An Online Evolving Framework for Advancing Reinforcement-Learning based Automated Vehicle Control

Han, Teawon; Nageshrao, Subramanya; Filev, Dimitar; Özgüner, Ü.

doi:10.1016/j.ifacol.2020.12.2283

Cited by 4 publications

(3 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For high‐dimensional state spaces, such a strategy may lead to high memory requirements. Cluster‐based or neural network‐based approximations of the dataset may be employed to alleviate this issue, where the AG uses a relatively small number of clusters or a neural network, instead of searching over a dataset, for online prediction of whether an action is viable/unviable at the current state, as pursued in References 31 and 52. Such strategies will be investigated in future work.…”

Section: Conclusion and Discussionmentioning

confidence: 99%

“…However, for more complex scenarios including those involving multiple vehicle interactions, an explicit model is typically not available. Therefore, an emerging approach is to train a safety supervisor through learning, as investigated in References 26,[31][32][33] Note that the learning objectives of those aforementioned learning-based approaches to control policy design and a learning-based approach to safety supervisor design are different: The former aims at developing a nominal control policy that achieves optimal performance with regard to (the expected value of) a reward function, while the latter focuses on the safety aspect and typically pursues minimum modification to the nominal control.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Improving autonomous vehicle in‐traffic safety using learning‐based action governor

Han

Tseng

et al. 2022

Adv Control Appl

View full text Add to dashboard Cite

The Action Governor (AG) is a supervisory scheme augmenting a nominal control system in order to enhance the system's safety and performance. It acts as an action filter, monitoring the action commands generated by the nominal control policy and adjusting the ones that might lead to undesirable system behavior. In this article, we present an approach based on learning to developing an AG for autonomous vehicle (AV) decision policies to improve their safety for operating in mixed‐autonomy traffic (i.e., traffic involving both AVs and human‐operated vehicles (HVs)). To achieve this, we demonstrate that it is possible to train the AG in a traffic simulator that is capable of representing in‐traffic interactions among AVs and HVs. We illustrate the effectiveness of this learning‐based AG approach to improving AV in‐traffic safety through simulation case studies.

show abstract

Section: Conclusion and Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Improving autonomous vehicle in‐traffic safety using learning‐based action governor

Han

Tseng

et al. 2022

Adv Control Appl

View full text Add to dashboard Cite

show abstract

“…More advanced methods combine RL with evolutionary computation [20] or model predictive control [21]. A RL-based online evolving framework is proposed to detect and revise a controller's imperfect decision-making in advance in [22]. Deep RL is characterized with performance enhancement on complex tasks [24].…”

Section: Related Workmentioning

confidence: 99%

A Safety-Critical Decision Making and Control Framework Combining Machine Learning and Rule-based Algorithms

Aksjonov¹,

Kyrki²

2022

Preprint

View full text Add to dashboard Cite

While artificial-intelligence-based methods suffer from lack of transparency, rule-based methods dominate in safety-critical systems. Yet, the latter cannot compete with the first ones in robustness to multiple requirements, for instance, simultaneously addressing safety, comfort, and efficiency. Hence, to benefit from both methods they must be joined in a single system. This paper proposes a decision making and control framework, which profits from advantages of both the rule-and machine-learning-based techniques while compensating for their disadvantages. The proposed method embodies two controllers operating in parallel, called Safety and Learned. A rule-based switching logic selects one of the actions transmitted from both controllers. The Safety controller is prioritized every time, when the Learned one does not meet the safety constraint, and also directly participates in the safe Learned controller training. Decision making and control in autonomous driving is chosen as the system case study, where an autonomous vehicle learns a multi-task policy to safely cross an unprotected intersection. Multiple requirements (i.e., safety, efficiency, and comfort) are set for vehicle operation. A numerical simulation is performed for the proposed framework validation, where its ability to satisfy the requirements and robustness to changing environment is successfully demonstrated.

show abstract

An Online Evolving Method For a Safe and Fast Automated Vehicle Control System

Han

Nageshrao

Filev

et al. 2022

IEEE Trans. Syst. Man Cybern, Syst.

View full text Add to dashboard Cite

An Online Evolving Framework for Advancing Reinforcement-Learning based Automated Vehicle Control

Cited by 4 publications

References 11 publications

Improving autonomous vehicle in‐traffic safety using learning‐based action governor

Improving autonomous vehicle in‐traffic safety using learning‐based action governor

A Safety-Critical Decision Making and Control Framework Combining Machine Learning and Rule-based Algorithms

An Online Evolving Method For a Safe and Fast Automated Vehicle Control System

Contact Info

Product

Resources

About