Multi-sensor combined calibration device and method

Abstract

The invention provides a multi-sensor combined calibration device and method, and relates to a multi-sensor calibration technology. The problem of multi-sensor combined calibration in the prior art issolved. The multi-sensor combined calibration device comprises a mechanical arm, a sensor fusion frame is arranged on the mechanical arm; a laser radar, a monocular camera and a computer for processing data are arranged on the sensor fusion frame, the sensor fusion frame further comprises a laser radar-camera four-calibration-plate combined calibration target, and the laser radar-camera four-calibration-plate combined calibration target comprises a first calibration plate, a second calibration plate, a third calibration plate and a fourth calibration plate; the central positions of the firstcalibration plate, the second calibration plate and the third calibration plate are marked by dots, and the dots are used for providing feature points for external parameter calibration. According tothe embodiment of the invention, the portable multi-sensor fusion framework is built, so that calibration and secondary development are facilitated; according to the embodiment of the invention, a mechanical arm auxiliary calibration method is used, and intelligent calibration and batch calibration can be realized.

Description

technical field [0001] The invention belongs to the technical field of sensors, in particular to a multi-sensor calibration technology. Background technique [0002] Simultaneous Localization and Mapping (SLAM) technology provides environment perception information for unmanned driving. Traditional SLAM technology is divided into laser SLAM and visual SLAM. Lidar has the advantages of high ranging accuracy and no influence of light. , the camera has the advantages of low cost and rich image information; however, single-sensor SLAM has great limitations, for example, the lidar update frequency is slow, there is motion distortion, and it cannot provide accurate measurements in harsh environments such as rain and snow value; the camera cannot obtain accurate 3D information, and is limited by ambient light. [0003] An inertial navigation system acts as a pose estimation aid, providing accurate angular velocity and angular velocity. Therefore, the fusion of multi-sensor data s...

AI Technical Summary

Problems solved by technology

The traditional calibration method is the hand-eye calibration method, but its calibration accuracy is difficult to guarantee; Baidu's Apollo calibration tool controls the vehicle to move around the "8" to realize sensor data collection and external parameter calibration

[0008] Multi-sensor joint calibration is currently one of the hottest topics in the field of unmanned driving. The existing calibration technology has a low degree of automation, and has disadvantages such as cumbersome operation and low accuracy.

Images