Decision-Making Technology for Autonomous Vehicles: Learning-Based Methods, Applications and Future Outlook

Liu, Qi; Li, Xueyuan; Yuan, Shuai; Li, Zirui

doi:10.1109/itsc48978.2021.9564580

Cited by 48 publications

(17 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Their survey in behavioral planning was summarized and did not account for each methodology application. In contrast to [5], a detailed review of BP is introduced by [17]. The topic was discussed comprehensively as they tackled the categorization of the different existing methodologies.…”

Section: Fig 1 Autonomous Vehicle Architecturementioning

confidence: 99%

Behavior Planning for Autonomous Driving: Methodologies, Applications, and Future Orientation

Kassem

2023

MSA Engineering Journal

View full text Add to dashboard Cite

Decision-making is a crucial task for autonomous driving. Taking the wrong decision might cause a cartographical accident. Decision-making implies planning the appropriate behavior based on the current state of the vehicle and its environment. The paper aims to review the current state of the art of behavior Planning for autonomous driving. A basic categorization for behavior planning algorithms is introduced. Besides, a review of different algorithms is discussed with a comparison between different algorithms from the point of view of the suitable scenario. Finally, promising research topics are discussed.

show abstract

Section: Fig 1 Autonomous Vehicle Architecturementioning

confidence: 99%

Behavior Planning for Autonomous Driving: Methodologies, Applications, and Future Orientation

Kassem

2023

MSA Engineering Journal

View full text Add to dashboard Cite

show abstract

“…Therefore, deep reinforcement learning (DRL) algorithms are effective in tasks requiring feature representation and policy learning, e.g., autonomous driving decision-making [11]. Using the functional approximation ability of a deep neural network (DNN), an intelligent controller integrating artificial intelligence technologies such as deep learning (DL) and reinforcement learning (RL) is designed to maintain and avoid obstacles in lanes [12][13][14], decision-making [15][16][17][18][19][20][21], longitudinal control [22], merger maneuvers [23], human-like driving strategies [24][25][26], and other large-scale autonomous driving control tasks. Yingjun Ye et al put forward a framework for decision-making training and learning.…”

Section: Introductionmentioning

confidence: 99%

Generalized Single-Vehicle-Based Graph Reinforcement Learning for Decision-Making in Autonomous Driving

Yang

Liu

et al. 2022

Sensors

Self Cite

View full text Add to dashboard Cite

In the autonomous driving process, the decision-making system is mainly used to provide macro-control instructions based on the information captured by the sensing system. Learning-based algorithms have apparent advantages in information processing and understanding for an increasingly complex driving environment. To incorporate the interactive information between agents in the environment into the decision-making process, this paper proposes a generalized single-vehicle-based graph neural network reinforcement learning algorithm (SGRL algorithm). The SGRL algorithm introduces graph convolution into the traditional deep neural network (DQN) algorithm, adopts the training method for a single agent, designs a more explicit incentive reward function, and significantly improves the dimension of the action space. The SGRL algorithm is compared with the traditional DQN algorithm (NGRL) and the multi-agent training algorithm (MGRL) in the highway ramp scenario. Results show that the SGRL algorithm has outstanding advantages in network convergence, decision-making effect, and training efficiency.

show abstract

“…Autonomous driving is one of the main uses. A comprehensive autonomous driving system integrates sensing, decision-making, and motion-controlling modules [2][3][4]. As the "brains" of connected autonomous vehicles (CAVs) [5], the decision-making module formulates the most reasonable control strategy according to the state feature matrix transmitted by the sensing module, the vehicle state, and the cloud transmission information [6].…”

Section: Introductionmentioning

confidence: 99%

“…The keys of DRL in uncertain interactive traffic scenarios can be summarized as follows: (1) Efficient modeling of interactive traffic scenes and accurate representation of state features. (2) Generating reasonable and cooperative decision-making behaviors based on uncertain scene changes and individual task requirements. The design of the reward function is an essential part of the DRL application.…”

Section: Introductionmentioning

confidence: 99%

Multi-Agent Decision-Making Modes in Uncertain Interactive Traffic Scenarios via Graph Convolution-Based Deep Reinforcement Learning

Gao

Liu

et al. 2022

Sensors

Self Cite

View full text Add to dashboard Cite

As one of the main elements of reinforcement learning, the design of the reward function is often not given enough attention when reinforcement learning is used in concrete applications, which leads to unsatisfactory performances. In this study, a reward function matrix is proposed for training various decision-making modes with emphasis on decision-making styles and further emphasis on incentives and punishments. Additionally, we model a traffic scene via graph model to better represent the interaction between vehicles, and adopt the graph convolutional network (GCN) to extract the features of the graph structure to help the connected autonomous vehicles perform decision-making directly. Furthermore, we combine GCN with deep Q-learning and multi-step double deep Q-learning to train four decision-making modes, which are named the graph convolutional deep Q-network (GQN) and the multi-step double graph convolutional deep Q-network (MDGQN). In the simulation, the superiority of the reward function matrix is proved by comparing it with the baseline, and evaluation metrics are proposed to verify the performance differences among decision-making modes. Results show that the trained decision-making modes can satisfy various driving requirements, including task completion rate, safety requirements, comfort level, and completion efficiency, by adjusting the weight values in the reward function matrix. Finally, the decision-making modes trained by MDGQN had better performance in an uncertain highway exit scene than those trained by GQN.

show abstract

Decision-Making Technology for Autonomous Vehicles: Learning-Based Methods, Applications and Future Outlook

Cited by 48 publications

References 47 publications

Behavior Planning for Autonomous Driving: Methodologies, Applications, and Future Orientation

Behavior Planning for Autonomous Driving: Methodologies, Applications, and Future Orientation

Generalized Single-Vehicle-Based Graph Reinforcement Learning for Decision-Making in Autonomous Driving

Multi-Agent Decision-Making Modes in Uncertain Interactive Traffic Scenarios via Graph Convolution-Based Deep Reinforcement Learning

Contact Info

Product

Resources

About