PRIMORIS      Contacts      FAQs      INSTICC Portal
 

Keynote Lectures

Autonomous, Versatile and Dependable Robot Manipulation based on Multiple Sensors
Angel P. Del Pobil, Universitat Jaume I, Spain

What Sensors are Needed for Autonomous Driving?
Christoph Stiller, KIT - Karlsruhe Institute of Technology, Germany

Off-road Robotics - Perception and Navigation
Karsten Berns, University of Kaiserslautern, Germany

Real Mobile Robots and Virtual Worlds - Putting them Together in a New Teaching Paradigm
Riccardo Cassinis, University of Brescia, Italy

Novel Signal Processing Techniques for Industrial Engineering
Len Gelman, Cranfield University, United Kingdom

 

Autonomous, Versatile and Dependable Robot Manipulation based on Multiple Sensors

Angel P. Del Pobil
Universitat Jaume I
Spain
 

Brief Bio
Angel Pasqual del Pobil is Professor of Computer Science and Artificial  Intelligence at Jaume I University (Spain), founder director of the UJI Robotic Intelligence Laboratory, and a Visiting Professor at Sungkyungkwan University (Korea). He holds a B.S. in Physics (Electronics, 1986) and a Ph.D. in Engineering (Robotics, 1991), both from the University of Navarra. He has been Co-Chair of two Technical Committees of the IEEE Robotics and Automation Society and is a member of the Governing Board of the Intelligent Autonomous Systems (IAS) Society and EURON. He has over 230 publications, including 11 books the last two published recently by Springer: Robot Physical Interaction through the combination of Vision, Tactile and Force Feedback (2013) and Robust Motion Detection in Real-life Scenarios (2012). Prof. del Pobil was co-organizer some 40 workshops and tutorials at ICRA, IROS, RSS, HRI and other major conferences.. He was Program Co-Chair of the 11th International Conference on Industrial and Engineering Applications of Artificial Intelligence, General Chair of five editions of the International Conference on Artificial Intelligence and Soft Computing (2004-2008) and Program Chair of Adaptive Behaviour 2014. He is Associate Editor for ICRA (2009-2013) and IROS (2007-2013) and has served on the program committees of over 115 international conferences, such as IJCAI, ICPR, ICRA, IROS, ICINCO, IAS, ICAR, etc. He has been involved in robotics research for the last 27 years, his past and present research interests include: humanoid robots, service robotics, internet robots, motion planning, mobile manipulation, visually-guided grasping, robot perception, multimodal sensorimotor transformations, robot physical and human interaction, visual servoing, robot learning, developmental robotics, and the interplay between neurobiology and robotics. Professor del Pobil has been invited speaker of 56 tutorials, plenary talks, and seminars in 14 countries. He serves as associate or guest editor for eight journals, and as expert for research evaluation at the European Commission. He has been Principal Investigator of 28 research projects. Recent projects at the Robotic Intelligence Lab funded by the European Commission include: FP6 GUARDIANS (Group of Unmanned Assistant Robots Deployed In Aggregative Navigation supported by Scent detection), FP7 EYESHOTS (Heterogeneous 3-D Perception Across Visual Fragments), and FP7 GRASP (Emergence of Cognitive Grasping through Emulation, Introspection, and Surprise).


Abstract

Autonomous robot manipulation is one of the most important challenges in robotics. It involves three challenges: versatility, defined as the capability to adapt to different situations, instead of being limited to a particular task; autonomy, that concerns the level of independence in the robot operation, and dependability, that refers to the capability of successfully completing an action even under important modeling errors or inaccurate sensor information. A complete manipulation task involves two sequential actions: that of achieving a suitable grasp or contact configuration, and the subsequent motion required by the task. We propose a unified framework with the introduction of task-related aspects into the classical knowledge-based grasp concept, leading to task-oriented grasps. In a similar manner, grasp-related issues are also considered during the execution of a task, leading to grasp-oriented tasks. We call this unified representation physical interaction. In the talk I will first present a theoretical framework for the integrated specification of physical interaction tasks, supporting a great variety of actions. Next, the problem of autonomous planning of physical interaction tasks will be addressed. I will then focus on the dependable execution of these tasks, and adopt a sensor-based approach with three different types of sensor feedback: force, vision and tactile. The methods proposed provide important advances with respect to the state-of-the-art versatility, autonomy and dependability of robotic manipulation, allowing to address a wide range of tasks. All these contributions are validated with several experiments using different real robots placed on household environments.

The talk will be based on my latest book titled Robot Physical Interaction through the combination of Vision, Tactile and Force Feedback: Applications to Assistive Robotics, that has been published in the Springer Tracts in Advanced Robotics (STAR) series in 2013, co-authored by Mario Prats and Pedro J. Sanz. This research was recipient of various awards, including the Georges Giralt European Award and the Robotdalen Scientific Award Honorary Mention.



 

 

What Sensors are Needed for Autonomous Driving?

Christoph Stiller
KIT - Karlsruhe Institute of Technology
Germany
 

Brief Bio
Christoph Stiller studied Electrical Engineering in Aachen, Germany and Trondheim, Norway, and received the Diploma degree and the Dr.-Ing. degree (Ph.D.) from Aachen University of Technology in 1988 and 1994, respectively. He worked with INRS-Telecommunications in Montreal, Canada for a post-doctoral year as Member of the Scientific Staff in 1994/1995. In 1995 he joined the Corporate Research and Advanced Development of Robert Bosch GmbH, Germany. In 2001 he became chaired professor and director of the Institute for Measurement and Control Systems at Karlsruhe Institute of Technology, Germany.
   
Dr. Stiller serves as immediate Past President of the IEEE Intelligent Transportation Systems Society, Associate Editor for the IEEE Transactions on Intelligent Transportation Systems (2004-ongoing), IEEE Transactions on Image Processing (1999-2003) and for the IEEE Intelligent Transportation Systems Magazine (2012-ongoing). He served as Editor-in-Chief of the IEEE Intelligent Transportation Systems Magazine (2009-2011). He has been program chair of the IEEE Intelligent Vehicles Symposium 2004 in Italy and General Chair of the IEEE Intelligent Vehicles Symposium 2011 in Germany. His automated driving team AnnieWAY has been finalist in the Darpa Urban Challenge 2007 and winner of the Grand Cooperative Driving Challenge in 2011.


Abstract
We are witnessing an exciting trend towards vehicle automation.
We extend the research on robotic vehicles of several international groups  that employ expensive on-roof sensors by investigating whether close-to-market sensor configurations may be sufficient for this task. We show that cognitive and autonomous  vehicles with a few close-to-market sensors are feasible. Vision plays the dominant role in our autonomous vehicle. We completely avoid bulky on-roof mounted sensors. The sensor suite enables the vehicle to perceive its environment and automatically navigate through everyday's traffic. Methods for 3D visual machine perception based mono- and binocular video sensors are presented. The contribution of prior knowledge from digital maps is elaborated as well as its curse in case of erroneous information. Real-time automated decision-making and trajectory planning methods are outlined. Extensive results of automated driving are shown in real world scenarios from our AnnieWAY vehicle, the winner of the 2011 Grand Cooperative Driving Challenge, and from the Bertha vehicle that drove autonomously on the 104 km of the Bertha Benz memorial route from Mannheim to Pforzheim through a highly populated area of Germany.



 

 

Off-road Robotics - Perception and Navigation

Karsten Berns
University of Kaiserslautern
Germany
 

Brief Bio

Prof. Dr. Karsten Berns has studied computer science with a special focus on artificial intelligence at the University of Kaiserslautern (1982 to 1988). For his research on "Neural Networks for the Control of a six-legged Walking Machine" he received his PhD from the University of Karlsruhe in 1994. As head of the IDS (Interactive Diagnosis and Service Systems) department of the FZI Research Center for Information Technology, Karlsruhe (till 2003) he examined adaptive control concepts for different types of service robots. Since 2003 he is a full professor at the University of Kaiserslautern.

Present research activities are the realization of reliable, complex autonomous robotic systems. Therefore, he and his research group are developing the robotic middleware Finroc, the behavior-based control architecture iB2C as well as different validation and verification methodologies. The main application is off-road robotics, in which autonomous or semi-autonomous vehicles like small trucks, excavators, harvesters, tractors, and rescue robots are under development.

Prof. Berns is frequently reviewer of several journals and robotic conferences. Furthermore, he is a member of a number of editorial boards. He also acts as reviewer for several national and international funding organizations. He is member of the IEEE, the Gesellschaft für Informatik (GI) and the CLAWAR Association. He is a member of the executive committee of the German Robotics Association (DGR) and is leader of the technical committee for robotic systems of the GI. He was Dean of the department of computer science at the University of Kaiserslautern (2007 – 2010) and is member of the scientific directorate Schloss Dagstuhl - Leibniz Center for Informatics of the Dagstuhl Seminar. Currently, he is spokesperson of the Center for Commercial Vehicle Technology (ZNT) at the University of Kaiserslautern.


Abstract

The research area of off-road robotics is focusing on autonomous or semiautonomous vehicles able to navigate in rough terrain without a predefined trail. Typical examples are agriculture and forestry machines or planetary rovers.  A detail environmental perception and navigation strategies under the consideration of soil conditions have to be examined for developing an adequate control concept for such vehicles.  In the talk first our behavior based control concept is introduced which is basis for the implementation of the control strategies Then different perception algorithms are presented for classifying soil conditions, detecting objects or tracing dynamical obstacles.  Thereafter, the hierarchical structured control modules of the behavior based control architecture will be discussed according to the navigation requirements of these vehicles. The talk will end with the presentation of different off-road vehicles and their applications like an excavator,  a tractor, and a rescue robot  which are developed at the RRlab of the University of Kaiserslautern during the last years.



 

 

Real Mobile Robots and Virtual Worlds - Putting them Together in a New Teaching Paradigm

Riccardo Cassinis
University of Brescia
Italy
 

Brief Bio

Riccardo Cassinis got his degree in Electrical Engineering in 1977 at Polytechnic University of Milan, and worked with that Institution until 1987, as Fellow, Assistant Professor and Research Associate.
In 1987 he was appointed Associate Professor of Robotics and of Numerical Systems Design at the University of Udine.
Since 1991 he is Associate Professor of Computer Science and of Robotics at the University of Brescia.
He has been founder and director of the Robotics Laboratory of the Department of Electronics of Milan Polytechnic University, of the Robotics Laboratory of the University of Udine, and is now Director of the Advanced Robotics Laboratory of the University of Brescia.
After graduation, he has been working for about fifteen years on several topics related to industrial robots, and has then addressed several navigation and sensing problems for advanced mobile robots, with a particular attention to humanitarian de-mining systems.
His last research interests aim at taking advantage of Internet technologies for building robots whose sensing and processing capabilities, rather than being concentrated in a single machine, are distributed over a network, allowing the construction of very simple and small devices. This experience has proved useful in his currently ongoing research on Internet-accessible mobile robotics labs for educational purposes.



Abstract

Mobile robots have been playing an important role in education during the last few years. This refers not only to robots used for teaching robotic concepts, but also, and in a more and more pervasive way, to a general approach that uses the robot as a teaching tool rather than as the tool being taught, extending their usage from high school down to the first grades of primary education.
This is very similar to what happened to computers: their first appearance in schools was related to the need of teaching programming languages, while today they are seen as a tool for teaching subjects that often have little or nothing to do with computer science.
On the practical side however, several difficulties must be overcome when trying to set up an educational robotics lab. Relying on a centralized, standard setup, maintained by trained personnel shared among all users (thus reducing costs), backed up by training programs and with the possibility of building a community of interested users and educators has proven definitely a plus. The widespread availability of Internet connections has also greatly helped making the physical distance of the lab from its users unimportant.
Furthermore, to-date technologies allow keeping things simple, introducing some virtual reality techniques to support and enhance the physical part of the lab.
A comparison of existing systems and of the advantages and drawbacks of such approach will be made, and some insight on currently ongoing projects will be given.



 

 

Novel Signal Processing Techniques for Industrial Engineering

Len Gelman
Cranfield University
United Kingdom
 

Brief Bio
Professor Len Gelman is PhD, Dr. of Sciences (habilitation) and an Academician.

He has more than 35 years’ experience in reliability centred maintenance, machinery failure analysis and prevention, maintenance planning and scheduling, risk assessment, hazard identification and condition monitoring of complex mechanical systems (e.g., rotating, reciprocating machinery, gearboxes, bearings, etc.) both in industry and academia.

Prof. Gelman is Chief Designer on numerous industrial and research contracts, including contracts from the USA National Academy of Sciences, USA National Research Council, USA International Science Foundation, USA Civilian Development Foundation (twice), USA MacArthur Foundation, Lady Davis, Israel, Centro Volta, Italy, UK EPSRC, UK Department of Trade and Industry (three times), UK Royal Society, Rolls Royce (four times), SKF (two times), Scottish Energy (two times), Caterpillar (twice) and Boeing (three times). Recently, he used to work for oil and gas industry under a contract with Shell (UK).

He is a Fellow of the British Institute of Non-Destructive Testing (BINDT), UK Institution of Diagnostic Engineers and International Association of Engineers, Chairman of the Condition Monitoring and Diagnostic Technology Technical Committee of the BINDT, Chairman of the International Society for Condition Monitoring, President-Elect of the International Institute of Acoustics and Vibration (USA) and Honorary Editor of the International Journal of Condition Monitoring. He was a member of the condition monitoring certification committee of the BINDT in 2002-2008.

Prof. Gelman is the author of over 200 publications (including 17 patents and 2 book chapters) and 12 keynote conference papers in the area of maintenance, machinery failure analysis and prevention and monitoring.

He is Chair of 2007 World Congress on Engineering Asset Management, Honorary Co-Chair of 2007, 2008, 2009, 2010, 2011, 2012, 2013 and 2014 World Congresses of Engineering and Chair of 2008, 2009, 2010, 2011, 2012, 2013 and 2014 International Condition Monitoring Conferences. He has participated in the technical boards of numerous international conferences.

Prof. Gelman is a Chief Designer of numerous technologies and engineering prototypes for proactive maintenance, fault detection/diagnosis/isolation. He is lecturing, training and consulting to industry in all parts of the world and has held visiting professorship at 5 overseas universities. Recently, he was awarded Rolls-Royce award for innovation for development and implementation of the novel technologies for maintenance of gas turbines.


Abstract

The current status and novel future directions in signal processing for industrial engineering will be presented.
The classical second order and higher order spectral techniques that currently widely employed for stationary conditions will be discussed. The presentation will review also three classical examples of the second-order time-frequency techniques (i.e. the short time Fourier transform, the wavelet transform and the Wigner distribution) that currently are widely used in non-stationary conditions.
However, for some important practical applications in industrial engineering it is necessary to perform higher order signal processing in non-stationary conditions. The classical techniques and simple non-adaptive non-stationary techniques are not suitable for those conditions.

Important future directions of higher order signal processing for non-stationary conditions will be presented based on
- new class of non-stationary adaptive second order and higher order spectral transforms
- new class of non-adaptive and adaptive higher order spectral frequency response functions
- new techniques for complete amplitude-phase extraction from second order and higher order stationary and non-stationary transforms for stationary and non-stationary conditions

Validation of these novel techniques by simulation and experiments in laboratory and field conditions will also be presented.



footer