Multi-train-number trajectory data fusion method, device and equipment and storage medium

Abstract

The embodiment of the invention discloses a multi-train-number trajectory data fusion method, device and equipment and a storage medium, and the method comprises the steps: carrying out the processing of a single train number trajectory based on the matching relation between the single train number trajectory and a geometric road network, obtaining first track fusion data corresponding to the first single track and second track fusion data corresponding to the second single track; based on the first trajectory fusion data, performing inverse distance weighted fusion on the second trajectory fusion data to obtain target fusion data; and carrying out weighted fusion on the target fusion data and the first trajectory fusion data based on observation times to obtain target trajectory data. Therefore, by the adoption of the method, weighted fusion is carried out on the multi-train-number trajectory data based on the number of observation times and the inverse ratio of the weight to the distance, high-precision trajectory data are automatically obtained, and then a more reasonable trajectory is planned.

Description

technical field [0001] The present application relates to the technical field of data processing, and more specifically, to a method, device, equipment and storage medium for merging multi-vehicle trajectory data. Background technique [0002] In the automatic driving system, positioning and navigation is one of the very important functions. However, in some scenarios, it is not enough to rely on the information in the map for trajectory planning. Therefore, in the related art, a solution is proposed to fuse the trajectory data of multiple trips to obtain the fused trajectory. At present, most of the mainstream solutions adopt the scheme of main curve or K-segment main curve, but these schemes are more suitable for high-speed or some urban roads, and are not very suitable for complex scenes such as parking lots. Therefore, in the related art, there is a problem of unreasonable planning of movement trajectories in complex scenes such as parking lots. Contents of the inven...

AI Technical Summary

Problems solved by technology

At present, most of the mainstream solutions adopt the scheme of main curve or K-segment main curve, but these schemes are more suitable for high-speed or some urban roads, and are not very suitable for complex scenes such as parking lots.

Therefore, in the related art, there is an unreasonable problem in planning the movement trajectory of complex scenes such as parking lots.

Images