The article discusses the challenges of cooperative decision-making in Connected Autonomous Vehicles (CAVs) due to its nonlinearity, non-convexity, and discrete characteristics. The study proposes a universal optimization approach to address these problems, representing various traffic scenarios as Directed Acyclic Graphs (DAGs). The decision-making of CAVs is approximated as a mixed-integer linear programming problem based on the DAGs, allowing for the use of standard numerical solvers. The approach considers factors like velocities, accelerations, conflict resolutions, and traffic efficiency.
Publication date: 12 Jan 2024
Project Page: Not Provided
Paper: https://arxiv.org/pdf/2401.04968
