一种基于偏航角的自动驾驶画龙检测方法
By setting yaw angle error thresholds and time thresholds in autonomous vehicles, and combining them with sliding window detection, the complexity and accuracy issues of dragon drawing detection are resolved, achieving efficient and accurate judgment of dragon drawing behavior.
CN115782900BActive Publication Date: 2026-07-17上海友道智途科技有限公司
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- 上海友道智途科技有限公司
- Filing Date
- 2022-11-16
- Publication Date
- 2026-07-17
AI Technical Summary
Technical Problem
In existing technologies, the design of dragon detection for autonomous vehicles is difficult, the logic is complex, the accuracy is hard to guarantee, and the angular velocity calculation is inefficient, which easily leads to false detections.
Method used
By setting time thresholds and yaw angle error thresholds, and combining them with a sliding window detection method, the system uses data directly obtained from the yaw angle to determine whether the vehicle is exhibiting "dragon-like" behavior.
Benefits of technology
It improves the accuracy and efficiency of dragon detection, avoids false detections, adapts to different road and vehicle conditions, and provides high flexibility and adaptability.
✦ Generated by Eureka AI based on patent content.
Smart Images
Figure CN115782900B_ABST
Abstract
本发明公开一种基于偏航角的自动驾驶画龙检测方法，通过自动驾驶过程中偏航角的表现进行检测车辆是否为画龙行为，偏航角为车辆传感器直接获取，获取方式简单且准确，结合偏航角误差阈值与时间阈值的配合，能够提高检测精度，避免误检，同时，偏航角误差阈值能够根据道路及车辆情况进行自适应调整，提高了检测的灵活性及适配性，适用于多种场景，对数据运用了滑动窗原理，分段检测，提高了检测效率及精度。
Need to check novelty before this filing date? Find Prior Art