A Hybrid Deep Reinforcement Learning For Autonomous Vehicles Smart-Platooning

Prathiba, Sahaya Beni; Raja, Gunasekaran; Dev, Kapal; Kumar, Neeraj; Guizani, Mohsen

doi:10.1109/tvt.2021.3122257

Cited by 58 publications

(13 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Edge devices and terminals, such as the vehicles, are inserted so as to expand the network coverage [28] and provide the seamless service [29][30] in 6G. Vehicles can be regarded as the integration of multiple computation and communication modules, aiming at breaking the restriction of 'last one mile' [31]. Generally speaking, the vehiclesassisted B5G networks can provide more tailored and novel services and applications.…”

Section: B Numerical Evaluation Resultsmentioning

confidence: 99%

Energy-Efficient Virtual Resource Allocation of Slices in Vehicles-Assisted B5G Networks

Cao

Zhao

Jindal

et al. 2022

IEEE Trans. on Green Commun. Netw.

View full text Add to dashboard Cite

Academia community started the research beyond 5G (B5G) while 5G systems and networks are still being landed for large-scale commercial applications. In order to enhance the agility and flexibility attributes of B5G networks, network function virtualization (NFV) and network slicing (NS) are attracting extensive research attention. Meanwhile, vehicles are promised to connect to the B5G networks so as to expand the service coverage and reach the 'last one mile'. In this paper, we research the virtual resource allocation of slices in vehicles-assisted B5G networks. We aim at saving total energy cost of deployed slices while ensuring high slice acceptance ratio. We firstly present the system model of vehicles-assisted B5G networks, supporting both virtualization and slicing schemes. Then, we present the energy cost of vehicles-assisted B5G networks. Afterwards, we propose one energy efficient algorithm, abbreviated as Ener-Eff-Slice, to solve the virtual resource allocation of slices in vehiclesassisted B5G networks. Numerical results are recorded, plotted and discussed, which prove the efficacy of our scheme. Finally, we do the conclusion marks and discuss the next-step work.

show abstract

Section: B Numerical Evaluation Resultsmentioning

confidence: 99%

Energy-Efficient Virtual Resource Allocation of Slices in Vehicles-Assisted B5G Networks

Cao

Zhao

Jindal

et al. 2022

IEEE Trans. on Green Commun. Netw.

View full text Add to dashboard Cite

show abstract

“…The authors used the greedy Q-learning technique to find the optimal path that reduces energy consumption. In [ 38 ], the authors proposed a hybrid RL technique with a genetic algorithm (GA) method to control platoon formation and reduce traffic congestion and fuel consumption. GA is adopted to enhance the exploration stage of training, reduce computational costs, and accelerate the convergence rate.…”

Section: Literature Reviewmentioning

confidence: 99%

Comparative Study of Cooperative Platoon Merging Control Based on Reinforcement Learning

Irshayyid

Chen

2023

Sensors

View full text Add to dashboard Cite

The time that a vehicle merges in a lane reduction can significantly affect passengers’ safety, comfort, and energy consumption, which can, in turn, affect the global adoption of autonomous electric vehicles. In this regard, this paper analyzes how connected and automated vehicles should cooperatively drive to reduce energy consumption and improve traffic flow. Specifically, a model-free deep reinforcement learning approach is used to find the optimal driving behavior in the scenario in which two platoons are merging into one. Several metrics are analyzed, including the time of the merge, energy consumption, and jerk, etc. Numerical simulation results show that the proposed framework can reduce the energy consumed by up to 76.7%, and the average jerk can be decreased by up to 50%, all by only changing the cooperative merge behavior. The present findings are essential since reducing the jerk can decrease the longitudinal acceleration oscillations, enhance comfort and drivability, and improve the general acceptance of autonomous vehicle platooning as a new technology.

show abstract

“…As a result, with high sample efficiency, the proposed method may concurrently identify the appropriate acceleration and action time at the medium-scale and macroscale levels (whether to change lanes or not). Prathiba et al [ 88 ] proposed a hybrid DRL and genetic algorithm (DRG-SP) for smart platooning of AVs. By leveraging the DRL technique, the computational complexity is addressed, and the highly dynamic platoon scenarios are supported.…”

Section: The Analyses Of Decision-making Relevant Solutions For Auton...mentioning

confidence: 99%

How Do Autonomous Vehicles Decide?

Malik

Khan

El-Sayed

et al. 2022

Sensors

View full text Add to dashboard Cite

The advancement in sensor technologies, mobile network technologies, and artificial intelligence has pushed the boundaries of different verticals, e.g., eHealth and autonomous driving. Statistics show that more than one million people are killed in traffic accidents yearly, where the vast majority of the accidents are caused by human negligence. Higher-level autonomous driving has great potential to enhance road safety and traffic efficiency. One of the most crucial links to building an autonomous system is the task of decision-making. The ability of a vehicle to make robust decisions on its own by anticipating and evaluating future outcomes is what makes it intelligent. Planning and decision-making technology in autonomous driving becomes even more challenging, due to the diversity of the dynamic environments the vehicle operates in, the uncertainty in the sensor information, and the complex interaction with other road participants. A significant amount of research has been carried out toward deploying autonomous vehicles to solve plenty of issues, however, how to deal with the high-level decision-making in a complex, uncertain, and urban environment is a comparatively less explored area. This paper provides an analysis of decision-making solutions approaches for autonomous driving. Various categories of approaches are analyzed with a comparison to classical decision-making approaches. Following, a crucial range of research gaps and open challenges have been highlighted that need to be addressed before higher-level autonomous vehicles hit the roads. We believe this survey will contribute to the research of decision-making methods for autonomous vehicles in the future by equipping the researchers with an overview of decision-making technology, its potential solution approaches, and challenges.

show abstract

A Hybrid Deep Reinforcement Learning For Autonomous Vehicles Smart-Platooning

Cited by 58 publications

References 37 publications

Energy-Efficient Virtual Resource Allocation of Slices in Vehicles-Assisted B5G Networks

Energy-Efficient Virtual Resource Allocation of Slices in Vehicles-Assisted B5G Networks

Comparative Study of Cooperative Platoon Merging Control Based on Reinforcement Learning

How Do Autonomous Vehicles Decide?

Contact Info

Product

Resources

About