Multi-intersection inter-cluster coupling-time attention multi-target robust co-regulation method
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- ZHONGBEI UNIV
- Filing Date
- 2026-01-26
- Publication Date
- 2026-07-21
AI Technical Summary
Existing traffic signal control methods fail to fully consider the mutual influence and constraints of traffic flow at multiple intersections in urban road networks. This makes it difficult for the optimization effect of a single intersection to radiate globally, the control effect is easily affected by interference, and the feedback correction mechanism is insufficient, failing to meet the global coordinated control needs of complex road networks.
A robust collaborative control method with multi-intersection cluster coupling and temporal attention is adopted. Multi-dimensional traffic data is collected through sensor networks, and generative adversarial networks are used for data augmentation. The method combines density peak-adaptive K-value clustering algorithm and improved multi-objective robust particle swarm optimization algorithm to calculate the comprehensive priority weight of intersections and adjust the traffic light timing scheme to achieve dynamic adaptation and anti-interference capability.
It improves the overall coordination and dynamic adaptability of traffic signal control at multiple intersections, enhances the efficiency of control resource allocation, significantly reduces the risk of control failure under emergencies, and improves traffic operation efficiency and stability.
Smart Images

Figure CN121921981B_ABST