一种基于车辆信息和地图信息的轨迹预测方法及相关装置
By combining trajectory prediction methods based on target vehicle, environmental vehicle, and map information, the problem of low accuracy in trajectory prediction in complex traffic scenarios in existing technologies has been solved, achieving more efficient and accurate trajectory prediction.
CN117238125BActive Publication Date: 2026-07-17CHONGQING CHANGAN TECH CO LTD
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- CHONGQING CHANGAN TECH CO LTD
- Filing Date
- 2023-06-26
- Publication Date
- 2026-07-17
AI Technical Summary
Technical Problem
Existing trajectory prediction methods rely solely on the vehicle's own driving behavior, resulting in low accuracy and limited applicability in complex traffic scenarios.
Method used
By acquiring information about the target vehicle, surrounding vehicles, and map information, the characteristics of the target vehicle are comprehensively determined, and a trajectory prediction model is used for prediction, including the multiple influences of the vehicle itself, surrounding vehicles, and roads.
Benefits of technology
It improves the accuracy of trajectory prediction results, assists drivers or autonomous driving systems in making more accurate driving decisions in complex traffic scenarios, and improves prediction efficiency and accuracy.
✦ Generated by Eureka AI based on patent content.
Smart Images
Figure CN117238125B_ABST
Abstract
本申请涉及智能驾驶技术领域，具体是涉及一种基于车辆信息和地图信息的轨迹预测方法及相关装置。通过获取与本车位于同一环境的目标车辆的第一车辆信息、若干环境车辆的第二车辆信息以及地图信息，各环境车辆包括环境中除目标车辆之外的车辆；根据第一车辆信息、各第二车辆信息以及地图信息，确定目标车辆的目标车辆特征；根据目标车辆特征，确定目标车辆的目标预测轨迹。本申请在对与本车位于同一环境的目标车辆进行轨迹预测时，考量了目标车辆自身、目标车辆的周围车辆以及当前道路对其行车路线的多重影响，可以有效提高轨迹预测结果的准确性。
Need to check novelty before this filing date? Find Prior Art