Mats Isaksson

Prof. Mats Isaksson

Swinburne University of Technology, Melbourne, Victoria, Australia
orcid

Research Focus & Metrics

Academic Career Length

22Years (2005-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
26 September 2005 in IEEE Robotics & Automation Magazine
Verified
Journal Article
Closed access
ABA. Blomdell
A. Blomdell
GBG. Bolmsjo
G. Bolmsjo
TBT. Brogardh
T. Brogardh
PCP. Cederberg
P. Cederberg
MIMats Isaksson
Mats Isaksson
JWJianjun Wang
Jianjun Wang
This paper describes the design and implementation of a platform for fast external sensor integration in an industrial robot control system. As an application and motivating example, the implementation of force controlled grinding and deburring within the AUTOFETT-project (EU Growth Programme) is reported.

1 June 2016
Verified
Conference Paper
Open access
AEAnders Eriksson
Anders Eriksson
JBJohn Bastian
John Bastian
TCTat-Jun Chin
Tat-Jun Chin
MIMats Isaksson
Mats Isaksson
In this paper we study large-scale optimization problems in multi-view geometry, in particular the Bundle Adjustment problem. In its conventional formulation, the complexity of existing solvers scale poorly with problem size, hence this component of the Structure-from-Motion pipeline can quickly become a bottle-neck. Here we present a novel formulation for solving bundle adjustment in a truly distributed manner using consensus based optimization methods. Our algorithm is presented with a concise derivation based on proximal splitting, along with a theoretical proof of convergence and brief discussions on complexity and implementation. Experiments on a number of real image datasets convincingly demonstrates the potential of the proposed method by outperforming the conventional bundle adjustment formulation by orders of magnitude.

1 July 2016 in Mechanism and Machine Theory
Verified
Journal Article
Closed access
MIMats Isaksson
Mats Isaksson
CGClément Gosselin
Clément Gosselin
KMKristan Marlow
Kristan Marlow

25 August 2022 in IEEE Transactions on Medical Robotics and Bionics
Verified
Journal Article
Closed access
MRMariadas Capsran Roshan
Mariadas Capsran Roshan
APAdrian Pranata
Adrian Pranata
MIMats Isaksson
Mats Isaksson
This systematic review was conducted to synthesize and critically appraise the current evidence on the automation of non-invasive diagnostic ultrasonography using robots. Medline, Scopus, EMBASE, Web of Science, and Pubmed databases were searched using a defined search strategy. Eighteen studies were included for consideration after reviewing 1,932 studies. Through appraisal, the selected studies were found to be of high quality. An automated ultrasound examination can be divided into two stages. The first stage involves localization of the region of interest and moving the probe close to that region, while the second stage involves manipulating the probe configuration around the region of interest to scan and acquire an optimized image. Although the second stage was fully automated in all the analyzed systems, the first initialization stage requires full or partial assistance from the sonographer in 11 of the systems. Future studies should propose novel methods to perform these procedures without the sonographer’s aid. Fourteen studies used a combination of visual and force feedback to control the scanning and optimization. The utilization of ultrasound image feedback for probe manipulation during this process has the potential to improve the accuracy and robustness of the system.

29 April 2016 in Journal of Mechanical Design
Verified
Journal Article
Closed access
PDF file
KMKristan Marlow
Kristan Marlow
MIMats Isaksson
Mats Isaksson
Jian S DaiJian S Dai
Jian S Dai
SNSaeid Nahavandi
Saeid Nahavandi

8 February 2017 in Journal of Mechanical Design
Verified
Journal Article
Closed access
PDF file
MIMats Isaksson
Mats Isaksson