Automatic driving environment perception method, medium and vehicle
By hierarchically fusing camera image data, LiDAR point cloud data, and positioning sensor data, the problem of insufficient environmental perception information caused by sensor damage is solved, ensuring the safe and stable driving of autonomous vehicles.
CN115205803BActive Publication Date: 2026-06-16安徽蔚来智驾科技有限公司
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- 安徽蔚来智驾科技有限公司
- Filing Date
- 2022-07-14
- Publication Date
- 2026-06-16
AI Technical Summary
⚠Technical Problem
In autonomous driving environmental perception, if the onboard camera or lidar is damaged, accurate environmental perception information cannot be obtained, affecting safe driving.
⚗Method used
By hierarchically fusing image data from cameras, point cloud data from LiDAR, and positioning data from positioning sensors, environmental perception information is obtained. This data is then processed using neural networks and perception fusion models to ensure that environmental perception information can still be output even when sensors are damaged.
🎯Benefits of technology
Even if any sensor fails, the system can still output independent environmental perception information, thus improving vehicle safety and driving stability.
✦ Generated by Eureka AI based on patent content.
Smart Images
Figure CN115205803B_ABST
Abstract
The present application relates to the technical field of automatic driving, and particularly provides an automatic driving environment perception method, medium and vehicle, aiming to solve the technical problem that environment perception information cannot be obtained when any one of a vehicle camera or a laser radar is damaged in the prior art. To this end, the automatic driving environment perception method comprises: acquiring first target detection information based on image data from a camera; acquiring second target detection information based on point cloud data from a laser radar; acquiring relative positioning information and global positioning information based on positioning data from a positioning sensor; fusing the first target detection information, the second target detection information and the relative positioning information to obtain first environment perception information; and fusing the first environment perception information, the relative positioning information and the global positioning information to obtain second environment perception information. In this way, the accuracy of the environment perception information is improved.
Need to check novelty before this filing date? Find Prior Art