Robust and dense visual SLAM for robotic-guided minimally invasive orthopedic procedures

This project aims to develop a vision-based robotic surgical assistant for minimally invasive orthopedic procedures. The system would be composed of a robotic arm with an attached camera-arthroscope bundle for intra-articular navigation. The system will be capable of a) localizing instruments robustly and reliably inside the human joints; b) generating dense and accurate 3D reconstructed models of the knee joint from intra-articular images; and c) semi-autonomously navigating the camera (via visual servoing) to follow the surgeons’ tools.


  • Dataset [Cadaveric and phantom experiments for the validation of SLAM algorithms for minimally invasive orthopedics procedures. Please see README file for further details. Data acquisition was approved by the Australian National Health and Medical Research Council (NHMRC) – Registered Committee Number EC00171 under Approval Number 1400000856.]

Contacts: Andres Marmol, Thierry Peynot, Jonathan Roberts

Author - Andres Marmol

Andres Marmol

Andres F. Marmol V. completed a BSc. in Mechatronics (2008) in Colombia with an honorific mention for his thesis in the retrofitting of a 3DoF milling machine. Afterwards, he engaged educational activities at two universities prior his relocation to Germany. At the Hamburg University of Technology (TUHH) he completed with distinction his MSc. Mechatronics (2011) devoting his thesis to medical imaging reconstruction. Upon the completion of his studies, Mr. Marmol enrolled as a research assistant at the TUHH until he decided to turn to industry and joined one of the world-leading companies in machine vision and industrial image processing: ISRA Vision AG (2012). At this German company he was in charge of the technical commissioning and maintenance of diverse vision-guided robotic solutions for the car industry. After one year, he took over administrative responsibilities as on-site project manager for Mercedes Benz-South Africa and Jaguar Land Rover-UK. Mr. Marmol is currently pursuing his PhD degree as part of the QUT team in the Australian Centre for Robotic Vision. His PhD research is focused on robotic knee arthroscopy, developing a vision-guided robotic system to assist doctors during strenuous surgical procedures.

Category: Datasets
Posted 07 January 2019

Australian Centre for Robotic Vision
2 George Street Brisbane, 4001
+61 7 3138 7549