SoftICE presenting intelligent virtual prototyping at ECMS 2017

SoftICE members Robin T. Bye and Ibrahim A. Hameed will be presenting some recent research results on intelligent virtual prototyping of maritime winches in two scientific papers to be presented at the 31st European Conference on Modelling and Simulation (ECMS) 2017 in Budapest, Hungary, on 23–26 May. The papers are co-authored by the two abovementioned researchers together with SoftICE colleagues Ottar L. Osen and  Webjørn Rekdalsbakken, as well as Birger Skogeng Pedersen (Mechatronics Lab, NTNU):

  • Robin T. Bye, Ibrahim A. Hameed, Birger Skogeng Pedersen, and Ottar L. Osen. An intelligent winch prototyping tool. In Proceedings of the 31st European Conference on Modelling and Simulation (ECMS ’17), May 2017. Download pdf.
  • Ibrahim A. Hameed, Robin T. Bye, Birger Skogeng Pedersen, and Ottar L. Osen. Evolutionary winch design using an online winch prototyping tool. In Proceedings of the 31st European Conference on Modelling and Simulation (ECMS ’17), May 2017. Download pdf.

A Prezi presentation of the first paper is available here:

Interactive Prezi presentation: An Intelligent Winch Prototyping Tool (ECMS’17)The full papers are available for download here:  http://www.robinbye.com | Publications

The paper abstracts are provided at the end of this blog post.

Intelligent computer-automated design of cranes and winches

W build on our earlier work on intelligent computer-automated product design, where we have used methods from artificial intelligence (AI) such as genetic algorithms (GAs), particle swarm optimisation (PSO), and simulated annealing (SA) to optimise offshore crane design. Within a matter of only minutes, the algorithms were able to outperform the design of a real and delivered offshore crane with respect to some desired key performance indicators (KPIs). A human being would likely spend days or weeks to obtain the same results.

Generic and modular product optimization system.

Here, we focus on an intelligent winch prototyping tool (WPT):

Intelligent Winch Prototyping Tool (WPT)

We perform several test with various algorithms and are able to optimize a set of winch design parameter values that yield winch designs with suitable torque profiles:

Torque profiles for winch. The black profile has been optimized by means of a GA.

Abstract: An intelligent winch prototyping tool

In this paper we present a recently developed intelligent winch prototyping tool for ptimising the design of maritime winches, continuing our recent line of work using
artificial intelligence for intelligent computer-automated design of offshore cranes. The tool consists of three main components: (i) a winch calculator for determining key
performance indicators for a given winch design; (ii) a genetic algorithm that interrogates the winch calculator to optimise a chosen set of design parameters; and (iii) a web graphical user interface connected with (i) and (ii) such that winch designers can use it to manually design new winches or optimise the design by the click of a button. We demonstrate the feasibility of our work by a case study in which we improve the torque profiles of a default winch design by means of optimisation. Extending our generic and modular software framework for intelligent product optimisation, the winch calculator can easily be interfaced to external product optimisation clients by means of the HTTP and WebSocket protocols and a standardised JSON data format. In an accompanying paper submitted concurrently to this conference, we present one such client developed in Matlab that incorporates a variety of intelligent algorithms for the optimisation of maritime winch design.

Abstract: Evolutionary winch design using an online winch prototyping tool

This paper extends the work of a concurrent paper on an intelligent winch prototyping tool (WPT) that is part of a generic and modular software framework for intelligent computer-automated product design. Within this framework, we have implemented a Matlab winch optimisation client (MWOC) that connects to the WPT and employs four evolutionary optimisation algorithms to optimise winch design. The four algorithms we employ are (i) a genetic algorithm (GA), (ii) particle swarm optimisation (PSO), (iii) simulated annealing (SA), and (iv) a multi-objective optimisation genetic algorithm (MOOGA). Here, we explore the capabilities of MWOC in a case study where we show that given a set of design guidelines and a suitable objective function based on these guidelines, we are able to optimise a particular winch design with respect to some desired design criteria. Our research has taken place in close cooperation with two maritime industrial partners, Seaonics AS and ICD Software AS, through two innovation and research projects on applying artificial intelligence for intelligent computer-automated design of maritime equipment such as offshore cranes and maritime
winches.

More information

We have previously presented some details of our work on intelligent virtual prototyping of cranes and winches in earlier blog posts:

Acknowledgements

The SoftICE lab at NTNU in Ålesund wishes to thank ICD Software AS for their contribution in the software development process, and Seaonics AS for providing
documentation and insight into the design and manufacturing process of offshore cranes. We are also grateful for the support provided by Regionalt Forskningsfond
(RFF) Midt-Norge and the Research Council of Norway through the VRI research projects Artificial Intelligence for Crane Design (Kunstig intelligens for krandesign
(KIK)), grant no. 241238, and Artificial Intelligence for Winch Design (Kunstig intelligens for vinsjdesign (KIV)), grant no. 249171.

Collaboration?

Parties interested in research collaboration, testing our software, or more information are encouraged to contact us.

The SoftICE Lab

NTNU Ålesund students win prestigious automation engineering award on USVs for aqua farm inspection

Better late than never!

In February 2017, bachelor students of automation engineering at NTNU Ålesund, Albert Havnegjerde, Vegard Kamsvåg og Sveinung Liavaag, won the prestigious Norwegian national award for the best bachelor thesis 2016 on automatic control given by the Norwegian Society for Automatic Control (NFA).

Jury member Rune Volden from Ulstein Power & Control hands over the award to NTNU Ålesund students Sveinung Liavaag and Albert Havnegjerde. Vegard Kamsvåg was unable to attend. Image courtesy: NFA

The students also co-wrote a paper based on their work together with SoftICE members Robin T. Bye and Ottar L. Osen (student supervisor) that was presented at IEEE Techno-Ocean 2016 and subsequently published in the proceedings:

  • Ottar L. Osen, Albert Havnegjerde, Vegard Kamsvåg, Sveinung Liavaag, and Robin T. Bye. A Low Cost USV for Aqua Farm Inspection. In Proceedings of IEEE Techno-Ocean ’16, pages 291–298, October 2016.

In their work, the students employed rapid prototyping to develop a low cost (~2000 EUR) remotely controlled unmanned surface vessel (USV) intended for inspection of aqua farms whilst incorporating a dynamic positioning (DP) system.

This work was partly financed by an internal educational project called Research-based and Innovation-driven Learning through Final Year Projects (Forskningsbasert og innovasjonsdrevet læring gjennom avsluttende oppgave – FILA).

The full paper and the conference presentation is available for download here: www.robinbye.com | Publications

Abstract: A Low Cost USV for Aqua Farm Inspection

This paper describes the rapid prototyping of a low cost remotely controlled unmanned surface vessel (USV) intended for inspection of aqua farms. There is an increased focus on inspection of ocean-based aqua farms due to three major challenges: escaping fish, sea lice, and algae. Escaping fish may bring diseases to other fish or interbreed with wild fish and damage their gene material. Sea lice is a parasite that may seriously damage the fish, lower its food quality, and if not treated, can spawn and multiply into an epidemic. Finally, algae blooms may lower oxygen levels and kill the fish. To proactively counter these challenges, aqua farm operators need to regularly inspect the fish cages for holes, the water for algae, and the fish for sea lice. Modern ocean-based aqua farms are usually constructed with two rows of sea cages separated by a gangway in the middle, often with a small operation and machinery building at one end. Staff visually inspect the cages from above and from the nearside by walking up and down the gangway. Inspection of the outer side of a cage will normally require a boat with a human inspector on board, whereas subsea inspection will normally require a human diver. Here, we propose a USV design solution for this kind of inspection that provides the aqua farm operator with a remotely controlled unmanned boat and subsea video feed. A working prototype has been designed in less than six months and successfully tested at sea.

Index Terms—USV; ROV; dynamic positioning; low cost; commercial off-the-shelf; rapid prototyping; aquaculture.

SoftICE presents intelligent virtual prototyping and mind control at ECMS 2016

SoftICE members Robin T. Bye, Ottar L. Osen, and Ibrahim A. Hameed will be presenting flaming hot research in four scientific papers to be presented at the 30th European Conference on Modelling and Simulation (ECMS) 2016 to be hold in Regensburg, Germany on 31 May — 3 June. The papers are co-authored by the three abovementioned researchers together with colleagues Hans Georg Schaathun and Birger Skogeng Pedersen (NTNU in Ålesund), Adrian Rutle (University College of Bergen), Filippo Sanfilippo (NTNU in Trondheim), and bachelor graduates Rolf-Magnus Hjørungdal (NTNU in Ålesund) and Tom Verplaetse (Ghent University).

Best paper award?

All four papers received excellent reviews by three independent reviewers, with one paper being nominated for the Best Paper Award and another paper being nominated for both Best Paper Award and Best Student Paper Award. Fingers crossed!

Intelligent computer-automated product design

Two of the papers relate to intelligent computer-automated product design, exemplified by a case study where we use methods from artificial intelligence (AI) such as genetic algorithms (GAs), particle swarm optimisation (PSO), and simulated annealing (SA) to optimise offshore crane design. Within a matter of only minutes, the algorithms are able to outperform the design of a real and delivered offshore crane with respect to some desired key performance indicators (KPIs). A human being would likelly spend days or weeks to obtain the same results.

nomenclature

Main components and load chart of a typical offshore crane.

EEG brain control (“mind control”)

The other two papers relate to EEG brain control, commonly known as “mind control,” for rehabilitation of stroke patients and for control of motorised, electrical wheelchairs.

These papers build on the work done during the bachelor thesis projects by Tom Verplaetse (Interfacing an EEG headset with a 3D simulation for rehabilitation in partially paraplegic stroke victims) and by Rolf-Magnus Hjørungdal and fellow students Fredrik Hoel Helgesen and Daniel Nedregård (Man/machine interaction through EEG).

EEG

Emotiv EPOC EEG headset for brain control.

More information

We have previously presented some details of our work in earlier blog posts:

Presentations, abstracts, and full papers

The titles of the four papers are listed further below, with abstracts, papers, and presentations readily available for download as indicated (also available here: http://robinbye.com | Publications).

Collaboration?

Parties interested in research collaboration, testing our software, or more information are encouraged to contact us.

— SoftICE lab

List of ECMS 2016 papers and presentations

  • Robin T. Bye, Ottar L. Osen, Birger Skogeng Pedersen, Ibrahim A. Hameed, and Hans Georg Schaathun. A software framework for intelligent computer-automated product design. In Proceedings of the 30th European Conference on Modelling and Simulation (ECMS’16), pp. xx–yy, 2016. Download abstract | paperpresentation.
  • Ibrahim A. Hameed, Ottar L. Osen, Robin T. Bye, Birger Skogeng Pedersen, and Hans Georg Schaathun. Intelligent computer-automated crane design using an online crane prototyping tool. In Proceedings of the 30th European Conference on Modelling and Simulation (ECMS’16), pp. xx–yy, 2016. Download abstract | paper | presentation.
  • Tom Verplaetse, Filippo Sanfilippo, Adrian Rutle, Ottar L. Osen, and Robin T. Bye. On Usage of EEG Brain Control for Rehabilitation of Stroke Patients. In Proceedings of the 30th European Conference on Modelling and Simulation (ECMS’16), pp. xx–yy, 2016. Download abstract | paper | presentation.
  • Rolf-Magnus Hjørungdal, Filippo Sanfilippo, Ottar L. Osen, Adrian Rutle, and Robin T. Bye. A Game-based Learning Framework for Controlling Brain-Actuated Wheelchairs. In Proceedings of the 30th European Conference on Modelling and Simulation (ECMS’16), pp. xx–yy, 2016. Download abstract | paper | presentation.

A Riemannian field theory of human movements

Building on his PhD work in neuroengineering and modelling and simulation of human movement control systems, SoftICE member Robin T. Bye has together with researchers Peter D. Neilson and Megan D. Neilson from the Neuroengineering Laboratory at the University of New South Wales, Sydney, co-authored a paper about a Riemannian theory of the entire human body moving in a 3D environment. The paper details a highly mathematical intelligent control engineering approach using Riemannian geometry to develop the intuitive groundwork for a Riemannian field theory of human movement encompassing the entire body moving in gravity and in mechanical interaction with the environment. In particular we present a geodesic synergy hypothesis concerning planning of multi-joint coordinated movements to achieve goals with minimal muscular effort.

The full paper is published in the journal Human Movement Science and can be freely accssed from ScienceDirect.

Citation

Peter D. Neilson, Megan D. Neilson, and Robin T. Bye. A Riemannian Geometry Model of Human Movement: The Geodesic Synergy Hypothesis. Human Movement Science 44: 42–72, 2015.

Selected illustrations

1-s2.0-S0167945715300208-gr4

Drawing of the two-DOF arm moving in the horizontal (x–y)-plane.

1-s2.0-S0167945715300208-gr1

The MATLAB/Simulink geodesic trajectory generator (GTG) simulator for the two-DOF arm moving in the horizontal plane.

Highlights

  • We develop a Riemannian theory of the entire human body moving in a 3D environment.
  • The theory addresses nonlinear inertial interactions within the body and externally.
  • Geometric concepts are explained intuitively to aid access for non-mathematicians.
  • We show how to plan geodesic synergies to achieve task goals with minimum effort.
  • We integrate the theory with previous descriptions of response planning and control.

Abstract

Mass-inertia loads on muscles change with posture and with changing mechanical interactions between the body and the environment. The nervous system must anticipate changing mass-inertia loads, especially during fast multi-joint coordinated movements. Riemannian geometry provides a mathematical framework for movement planning that takes these inertial interactions into account. To demonstrate this we introduce the controlled (vs. biomechanical) degrees of freedom of the body as the coordinate system for a configuration space with movements represented as trajectories. This space is not Euclidean. It is endowed at each point with a metric equal to the mass-inertia matrix of the body in that configuration. This warps the space to become Riemannian with curvature at each point determined by the differentials of the mass-inertia at that point. This curvature takes nonlinear mass-inertia interactions into account with lengths, velocities, accelerations and directions of movement trajectories all differing from those in Euclidean space. For newcomers to Riemannian geometry we develop the intuitive groundwork for a Riemannian field theory of human movement encompassing the entire body moving in gravity and in mechanical interaction with the environment. In particular we present a geodesic synergy hypothesis concerning planning of multi-joint coordinated movements to achieve goals with minimal muscular effort.

Parallel Randomness

dice

My latest paper Evaluation of splittable pseudo-random generators has appeared online last week in the Journal of Functional Programming.

What is the big deal of randomness? Randomness is the key to several common applications of computers, including games and secure communication to name but two of the most obvious ones. Games, such as lotteries and poker, are obviously supposed to be random. Imperfect randomness amounts to loading the dice. Secure communications may be less obvious to the uninitated, but the cryptography which is used to keep secrets depends on random keys to be secure. Loaded dice gives the attacker or intruder an edge. And obviously we want our banking and credit card transactions to be secure.

Programming randomness in computers was recognised as an importent challenge even in the early days of computing (around 1950), and it has been studied ever since. One would think the topic be exhausted by now. In fact, I believed enough had been written on computer randomness when I started this work in 2013.

In fact, randomness is well understood for application in sequential computer programs, i.e. a program which only utilises one of the CPU cores in the computer. A typical consumer-end computer these days has four. If you want to use all of them in one application, the software must be written for parallel execution.

True randomness is hard to achieve in a computer. It is possible to a certain degree, but a large number of random values take time to generate. Instead, the common solution is a so-called pseudo-random number generator (PRNG). Many exist. Most of them are flawed, but there are enough PRNG constructions which are considered trustworthy. However, the well-known solutions are all sequential. The random numbers are generated one by one in sequence. Distributing randomness across parallel threads (or multiple cores in the CPU to take a concrete view) is non-trivial.

Parallel randomness was recognised as an important problem already in the first half of the 1980-s. Yet, the literature is sparse. Some constructions have appeared, but few inspires any confidence. In fact, my paper demonstrates serious flaws in almost all of the known constructions. The first solution which inspires any confidence is that of Claessen and Pałka in 2013.

A preprint is available on my web page.

Paper on intelligent virtual prototyping of offshore cranes accepted for ECMS 2015

ECMS_15smallSoftICE members Robin T. Bye and Ottar L. Osen have together with eminent automation student Birger Skogeng Pedersen written a scientific research paper called “A Computer-Automated Design Tool for Intelligent Virtual Prototyping of Offshore Cranes.” The paper has been peer-reviewed and accepted for publication in the Proceedings of the 29th European Conference on Modelling and Simulation (ECMS’15) and will be presented in the Simulators for Virtual Prototyping and Training (SVT) track (chaired by Robin T. Bye and AAUC colleague Vilmar Æsøy) at the conference in Varna, Bulgaria 26-29 May 2015.

knuckleboom

Example of an offshore knuckleboom crane.

AAUC researchers have been regular attenders and contributors at ECMS conferences over the years, which have resulted in AAUC chairing several own tracks and even hosting the conference in Ålesund in 2013 (chairs were AAUC staff Webjørn Rekdalsbakken, Robin T. Bye, and Houxiang Zhang), a conference that was honoured to have recent Norwegian Nobel Prize laureate May-Britt Moser as a keynote speaker.

We will make the full paper available when the conference proceedings have been released. In the meantime, we provide the paper abstract below.

Continue reading

SoftICE presenting pedagogical research at STEM-conference

SoftICE members Hans Georg Schaathun and Robin T. Bye together with first author Welie A. Schaathun will be presenting pedagogical research on “Active Learning Using Microcontrollers (Aktiv læring i Mikrokontrollarar)” at the Norwegian STEM conference in Bergen 18-19 March (MNT-konferansen 2015).

AAUC is also represented with other work, including “Development and Testing of Method to Avoid Quitting in Engineering Education (Utvikling og utprøving av metode for å hindre frafall i ingeniørutdanningene)” and “Student-Active Research in the Course Real-Time Computer Engineering (Studentaktiv forskning i emnet Sanntids datateknikk)“.

Abstract of our paper (in Norwegian only): Continue reading