Autonomous vehicles (AV) technology is designed for replacing conventional transportation systems ahead of energy conservation, pollution control, accident prevention, etc. The benefits of AV are feasible by the incorporation of information technology and connected infrastructures. These provide seamless support for driving and navigation assistance with the knowledge of the environment. However, the vehicles' independent assistance relies on the cooperative nature of the neighbors and infrastructure units. In this article, assisted cooperative decision-support (ACDS) is proposed for improving the spontaneous decisions for vehicle connectivity and navigation issues. The interrupt due to multiple connectivity issues from a specific infrastructure region is addressed for leveraging the decision support for AVs. In this decision-making process, neural learning is used for improving the analysis of radial inputs. The learning process categorizes connectivity and outage information based on the assisted navigation ratio between the neighbors and infrastructures. This helps to provide flexible, cooperative analysis in different navigation scenarios, promoting accuracy, and reducing the input complexity. The performance of ACDS is verified using outage, complexity, analysis time, and accuracy measures.

自动驾驶汽车（AV）技术旨在在节能，污染控制，事故预防等方面取代传统的交通系统。通过结合信息技术和相连的基础设施，AV的好处是可行的。这些在了解环境的情况下为驾驶和导航辅助提供了无缝支持。但是，车辆的独立援助取决于邻居和基础设施单位的合作性质。在本文中，提出了辅助合作决策支持（ACDS），以改善针对车辆连通性和导航问题的自发决策。解决了来自特定基础结构区域的多个连接问题引起的中断，以利用对AV的决策支持。在这个决策过程中，神经学习用于改善径向输入的分析。学习过程根据邻居和基础设施之间的辅助导航比率对连通性和中断信息进行分类。这有助于在不同的导航场景中提供灵活的协作分析，从而提高准确性并降低输入复杂度。ACDS的性能通过中断，复杂性，分析时间和准确性度量来验证。