Stabilization Approaches for Reinforcement Learning-Based End-to-End Autonomous Driving

Chen, Siyuan; Wang, Meiling; Song, Wenjie; Yang, Yi; Li, Yujun; Fu, Mengyin

doi:10.1109/tvt.2020.2979493

Cited by 47 publications

(17 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Thus, it automatically adapts to the 4 Wireless Communications and Mobile Computing new environment. Moreover, it allows online learning to support real-time signal communication between V2V, V2I, and V2X links [28]. Hence, it takes advantages in a dynamic vehicular network.…”

Section: Background Of Deep Reinforcement Learningmentioning

confidence: 99%

DRL‐Based Intelligent Resource Allocation for Diverse QoS in 5G and toward 6G Vehicular Networks: A Comprehensive Survey

Nguyen

et al. 2021

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

The vehicular network is taking great attention from both academia and industry to enable the intelligent transportation system (ITS), autonomous driving, and smart cities. The system provides extremely dynamic features due to the fast mobile characteristics. While the number of different applications in the vehicular network is growing fast, the quality of service (QoS) in the 5G vehicular network becomes diverse. One of the most stringent requirements in the vehicular network is a safety-critical real-time system. To guarantee low-latency and other diverse QoS requirements, wireless network resources should be effectively utilized and allocated among vehicles, such as computation power in cloud, fog, and edge servers; spectrum at roadside units (RSUs); and base stations (BSs). Historically, optimization problems have mostly been investigated to formulate resource allocation and are solved by mathematical computation methods. However, the optimization problems are usually nonconvex and hard to be solved. Recently, machine learning (ML) is a powerful technique to cope with the complexity in computation and has capability to cope with big data and data analysis in the heterogeneous vehicular network. In this paper, an overview of resource allocation in the 5G vehicular network is represented with the support of traditional optimization and advanced ML approaches, especially a deep reinforcement learning (DRL) method. In addition, a federated deep reinforcement learning- (FDRL-) based vehicular communication is proposed. The challenges, open issues, and future research directions for 5G and toward 6G vehicular networks, are discussed. A multiaccess edge computing assisted by network slicing and a distributed federated learning (FL) technique is analyzed. A FDRL-based UAV-assisted vehicular communication is discussed to point out the future research directions for the networks.

show abstract

Section: Background Of Deep Reinforcement Learningmentioning

confidence: 99%

DRL‐Based Intelligent Resource Allocation for Diverse QoS in 5G and toward 6G Vehicular Networks: A Comprehensive Survey

Nguyen

et al. 2021

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

show abstract

“…For instance, Li et al [26] proposed a combined trajectory planning and tracking algorithm for vehicle control under the effects of the traffic environments and human driving styles. Chen et al, [27] suggested two techniques to improve the stability of the policy model training with as little manual data as possible on endto-end autonomous driving. Chen et al [28] developed a deep Monte Carlo Tree Search (deep-MCTS) control method for vision-based autonomous driving for predicting driving maneuvers to assist in enhancing the stability and performance of driving control.…”

Section: Literature Reviewmentioning

confidence: 99%

A Security-by-Design Decision-Making Model for Risk Management in Autonomous Vehicles

et al. 2021

View full text Add to dashboard Cite

Autonomous/self-driving vehicles have gained significant attention these days, as one of the intelligent transportation systems. However, those vehicles have risks related to their physical implementation and security against cyber threats. Therefore, this study proposes a new security-by-design model for estimating the uncertainty of autonomous vehicles and measuring cyber risks; thus it assists decision-makers in addressing the risks of the physical design and their attack surfaces. The proposed model is developed using neutrosophic sets that efficiently tackle multi-criteria decision-making (MCDM) problems with extensive conflicting criteria and alternatives. The proposed model integrates MCDM, Analytic Hierarchy Process (AHP), Multi-Attributive Border Approximation Area Comparison (MABAC), and Preference Ranking Organization Method for Enrichment Evaluations II (PROMETHEE II), along with single-valued neutrosophic sets (SVNSs). An illustrative case considering ten risks in self-driving vehicles is used to validate the feasibility of the proposed model. Compared to the state-of-the-art methods, the proposed model is considered consistent and reliable to deal with and represent uncertainty and incomplete risk information using neutrosophic sets.

show abstract

“…The selection strategy of 𝜌 L and Δ is based on the relation between u L and u K , see (5). Due to the expression I n×n •(𝜌 * L J 1×n )u K in (3) the control input u i is independent of u K, j , for all i ≠ j; i, j ∈ [i; n], as it is detailed in Section 2.…”

Section: Calculation Of the Scheduling Variable And The Measured Disturbancementioning

confidence: 99%

“…In the following, the representation of the system ( 15) is used for the design of the robust LPV control (𝜌 K , y K ), see (2). The purpose of the design is to derive the LPV controller which guarantees a minimum performance level for the closed-loop system, considering the predefined control rule (5). The output of the LPV controller u K is used in the expression u = I n×n •(𝜌 L J 1×n )u K + Δ L .…”

Section: Iterative Design Of the Lpv Controlmentioning

confidence: 99%

“…2,3 Another example is reinforcement learning, in which the performance requirements can be achieved through high number of learning scenarios in a training process. 4,5 Although the different types of enhanced machine-learning methods are able to solve various control tasks effectively, the resulting performance level is not theoretically guaranteed, that is, the numerous training samples cannot guarantee the avoidance of the performance degradation in any scenario.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Ensuring performance requirements for semiactive suspension with nonconventional control systems via robust linear parameter varying framework

Németh

Gáspár

2020

Intl J Robust & Nonlinear

View full text Add to dashboard Cite

In the article a method which is able to provide the required performance level of a system is proposed. Its principle is to combine the results of conventional control methods with those of methods based on nonconventional, for example, machine-learning-based ones. In more detail, it designs a robust linear parameter varying (LPV) control in a predefined form, whose output is equivalent to the output of a machine-learning-based control inside a predefined operational range. Outside of the operation range the output of the machine-learning-based control is overridden, while the intervention with the performance level is guaranteed. The efficiency of the proposed method is illustrated through an example on the semiactive suspension control design. The nonlinearities in the dynamics of the magneto-rheological damper are considered through a nonlinear parameter varying (NLPV) model. It designs an NLPV model-based LPV control, which is combined with a neural network to achieve preview capability.

show abstract

Stabilization Approaches for Reinforcement Learning-Based End-to-End Autonomous Driving

Cited by 47 publications

References 22 publications

DRL‐Based Intelligent Resource Allocation for Diverse QoS in 5G and toward 6G Vehicular Networks: A Comprehensive Survey

DRL‐Based Intelligent Resource Allocation for Diverse QoS in 5G and toward 6G Vehicular Networks: A Comprehensive Survey

A Security-by-Design Decision-Making Model for Risk Management in Autonomous Vehicles

Ensuring performance requirements for semiactive suspension with nonconventional control systems via robust linear parameter varying framework

Contact Info

Product

Resources

About