Obstacle avoidance methods, devices, electronic equipment, and storage media for automatic parking vehicles
By combining multiple sensors and fusing dual algorithms to overcome obstacles, the problem of blind spots and insufficient accuracy in perception of automatic parking systems in complex scenarios has been solved, achieving high-precision and safe automatic parking control.
CN121822452BActive Publication Date: 2026-05-26MOTOVIS TECH SHANGHAI CO LTD
View PDF 2 Cites 0 Cited by
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- MOTOVIS TECH SHANGHAI CO LTD
- Filing Date
- 2026-03-11
- Publication Date
- 2026-05-26
AI Technical Summary
Technical Problem
Existing automatic parking systems suffer from blind spots, misjudgments, and insufficient accuracy in complex scenarios, resulting in inaccurate parking and potential collision risks.
Method used
A combination of multiple ultrasonic radars and fisheye cameras is used to achieve 360° perception. By combining DTC and LAEB dual-algorithm fusion strategies, the vehicle is safely stopped through graded braking and closed-loop control.
Benefits of technology
It achieves high-precision parking in complex environments, improves perception reliability and safety, reduces the misjudgment rate, and enhances passenger comfort.
✦ Generated by Eureka AI based on patent content.
Smart Images
Figure CN121822452B_ABST
Abstract
This invention discloses an obstacle avoidance method, device, electronic equipment, and storage medium for automatic parking of vehicles. It adopts a combination of multiple ultrasonic radars and multiple fisheye cameras to achieve 360° perception without blind spots. The distance accuracy of the ultrasonic radar and the coordinate accuracy of the fisheye cameras ensure the reliability of perception in complex environments (rainy night, strong light, low obstacles), solve the blind spot and error problems of single sensors, and innovate the "DTC+LAEB dual algorithm fusion" strategy. It achieves a safety distance backup through the "smaller of two distances" logic to avoid misjudgment by a single algorithm. It replaces the traditional open-loop slow braking with three-level control and adjusts the braking pressure through real-time distance deviation. The stopping distance accuracy is improved from ±10cm in the existing solution to ±5cm, solving the problems of "overshoot" and "undershoot".
Need to check novelty before this filing date? Find Prior Art