Research On Adaptive Cruise Control Capable Of Recognizing The Intention Of Vehicle Merging

The adaptive cruise control system is an important part of the intelligent driving assistance system,which can effectively improve the driver’s fatigue driving problem and improve the driver’s comfort.Most of the traditional ACC system can only identify the vehicles in the owner-vehicle lane.However,when the vehicles in the side-lane are parallel,only when the side-lane vehicle completely enters the owner-vehicle lane will the target of the ACC system follow the vehicle change.Therefore,the target update and control of the traditional ACC system are relatively lagging behind.In order to improve the comfort and safety of the ACC system,an improved ACC system which can recognize the intention of parallel vehicles is proposed.The main research contents are as follows:Firstly,the hierarchical architecture of ACC system is determined,and the lower controller is designed.The inverse model of the drive system and the inverse model of the brake system were designed and built in Simulink to prevent frequent switching between the drive and the brake.The logic module of the drive/brake switching was designed,and the control strategy of feedforward and feedback was added into the lower controller.Using typical signals to verify it,the results show that the lower controller can follow the expected acceleration effectively.Secondly,design the side-lane vehicle cut-in identification model.Samples were screened from the motion data set to construct a training set and a test set,and characteristic parameters were selected and discretized by using the chi-square splitting algorithm.On the basis of the score search-based network structure learning,random sampling was added to avoid local optimum,and the optimal network structure was selected by constructing a Markov chain close to the target’s stationary distribution and iterating it repeatedly until it converged to a stationary state.The Bayesian estimation method was used to learn network parameters and build a side-lane vehicle cut-in identification model based on the Bayesian Network.Test samples are used to verify the effect of the model,and the results show that the model can effectively identify the intention of merging vehicles.Then,In the upper control of the ACC system,the recognition result of the paralleling intention of the side-car is integrated,and the upper control algorithm of the ACC system is designed based on the MPC.The intention recognition model is used to calculate the probability of merging by the side car.If the probability of merging is greater than 50%,a virtual vehicle ahead is established in front of the vehicle,and the ACC system updates the following target and follows the virtual vehicle ahead.If the probability of merging is less than or equal to 50 %,then continue to follow the preceding vehicle Based on 5 state variables,build an ACC system follow-up prediction model.Based on the relative speed and the following distance error,the following performance index is established,and soft constraints are applied.Finally,the objective constraint solving problem is transformed into a quadratic programming problem,and the optimal solution is obtained.Finally,a joint simulation platform of Simulink and Carsim was built to verify the control effect.The simulations were carried out under three typical speed conditions:low,medium and high speeds.The results show that under the three speed conditions,compared with the traditional ACC system,the improved ACC system has a smooth deceleration process,and the acceleration and acceleration rate of change change smoothly.The distance between following the car is reasonable,the fuel consumption is lower,and the comfort,safety and fuel economy are all effectively improved.Moreover,the speed error and the following distance error of the improved ACC system converge quickly,which proves that the following performance is good.To sum up,the improved ACC system can effectively improve the control lag problem of traditional ACC under the condition of side-car parallel,and improve the comfort,safety and fuel economy.