<p>In multi-hop routing of 5G vehicle network, node movement and link failure often lead to frequent changes in network topology, which in turn cause delay and packet loss problems. A multimodal transmission strategy based on environment perception is proposed in this study to achieve adaptive switching of routing protocols. Vehicle-mounted sensors are used to collect location, speed, network load and traffic density information in real-time. Then, graph sample and aggregation (GraphSAGE) is used to process the network topology and extract node and edge features of the data. The features are input into gated recurrent unit (GRU) for time series modeling to predict the link node movement pattern. Then, ad hoc on-demand distance vector routing (AODV), greedy perimeter stateless routing (GPSR) and dynamic source routing (DSR) are integrated, and the best protocol is automatically selected through the classification and regression trees (CART) algorithm. Finally, a route request packet (RREQ) is generated and broadcast according to the selected routing protocol. After being processed by the intermediate node, the route reply packet (RREP) is returned to the source node to achieve real-time update of the routing table and maintain the link status. The results show that when the number of nodes reaches 1200, the system delay is 146.99 ms; when the average vehicle speed is 30 km/h and the network load is 50 Mbps, the packet loss rate of switching to the DSR protocol is only 0.833%. The method can significantly reduce the real-time delay in multi-hop routing of 5G vehicle network.</p><p><i>Clinical trial numbe</i>r:&#xa0;Not applicable.</p>