Ground And Air Traffic Control Of Human-in-the-loop

At present,all machines are developing in the direction of intelligence.Autonomous driving vehicles and autonomous driving aircraft are gradually entering people’s lives.Before all the driving vehicles are autonomous,autonomous driving vehicles should interact with human drivers.So,it is particular important for the autonomous driving vehicles to understand drivers’ intentions well,make corresponding decisions,perform corresponding actions,and complete driving tasks safely and efficiently.The control idea of human-in-the-loop control can be applied to this situation.Based on the control idea of human-in-the-loop and use appropriate control strategies can control the mixed ground and air traffic where autonomous driving vehicles and human-driven vehicles are interacted safely and effectively.This thesis includes the following three parts:(1)The human-in-the-loop dynamics model of autonomous driving system and human interaction is established and simplified.It is assumed that human inputs are determined by the system state and the input of the autonomous system at the same time.In addition,in order to solve the problem of modeling external factors,the input generated by human affected by external factors is also added as one of human intentions.(2)In order to cope with the uncertainty of human intentions and the interference of random noise,a control strategy based on stochastic model predictive control for human in-the-loop ground traffic is proposed.The corresponding objective function is established.After that,according to the properties of Gaussian distribution and related theorems,a series of simplifications and transformations are carried out for the objective function.Therefore,the control strategy is transformed into a deterministic model predictive control problem.In addition,an intention exploration item is added to the objective function to explore human intentions.Finally,simulations of two ground traffic driving scenarios(turn left and line merging)are given.It has been proven that the proposed control strategy can control mixed ground traffic(coexistence of human driving and autonomous driving)safely,effectively and robustly.(3)In the air traffic system,aircraft have three-dimensional flight paths,flexible flight and multiple degrees of freedom.A human-in-the-loop air traffic control strategy based on fuzzy control principle is proposed.According to the steps of fuzzy controller design,the inputs and outputs of the fuzzy controller are determined firstly.In order to reduce the huge workload,the inputs are simplified and integrated,at the same time the outputs are restricted.Then,based on the actual experience of the driver and the personnel common sense,the fuzzy inference rules are compiled.Finally,the fuzzy inference method and the method of defuzzification are selected.The control strategy proposed is simulated.It has been proven that our method can control the mixed air traffic(coexistence of human driving and autonomous driving)safely and effectively as well as robustly.