一种基于多传感器融合的AGV定位导航方法及装置
By using multi-sensor fusion technology, combining visual and ultra-wideband positioning information, high-precision environmental modeling and dynamic obstacle avoidance are achieved, solving the problem of insufficient positioning accuracy of traditional AGVs in complex environments and realizing efficient and reliable navigation and path planning.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- 广州乐比机器人有限公司
- Filing Date
- 2025-09-17
- Publication Date
- 2026-07-17
AI Technical Summary
Traditional AGV positioning and navigation methods suffer from insufficient accuracy and poor robustness in complex dynamic environments, making it difficult to provide continuous and stable positioning data. In particular, they are unable to achieve efficient and reliable path planning and obstacle avoidance in environments with changing lighting, occlusion, or other variable conditions.
By employing multi-sensor fusion technology, combining real-time visual detection video and ultra-wideband positioning information, super-resolution optimization and global topology perception modeling are performed to construct a real-time scene physical perception map. Abnormal object detection and obstacle avoidance fine-tuning are performed by combining lidar detection parameters. Dynamic response compensation and adaptive learning are achieved through intelligent obstacle avoidance path planning and time deviation calculation.
It improves the positioning accuracy and navigation stability of AGVs in complex environments, enhances the ability to perceive dynamic obstacles, ensures the accuracy and efficiency of path planning, and improves the autonomy and robustness of AGVs in changing environments.
Smart Images

Figure CN121274968B_ABST
Abstract
Citation Information
Patent Citations
Self-healing oxides for ionizing radiation damage
US20250051212A1
AGV positioning navigation method based on binocular vision, IMU and UWB fusion
CN114323002A
Real-time dynamic intelligent path planning method and system based on multi-sensor information fusion
CN116678394A