Research on SLAM Based on the Fusion of Stereo Vision and Inertial Measurement Unit

With the continuous improvement of positioning technology and industry demand, the shortcomings of each sensor are constantly amplified. Only relying on a single sensor, the demand of high-precision positioning and mapping for intelligent vehicles is difficult to be satisfied. The accuracy of system positioning and mapping is reduced due to the loss of feature points in pure visual SLAM as the environmental characteristics are not obvious or the texture is not abundant. IMU is a sensor with low cost and high update frequency, which can correct the running trajectory in real time and reduce the error of environmental factors on visual sensor data. Therefore, a method based on ORB_SLAM2 algorithm and VINS-Fusion algorithm, the stereo camera information and inertial measurement unit information are extracted and fused in robot operating system is proposed. ORB_SLAM2 algorithm is adopted as the main body and the feature point matching of ORB_SLAM2 algorithm is employed to enhance the mapping effect. While the tightly-coupled approach to visual information and inertial measurement unit information in VINS-Fusion algorithm is integrated into ORB_SLAM2 algorithm to achieve higher-precision synchronous positioning and mapping, and improve the robustness of the system. The tracked vehicle is tested in an appropriate scenario. On the basis of the testing results, it can be proved that the positioning and mapping effect of SLAM system fused with inertial measurement unit information is significantly improved compared with pure visual SLAM system. It can also be attested indirectly that the ORB_SLAM2 algorithm tightly-coupled with inertial measurement unit can effectively improve the global consistency of the localization trajectory, furthermore improve the accuracy and robustness of SLAM system.