Path planning methods, apparatus, electronic devices and computer-readable storage media

By pre-storing path planning for preset points of unmanned delivery vehicles and trimming or splicing when the starting point information does not match the current pose, the problem of high computational resources and time costs for path planning of unmanned delivery vehicles is solved, and more efficient path planning is achieved.

CN116124167BActive Publication Date: 2026-07-17YOUDI ROBOT (WUXI) CO LTD
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
YOUDI ROBOT (WUXI) CO LTD
Filing Date
2023-02-27
Publication Date
2026-07-17

AI Technical Summary

Technical Problem

The path planning of unmanned delivery vehicles in existing technologies requires high computational resources and time costs, especially when the map is expanded and the number of target points increases.

Method used

By pre-planning paths for multiple preset points, a pre-stored path is obtained. When the starting point information does not match the current pose, the pre-stored path is trimmed or spliced ​​according to the current pose to generate the target path, thus avoiding the need to call the global planner again for path planning.

Benefits of technology

It reduces the number of global path planning operations, thereby lowering computational resource and time costs. This is especially true in scenarios where delivery points are relatively fixed, such as industrial parks, where it significantly saves computational resources and time.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN116124167B_ABST
    Figure CN116124167B_ABST
Patent Text Reader

Abstract

This application relates to the field of path planning technology, and provides a path planning method, apparatus, electronic device, and computer-readable storage medium. The path planning method includes: acquiring a pre-stored path, wherein the pre-stored path is a path obtained by pairwise path planning of multiple preset points; acquiring the current pose of a target object and a target point that the target object needs to reach, wherein the target point is any one of the multiple preset points; filtering out a path to be confirmed from the pre-stored path to reach the target point; if the starting point information of the starting point of the path to be confirmed does not match the current pose, then, based on the current pose, trimming or splicing the pre-stored path to obtain the target path used by the target object to reach the target point. Embodiments of this application can, to a certain extent, reduce the number of times global path planning is performed using a map, reducing computational resources and time costs.
Need to check novelty before this filing date? Find Prior Art