A Generative Policy Model for Connected and Autonomous Vehicles

Cunnington, Daniel; Manotas, Irene; Law, Mark; Mel, Geeth de; Calo, Seraphin; Bertino, Elisa; Russo, Alessandra

doi:10.1109/itsc.2019.8916782

Cited by 9 publications

(9 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Highlevel policies help agents adapt their goals according to different situations of the environment. Generative Policybased Models (GPM) can be used to enable agents to observe, learn, and adapt high-level policy models [7].…”

Section: Discussionmentioning

confidence: 99%

“…The importance of observation Each agent g i observes the environment at time step t based on its ontology L t g i , so the importance of each observation s t g i is determined based on the importance of the concepts C t g i involved (line 5 of Algorithm 1). A concept weighting function is used to quantify the degree of importance of each concept x ∈ C t g i in a domain using an iweighting indicator [28] (see (7)):…”

Section: Q-valuementioning

confidence: 99%

See 1 more Smart Citation

Using ontology to guide reinforcement learning agents in unseen situations

Ghanadbashi

Golpayegani

2021

Appl Intell

View full text Add to dashboard Cite

In multi-agent systems, goal achievement is challenging when agents operate in ever-changing environments and face unseen situations, where not all the goals are known or predefined. In such cases, agents need to identify the changes and adapt their behaviour, by evolving their goals or even generating new goals to address the emerging requirements. Learning and practical reasoning techniques have been used to enable agents with limited knowledge to adapt to new circumstances. However, they depend on the availability of large amounts of data, require long exploration periods, and cannot help agents to set new goals. Furthermore, the accuracy of agents’ actions is improved by introducing added intelligence through integrating conceptual features extracted from ontologies. However, the concerns related to taking suitable actions when unseen situations occur are not addressed. This paper proposes a new Automatic Goal Generation Model (AGGM) that enables agents to create new goals to handle unseen situations and to adapt to their ever-changing environment on a real-time basis. AGGM is compared to Q-learning, SARSA, and Deep Q Network in a Traffic Signal Control System case study. The results show that AGGM outperforms the baseline algorithms in unseen situations while handling the seen situations as well as the baseline algorithms.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Q-valuementioning

confidence: 99%

Using ontology to guide reinforcement learning agents in unseen situations

Ghanadbashi

Golpayegani

2021

Appl Intell

View full text Add to dashboard Cite

show abstract

“…Typically, the policies are stored in a specific format, for example, Extensible Access Control Markup Language (XACML). In addition, the PAP makes the complete access control policies available for the policy decision point to grant or deny permissions [ 32 , 33 ]. In an IoT environment, PAP should be designed so that policies can be added, removed or modified at runtime.…”

Section: Access Control Authorization Architecturementioning

confidence: 99%

“…Policy Refinement Point: The PRP is a component that is responsible for refining policies at runtime and updating the policy repository. The refining process can be triggered for several reasons such as any change in the context of the environment or detection of an abnormal or unauthorized access behavior [ 33 , 36 ]. Various techniques have been adopted in the literature for the policy refinement process [ 32 , 33 , 34 , 37 ].…”

Section: Access Control Authorization Architecturementioning

confidence: 99%

Access Control for IoT: A Survey of Existing Research, Dynamic Policies and Future Directions

Ragothaman

Wang

Rimal

et al. 2023

Sensors

View full text Add to dashboard Cite

Internet of Things (IoT) provides a wide range of services in domestic and industrial environments. Access control plays a crucial role in granting access rights to users and devices when an IoT device is connected to a network. However, many challenges exist in designing and implementing an ideal access control solution for the IoT due to the characteristics of the IoT including but not limited to the variety of the IoT devices, the resource constraints on the IoT devices, and the heterogeneous nature of the IoT. This paper conducts a comprehensive survey on access control in the IoT, including access control requirements, authorization architecture, access control models, access control policies, access control research challenges, and future directions. It identifies and summarizes key access control requirements in the IoT. The paper further evaluates the existing access control models to fulfill the access control requirements. Access control decisions are governed by access control policies. The existing approaches on dynamic policies’ specification are reviewed. The challenges faced by the existing solutions for policies’ specification are highlighted. Finally, the paper presents the research challenges and future directions of access control in the IoT. Due to the variety of IoT applications, there is no one-size-fits-all solution for access control in the IoT. Despite the challenges encountered in designing and implementing the access control in the IoT, it is desired to have an access control solution to meet all the identified requirements to secure the IoT.

show abstract

“…Cunnington et. al have proposed an ASG based GPM for CAVs [25]. This enables a CAV to learn a policy model that states whether a particular request to execute a driving task should be accepted or rejected, based on the current environmental conditions and the LOA of the vehicle, region and driving task.…”

Section: A Autonomous Systemsmentioning

confidence: 99%

Generative Policies for Coalition Systems - A Symbolic Learning Framework

Bertino

White²,

Lobo

et al. 2019

2019 IEEE 39th International Conference on Distributed Computing Systems (ICDCS)

Self Cite

View full text Add to dashboard Cite

Policy systems are critical for managing missions and collaborative activities carried out by coalitions involving different organizations. Conventional policy-based management approaches are not suitable for next-generation coalitions that will involve not only humans, but also autonomous computing devices and systems. It is critical that those parties be able to generate and customize policies based on contexts and activities. This paper introduces a novel approach for the autonomic generation of policies by autonomous parties. The framework combines context free grammars, answer set programs, and inductionbased learning. It allows a party to generate its own policies, based on a grammar and some semantic constraints, by learning from examples. The paper also outlines initial experiments in the use of such a symbolic approach and outlines relevant research challenges, ranging from explainability to quality assessment of policies.

show abstract

A Generative Policy Model for Connected and Autonomous Vehicles

Cited by 9 publications

References 16 publications

Using ontology to guide reinforcement learning agents in unseen situations

Using ontology to guide reinforcement learning agents in unseen situations

Access Control for IoT: A Survey of Existing Research, Dynamic Policies and Future Directions

Generative Policies for Coalition Systems - A Symbolic Learning Framework

Contact Info

Product

Resources

About