Michael Beetz is a professor for Computer Science at the Faculty for Mathematics & Informatics of the University Bremen and head of the Institute for Artificial Intelligence (IAI). IAI investigates AI-based control methods for robotic agents, with a focus on human-scale everyday manipulation tasks. With his openEASE, a web-based knowledge service providing robot and human activity data, Michael Beetz aims at improving interoperability in robotics and lowering the barriers for robot programming. Due to this the IAI group provides most of its results as open-source software, primarily in the ROS software library.

Abstract

One of important research topics of RoboCup is integration technology toward real applications. RoboCup includes several application-oriented leagues like rescue, @home, and industrial, in which the real applications are driving force of technologies and the link from RoboCup researches to the real world. GKK was the key person of this field and leaded several movements in RoboCup. In this talk, I like to describe related results of RoboCup mainly in simulation leagues and emphasize GKK's contribution to foster these activities.

Biography

Dr. Itsuki Noda is a principal research manager of Artificial Intelligence Research Center in National Institute of Advanced Industrial Science and Technology (AIST), Japan. He received the B.E., M.E. and Ph.D., degrees in electrical engineering from Kyoto University, Kyoto, Japan, in 1987, 1989, and 1995, respectively. He worked at Electrotechnical Laboratory (one of former organizations of AIST) as a researcher since 1992. He was also

a visiting researcher of Stanford University in 1999, and worked as a staff of Council of Science and Technology Policy of Japanese government in 2003.

He was a founding member of RoboCup and promoted Soccer Simulation League since 1995. He was the president of RoboCup Federation during 2014 to 2017. He is now the president of Japanese Society of Artificial Intelligence. He is also one of founders of a venture company, Mirai Share, for taxi-share system.

He has been joining and promoting several research projects on AI, robotics, and disaster-and-rescue domains. In addition to Soccer Simulation League, he joined the development of Rescue Simulation League, and join Rescue Robot League as a team member. He was a member of the project to develop integrated information sharing and simulation system of disaster and rescue. The results of the project were used to support rescue activity for the most of disaster in Japan including the Great East Japan Earthquake. He also leaded a project

on large scale multiagent social simulation system using high performance computing facilities. Based these results, he is now promoting a project on MaaS (mobility as a service) as a next generation transportation system for sustainable smart societies.

Abstract

For today's kids, "motivation" is the keyword for learning and getting involved in a certain area which might become their future job. There are some events worldwide dedicated to youngsters where they can learn, participate, and do a hands-on experience, and robotics is an area very rich in that. Even though *Gerhard Kraetzschmar* was a remarkable scientist worldwide known, he was also very much involved in teaching and helping youngsters in getting involved in robotics and computer science areas. In 2009 a new challenge was given to him, which consisted of giving a talk to youngsters (from 10 to 19 years old) in order to convince them to become an Engineer. And he fulfilled it quite remarkably given a talk hold completely the attention os the kids to listen to what he was saying and absorbing his advice. After the talk, he spent the remaining RoboParty 3 days talking and playing games with the kids, but above all doing what he liked most, mixing robotics and enjoyment.

This talk will tell you to the whole story behind this experience.

Abstract

Robotics has always triggered emotions in us, frequently of awe, sparking curiosity. This effect is best observed in children and youngsters and it can be used to foster the appeal for technological development. This has been used by educators around the world to raise students interest on technology and their technical skills. I am part of this group, in my educator role, and contributed to the development of this approach, first in Portugal and later internationally, particularly within RoboCup. However, this approach is not free from issues. In this talk I will briefly present some of my experiences and discuss some virtues and challenges that I witnessed in using Robotics as a non-formal educational tool.

Biography

Luis Almeida graduated in Electronics and Telecommunications Eng. in 1988 and received a Ph.D. in Electrical Eng. in 1999, both from the University of Aveiro in Portugal. He is currently an associate professor in the Electrical and Computer Engineering Department of the University of Porto (UP), Portugal, and member of the CISTER research unit at UP where he coordinates the Distributed and Real-Time Embedded Systems (DaRTES) lab. Among several appointments, he is the chair of the IEEE Technical Committee on Real-Time Systems, he was Program and General Chair of the IEEE Real-Time Systems Symposium in 2011 and 2012, respectively, and Vice-President of the RoboCup Federation from 2011 to 2013, integrating the Board of Trustees of this organization from 2008 to 2016 and the Executive Board from 2004 to 2008. His research interests revolve around real-time communication for distributed industrial/embedded systems, with a particular appeal for engineering education.

Abstract

For people involved in RoboCup it is totally clear that Robotics and Artificial Intelligence (AI) are a unit. Moreover, AI started to play a dominant role in our daily life in private as well as in professional concerns. A sound basic understanding of this technology is crucial for the next generation as well as for the general public as it allows on one hand to build up a professional career but also on the other hand it allows an informed discussion and the participation in public decisions that need to be made in relation to AI. The idea of RoboCupJunior (RCJ) was a good start into the direction to inform and motivate young people in the area of Robotics. Although, Robotics is not yet a subject in every curriculum in the world RCJ contributed to this goal a lot during the last 20 years. Meanwhile people agreed that we need to do the same for AI. In this talk I will report recent activities in early stage (pre-university) education in AI in Europe and other places in the world and want also raise the question to what level we should or should not push these ideas. Finally, I will also want to talk about the relation to RCJ and in particular to Gerhard's contributions in these areas.

Bio

Gerald Steinbauer is an Associate Professor at the Institute of Software Technology iat Graz University of Technology. His central research interest is how techniques from Software Engineering and Artificial Intelligence can be used to improve the dependability of autonomous robots. He is involved in RoboCup for almost 2 decades and served as General Chair of RoboCup 2009 and since 2017 as Trustee of the RoboCup Federation with a special interest in RoboCupJunior.

Abstract:

The wider adoption of robotic and autonomous systems by society depends upon the perceived trust of various stakeholders (e.g., engineers, users, regulators and so forth) on the dependable and ethical nature of these systems. However, the developers of robotic and autonomous systems face unprecendented dependability challenges caused by the intrinsic characteristics of robotic and autonomous systems such as learning and adaptation, uncertainty, openness and resilience to name a few. Considering these characteristics the construction of trustworthy robotic and autonomous systems remains a key challenge which calls for new engineering methods and tools. In this talk, I will present our latest research about methods, frameworks and tools to engineer robotic and autonomous systems which are a bit more trustworthy.

Bio

Nico Hochgeschwender is a Full Professor for Autonomous Systems at the Bonn-Rhein-Sieg University of Applied Sciences (since 2019) where he teaches in the International Master of Science program in Autonomous Systems. He received his Master in Computer Science at the University of Applied Sciences Ravensburg-Weingarten, Germany and in 2006 he joined ESG GmbH, Munich (Germany) as a system engineer developing safety-critical avionics software for Unmanned Aerial Vehicles. In 2009 he joined Bonn-Rhein-Sieg University, Sankt Augustin (Germany) as a Research Scientist and doctoral candidate in the EU-funded project BRICS (Best Practice in Robotics), researching model-driven engineering methods for autonomous systems. He is co-founder of the RoboCup@Work league and participated in several RoboCup competitions with the b-it-bots team placing second and third in World Championchips. In 2016 he received his PhD from the University of Luxembourg and subsequently he joined the Interdisciplinary Centre for Security, Reliability and Trust (SnT) of the University of Luxembourg as a postdoctoral researcher developing model-based engineering methods to assure the safety and security of autonomous systems. In 2018 he joined the German Aerospace Center (DLR) in Cologne (Germany) as a research group leader for intelligent software systems. Since many years Dr. Hochgeschwender serves as a program committee member of various robotic conferences like ICRA, IROS, SIMPAR, Robotic Computing and journals like IEEE Robotics and Automation Magazine and Journal of Software Engineering in Robotics (JOSER). He co-organized several robotics software engineering workshops like RoSE (Robot Software Engineering), SDIR (Software Development and Integration in Robotics) and DSLRob (Domain-specific Languages in Robotics) at major robotic and software engineering venues like IROS, ICRA and ICSE.

Bio

Prof. Luca Iocchi (http://www.diag.uniroma1.it/iocchi) is Full Professor at Sapienza University of Rome, Italy. His main research interests include cognitive robotics, multi-robot coordination, robot learning, human-robot interaction, and robot competitions. He is and has been PI of several international projects in artificial intelligence and robotics and was involved in the organization of several scientific events, as well as scientific robot competitions and educational robot competition.

He is currently Vice President of RoboCup Federation and contributed to benchmarking domestic service robots through scientific competitions within RoboCup@Home and the European Robotics League Service Robots (ERL-SR).

Abstract

Human robot interaction requires a common understanding of the operational environment, which can be provided by a representation that blends geometric and symbolic knowledge: a semantic map. Through a semantic map the robot can interpret user commands by grounding them to its sensory observations. Semantic mapping is the process that builds such a representation. Despite being fundamental to enable cognition and high-level reasoning in robotics, semantic map- ping is a challenging task due to generalization to different scenarios and sensory data types. In fact, most techniques do not obtain a rich and accurate semantic map of the environment and of the objects therein. Moreover, to date there are no frameworks that allow for a comparison of the performance in building semantic maps for a given environment. To tackle these issues we created a novel framework based on the Gazebo simulator, where we introduce two key novelties: (1) a methodology for a systematic evaluation of semantic mapping; (2) a new family of approaches to semantic mapping that exploit both active vision and domain knowledge, to improve the performance of the system with respect to state-of- the-art approaches. We release our framework with multiple simulation environments with the aim to provide a general set-up to quantitatively measure the performances in acquiring semantic knowledge about the environment. We additionally include a user study that serves as baseline for the map building methods and for testing the simulation environments.

Bio

Daniele Nardi (http://www.dis.uniroma1.it/~nardi/) is full Professor (since 2000) at Sapienza Univ. Roma, Faculty of Ingegneria dell'Informazione, Informatica, Statistica, and member of the Dept. Computer, Control and Management Engineering "A. Ruberti". He is currently referent for the Master curriculum in Artificial Intelligence and Robotics; he has been teaching the course Artificial Intelligence of the master, since several years. Daniele Nardi leads the research laboratory "Cognitive Robot Teams", addressing different research topics: Cognitive Robotics, Localization, Navigation, Perception, Cooperation in multi-robot systems, Human Robot Interaction, Multimodal Interfaces and Spoken Dialog. His scientific and technical achievements have been deployed in manifold application domains: Ambient Intelligence and robots to support elderly people, Service Robots, Robots for Disaster Response, for Cultural Heritage, for Precision Agriculture, Soccer Player robots for RoboCup competitions. Daniele Nardi has been principal investigator of several collaborative projects funded by FP7, H2020 and several other research funding institutions. He is author on more than 100 publications in Artificial Intelligence and Robotics; he is EurAI Fellow, and was President of RoboCup Federation (2011-2014).

ABSTRACT

When I was doing my PhD, Automatic Control and Artificial Intelligence used to be seen as distinct, even antagonistic, approaches to Robotics. I was fortunate to be supervised by George Saridis, who advocated Intelligent Control was in the intersection of AI, Control and Operations Management, and inspired my current integrated view of Robotics as a multidisciplinary blend of these and other scientific areas. Even so, having a Control Systems original background, my attitude has been inevitably biased towards attempting to formalize intelligent robot systems using mathematical approaches familiar to the control community. This discussion about “Control vs AI” was recurrent between me and Gerhard, often just to have fun, but occasionally also quite seriously. It so happens that many roboticists are pursuing paths that lie in on frameworks mixing the two approaches. Examples of these are (not exhaustively listed): optimal control and sequential decision-making under uncertainty; hybrid systems and hybrid motion and task planning; logic-based planning and supervision + control of discrete-event systems in my talk I will walk through some of these concepts just to revive some of the debates I had with Gerhard and others, the pros and cons of the two views, the merits of merging them and some examples.

BIO

Pedro U. Lima received the Licenciatura (5 years) and M.Sc degrees in Electrical and Computer Engineering from IST in 1984 and 1989, respectively, and the Ph.D. (1994) in Electrical Engineering from the Rensselaer Polytechnic Institute, NY, USA, Currently, he is a Full Professor at IST, Universidade de Lisboa, where he coordinates the MSc Program on Electrical and Computer Engineering (the largest MSc Program at IST) and a researcher of the Institute for Systems and Robotics, where he is the Coordinator of the Intelligent Robots and Systems group and Deputy President for Scientific Matters. His research interests lie in the areas of formation control, cooperative perception, discrete event models of robot tasks and planning under uncertainty, with applications to multi-robot and networked robot systems. Pedro has been the PI of several European and national research projects at ISR/IST. He is a Trustee of the RoboCup Federation, was the General Chair of RoboCup2004, held in Lisbon, the Coordinator of the FP7 Coordination Action RoCKIn, and member of the Advisory Board of the Mohamed Bin Zayed International Robotics Challenge (MBZIRC).

Abstract

Twenty years ago, on a soccer field, I did not imagine that robot competitions were going to become a way to benchmark intelligent systems. Nowadays, after several international initiatives and funded projects, competitions are an accepted way to challenge and compare physical intelligent systems. At some point, the idea of Benchmarking through Competitions was named as the "RoCKIn (EU project) Legacy" and since then it has impacted EU funded initiatives such as eurathlon, EuRoC, RockEU2, the European Robotics League, Sciroc, and Metrics to name a few.