Trajectory prediction method, system and device, electronic equipment and storage medium

By coordinating the processing of roadside units, cloud-side devices, and edge computing devices, the location information and estimated collision duration of target objects are detected in real time, and tasks are migrated when resources are insufficient, thus solving the problem of insufficient computing power in the vehicle-to-everything (V2X) system and achieving high real-time trajectory prediction.

CN121366496APending Publication Date: 2026-01-20CHINA UNICOM SMART CONNECTION TECH LTD
View PDF 4 Cites 0 Cited by

Patent Information

Application Number
CN202511587016.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-10-31
Publication Date
2026-01-20

AI Technical Summary

Technical Problem

In existing technologies, vehicle-to-everything (V2X) systems suffer from insufficient computing power and low resource allocation efficiency, making it difficult to meet the real-time requirements of ultra-low latency scenarios such as emergency braking and pedestrians entering the vehicle lane.

Method used

In the trajectory prediction system, the location information and estimated collision duration of the target object are detected in real time through the collaborative processing of roadside units, cloud-side devices and edge computing devices. When the resource occupancy rate exceeds the threshold, a task migration request is sent to the cloud-side device to continue to execute the trajectory prediction task using other roadside units or edge computing devices.

Benefits of technology

It improves the real-time performance of target vehicle trajectory prediction, avoids mission interruptions and delays, and ensures timely response in emergency situations.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN121366496A_ABST
    Figure CN121366496A_ABST
Patent Text Reader

Abstract

The invention provides a trajectory prediction method, system and device, an electronic device and a storage medium, the method is applied to a first road side unit in at least two road side units of the trajectory prediction system, the trajectory prediction system further comprises a cloud side device and an edge computing device, and the method comprises the following steps: performing target detection on acquired to-be-processed task data, and obtaining a target detection result; determining position information and predicted collision duration of a target object in the to-be-processed task data; according to the position information and the predicted collision duration, executing a target prediction task for the moving trajectory of the target vehicle; and during execution of the target prediction task, under the condition that the resource occupancy rate of the first road side unit is greater than a resource occupancy threshold, sending a task migration request to the cloud side device. According to the embodiment of the invention, the relay processing of the target prediction task can be completed, the interruption and delay processing of the target prediction task are avoided, and the real-time performance of predicting the moving trajectory of the target vehicle is improved.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • Vehicle computing resource using method based on trajectory prediction

    CN110276970A

  • Automatic driving road condition navigation method and system based on 5G network, and medium

    CN113936491A

  • Computing power scheduling method and device, electronic equipment and storage medium

    CN116132449A

  • Fall detection method and device based on cloud edge collaboration, and storage medium

    CN116935193A