Research On Automatic Driving Control Of Urban Bus Based On Data Driving

With the development and improvement of automatic driving technology,the urban bus equipped with automatic driving system has been piloted in many places at home and abroad;it gradually comes into view.Autonomous buses has a bright future due to the advantages of reducing greenhouse gas emissions,alleviating traffic pressure and improving productivity,promising development prospects.Autonomous driving motion control system as the core of autonomous driving technology has always been the mainstream of academic and engineering research because of its complexity and importance.The automatic driving bus motion control system can be divided into longitudinal motion control and horizontal motion control,which are respectively aimed at the speed and the position and attitude of the bus control.For the longitudinal and horizontal control of autonomous bus,most of the existing research methods are model-based control methods.However,the mathematical model of bus is difficult to establish accurate model,and then the use of inaccurate model to design controller will lead to poor control performance.This problem can be solved effectively by the data-driven control method.Model-free Adaptive control(MFAC)and Model-free Adaptive Predictive control(MFAPC)are two typical data-driven control methods.With no model for controller design,they are strong adaptability and easy engineering implementation.Therefore,using MFAC and MFAPC algorithm to study the autonomous bus motion control system has important practical significance.The main work of this paper includes:(1)For the longitudinal control problem of autonomous bus,a MFAC controller is designed to track and control the longitudinal speed according to the relationship between actual and expected bus speed.Secondly,the improved model-free Adaptive control(IMFAC)algorithm is proposed to eliminate time delays within the bus system,combining with Smith prediction technology and tracking differentiator idea.Numerical simulation shows the effectiveness of the algorithm proposed in this paper.(2)For the horizontal control of autonomous bus,a Disturbance-improved Model Free Adaptive Predictive Control(D-IMFAPC)algorithm for time-delay disturbance systems is proposed,considering the bus system both has time delay and disturbance.The design process of the controller is derived and stability analysis is given.Numerical simulation shows its effectiveness.In addition,the horizontal motion control of autonomous bus is simplified to a discrete-time nonlinear single input and single output system.The proposed control algorithm is applied to the bus trajectory tracking control for verification.The results show that the proposed algorithm can effectively restrain the bus delay and disturbance in the system;it has a good effect in the horizontal control of autonomous bus.