Safe driving decision generation method supported by intelligent driving vehicle data

The invention discloses an intelligent driving vehicle data-supported safe driving decision generation method, which comprises the steps of 1, data perception preparation and multi-modal information acquisition, 2, time registration among sensors with different scales, and 3, time registration among sensors with different scales. 3, performing multi-target tracking data association based on a deep neural network driven by dual image reconstruction data, and outputting a data association result between LSTM sequences; 4, performing multi-sensor data fusion according to the multi-target tracking data association result, step 5, an intelligent driving vehicle safe driving decision model based on multi-modal data fusion is established, and a driving decision is output; according to the method, correct fusion of multi-sensing information of the intelligent driving vehicle under the condition of clutter environment multi-target intersection and safe driving decision of the vehicle under the support of multi-modal i