Autonomous mobile platform, external parameter optimization method, device and storage medium

Abstract

The invention relates to the field of artificial intelligence, and provides an autonomous mobile platform, a device, an external parameter optimization method and a readable storage medium. In the present invention, the autonomous mobile platform synchronously records the image of the calibration board captured by the camera, the sensing data of the first sensor, and the sensing data of the second sensor when running in the pre-deployed calibration scene, and the recorded image / data Import the relevant algorithm to carry out the calibration operation. First, the preliminary calibration will be performed to obtain the first extrinsic parameter between the first sensor and the camera and the second extrinsic parameter between the second sensor and the camera. The first extrinsic parameter, the second extrinsic parameter, the constraint residual of the camera pose, and the visual reprojection error are used for optimal calibration. This optimal calibration method can simultaneously calculate the extrinsic parameters of multiple sensors at one time, not the traditional decoupling solution. , but coupled together for optimization, while reducing the number of calibrations, it can also achieve millimeter-level calibration accuracy.

Description

technical field [0001] The invention relates to the field of artificial intelligence, in particular to an autonomous mobile platform, an external parameter optimization method, a device and a storage medium. Background technique [0002] With the explosion of artificial intelligence technology, the research and development and implementation of various autonomous mobile platforms that can drive automatically have also received extensive attention. Positioning technology is the core technology of this type of autonomous mobile platform, and its related academic research and practical implementation have also been extensively researched and explored. [0003] In recent years, vision-based indoor positioning technology has made great progress. Due to the relatively low price of the camera sensor used and the large amount of collected data information, the visual positioning technology can be more robust to complete the work requirements such as perception and relocation, and h...

AI Technical Summary

Problems solved by technology

However, the positioning scheme based on pure vision is also affected by irresistible factors such as illumination changes, motion blur, and occlusion due to visual positioning, and it cannot achieve the robustness of the laser positioning scheme for the time being. just in time

Images