Skip to main navigation Skip to search Skip to main content

A High-precision Calibration Method for Microsurgical Robots: Combining Iterative Least Squares and PSO-Optimized Support Vector Machine

  • Linjun Pang
  • , Haiming Li
  • , Peiyuan Gao
  • , Haotian Li
  • , He Zhang*
  • , Jie Zhao
  • *Corresponding author for this work
  • Harbin Institute of Technology

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Microsurgical robot calibration is essential for achieving high precision in surgical operations. This paper proposes a high-precision calibration approach combining Iterative Least Squares (ILS) for geometric error correction and Particle Swarm Optimization-optimized Least Squares Support Vector Machine (PSO-LSSVM) for non-geometric error compensation. Experimental results show that the proposed method reduces positioning errors from 3.2541 mm to 0.2310 mm through geometric calibration, achieving a 92.90 % accuracy improvement, and further reduces the error to 0.0749 mm after non-geometric error compensation.

Original languageEnglish
Title of host publication2025 11th International Conference on Mechatronics and Robotics Engineering, ICMRE 2025
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages99-103
Number of pages5
ISBN (Electronic)9798331509293
DOIs
StatePublished - 2025
Event11th International Conference on Mechatronics and Robotics Engineering, ICMRE 2025 - Lille, France
Duration: 24 Feb 202526 Feb 2025

Publication series

Name2025 11th International Conference on Mechatronics and Robotics Engineering, ICMRE 2025

Conference

Conference11th International Conference on Mechatronics and Robotics Engineering, ICMRE 2025
Country/TerritoryFrance
CityLille
Period24/02/2526/02/25

Keywords

  • Robot Calibration
  • kinematics
  • microsurgical robot

Fingerprint

Dive into the research topics of 'A High-precision Calibration Method for Microsurgical Robots: Combining Iterative Least Squares and PSO-Optimized Support Vector Machine'. Together they form a unique fingerprint.

Cite this