Research On Cooperative Adaptive Cruise Control (CACC) Considering Vehicle Cut-in Situation

With the rapid development and updating of intelligent transportation systems,cooperative adaptive cruise control(CACC)has gradually become a popular research direction in the field of intelligent transportation.Compared with the traditional adaptive cruise technology(ACC),CACC has the advantages of strong reliability and faster data transmission,as well as higher safety and fuel economy.This paper studies the decision-making control model of multi-vehicle platooning cooperative driving.Different from the traditional CACC model based on rule control,the platoon can only respond after the incoming vehicle has entered the target lane.This paper chooses reinforcement learning to solve the problem of CACC platooning.Acceleration decision control problem during driving.All vehicles in the queue except the head vehicle share the same reinforcement learning neural network,which makes action decisions.This paper first studies the decision-making control of CACC platooning on a single lane,analyzes the influencing factors of CACC platooning decision-making,establishes a single-lane CACC platooning Markov decision-making process,and uses DQN enhancement based on multivehicle network sharing.The learning method optimizes the acceleration decision-making control strategy;secondly,based on the single-lane CACC platoon-following decision-making control model,a CACC control model considering vehicles merging into the platoon is established.The influencing factors of vehicle-following decision-making in the entire merging process are analyzed,and the CACC vehicle-following Markov decision-making process considering the merging of vehicles is established,and the DQN reinforcement learning method is used to train and optimize the model.In order to verify the validity and feasibility of the model,a co-simulation was carried out through the traffic simulation software SUMO,and a comparative experiment was carried out with the traditional platoon control model.The results of simulation and experiments show that the single-lane CACC car following model proposed in this paper can improve the driving efficiency of the platoon and improve the fuel economy on the basis of ensuring the stability of the platoon.The proposed CACC control model considering vehicle merging and queuing can ensure that the queuing and merging vehicles can change lanes cooperatively during the entire merging process,improve the stability of the platoon during the merging process,and effectively improve lane changing.effectiveness.