Font Size: a A A

Research On Self-Driving Vehicles Turning Control Algorithm At Intersections Under Vehicular Ad-Hoc Network

Posted on:2022-03-31Degree:MasterType:Thesis
Country:ChinaCandidate:C SunFull Text:PDF
GTID:2492306560955499Subject:Information and Communication Engineering
Abstract/Summary:
Currently the research and development of autonomous driving vehicle(ADV)mainly consider the situation that manual driving vehicles and ADVs run simultaneously on lanes.In order to acquire the information of the vehicle itself and the environment necessary for decision-making and controlling,the ADV under development now is normally equipped with a lot of sensing units,for example,high precision globe positioning system,various types of radar,and video processing systems.Obviously,the current solutions of ADAS or ADV still have some problems in high reliability of driving safety,as well as the vehicle’s cost and price.It could be certain,however,that in the future there are some roads,areas or cities where all the vehicles are totally ADVs,i.e.,without any human driving vehicles in traffic.For such scenarios,the way of environment sensing,traffic instruction indicating,and vehicle controlling should be different from that of upcoming situation mentioned above if the reliability of driving safety and the production cost expectation should be improved significantly.With the anticipation that a more sophisticated vehicle ad-hoc network(VANET)should be an essential transportation infrastructure for future ADV scenarios,the problem of vehicle turning control based on vehicle to everything(V2X)communication at road intersection is studied.Turning control at intersection mainly consists of three basic issues,i.e.,target lane selection,trajectory planning and calculation,and vehicle controlling and tracking.In this thesis,the main contributions are as follows.(1)The architecture design of left turn,right turn,and U-turn control system under the scenario of automatic driving is conceived to form a general frame diagram,including environment perception,trajectory planning,MPC,actuator module and so on.(2)A simple and feasible target lane selection strategy is proposed for multi lanes and multi vehicles full ADV scenarios such as left turn,right turn,and U-turn.At the same time,an approach based on V2 X communication to the problem of controlling the turning maneuver at intersections is proposed,which is including trajectory planning and trajectory tracking control.(3)By using the co-simulation platform of CarSim/Simulink and making full use of the mature vehicle dynamics characteristics in CarSim,the safety and effectiveness of the vehicle turning system designed in this thesis are further verified.The simulation results verify the effectiveness of the design system on the simulation platform.
Keywords/Search Tags:VANET, Autonomous driving, Vehicle turning control, Model predictive control
Related items