver/rider; (3) From the results of sensitivity analysis, it is found that the rider always changes his steering torque gain to suit the environmental information; and (4) it seems that the rider control behaviour for the two stabilities, directional and standing, are independent of each other. (A)