A cooperative lane change approach for heterogeneous platoons under different communication topologies

Nie, Guangming; Xie, Bo; Lu, Huiqiu; Tian, Yantao

doi:10.1049/itr2.12128

Cited by 9 publications

(7 citation statements)

References 58 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The RL agent has the action space of size 5 to choose among the 5 possible driving actions:

A\{ {\rm{lane - left,}} {\rm{idle,}}{\rm{lane - right,}}{\rm{faster,}}{\rm{slower}}\}

. Through the interaction with other vehicles, determine the acceleration of the ego vehicle, whether to change lanes [34] to accelerate or to give way. Since this paper uses the GAIL‐based algorithm, it is not necessary to provide any environmental reward function for training.…”

Section: Methodsmentioning

confidence: 99%

HKGAIL: Policy shaping via integrating human knowledge with generative adversarial imitation learning

Peng

Tan

2022

IET Intelligent Trans Sys

View full text Add to dashboard Cite

Generative adversarial imitation learning (GAIL) has shown good results in several research areas by taking advantage of generative adversarial networks. However, GAIL lacks a reward mechanism and usually adopts a model-free approach based on stochastic policies, which is not ideal for solving complex, dynamically uncertain population intelligence problems, especially in the face of autonomous driving environments. In this paper, a policy framework is shaped by combining the human knowledge with GAIL (HKGAIL). HKGAIL embeds human decision models into the learning process to infer the underlying structure of expert demonstrations. The skills learned from expert demonstrations can directly guide the actions (policies) of the learning process of the agents, and the policies can be optimized through the feedback function of the discriminator. Experiments on both driving and landing tasks show that HKGAIL was able to better fit the policy close to the expert, and was 16.2% safer than GAIL for the driving task.

show abstract

“…The RL agent has the action space of size 5 to choose among the 5 possible driving actions:

A\{ {\rm{lane - left,}} {\rm{idle,}}{\rm{lane - right,}}{\rm{faster,}}{\rm{slower}}\}

Section: Methodsmentioning

confidence: 99%

HKGAIL: Policy shaping via integrating human knowledge with generative adversarial imitation learning

Peng

Tan

2022

IET Intelligent Trans Sys

View full text Add to dashboard Cite

show abstract

“…In [16,18], and [20], the strategy was implemented through a finite state machine (FSM) to describe the operating process of different maneuvers. Platoon lane change strategies can be observed in [21]. In [22], a management strategy for multiple vehicle joining and leaving a platoon simultaneously was proposed.…”

Section: Maneuver Management Strategymentioning

confidence: 99%

An extendable maneuver management framework with fault‐tolerant mechanism for vehicle platoon control system in highway scenario

Liu

Luo

et al. 2023

IET Intelligent Trans Sys

View full text Add to dashboard Cite

Vehicle platoons can encounter many complex scenarios in practice that were not considered in the design, which reveals the need to add new maneuvers. Platoon control system will face the challenge of the lack of maneuver scalability in practical applications. To address this problem, this study introduces an extendable maneuver management framework with fault‐tolerant mechanism on the basis of the hierarchical architecture for the platoon control system. Maneuvers and roles are two dimensions, based on which the management strategies are decoupled. They enable each vehicle in the platoon to execute management strategies of various maneuvers and make it possible to expanding new behaviors into existing strategies. The fault‐tolerant mechanism is designed as a maneuver triggered by hardware failures to remain safe before taking over. Furthermore, three typical maneuvers are selected for case studies to illustrate the management strategies in this framework. Finally, a comprehensive simulation scenario integrating different maneuvers is designed and a real‐world implementation using micro‐vehicles is conducted. The results demonstrate that the proposed two‐dimensional framework could effectively address various maneuvers and satisfy the computational real‐time requirements.

show abstract

“…They also studied two types of ad-hoc platoon formation and platoon dissolution strategies in [22]. And the platoon lane change strategies can be seen in [23]. In [24], the management strategy for multiple vehicle joining and leaving the platoon simultaneously was proposed.…”

Section: A Maneuver Management Strategymentioning

confidence: 99%

An Extendable Maneuver Management Framework with Fault-Tolerant Mechanism for Vehicle Platoon Control System in Highway Scenario

Liu¹,

Luo²,

Li³

et al. 2022

Preprint

View full text Add to dashboard Cite

Vehicle platoon often face the problem of lack of scalability of maneuvers in practical applications. Once a new scenario is added, the original program may no longer be available. To deal with this problem, this paper introduces a two-dimensional maneuver management framework with faulttolerant mechanism on the basis of the proposed hierarchical architecture for the platoon control system. Maneuvers and roles are two dimensions, based on which the management strategies are decoupled. This makes each vehicle in the platoon has the ability to execute management strategies of various maneuvers and the new maneuver could be extended without revising the existing part. The fault-tolerant mechanism is designed as a maneuver triggered by hardware failures to keep safe before taking over. Furthermore, three typical maneuvers are selected for case studies to illustrate how the management strategies in this framework work. Finally, a comprehensive simulation scenario integrating different maneuvers is designed and a real-world implementation using micro-vehicles is conducted. Result shows that the proposed two-dimensional framework could effectively deal with various maneuvers and satisfy the computational real-time requirements.

show abstract

A cooperative lane change approach for heterogeneous platoons under different communication topologies

Cited by 9 publications

References 58 publications

HKGAIL: Policy shaping via integrating human knowledge with generative adversarial imitation learning

HKGAIL: Policy shaping via integrating human knowledge with generative adversarial imitation learning

An extendable maneuver management framework with fault‐tolerant mechanism for vehicle platoon control system in highway scenario

An Extendable Maneuver Management Framework with Fault-Tolerant Mechanism for Vehicle Platoon Control System in Highway Scenario

Contact Info

Product

Resources

About