Multi-Agent DRL-Based Lane Change With Right-of-Way Collaboration Awareness

Zhang, Jiawei; Chang, Cheng; Zeng, Xianlin; Li, Zhiheng

doi:10.1109/tits.2022.3216288

Cited by 30 publications

(6 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In recent years, MARL has been utilized to solve plenty of multi-agent problems, such as traffic control [27], decision-making of autonomous driving [24], [25], [28], games [29], resource allocation [30], etc. Some works have modeled the traffic system with multivehicle scenarios by MARL, which has shown exciting and outstanding performance in lane changing [24], [31], merging [25], intersection [9] scenarios. Nevertheless, these algorithms still fail to guarantee enough security and reliability, which greatly limits further application.…”

Section: A Decision-making Of Cavs At Intersectionsmentioning

confidence: 99%

Cooperative Decision-Making for CAVs at Unsignalized Intersections: A MARL Approach with Attention and Hierarchical Game Priors

Liu¹,

Hang²,

Na³

et al. 2023

Preprint

View full text Add to dashboard Cite

<p>The development of autonomous vehicles has shown great potential to enhance the efficiency and safety of transportation systems. However, the decision-making issue in complex human-machine mixed traffic scenarios, such as unsignalized intersections, remains a challenge for autonomous vehicles. While reinforcement learning (RL) has been used to solve complex decision-making problems, existing RL methods still have limitations in dealing with cooperative decision-making of multiple connected autonomous vehicles (CAVs), ensuring safety during exploration, and simulating realistic human driver behaviors. In this paper, a novel and efficient algorithm, Multi-Agent Game-prior Attention Deep Deterministic Policy Gradient (MA-GA-DDPG), is proposed to address these limitations. Our proposed algorithm formulates the decision-making problem of CAVs at unsignalized intersections as a decentralized multi-agent reinforcement learning problem and incorporates an attention mechanism to capture interaction dependencies between ego CAV and other agents. The attention weights between the ego vehicle and other agents are then used to screen interaction objects and obtain prior hierarchical game relations, based on which a safety inspector module is designed to improve the traffic safety. Moreover, we consider the heterogeneity of human drivers in traffic environments and conduct a series of comprehensive experiments. The proposed approach shows better performance in terms of driving safety, efficiency and comfort than conventional RL algorithms.</p>

show abstract

Section: A Decision-making Of Cavs At Intersectionsmentioning

confidence: 99%

Cooperative Decision-Making for CAVs at Unsignalized Intersections: A MARL Approach with Attention and Hierarchical Game Priors

Liu¹,

Hang²,

Na³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Several studies focused on how to establish reliable V2X communication for cooperative driving [5,6] . Some studies emphasized the self-organized controller design of individual vehicles [7] . Other studies discussed how to formulate a good cooperative driving plan for multiple vehicles, so that these vehicles can pass a certain conflict point (e.g., unsignalized intersection, ramp areas, and working zones) as quickly as possible.…”

Section: Introductionmentioning

confidence: 99%

Theoretical Analysis of Cooperative Driving at Idealized Unsignalized Intersections

Li,

Zhang,

Chen

et al. 2024

Tsinghua Sci. Technol.

Self Cite

View full text Add to dashboard Cite

Cooperative driving is widely viewed as a promising method to better utilize limited road resources and alleviate traffic congestion. In recent years, several cooperative driving approaches for idealized traffic scenarios (i.e., uniform vehicle arrivals, lengths, and speeds) have been proposed. However, theoretical analyses and comparisons of these approaches are lacking. In this study, we propose a unified group-by-group zipper-style movement model to describe different approaches synthetically and evaluate their performance. We derive the maximum throughput for cooperative driving plans of idealized unsignalized intersections and discuss how to minimize the delay of vehicles.The obtained conclusions shed light on future cooperative driving studies.

show abstract

“…To ensure that vehicles can handle a wide range of driving scenarios, learning-based methods [9][10][11][12][13][14][15][16] have become the mainstream approach in modern autonomous driving systems for behavior decisions. These methods are data-driven, using human driving data to train decision models.…”

Section: Introductionmentioning

confidence: 99%

DriveLLaVA: Human-Level Behavior Decisions via Vision Language Model

Zhao,

Yuan,

et al. 2024

Sensors

View full text Add to dashboard Cite

Human-level driving is the ultimate goal of autonomous driving. As the top-level decision-making aspect of autonomous driving, behavior decision establishes short-term driving behavior strategies by evaluating road structures, adhering to traffic rules, and analyzing the intentions of other traffic participants. Existing behavior decisions are primarily implemented based on rule-based methods, exhibiting insufficient generalization capabilities when faced with new and unseen driving scenarios. In this paper, we propose a novel behavior decision method that leverages the inherent generalization and commonsense reasoning abilities of visual language models (VLMs) to learn and simulate the behavior decision process in human driving. We constructed a novel instruction-following dataset containing a large number of image–text instructions paired with corresponding driving behavior labels, to support the learning of the Drive Large Language and Vision Assistant (DriveLLaVA) and enhance the transparency and interpretability of the entire decision process. DriveLLaVA is fine-tuned on this dataset using the Low-Rank Adaptation (LoRA) approach, which efficiently optimizes the model parameter count and significantly reduces training costs. We conducted extensive experiments on a large-scale instruction-following dataset, and compared with state-of-the-art methods, DriveLLaVA demonstrated excellent behavior decision performance. DriveLLaVA is capable of handling various complex driving scenarios, showing strong robustness and generalization abilities.

show abstract

Multi-Agent DRL-Based Lane Change With Right-of-Way Collaboration Awareness

Cited by 30 publications

References 50 publications

Cooperative Decision-Making for CAVs at Unsignalized Intersections: A MARL Approach with Attention and Hierarchical Game Priors

Cooperative Decision-Making for CAVs at Unsignalized Intersections: A MARL Approach with Attention and Hierarchical Game Priors

Theoretical Analysis of Cooperative Driving at Idealized Unsignalized Intersections

DriveLLaVA: Human-Level Behavior Decisions via Vision Language Model

Contact Info

Product

Resources

About