The use of Remotely Operated Vehicles (ROVs) is ultimately limited by economic support costs, and the presence and skills of the human operator. Autonomous surface and underwater vehicles have the potential to operate with greatly reduced overhead costs and level of operator intervention. This paper proposes an Intelligent Control Architecture (ICA) to enable multiple collaborating marine vehicles to carry out autonomous underwater intervention missions. The architectural foundation to achieve the ICA lays on the flexibility of service-oriented computing. A knowledge-based database captures the operator skills, platform capabilities and, changes in the environment. The information captured enables reasoning agents to plan missions based on the current situation. This paper also presents a marine vehicle platform for the ICA evaluation, simulation results of a mission, and future research directions.