Research on the Human-Machine Collaborative Optimisation Algorithm for Intelligent Traffic Signal Control Systems

With the worsening of urban traffic congestion, improving traffic flow and resource utilisation efficiency has become an important challenge in the field of intelligent transportation. Traditional traffic signal control systems lack dynamic adaptability and are difficult to cope with complex and ever-changing traffic environments. To address this problem, this paper proposes a bionic ant path planning algorithm based on human-machine collaborative optimisation. The system obtains real-time road traffic data, including information such as signal status, traffic flow and obstacle distribution, through a data acquisition module, and uses an improved ant colony algorithm to achieve global path search and dynamic optimisation. At the same time, a human-machine collaborative interaction mechanism is designed to allow users to adjust path weight parameters in real time according to actual needs, enhancing the flexibility and adaptability of the system. Through simulation experiments, this paper verifies the performance of the proposed algorithm in different scenarios and compares it with traditional path planning algorithms. The results show that the ant colony algorithm based on human-machine collaborative optimisation has significant advantages in terms of convergence speed, path optimisation effect and dynamic environmental adaptability. This study provides an efficient, real-time and flexible path optimisation solution for intelligent traffic signal control systems, which can effectively improve traffic scheduling capabilities in complex dynamic environments.