Yicheng Chen

It is of great significance to construct a networked energy-saving driving strategy method and application framework to solve the problems of traffic disorder, speed fluctuations, and high energy consumption caused by frequent acceleration, deceleration, and lane changing of vehicles in road sections with variable traffic flow. Considering the mixed traffic scenario where autonomous vehicles and manually driven vehicles interact and infiltrate, a hybrid traffic flow vehicle energy-saving driving model was established, and the Dueling Double Deep Q-Network (D3QN) was used to optimize and solve the energy-saving driving model; Selecting Qingdao urban intersections as application scenarios, energy-saving driving strategy application facilities were constructed in simulation experiments to carry out simulation verification of energy-saving driving strategies for mixed traffic flow in the context of vehicle networking. The simulation results show that in different scenarios with different proportions of CAVs, the energy-saving strategy based on D3QN deep reinforcement learning algorithm can achieve fuel savings of 8.41%~6.67% compared to conventional strategies. Compared with the ordinary reinforcement learning algorithm Q-learning, its fuel saving rate is increased by 1.94%~1.5%, and the energy-saving effect becomes more significant with the increase of traffic density; From the perspective of dynamic characteristics, the speed stability under the control of D3QN algorithm is superior to Q-learning algorithm, and significantly better than conventional strategies, further highlighting the comprehensive advantages of D3QN algorithm in optimizing traffic flow status and energy consumption control. The energy-saving driving strategy in the networked environment can reduce fuel consumption caused by speed fluctuations and traffic flow frequency disturbances, and optimize the stability of traffic flow operation.

It is of great significance to construct a networked energy-saving driving strategy method and application framework to solve the problems of traffic disorder, speed fluctuations, and high energy consumption caused by frequent acceleration, deceleration, and lane changing of vehicles in road sections with variable traffic flow. Considering the mixed traffic scenario where autonomous vehicles and manually driven vehicles interact and infiltrate, a hybrid traffic flow vehicle energy-saving driving model was established, and the Dueling Double Deep Q-Network (D3QN) was used to optimize and solve the energy-saving driving model; Selecting Qingdao urban intersections as application scenarios, energy-saving driving strategy application facilities were constructed in simulation experiments to carry out simulation verification of energy-saving driving strategies for mixed traffic flow in the context of vehicle networking. The simulation results show that in different scenarios with different proportions of CAVs, the energy-saving strategy based on D3QN deep reinforcement learning algorithm can achieve fuel savings of 8.41%~6.67% compared to conventional strategies. Compared with the ordinary reinforcement learning algorithm Q-learning, its fuel saving rate is increased by 1.94%~1.5%, and the energy-saving effect becomes more significant with the increase of traffic density; From the perspective of dynamic characteristics, the speed stability under the control of D3QN algorithm is superior to Q-learning algorithm, and significantly better than conventional strategies, further highlighting the comprehensive advantages of D3QN algorithm in optimizing traffic flow status and energy consumption control. The energy-saving driving strategy in the networked environment can reduce fuel consumption caused by speed fluctuations and traffic flow frequency disturbances, and optimize the stability of traffic flow operation.

Connected autonomous vehicles (CAVs) face constraints from multiple traffic elements, such as the vehicle, road, and environmental factors. Accurately quantifying the vehicle’s operational status and driving risk level in complex traffic scenarios is crucial for enhancing the efficiency and safety of connected autonomous driving. To continuously and dynamically quantify the driving risks faced by CAVs in the road environment—arising from the front, rear, and lateral directions—this study focused s on the self-driving particle characteristics that enable CAVs to perceive their surrounding environment and make driving decisions. The vehicle-to-vehicle interaction behavior was analogized to the inter-molecular interaction relationship, and a molecular Morse potential model was applied, coupled with the vehicle dynamics theory. This approach considers the safety margin and the specificity of driving styles. A multi-layer decoder–encoder long short-term memory (LSTM) network was employed to predict vehicle trajectories and establish a risk quantification model for vehicle-to-vehicle interaction behavior. Using SUMO software (win64-1.11.0), three typical driving behavior scenarios—car-following, lane-changing, and yielding—were modeled. A comparative analysis was conducted between the risk field quantification method and existing risk quantification indicators such as post-encroachment time (PET), deceleration rate to avoid crash (DRAC), modified time to collision (MTTC), and safety potential fields (SPFs). The evaluation results demonstrate that the risk field quantification method has the advantage of continuously quantifying risk, addressing the limitations of traditional risk indicators, which may yield discontinuous results when conflict points disappear. Furthermore, when the half-life parameter is reasonably set, the method exhibits more stable evaluation performance. This research provides a theoretical basis for the dynamic equilibrium control of driving risks in connected autonomous vehicle fleets within mixed-traffic environments, offering insights and references for collision avoidance design.

Aiming at the interactive behavior of vehicles changing lanes in the intelligent network traffic environment, the relative position of vehicle, speed, acceleration, and steering angle are introduced to correct the molecular interaction potential, and the vehicle interaction potential model is established. The spatial distribution map of the vehicle interaction potential field under different motion states was drawn, and the changing law of the vehicle interaction potential field was described. By analyzing the longitudinal critical distance of the lane changing safe critical time, the expression of acceptable clearance for lane changing is defined, and the relationship between acceptable clearance and the speed and acceleration of the interactive vehicle is verified by simulation. Combined with the acceptable clearance of lane changing, a lane changing behavior model based on the vehicle interaction potential is established, and the situation of lane changing vehicles subjected to the interaction potential and potential field forces generated by the surrounding vehicles is analyzed, and the driving decision of lane changing vehicles under the action of different potential field forces is given. Compared with the molecular dynamics lane changing model and LS2015 lane changing model, the results show that the vehicle action potential lane changing model can effectively improve the running speed and stability of traffic flow. The research has theoretical significance for the lane changing behavior decisions of networked autonomous vehicles in the future.

To study the lane-change interaction characteristics of intelligent connected vehicles (ICVs) and reduce the risk of vehicle lane-changing decisions, a decision model based on the lane-changing game characteristics of the ICV is proposed in this paper. In the modeling process, the characteristics of vehicle lane-changing interaction behavior are analyzed based on evolutionary game theory and the vehicle game lane-changing payoff functions are quantified. The stability of the game equilibrium points is analyzed by using a dynamic evolution equation, and sensitivity analysis of the main factors affecting vehicle lane changes and the time to the collision of vehicles is conducted. The SUMO software is used to simulate and verify the vehicle game decision model, and the results show that the game decision system converges to different optimal strategy combinations under different traffic conditions, and this model can effectively reduce the decision-making conflict and the collision risk of vehicles.