Paper Accepted at Number 1 Robotics Conference

The following paper was accepted for publication at the number 1 robotics conference in the world.

Atle Aalerud and Geir Hovland, “Benchmarking Perception Latencies in a Human-Robot Collaborative Environment”, Proc. of IEEE Intl. Conference on Robotics and Automation (ICRA), Paris, France, June 2020.

One of the reviewers wrote: Overall, I believe this paper is significant for the field in that the authors are taking steps to better capture the performance of camera-based systems for safety applications.

ICRA received over 3,512 submissions, a new record, from 64 countries. Overall, 3,446 papers were reviewed: 2,456 for ICRA 2020 and 990 for the IEEE Robotics and Automation Letters (RA-L). The 10 most popular keywords, in descending order, were: Deep Learning in Robotics and Automation, Motion and Path Planning, Localization, Learning and Adaptive Systems, Autonomous Vehicle Navigation, Multi-Robot Systems, SLAM, Object Detection, Segmentation and Categorization, and Visual-Based Navigation. From the very large number of high-quality papers we selected 1,483 for presentation which represents an acceptance rate of 42%.

Best Presentation Award at IEEE Conference

The PhD candidate Dipendra Subedi (WP3.6) received the Best Presentation Award in Session 2: System Control and Management Engineering at the 2020 IEEE 11th International Conference on Mechanical and Intelligent Manufacturing Technologies,

The presentation was based on the following paper: Dipendra Subedi, Ilya Tyapin and Geir Hovland, “Modeling and Analysis of Flexible Bodies Using Lumped Parameter Method”, 2020 IEEE 11th International Conference on Mechanical and Intelligent Manufacturing Technologies (ICMIMT 2020), January 20-22, 2020, Cape Town, South Africa.

In addition to funding from SFI Offshore Mechatronics, the work was also funded by the spin-off project titled “Lifting and Assembly Manipulator for Improved Efficiency of Construction Processes” which was funded by the Research Council of Norway, project number 261647/O20, under the BIA Program and led by the industry partner MacGregor Norway AS. The project started in Q3-2016 and was completed in Q4-2019.

GCE NODE Publishes a Series of Articles about SFI Offshore Mechatronics

SFI Offshore Mechatronics, here represented by the Chairman of the Board, Leif Haukom.

GCE NODE has published a series of articles about SFI Offshore Mechatronics. Below are the links to these articles:

SFI Offshore Mechatronics – A Driver for Innovation:

SFI Product on Autonomous Vessel:

Companies Attitude to Research Has Changed:

New Research Project Funded

In the project DEEPCOBOTS, researchers from several professional backgrounds at UiA will work together to develop collaborative robots for use in industry in southern Norway. Top left: Professor Geir Grasmo, Head of Department of Engineering Sciences; Associate Professor Ilya Tyapin, Department of Engineering Sciences, Associate Professor Linga Reddy Cenkeramaddi from the Department of ICT; Professor Jing Zhou, project manager from the Department of Engineering Sciences; Professor Baltasar Beferull-Lozano from the Department of ICT (by courtesy, member of the Department of Engineering Sciences).

Title: Collective Efficient Deep Learning and Networked Control for Multiple Collaborative Robot Systems (DEEPCOBOT)
Research programme: Ubiquitous Data and Services-Researcher Project, Research Council of Norway
Financing from research council: 16 MNOK
Own financing from UiA: 3.5 MNOK
In Total: 19.5 MNOK

PhD Thesis Submitted WP1.2

Sondre Nordås, WP1.2, submitted his PhD thesis on December 15, 2019. The title of the thesis is: Using Digital Hydraulics in Secondary Control of Motor Drive. This is the first PhD thesis completed in work-package 1.

New Innovation Projects Funded

On December 16 the Research Council of Norway announced the new projects funded through the “Innovation Projects in Industry” (IPN) program, see:

In total 352 applications where received from companies all over Norway before the September 25 application deadline. In total 1,25 billion NOK will be handed out to the highest ranked projects.

Two partner companies in SFI Offshore Mechatronics were successful in this round. The the topics in both projects are directly linked to topics being worked on in the centre. The projects are:

MacGregor Norway AS, Project Number 309895. Increasing Operational Efficiency by Retrofitting Sensor-Based Anti-Swing Technology on Offshore Cranes. Funding received 2,625 MNOK. Researchers in SFI Offshore Mechatronics WP3 Robotics and Autonomy will participate in this project.

National Oilwell Varco Norway AS, Project Number 310050. Next generation fiber rope system product for real-time fiber rope condition monitoring. Funding received 9,0 MNOK.

The IPN scheme requires the companies to contribute 50% of the funding themselves, so the total budgets of these two projects are 23,25 MNOK.

As the centre is now in the second half of it’s funding period, the centre administration of SFI Offshore Mechatronics plans to increase it’s effort towards new spin-off projects and activities. The next funding deadlines in Norway are in May and September 2020.

New Researcher WP3.7

Ronny Landsverk started working on WP3.7 in Q1-2019. The title of his work package is: “Coupled Dynamics between Vessel and Crane”. He has an MSc from UiA within Mechatronics. The main supervisor of this project is Professor Jing Zhou. This work-package was created with additional funding from UiA.

New Researcher WP2.7

Hans Kristian Holen started working on WP2.7 as an integrated PhD in February 2019 and as a full time PhD from June 2019. He has a MSc degree in Mechanical Engineering from NTNU, 2019, a BSc in Mechanical Engineering from UiS, 2016 and a year of economic studies at NHH in 2017. The title of his project is: Vision systems for supervision of offshore drilling operations.

New Researcher WP3.6

Dipendra Subedi started as a PhD Research Fellow at University of Agder (UiA, Norway) under WP3.6 on 22 February 2019 with Associate Professor Ilya Tyapin and Geir Hovland as supervisors. Subedi holds a B.E. degree in Electrical and Electronics Engineering (Anna University, India) and a Joint Master’s Degree in Advanced Robotics (University of Genoa, Italy and Jaume I University, Spain). He worked as a Robotics Software Engineer at Dorabot Inc., China for 1 year before starting his PhD at UiA.

In the SFI, he is working on Instrumentation and Real-Time Control of Long-Reach Light-Weight Arm for Offshore Use.

WP7 Workshop on Machine Learning, November 29

When: Friday, November 29, 2019 9:00 AM-12:30 PM.
Location: GCE NODE, Tordenskjoldsgate 9, Kristiansand

09:00 – 09:10 Welcome & Coffee
09:10 – 09:45 Advancing Machine Learning and Optimization: Algorithms and Applications
09:55 – 10:10 Questions & discussion
10:10 – 10:40 Bringing SFI OM results forward with EU funding
10:40 – 10:50 Questions & discussion
10:50 – 11:00 Break
11:00 – 11:30 Innovation in ocean technology
11:30 – 12:30 Lunch

Advancing Machine Learning and Optimization: Algorithms and Applications
Professor Thomas Bäck
Leiden Institute of Advanced Computer Science, Leiden University, Netherlands

Today, industrial production processes generate a significant amount of process data through sensor measurements. In this talk, I will show how data-driven machine learning and optimization algorithms can be enhanced and applied to such processes for optimizing, e.g., process quality criteria. Like for many other datacentric application domains, it is impossible to apply analytical methods to such a task.

Instead, a range of methods including supervised learning (regression and/or classification), hyperparameter optimization, and evolutionary optimization need to be combined and applied, often in an automatic way. Moreover, enhancements of such algorithms need to be developed to fit the requirements of such industrial processes, including the on-line application of predictive models.

To illustrate this approach towards data-driven machine learning in industrial processes, some practical examples from industries such as automotive are discussed.

My fundamental research activities are often driven by the requirements of practical applications. In the talk, I will provide some examples such as my research in efficient global optimization, automatic configuration of evolutionary strategies, and online algorithm configuration of optimization algorithms – all of which are directly related to the area of automatic machine learning.

The talk concludes by providing a short overview of my other research topics and industrial projects in my research group.

Brief Biography:
Thomas Bäck is full professor of computer science at the Leiden Institute of Advanced Computer Science (LIACS), Leiden University, The Netherlands, since 2004. His research interests are in evolutionary and Bayesian optimization, machine learning, and data mining.

He received his PhD in Computer Science (under supervision of Hans-Paul Schwefel) from Dortmund University, Germany, in 1994, and then worked for the Informatik Centrum Dortmund (ICD) as department leader of the Center for Applied Systems Analysis. From 2000-2009, Thomas was President of NuTech Solutions GmbH and CTO of NuTech Solutions, Inc. In his work with industrial partners in the industry 4.0 domain, he develops solutions with companies such as BMW, Daimler, Honda, Tata Steel, and KLM – to name a few.

Thomas Bäck has more than 350 publications (H-Index: 56) and authored a book on evolutionary algorithms, (Evolutionary Algorithm in: Theory and Practice). He is co-editor of the Handbook of Evolutionary Computation and the Handbook of Natural Computing, and co-author of the book Contemporary Evolution Strategies (Springer, 2013). He is editorial board member of a number of journals, co-Editor-in-Chief of Theoretical Computer Science C (Elsevier) and the Natural Computing Book Series (Springer), and has served as program chair for major conferences in evolutionary computation. He received the best dissertation award from the Gesellschaft für Informatik (GI) in 1995 and is an elected fellow of the International Society for Genetic and Evolutionary Computation for his contributions to the field. In 2015, he received the IEEE Evolutionary Computation Pioneer Award for his contributions in synthesizing evolutionary computation.