Multi-Controller Architecture for Reliable Autonomous Vehicle Navigation: Combination of Model-Driven and Data-Driven Formalization

In this paper, a design of a multi-controller architecture (MCA) is presented. It effectively links model-based approaches and Artificial Intelligence (AI) developments for intelligent vehicles navigation in a highway. In this MCA, the model-based approach appears in the path planning (based on analytical target set-points definition) and the control law (based on a Lyapunov stability analysis). The AI-based approach appears in the proposed Two-Sequential Level Bayesian Decision Network (TSLBDN) for handling lane change maneuvers in uncertain environment and changing dynamic/behaviors of the surrounding vehicles. In addition, a combination of both trajectory prediction (based on dynamic target set-points and elliptic limit-cycles) and maneuver recognition based on Dynamic Bayesian Network (DBN) is proposed to infers surrounding vehicles actions. Several simulation results show the efficiency of the model-driven/data driven overall proposed control architecture.