We consider the problem of collaborative driving systems in which the vehicles share sensor information and make joint decisions on vehicle control. Such a system involves vehicular control, communications links, and environment sensing. We propose a multiple stack architecture that is based on the nature of collaborative driving systems. The architecture facilitates the design, implementation, verification, and testing of a collaborative driving protocol. The advantage of using absolute time in a distributed system is also demonstrated. Specifically, we propose a merge protocol that assists a driver in merging with other vehicles based on the proposed architecture. We create a lock protocol and specify it as an extended finite state machine as a subroutine of the merge protocol. Absolute time simplifies a deadlock-free lock protocol. The lock protocol is verified using probabilistic verification.

We present a general architecture for intelligent vehicles, especially collaborative driving applications. Intelligent vehicles are similar to communication networks as both types of systems interact with physical world using devices that are rapidly evolving, while intelligent vehicles are more complicated than communication network because they interact with the physical world in not only, one but several ways, and because many of the interactions have severe time constraints. The proposed architecture adopts multiple layered stack structures to address the issues. We also present a collaborative merge protocol as an instantiation of the proposed architecture, and discuss the advantage of the architecture in terms of the feasibility of model checking and conformance testing.

No abstract

No abstract

No abstract