Current unmanned marine vehicles are increasing their autonomy so that more sophisticated maritime missions can be carried out. Remotely operated vehicles are no longer costeffective since they are limited by economic support costs, and the presence and skills of the human operator. This paper proposes an Intelligent Control Architecture ( ICA) to enable multiple collaborating marine vehicles to autonomously carry out underwater intervention missions. The ICA is generic in nature but aimed at a case study where a marine surface craft and an underwater vehicle are required to work cooperatively. Service-oriented computing as well as agent technology lay the ICA foundations. An ontological database captures the operator skills, platform capabilities, and potential changes in the environment. This knowledge enables reasoning agents to plan missions. The ICA implementation is verified in simulation. This paper also presents architectural details of the ICA, and experimental results from simulation.