A Secure and Dependable Multi-Agent Autonomous Intersection Management (MA-AIM) System Leveraging Blockchain Facilities

Every year, traffic collisions have increased rapidly in proportion to the increase in the number of vehicles, especially at intersections. The main cause is human error in recognition and decision-making. Autonomous Vehicles (AVs) and Autonomous Intersection Management (AIM) systems represent emerging challenges. AVs can take a great deal of different actions when approaching an intersection. Several research centers are developing algorithms to solve one of the crucial aspects of autonomous driving, i.e the intersections management, trying to avoid collisions and traffic congestion. In this context, security is the main concern, due to the high exposure to data and information between Vehicle-to-Vehicle (V2V) and Vehicle-to-Intersection (V2I) communications. Blockchain and smart contracts, one of most promising technologies emerged in recent years, represent a possible solution for the existing security issues. Smart contracts are the orchestration and choreography protocols that facilitate, verify and negotiated agreement between the consenting parties participating in the Blockchain network. In this paper, we propose a Multi-Agent AIM (MA-AIM) system based on V2I/I2V communication to securely manage vehicles crossing though an intersections by leveraging Blockchain facilities. A central Intersection Manager Agent (IMA) is implemented at each intersection while each vehicle is controlled by a Driver Agent (DA).