Predictive Freeway Overtaking Strategy for Automated Vehicles Using Deep Reinforcement Learning

Li, Teng; Deng, Zejian; Wang, Hong; Cao, Dongpu

doi:10.1109/cvci47823.2019.8951536

Cited by 13 publications

(5 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Ha [45] used the graph convolutional network and the DDPG to control the CAVs platoon by the multi‐agent method and improved the road capacity. Liu [46] combined deep learning with RL, and used the long short‐term memory (LSTM) to predict the longitudinal and the lateral movements of vehicles. Gao [47] proposed a data‐driven CACC control method based on the RL to optimize the headway, speed, and acceleration of the first vehicle in the driving process of platoon members.…”

Section: Related Workmentioning

confidence: 99%

Altruistic cooperative adaptive cruise control of mixed traffic platoon based on deep reinforcement learning

Cai

Chen

et al. 2023

IET Intelligent Trans Sys

View full text Add to dashboard Cite

Cooperative adaptive cruise control (CACC) realizes efficient, intelligent control of vehicle acceleration, deceleration, and steering, through inter‐vehicle communication and cooperative control. However, the close combination of the platoon makes it difficult for other vehicles to cut‐in, which can lead to severe traffic jams on certain sections of the road. The control effect of the CACC depends on the platoon penetration rate, which is the percentage of connected and autonomous vehicles (CAVs) in the total number of platoon members. There is no quantitative control method for different penetration rates, and it is difficult to quantify the impact of CACC vehicles on traffic. Therefore, this paper proposes an innovative CACC control method based on deep reinforcement learning (DRL). First, the altruism control and the quantitative control of the car‐following strategy are realized by the virtual car‐following distance method to reduce the exclusivity of the CACC platoon or improve the road utilization efficiency. Second, a more appropriate platoon reward function and collision avoidance method are proposed. Finally, the Car Learning to Act (CARLA) simulator is used. The obtained results confirm that the CACC control of CAVs based on DRL can absorb speed oscillation and improve fuel economy.

show abstract

Section: Related Workmentioning

confidence: 99%

Altruistic cooperative adaptive cruise control of mixed traffic platoon based on deep reinforcement learning

Cai

Chen

et al. 2023

IET Intelligent Trans Sys

View full text Add to dashboard Cite

show abstract

“…. a e is the derivative of acceleration (also called Jerk [45]), (3) Safety-related reward R s : To ensure driving safety, the AV should learn to keep a safe distance from the leading vehicle in the same lane in the longitudinal direction (x-direction) to reduce collision. Thus, the safety-related reward can be adopted by…”

Section: Reward Functionmentioning

confidence: 99%

“…The model parameters ε and ∆a th were set within the reasonable range. The detailed parameter setting of IDM and MOBIL and the traffic scenario [45] are listed in Table 3.…”

Section: Initial Scenario and Surrounding Vehicles Driving Modelmentioning

confidence: 99%

A Safe and Efficient Lane Change Decision-Making Strategy of Autonomous Driving Based on Deep Reinforcement Learning

Pei

Chen

et al. 2022

Mathematics

View full text Add to dashboard Cite

As an indispensable branch of machine learning (ML), reinforcement learning (RL) plays a prominent role in the decision-making process of autonomous driving (AD), which enables autonomous vehicles (AVs) to learn an optimal driving strategy through continuous interaction with the environment. This paper proposes a deep reinforcement learning (DRL)-based motion planning strategy for AD tasks in the highway scenarios where an AV merges into two-lane road traffic flow and realizes the lane changing (LC) maneuvers. We integrate the DRL model into the AD system relying on the end-to-end learning method. An improved DRL algorithm based on deep deterministic policy gradient (DDPG) is developed with well-defined reward functions. In particular, safety rules (SR), safety prediction (SP) module and trauma memory (TM) as well as the dynamic potential-based reward shaping (DPBRS) function are adopted to further enhance safety and accelerate learning of the LC behavior. For validation, the proposed DSSTD algorithm is trained and tested on the dual-computer co-simulation platform. The comparative experimental results show that our proposal outperforms other benchmark algorithms in both driving safety and efficiency.

show abstract

“…In self-driving vehicles, overtaking trajectories are computed in planning modules by decision-making algorithms. Different types of decisionmaking algorithms are available in the literature, such as binary decision diagrams (Claussmann et al, 2015), learning-based technologies (Liu et al, 2019(Liu et al, , 2020Mo et al, 2021) model predictive control (MPC), and nonlinear MPC (Palatti et al, 2021;Viana et al, 2019).…”

Section: Related Workmentioning

confidence: 99%

Practical path planning techniques in overtaking for autonomous shuttles

Malayjerdi

Sell

Malayjerdi

et al. 2022

Journal of Field Robotics

View full text Add to dashboard Cite

This paper proposes a reliable optimized sigmoid‐based path planning algorithm that ensures smooth, fast and safe overtaking maneuver, while maintaining the necessary safety distance. In the proposed method, the desired smoothness of trajectories, the changes in steering angle and the lateral acceleration are controlled in a robust way. This paper describes the simulations, and the confirming real‐world experiments, conducted using the autonomous shuttle iseAuto. Our results suggest that the sigmoid A‐star algorithm leads to a smoother and more reliable motion when compared to other two standard methods. Specifically, the abruptness of necessary steering angle changes is reduced by factor of 4, and approaching the level of an experienced driver‐like maneuver.

show abstract

Predictive Freeway Overtaking Strategy for Automated Vehicles Using Deep Reinforcement Learning

Cited by 13 publications

References 15 publications

Altruistic cooperative adaptive cruise control of mixed traffic platoon based on deep reinforcement learning

Altruistic cooperative adaptive cruise control of mixed traffic platoon based on deep reinforcement learning

A Safe and Efficient Lane Change Decision-Making Strategy of Autonomous Driving Based on Deep Reinforcement Learning

Practical path planning techniques in overtaking for autonomous shuttles

Contact Info

Product

Resources

About