Improving situation awareness for intelligent on-board vehicle management system using context middleware

The proliferation of intelligent vehicle, sensor and communication technology has led to the emergence of vehicle-to-vehicle (V2V) applications that aim to increase safety and efficiency of driving. The important requirements of these applications are the capabilities to provide unobtrusive support to the driver and the application capability to adapt to changing situations in the environment without having explicit driver intervention. This paper proposes a new approach for context and situation reasoning in V2V environment. We model context and situations based on context spaces and integrate the model with Dempster-Shafer rule of combination for situation reasoning. We also incorporate reliability of each information source in the fusion mechanism based on discount rule. We apply this approach to a context middleware framework that aims to facilitate context and situation reasoning to provide reliable support for cooperative applications in V2V environment and discuss the implementation and experimentation issues of the prototype.