Autonomous vehicles suffer from restrictions in their motion behavior and decision-making in an urban scene because there are many disturbances, e.g., manned vehicles, roadside obstacles, traffic lights, and pedestrians, thus hindering their application. Autonomous vehicle groups provide a new solution to alleviate these problems via intelligent cooperation but suffer from low connectivity and coupling as well as poor timeliness and stability. Existing methods mainly focus on autonomous vehicle groups in closed and highway scenes. They face the following issues: To address them, this chapter presents autonomous vehicle group formation, dynamic evolution, cooperation model, cooperation method, and simulation studies in an urban scene. Simulation results and applications show that our methods outperform existing vehicle group formation, dynamic evolution, and cooperation for approaches in urban scenes.