A digital decision approach for indirect-reciprocity based cooperative lane-changing

Digital technology plays an important role in the construction of intelligent transportation systems. The digitization of travel and traffic information contributes to the efficiency, equality and safety of travel for urban residents. This paper developed a cooperative lane-changing decision system based on digital technology and indirect reciprocity. The connected vehicle in the vehicle networking environment refers to a vehicle equipped with advanced on-board sensors, control systems, actuators and other devices, which integrates modern communication and network technology to realize intelligent information exchange and sharing between vehicles, roads, people, and clouds. Therefore, connected vehicles can know each other's communication position, speed, and acceleration. Under this premise, this paper innovatively proposes a decision system that introduces image scoring to attempt to solve the problem of drivers having difficulty cooperating in lane-changing at intersection. The lagging vehicle can gain image scores by yielding to the lane-changing vehicle, thus gaining a greater chance of being yielded to in the future. This paper also extends the model to a repeated evolutionary game, proposing a Qlearning based reinforcement learning algorithm that enables drivers in the simulation to continuously evaluate gains and adjust their strategies. The conclusions are summarized as follows. For non-fully rational drivers, this lane-changing mechanism considering indirect reciprocity can indeed improve driver cooperation which is more than 50% under any connected vehicles penetration and traffic density, especially under medium and low traffic density and high penetration, the cooperation probability can reach 100%. Lane-changing time is also saved, which means that the application of digital technologies based on indirect reciprocity can achieve unity of efficiency and equality. Meantime, traffic efficiency and delays at intersection where connected and non-connected vehicles are mixed can be improved, especially at high connected vehicles penetration and medium to high traffic density. Therefore, this study reflects the sustainable improvement of urban transportation with digital decision systems and is beneficial for the future application of digital technology in urban intelligent transportation systems and automatic driving field.

Automated summary

This paper developed a cooperative lane-changing decision system based on digital technology and indirect reciprocity. By introducing image scoring and a Q-learning based reinforcement learning algorithm, drivers can continuously evaluate gains and adjust their strategies. The study shows that this decision system can improve driver cooperation and traffic efficiency, achieving over 50% cooperation probability under any connected vehicles penetration and traffic density, and reaching 100% cooperation probability under high penetration and medium to high traffic density.