|
|
|
Think weird, design big, implement small, cooperate worldwide, exploit regionally!
Professor (“Hoogleraar”)
at the University of Leuven
since October 2008.
(PhD under supervision of
Joris De Schutter
in 1995;
Assistant Professor since October 1998;
Associate Professor since October 2003.)
On March 20th, 2013, I was (re)elected as Vice-President Research of the euRobotics AISBL, serving a two-year term on the Board. The euRobotics association was founded in Brussels on September 17th, 2012, to realise the large-scale, long-term and self-sustainable integration of the academic and industrial robotics stakeholders in Europe. My industrial counter-part is the Vice-President Industry, dr. Rainer Bischoff from KUKA. Dr. Bernd Liepert, the CTO from KUKA, serves as the President of euRobotics. At this moment, euRobotics is working closely together with the European Commission to create a Public-Private Partnership (“Robotics 2020”) “to boost European industrial leadership, extend its excellent science base and provide a forum for end-user participation in European robotics.”.
Before the creation of the
euRobotics AISBL,
I served two terms (from 2008 till 2013) as
the Coordinator of the seminal European robotics network
EURON, as successor of the founding Coordinator
Henrik Christensen.
Thanks Henrik, for having been instrumental in creating an
internationally respected identity for European robotics!
KU Leuven was
Member no. 11
of the (now inactive) network, since my esteemed emeritus colleague
Hendrik van Brussel made sure that we were among the founding members.
Our Robotics Research group is partner in the RoboNed network of robotics groups (academic as well as industrial) in the Netherlands and Belgium. I expect such “local clusters” to start playing an ever more important role in the European robotics scene, because they offer a good trade-off between “locality” of, on the one hand, direct person-to-person interaction and information dissemination, and, on the other hand, a critical mass of researchers and industries that can foster innovation.
The most important “Key Performance Indicator” of individual researchers (that can not be quantified…) is their impact on their research community's progress towards solving societal challenges
Academic research partner of the FMTC (Flanders' Mechatronics Technology Centre).
Academic partner of the OSADL (Open Source Automation Development Lab).
Co-founder and Associate Editor of the
Journal of Software Engineering in Robotics (JOSER).
Officer of the
International Foundation of Robotics Research
(2003–…).
Expert (and advocate since 1996) on Free and Open Source Software, and open IT standards, in which domain I have been consulted many times by various governmental, educational and industrial organisations and administrations.
“Sense-Plan-Act” and “Subsumption Architectures” are things of the past in robotics, to be replaced by the “Every robot task is a constrained optimization problem” paradigm, that links continuous, discrete and symbolic information, at runtime, and all the time.
My research focuses on making use of as much domain knowledge (the “robotics ontology”!) as possible, especially for realtime algorithms and software, close to the hardware, the controller(s) and the sensor(s). My major research questions are:
How can knowledge-driven, affordance-based robot programming, perception and learning be made more realtime, while still taking into account more prior knowledge (“models” about he objects and the robots), more sensors, and more features in each sensor?
How should the robot control software of the future be developed? And how will it cope with the exploding complexity in knowledge, distributed components, and variation in tasks?
The currently most popular robot software architecture is Sense-Plan-Act (as an unfortunate by-product of the ROS domination of the software field), but its architectural primitives are too limiting to support real affordance approaches.
What are the new Domain Specific Languages (DSLs) that we have to develop to make the knowledge representation and the programming of robots a lot more easy? (And, at the same time, a lot more deterministic and semantically consistent!)
How should we design and apply multi-sensor perception networks, to replace the traditional “single-sensor pipeline architectures”?
My ambition is to become the best meta-level, systems-thinking roboticist alive
Here is a bit more detailed description of my research areas:
Modelling, Perception and Control of robot affordances (``Skills'')
I look into the combination of on-line,
recursive (Bayesian) estimation techniques to make (mobile) robot
manipulators adapt intelligently to their environment.
“Intelligently” to me means: according to the most appropriate
explicit sensing-action-environment model available to the
robot controller. Such controllers contain realtime
motion servoing based on the estimation results, as well as
event-based, task-driven switches between such realtime
estimation/servo control combinations.
Most of this research takes place in close cooperation with Joris De Schutter, Erwin Aertbeliën, Hendrik van Brussel and Jan Swevers.
Robotics software
I started the
Open RObot COntrol Software (OROCOS)
project in 2001, with later “spin-off” projects
Kinematics and Dynamics Library (KDL)
and
Bayesian Filtering Library (BFL).
I was a key creator of the BRICS Component Model, which is
a scientific paradigm to support the design, development, deployment and
adaptation of complex robotics systems.
My first PhD student on this material, Peter Soetens, started his spin-off company Intermodalics.eu in 2010, on the basis of his unique expertise with the Orocos code.
Learn to love throwing away years of research and development: real progress should not be hindered by deprecated legacy
Applied mechatronics and estimation projects,
with various industrial and biomechanical partners in Belgium and Europe.
Some of this research takes place in close cooperation with
FMTC (Flanders' Mechatronics
Technology Centre).
Too few academic researchers are aware of the wealth of fundamental problems that lie waiting below the surface of daily industrial practice.
Co-promotor of KU Leuven's GOA (“Concerted Research Action”) project on Global real-time optimal control of autonomous robots and mechatronic systems (2009–2013), and its predecessors Model based intelligent robot systems (2005–2009), and Active Sensing for Intelligent Machines (1999–2004).
Partner in European Integrated Projects of the European Seventh Framework Programme, BRICS (Best practices in robotics), Rosetta, (2009–2013), RoboHow (2012–2016), Pick-n-Pack (2012–2016), and Sherpa (2013–2017),
Co-promotor of the IWT-TBM (“Applied Biomedical Research”) projects IPSA (“Integrated Platform for clinical Spasticity Assessment”, 2007–2010), with Kaat Desloovere (KU Leuven/FABER), and Erwin Aertbeliën, and ACEP (“An advanced clinical examination platform for the examination of the diabetic foot”, 2010–2013), with Kaat Desloovere (KU Leuven/FABER), Filip Staes (KU Leuven/FABER), Erwin Aertbeliën and Jos Vander Sloten.
Bibliometrics-driven science policies create schisms between scientists and society, hindering the impact and application of scientifc research, and the creation of innovative new paradigms
Contact me to get electronic copies of my publications. (This database-generated list only goes back five years.)
I have been very active in promoting the introduction into the robotics domain of the separation of concerns concept, originally via the 4Cs (of Radestock and Eisenbach, 1996, see below), which I recently refined into the 5Cs: Computation, Communication, Coordination, Composition, and Configuration.
In expectation of the first “real” publication of the 5Cs, please, refer to this White Paper, created in the context of the Robot Standards (RoSta) project: Erwin Prassler, Herman Bruyninckx, Klas Nilsson, and Azamat Shakhimardanov, The Use of Reuse for Designing and Manufacturing Robots. Klas deserves the credit of introducing me to the seminal paper by Matthias Radestock and Susan Eisenbach, Coordination in evolving systems, Trends in Distributed Systems. CORBA and Beyond, Springer-Verlag, 1996, pp. 162-176.
Robotics PhD students of all countries, unite! Not to write yet another thousand papers “full” of Least Publishable Units of knowledge, but to let your progress have an impact on solving the real societal challenges of this century
Erwin Aertbeliën, our industrial and clinical
robotics wizard and the memory and backbone of many of our
research projects.
PhD on Development and Acquisition of Skills for Deburring with Kinematically Redundant Robots, 2009.
Tinne De Laet: our
perception and estimation wizard and Bayesian theory genius.
PhD on Rigorously Bayesian Multitarget Tracking and Localization, 2010.
Wilm Decré:
our optimization wizard and KUKA LWR genius.
PhD on Optimization-Based Robot Programming with Application to Human-Robot Interaction , 2011.
Take all criticism seriously but not personally. If there is truth or merit in the criticism, try to learn from it. Otherwise, let it roll right off you.
Hillary Rodham Clinton
If you want to come and work with me, I expect you to be a full-time user of Linux, advanced editors (such as Vim or Emacs), Inkscape, Blender, version control systems (e.g., subversion or git), LaTex (for documents as well as presentations). Contributions to Free and Open Source Software projects are very much stimulated, and (more than weekly) contributions to “a friendly Wikipedia page near you” are mandatory.
The most important thing I can offer to potential post docs is a lot of opportunities to get immersed into the most vibrant core of the European robotics research scene, including lots of interactions with some dozens of the best groups in Europe and worldwide.
I am a firm believer in the maturity and responsibility of PhD students. Hence, I do not want to be their “supervisor” but rather their “coach”. In return, I expect them to always have a clear idea about where exactly they want to go with their research. My rule of thumb for a PhD student is to have 2–3 research hypotheses written out in full, at all times. They need them, not only to explain to visitors what their research is all about, but also to keep their strength and self-confidence, since I flood them continuously with (potentially) good ideas, papers and software, with constructive criticism, and with stimuli to “think weird” and “desgin big”. I do realise that such a turmoil of scientific discussions and doubts can take some time to adapt to, and requires strong nerves to keep one's research focus, but I do not apologize for this behaviour of mine, because:
Progress comes from fierce and ruthless confrontation of ideas, not of people
I do not have a Skype account, nor am I part of asocial media such as Facebook, Twitter or LinkedIn. And I am not planning to get those accounts, because of ethical and pragmatic principles: these initiatives introduce proprietary protocols and/or prevent inter-community, multi-vendor communication, and such things are known to create monopolies, and hence prevent fair markets of VOIP or social networking as emerging communication instruments. It's only 30 years ago that our society succeeded to escape from under the traditional telecom monopolies, but it seems not to have learned anything from those experiences…
I am prepared to pay a price for fairness and freedom; I suggest to use the facilities offered by the free market of teleconferencing via the traditional telephone line and to use open VOIP protocols. Or, preferably, use Open Standards formats, such as WebRTC, which I have good although limited experiences with.
I am strongly convinced of the long-term advantages of using only Open Standards in all ICT matters: vendor independence, software independence, better chances of long-term archiving, stimulation of better decoupled ICT solutions, etc. So, please, send me only plain text, HTML, PDF, or ODF messages and documents in your electronic communication.
If universities are serious about lifelong learning, they stimulate their professors, staff and students to develop educational contents primarily within the Wikipedia ecosystem: Wiki articles, Wiki books, and Wiki courses. The others pay lots of money to keep their educational material behind passwords, preventing their students to access the material almost immediately after they have passed a course…
The contributions to the education of our young engineers that I value most are my emphasis on (i) system-level thinking, and (ii) attitude of constructively critical evaluation of all available sources of information, starting with pseudo-peer reviewed open content such as the Wikipedia. Our students score poorly on both aspects, which I think are fundamental for Europe's ability to maintain an innovative R&D ecosystem. The future does not belong to those who posess the most knowledge, but to those who are able to understand how and where that knowledge could be applied.
My most revolutionary contribution to education is the extensive use of professional mailing list tools to teach a course: this is the most effective (albeit labour intensive and not always efficient…) approach to provide learning feedback to students on an individual basis, answering to their problems when they are ready for it. This best practice comes directly from my long-term, intensive immersion in, and contributions to, the “open source” community.
Since 2008, I am Chairman of the Jury, for the Georges Giralt PhD Award.
This page has a list of topics for Summer internships, or stages, which I would very much like to supervise. I welcome Master students from universities as well as technical high schools. I'm especially interested in computer-literate students (Linux, C++, Java), who want to contribute to Free and Open Source Software projects to make them better suited for robotics.
ICT empowerment is about much more than just using a computer for what you did 20 years ago already with pen, paper and file cabinets. It's all about standing on the shoulders of thousands and thousands of open source midgets, and, especially, about throwing out that Outlook programme of yours, because it only supports top posting, sigh…
Born: 22 December 1962,
Turnhout, Belgium
Licentiate Mathematics (1984).
Burgerlijk Ingenieur Computerwetenschappen (1987). (Masters Degree in
Computer science)
Postgraduate Engineering Degree
Mechatronics (1988).
Military service (Aug. 1988–Jul. 1989).
1989-1995: Research Assistant at the
University of Leuven,
Department of Mechanical Engineering, Division
PMA.
PhD (1995), Kinematic Models for Robot Compliant Motion with
Identification of Uncertainties.
[abstract]
[A4
paper, gzipped PostScript]
[US
letter, gzipped PostScript]
1995–2003: Postdoctoral Fellow of the Fund for Scientific
Research-Flanders
(F.W.O.) in Belgium.
Mar. 1996–Aug. 1996: Postdoc at
GRASP Lab,
University of Pennsylvania,
Philadelphia, U.S.A., with
Vijay Kumar.
April–August 1999: sabatical with the
Robotics group
at Stanford University,
headed by Prof.
Oussama Khatib.
July–August 2002: visiting the
Centre for Autonomous Systems
at the
Royal Institute of Technology in
Stockholm, Sweden, headed by Prof.
Henrik Christensen.
If you are really concerned about a better world, get rid of your car and become a vegetarian: all other options are irresponsible wastes of energy and health.
Science is never value-free!
|
Copyleft 1997–2013, Herman Bruyninckx http://people.mech.kuleuven.be/~bruyninc |
|
|
Last update: 5 June, 2013
Optimized for web standards. |