一种基于实时交通态势预测的车辆协同决策系统及方法
By constructing a real-time dynamic traffic scene map based on multi-source traffic fusion data and an improved LSTM neural network, combined with centralized planning and distributed execution, the problem of insufficient prediction of complex spatiotemporal topological relationships among traffic participants is solved, and efficient and safe vehicle cooperative control is achieved.
CN121483028BActive Publication Date: 2026-07-17HEFEI UNIV
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- HEFEI UNIV
- Filing Date
- 2025-11-12
- Publication Date
- 2026-07-17
Smart Images
Figure CN121483028B_ABST
Abstract
本发明公开了一种基于实时交通态势预测的车辆协同决策系统及方法，涉及智能交通技术领域；本发明通过车‑路‑云协同感知体系融合多源交通数据，构建实时动态交通场景图谱；基于改进的LSTM神经网络，通过引入时空图谱卷积和双重注意力机制进行交通态势预测；将预测结果转化为风险场与机遇场数据；采用集中规划与分布式执行的分层优化策略，基于遗传算法生成全局优化指令，各车辆再根据实时查询的风险场与机遇场数据进行局部调整，生成最终控制指令，实现安全与效率并重的多车协同控制；本发明有效解决了复杂交通环境下感知不完整、预测不准确、控制响应迟滞等问题，显著提升了区域交通的整体效率与安全性。
Need to check novelty before this filing date? Find Prior Art