Nowadays, the rapidly developing Connected and Autonomous Vehicle (CAV) provides
a new mode of intersection vehicle cooperative control, which can optimize
vehicle trajectories and signal phases in real time and reduce intersection
delays through the advantages of vehicle-road cooperative information
interaction and the high controllability of CAV. In this paper, the intersection
of Jintong West Road and Guanghua Road in Beijing is taken as the research
object, and the vehicle trajectory constraints, acceleration constraints, speed
constraints, safe driving constraints, signal switch constraints and traffic
signal control constraints are set up with the minimization of traffic delay as
the objective function. The DQN deep reinforcement learning network is
constructed based on vehicle states, vehicle actions, reward functions, and
update rules, and starts learning and updating to generate the target network.
Then, SUMO software is used to simulate and test and compare the trajectory
optimization process. Firstly, the road network environment is constructed and
the signal light phases are set, and then the parameters of each vType and
vehicle are set according to the existing data, so that the traffic simulation
is as consistent as possible with the actual situation. Then we take 1s as a
step, export the state data of the vehicle at each step through the TraCI
interface, use the trajectory optimization model to control the acceleration of
the vehicle and the state of the signal light, and feedback the control results
in real time, and finally compare the indexes before and after the optimization.
It is found that the trajectory optimization scheme not only improves the
traffic condition of the intersection, but also reduces the average
CO, CO2 emission and fuel
consumption by 11.6%, 8.5% and 20.3%, respectively.