English

Adaptive Graduated Non-Convexity for Pose Graph Optimization

Robotics 2023-09-26 v2

Abstract

We present a novel approach to robust pose graph optimization based on Graduated Non-Convexity (GNC). Unlike traditional GNC-based methods, the proposed approach employs an adaptive shape function using B-spline to optimize the shape of the robust kernel. This aims to reduce GNC iterations, boosting computational speed without compromising accuracy. When integrated with the open-source riSAM algorithm, the method demonstrates enhanced efficiency across diverse datasets. Accompanying open-source code aims to encourage further research in this area. https://github.com/SNU-DLLAB/AGNC-PGO

Keywords

Cite

@article{arxiv.2308.11444,
  title  = {Adaptive Graduated Non-Convexity for Pose Graph Optimization},
  author = {Seungwon Choi and Wonseok Kang and Jiseong Chung and Jaehyun Kim and Tae-wan Kim},
  journal= {arXiv preprint arXiv:2308.11444},
  year   = {2023}
}

Comments

4 pages, 3 figures. Accepted for the workshop on Robotic Perception and Mapping(ROPEM): Frontier Vision & Learning Techniques, organized at the 2023 International Conference on Intelligent Robots and Systems (IROS)

R2 v1 2026-06-28T12:01:30.242Z