Obstacle trajectory prediction method and device, unmanned vehicle and storage medium
By acquiring perception information and determining the road scene in autonomous vehicles, and using obstacle numbers and motion constraint boundary conditions to predict obstacle trajectories, the problem of low accuracy of obstacle trajectories in unstructured road scenes is solved, the prediction efficiency and accuracy are improved, and the safety of autonomous vehicles is ensured.
CN115723786BActive Publication Date: 2026-05-26SHENZHEN HAIXING ZHIJIA TECH CO LTD
View PDF 2 Cites 0 Cited by
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- SHENZHEN HAIXING ZHIJIA TECH CO LTD
- Filing Date
- 2022-12-07
- Publication Date
- 2026-05-26
Smart Images
Figure CN115723786B_ABST
Abstract
This invention provides a method and apparatus for predicting obstacle trajectories, an unmanned vehicle, and a storage medium. The obstacle trajectory prediction method includes: determining the target road scene currently occupied by the unmanned vehicle based on location information; if the target obstacle's number is among multiple obstacle numbers in the obstacle prediction queue, then determining the target obstacle's motion constraint boundary conditions in the target road scene based on a preset correspondence between the road scene, the obstacle, and the obstacle's motion constraint boundary conditions; if the target obstacle's motion information satisfies the target motion constraint boundary conditions, then obtaining target motion observation information based on the location information and the target obstacle's motion information; and predicting the target obstacle's trajectory within a specified time based on the target motion observation information and size information, thereby improving the effectiveness of the predicted trajectory and reducing prediction costs.
Need to check novelty before this filing date? Find Prior Art