Adaptive Graduated Non-Convexity for Pose Graph Optimization

2023/08/22 by Seungwon Choi, Won‐Seok Kang, Choi, Seungwon +7
Computer Science · Engineering · #FOS: Computer and information sciences #Hand Gesture Recognition Systems #Human Pose and Action Recognition #Robotics (cs.RO) #Robotics and Sensor-Based Localization

paper · pdf · doi:10.48550/arxiv.2308.11444

openalex publication_date 2023/08/22 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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

Related

• Efficient Graduated Non-Convexity for Pose Graph Optimization
• A Decoupled and Linear Framework for Global Outlier Rejection over Planar Pose Graph
• Matrix Difference in Pose-Graph Optimization
• A Recursive Least Square Method for 3D Pose Graph Optimization Problem
• Convex Relaxations for Pose Graph Optimization with Outliers