Artificial Intelligence is rapidly enhancing human capability by providing support and guidance on a wide variety of tasks. However, one of the main challenges for autonomous systems is effectively managing the decisions and interactions between multiple entities in a dynamic environment. Policies are frequently used in cyber-physical systems to define target goals and constraints, such as maximising security whilst preventing communication to unauthorised systems. In this paper we introduce an approach for learning high-level policy models for future Connected and Autonomous Vehicles (CAVs). Since CAVs are required to operate in complex, safety-critical environments with a wide range of varying contextual conditions, high-level policies can help systems achieve their goals whilst adhering to varying environmental constraints. We present a Generative Policy Model (GPM) that enables a CAV to observe, learn, and adapt high-level policy models using local knowledge shared by related entities in the environment such as other CAVs, when reliable communication to traditional policy management systems may not be available. Within the proposed CAV GPM architecture, we utilise a novel context-free grammar bounded by a set of context-sensitive annotations called Answer Set Grammars (ASGs) and perform an evaluation of CAV policy generation in varying contexts. We also release the CAVPolicy dataset of annotated policies to enable future research in this area.