Nonlinear back-end optimization method for VSLAM with multi-convex combined maximum correntropy criterion

Lan Cheng; Ting Wang; Xinying Xu; Gaowei Yan; Mifeng Ren; Zhe Zhang

doi:10.1016/j.isatra.2023.08.006

Nonlinear back-end optimization method for VSLAM with multi-convex combined maximum correntropy criterion

ISA Trans. 2023 Nov:142:731-746. doi: 10.1016/j.isatra.2023.08.006. Epub 2023 Aug 8.

Authors

Lan Cheng¹, Ting Wang², Xinying Xu³, Gaowei Yan⁴, Mifeng Ren⁵, Zhe Zhang⁶

Affiliations

¹ College of Electrical and Power Engineering, Taiyuan University of Technology, Taiyuan, 030024, China. Electronic address: chenglan@tyut.edu.cn.
² College of Electrical and Power Engineering, Taiyuan University of Technology, Taiyuan, 030024, China. Electronic address: wangting0389@link.tyut.edu.cn.
³ College of Electrical and Power Engineering, Taiyuan University of Technology, Taiyuan, 030024, China. Electronic address: xuxinying@tyut.edu.cn.
⁴ College of Electrical and Power Engineering, Taiyuan University of Technology, Taiyuan, 030024, China. Electronic address: yangaowei@tyut.edu.cn.
⁵ College of Electrical and Power Engineering, Taiyuan University of Technology, Taiyuan, 030024, China. Electronic address: renmifeng@tyut.edu.cn.
⁶ College of Electrical and Power Engineering, Taiyuan University of Technology, Taiyuan, 030024, China. Electronic address: zhangzhe@tyut.edu.cn.

PMID: 37596149
DOI: 10.1016/j.isatra.2023.08.006

Abstract

Back-end optimization plays a key role in eliminating the accumulated error in Visual Simultaneous Localization And Mapping (VSLAM). Existing back-end optimization methods are usually premised on the Gaussian noise assumption which does not always hold true due to the non-convex nature of the image and the fact that non-Gaussian noises are often encountered in real scenes. In view of this, we propose a back-end optimization method based on Multi-Convex combined Maximum Correntropy Criterion (MCMCC). A MCMCC-based cost function is first tailored for nonlinear back-end optimization in the context of VSLAM and the optimization problem is solved through Levenberg-Marquardt algorithm iteratively. Then, the proposed method is applied to ORB-SLAM3 to test its performance on public indoor and outdoor datasets. The real time performance is also validated using a RaceBot platform in real indoor and outdoor environments. In addition, the reprojection error is statistically analyzed to demonstrate the non-Gaussian characteristics in the back-end optimization process. Finally, the suggestion parameters are also provided through experiments for further study.

Keywords: Back-end optimization; Maximum correntropy criterion; Non-Gaussian noises; Visual SLAM.