Online longitudinal trajectory planning for connected and autonomous vehicles in mixed traffic flow with deep reinforcement learning approach

Cheng, Yanqiu; Hu, Xianbiao; Chen, Kuanmin; Yu, Xinlian; Luo, Yulong

doi:10.1080/15472450.2022.2046472

Cited by 13 publications

(3 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The tracking results showed that, in the two scenarios, based on the DDPG-MPC algorithm's steering wheel angle, the instantaneous change value of the steering wheel angle, and the lateral deviation and angular deviation generated during the tracking process were all better than those of the other two algorithms, which shows the effectiveness of the proposed method. However, the proposed method focuses on solving the problem of the lateral control of autonomous driving trajectory tracking, which belongs to the lower-level control problem of autonomous vehicles, and the closely related trajectory planning problem (Cheng et al, 2023;Li et al, 2022) was not studied. In future work, end-to-end control (Amini et al, 2020;Teng et al, 2022) will be explored, with a focus on the combination of trajectory planning and trajectory tracking.…”

Section: Discussionmentioning

confidence: 99%

“…However, the proposed method focuses on solving the problem of the lateral control of autonomous driving trajectory tracking, which belongs to the lower-level control problem of autonomous vehicles, and the closely related trajectory planning problem (Cheng et al, 2023; Li et al, 2022) was not studied. In future work, end-to-end control (Amini et al, 2020; Teng et al, 2022) will be explored, with a focus on the combination of trajectory planning and trajectory tracking.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

A model predictive control trajectory tracking lateral controller for autonomous vehicles combined with deep deterministic policy gradient

Xie,

Huang,

Luo

et al. 2023

Transactions of the Institute of Measurement and Control

View full text Add to dashboard Cite

To solve the problem of trajectory tracking lateral control in autonomous driving technology, a model predictive control (MPC) controller trajectory tracking lateral control method combined with a deep deterministic policy gradient algorithm (DDPG) is proposed in this paper. This method inputs the real-time state of the vehicle into DDPG to achieve real-time automatic optimization of the prediction time domain and control time domain parameters of the MPC controller, and then affects the specific performance of the MPC controller in trajectory tracking lateral control. Specifically, the state space, action space, and reward function of DDPG are defined, and the automatic driving trajectory tracking lateral controller is designed in combination with the vehicle dynamics model. To reduce the exploration space of DDPG and improve the training efficiency of the entire model, the technique of advantage-disadvantage experience separation and extraction is introduced. Finally, the proposed method was trained and verified in various scenarios, and compared with two other lateral control methods for autonomous driving. The results showed that the learning and training time of the trajectory tracking lateral control method based on DDPG-MPC was shorter than that of the DDPG-based method, and the evaluation indicators in the trajectory tracking control process were better than those of the DDPG-based method and original MPC-based method.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

A model predictive control trajectory tracking lateral controller for autonomous vehicles combined with deep deterministic policy gradient

Xie,

Huang,

Luo

et al. 2023

Transactions of the Institute of Measurement and Control

View full text Add to dashboard Cite

show abstract

“…They realized path generation based on quintic polynomials, and optimized the target trajectory by using cost functions with four indexes including safety, consistency, smoothness and distance from local path to global path. Cheng et al (2022) proposed a deep reinforcement learning method based on time difference to solve the longitudinal trajectory planning of autonomous vehicles at signal-controlled intersections. Xiao et al (2021) [10] proposed the control barrier function method for critical safety control and developed a real-time control framework that combines the optimal trajectory generated with the computational efficiency method that provides safety assurance.…”

Section: Introductionmentioning

confidence: 99%

Research on automatic emergency steering collision avoidance and stability control of intelligent driving vehicle

Liu

Wen²,

Liu³

et al. 2023

Front. Robot. AI

View full text Add to dashboard Cite

In view of the need for emergency steering to avoid collision when the vehicle is in a dangerous scene, and the stability control of the vehicle during collision avoidance. This paper proposes a planning and control framework. A path planner considering the kinematics and dynamics of the vehicle system is used to formulate the safe driving path under emergency conditions. LQR lateral control algorithm is designed to calculate the output steering wheel angle. On this basis, adaptive MPC control algorithm and four-wheel braking force distribution control algorithm are designed to achieve coordinated control of vehicle driving stability and collision avoidance safety. The simulation results show that the proposed algorithm can complete the steering collision avoidance task quickly and stably.

show abstract

Online inference of lane changing events for connected and automated vehicle applications with analytical logistic diffusion stochastic differential equation

Chen

et al. 2022

Transportation Research Part C: Emerging Technologies

View full text Add to dashboard Cite

Online longitudinal trajectory planning for connected and autonomous vehicles in mixed traffic flow with deep reinforcement learning approach

Cited by 13 publications

References 25 publications

A model predictive control trajectory tracking lateral controller for autonomous vehicles combined with deep deterministic policy gradient

A model predictive control trajectory tracking lateral controller for autonomous vehicles combined with deep deterministic policy gradient

Research on automatic emergency steering collision avoidance and stability control of intelligent driving vehicle

Online inference of lane changing events for connected and automated vehicle applications with analytical logistic diffusion stochastic differential equation

Contact Info

Product

Resources

About