Communications

The communication presentations (keynote talks, facilitated break-out sessions, posters) will be continuously uploaded in May and June.

Barbara Caputo
Robots learning about objects from the Web

Barbara Caputo is an Associate Professor at the Department of Computer, Control and Management Engineering of the University of Rome La Sapienza, where she leads the Visual Learning and Multimodal Applications Laboratory (VANDAL).  Barbara Caputo received her PhD in computer science from the Royal Institute of Technology (KTH) in 2005. Her main research interest is to develop algorithms for learning, recognition and categorization of visual and multimodal patterns for artificial autonomous systems. These features are crucial to enable robots to represent and understand their surroundings, to learn and reason about it, and ultimately to equip them with cognitive capabilities. Her research is sponsored by the Swiss National Science Foundation (SNSF), the Italian Ministry for Education, University and Research (MIUR), the European Commission (EC) and the European Research Council (ERC).

Abstract

While todays robots are able to perform sophisticated tasks, they can only act on objects they have been trained to recognize. This is a severe limitation: any robot will inevitably face novel situations in unconstrained settings, and thus will always have knowledge gaps. This calls for robots able to learn continuously about objects by themselves. The learning paradigm of state-of-the-art robots is the sensorimotor
toil, i.e. the process of acquiring knowledge by generalization over observed stimuli. This is in line with cognitive theories that claim that cognition is embodied and situated, so that all knowledge acquired by a robot is specific to its sensorimotor capabilities and to the situation in which it has been acquired. Still, humans are also capable of learning from externalized sources like books, illustrations, etc containing
knowledge that is necessarily unembodied and unsituated. In this talk I will advocate for a third alternative, i.e. learning from extrenalized perceptual and semantic knowledge sources like the Web. I will present results showing how to mine effectively the Web for perceptual knowledge to be used effectively in situated robot scenarios. I will then outlined the importance of this learning paradigm in manipulation, and point to timely challenges for the community.

Wednesday 21/06/2017

Keynote talk

AttachmentSize
PDF icon CHIST-ERA_Caputo.pdf1.36 MB
Object recognition and manipulation by robots: data sharing and experiment reproducibility (ORMR)
Diego Calvanese
Combined Data and Process Modeling and Verification

Diego Calvanese is a full professor at the Research Centre for Knowledge and Data (KRDB), Faculty of Computer Science, Free University of Bozen-Bolzano, where he teaches graduate and undergraduate courses on knowledge bases and databases, ontologies, theory of computing, and formal languages. He received a PhD from Sapienza University of Rome in 1996. His research interests include formalisms for knowledge representation and reasoning, ontology based data acces and integration, description logics, Semantic Web, graph data management, data-aware process verification, and service modeling and synthesis. He has been actively involved in several national and international research projects in the above areas (including FP6-7603 TONES, FP7-257593 ACSI, FP7-318338 Optique). He is the author of more than 300 refereed publications, including ones in the most prestigious international journals and conferences in Databases and Artificial Intelligence, with more than 25000 citations and an h-index of 66, according to Google Scholar. He is one of the editors of the Description Logic Handbook. He has served in over 100 program committee roles for international events, and he is an associate editor of Artificial Intelligence and of JAIR. In 2012-2013 he has been a visiting researcher at the Technical University of Vienna as Pauli Fellow of the ``Wolfgang Pauli Institute''. He has been the program chair of the 34th ACM Symposium on Principles of Database Systems (PODS 2015), the program co-chair of the 28th Description Logic Workshop (DL 2015), and the general chair of the 28th European Summer School in Logic, Language and Information (ESSLLI 2016). He has been nominated Fellow of the European Association for Artificial Intelligence (EurAI, formerly ECCAI) in 2015.

Weblink
http://www.inf.unibz.it/~calvanese/

Other authors
Diego Calvanese, Marco Montali

Abstract

In recent years, the need of combining business process management with master data management has been increasingly recognized as a critical strategic problem, by both academia and industry. This led to a flourishing line of work focused on data- and knowledge-aware business processes, and in particular on intelligent techniques to support human stakeholders in modeling, verifying, enacting, monitoring, and mining integrated models of processes and data.  We are interested in studying these problems and in devising techniques and tools that support them, also in the context of smart factories.

Thursday 22/06/2017

Poster

Industrial big data and process modelling for smart factories (IBDSF)
Edyta Brzychczy
From big data to useful knowledge: challenges and opportunities in smart factories

Edyta Brzychczy has been graduated with distinction in Management and Marketing in Industry at Mining Faculty AGH University of Science and Technology (2001).
Since 2002 she has been working at the Department of Economics and Management in the Industry AGH-UST, obtaining doctorate (2005) and habilitation degree (2013) in technical sciences in discipline of mining and geology. Author and co-author over 80 publications, mainly in the field of modeling and optimisation of mining production. Participant of many national and international scientific conferences.
Member of the Polish Artificial Intelligence Society and Polish Production Management Society. Since 2013 she has been a member of the Mining Economics and Organization Section of the Mining Committee of the Polish Academy of Sciences. Initiator of Data and Process Mining Group (www.bigdata.agh.edu.pl).
Her scientific interests include: production optimisation with evolutionary algorithms and artificial immune systems, data mining, process mining and expert systems.

Other author :
Grzegorz J. Nalepa

Abstract

We start with identification of selected challenges of smart factories. Then we focus on handling big data with machine learning and introduction of semantics for interoperability. Important challenges of smart factories are also related to the use of sensor networks and the Internet of Things paradigm. Intelligent processing of big data can be simplified in context-aware systems handling uncertainty. Finally, managing smart factories requires business process management techniques, where process models are learned from data.

Thursday 22/06/2017

Keynote talk

AttachmentSize
PDF icon CHIST-ERA_Nalepa_Brzychczy.pdf11.64 MB
Industrial big data and process modelling for smart factories (IBDSF)
Fabio Bonsignorio
Reproducible Research in Robotics: the Road Ahead

Prof. Fabio Bonsignorio is an Affiliate Professor at the Biorobotics Institute of the Scuola Superiore Sant'Anna in Pisa. He has been professor in the Department of System Engineering and Automation of the University Carlos III of Madrid until 2014. In 2009 he was awarded the Santander Chair of Excellence in Robotics at the same university (a distinguished professor position). He is founder and CEO of Heron Robots (advanced robotic solutions), see www.heronrobots.com.  He has been working in the R&D departments of several major Italian and American companies for more than 20 years.  He is a member of the Research Board of Directors of SPARC, the Eu Robotics PPP. He coordinated and has been the main teacher of the ShanghAI Lectures 2013, 2014, 2015 (www.shanghailectures.org), intitiated several years ago by Rolf Pfeifer. He is currently coordinating the 2016 edition. He has pionereed and introduced the topic of Reproducible Research and Benchmarking in Robotics and AI. He is an Associate Editor of the IEEE Robotics and Automation Magazine. \newline He is author or co-author of about 140 publications He is a member of the Euron Training Board (the George Giralt PhD Award jury). He is the coordinator of the euRobotics Topic Group on Experiment Replication, Benchmarking, Challenges and Competitions and is co-chair of the IEEE RAS TC-PEBRAS (PErformance and Benchmarking of Robotics and Autonomous Systems).

Abstract

In Robotics Research the Replicability  and Reproducibility of results and their objective evaluation and comparison is very difficult to put into practice.  Controlling for environmental considerations is hard, defining comparable metrics and identifying goal similarity across various domains is poorly understood. Even determining the information required to enable replication of results has been the subject of extensive discussion. Even worse, there is still no solid theoretical foundation for experimental replicability in robotics.  This situation impairs both research progress and technology transfer, and also mundane issues such the proper determination of insurance fee for partially or totally autonomous physically embedded systems.
Some believe that actually the issues of benchmarking are related to the scientific core of Robotics and AI when they are seen as experimental sciences.
Significant progress has been made in these respects in recent years and this talk will provide a view of the state of the art.
The importance and timeliness of this topic is highlighted in the editorial and the turning point column interview in the IEEE  RAM's September 2015 issue.

Wednesday 21/06/2017

Keynote talk

AttachmentSize
PDF icon CHIST-ERA_Bonsignorio.pdf7.15 MB
Object recognition and manipulation by robots: data sharing and experiment reproducibility (ORMR)
Grzegorz J. Nalepa
From big data to useful knowledge: challenges and opportunities in smart factories

Grzegorz J. Nalepa is an engineer with degrees in computer science - artificial intelligence, and philosophy. He has been working in the area of intelligent systems and knowledge engineering for over 15 years. He formulated the eXtended Tabular Trees rule representation method, as well as the Semantic Knowledge Engineering approach. He authored a book "Modeling with Rules using Semantic Knowledge Engineering", to be published by Springer in 2017. He co-authored over 150 research papers in international journals and conferences. He coordinates GEIST - Group for Engineering of Intelligent Systems and Technologies (http://geist.re) cooperating with AGH University and Jagiellonian University in Krakow, Poland. For almost 10 years he has been co-chairing the Knowledge and Software Engineering Workshop (KESE) at KI, the German AI conference,  Spanish CAEPIA, as well ECAI. He is the President of the Polish Artificial Intelligence Society(PSSI), member of EurAI. He is also a member of IEEE, Italian Artificial Intelligence Society (AI*IA), KES, Polish Cognitive Science Society (PTK). His recent interests include context-aware systems and affective computing.

Other author :
Edyta Brzychczy

Abstract

We start with identification of selected challenges of smart factories. Then we focus on handling big data with machine learning and introduction of semantics for interoperability. Important challenges of smart factories are also related to the use of sensor networks and the Internet of Things paradigm. Intelligent processing of big data can be simplified in context-aware systems handling uncertainty. Finally, managing smart factories requires business process management techniques, where process models are learned from data.

Thursday 22/06/2017

Keynote talk

AttachmentSize
PDF icon CHIST-ERA_Nalepa_Brzychczy.pdf11.64 MB
Industrial big data and process modelling for smart factories (IBDSF)
Jean Rouat
Scene Analysis and Interpretation for Objects Recognition and Manipulation

Jean Rouat is full professor of the Université de Sherbrooke - Canada (Département de génie électrique et de génie informatique) and adjunct professor at the Université de Montréal - Canada (Département de sciences biologiques, Faculté des arts et des sciences). His research expertise are : Intelligent systems, Artificial Intelligence, Machine Learning, Signal, speech and audible signals processing, Visual Processing, Computational and Systems Neurosciences, Neurophysiological Signal analysis, Human-Systems interfaces, Sensorial substitution. His Areae of research are : Neuronal system simulations and modelling, Sensorial substitution, Plasticity, Audition, Vision, Signal processing, Computational and Systems Neuroscience and Machine Learning, Speech and Image processing/recognition.

Weblink
https://www.gel.usherbrooke.ca/rouat/english.html

Abstract

Most of the time, robots interact with objects through manipulations within a specific environment. To grasp and manipulate the object the robot needs to understand and interpret the scene. Evaluation protocols need to be discussed between researchers along with sharing of databases to allow reproducibility. The poster discusses these elements and lists potential partners interested in taking part in the call.

Wednesday 21/06/2017

Poster

AttachmentSize
Image icon CHISTERA_Conf2017_ORMR_poster_Rouat.jpg869.81 KB
Object recognition and manipulation by robots: data sharing and experiment reproducibility (ORMR)
Martin Atzmueller
Towards Semantic Big Data Analytics for Smart Production
Abstract

In the age of digital transformation, information and data is becoming ubiquitous. Especially in smart production scenarios large volumes of data are being automatically collected, and a variety of heterogeneous data becomes available for data analytics. However, often prior knowledge, that is, information about specific processes is either not directly available in structured form, or is not being integrated and exploited. In this talk, I focus on big data analytics in smart production contexts, and present exemplary approaches and methods in order to extract meaningful insights from large amounts of heterogeneous data and to support decision making.

Thursday 22/06/2017

Keynote talk

Industrial big data and process modelling for smart factories (IBDSF)
Matteo Matteucci
The RAWSEEDS benchmarking toolkit: How we did it!

Matteo Matteucci (M) (PhD in Computer Engineering and Automation, 2003, Politecnico di Milano) is an Associate Professor at Politecnico di Milano. He got a Master of Science in Knowledge Discovery and Data Mining at Carnegie Mellon University (Pittsburgh, PA), and a PhD in Computer Engineering and Automation at Politecnico di MIlano. He has published more than 30 (peer-reviewed) papers on international journals and more than 100 (peer-reviewed) contributions to international conferences and book chapters. He is part of the Program Committee of several conferences on Artificial Intelligence and Robotics, he is in the Technical Committee of Intelligent Autonomous Vehicles of the International Federation of Automatic Control, and he serves as reviewer for international journals and main conferences in his field of expertise. He is deeply involved in the field of Robot Benchmarking; he participated as benchmarking expert in the FP7 EU funded RoSta Project; he has been an active participant to the Special Interest Group on Good Experimental Methodologies and Benchmarking of EURON, and he is one of the co-authors of the Review guidelines produced by the Special Interest Group; he has been one of the proposers of the euRobotics “Topic group on Benchmarking and Competitions” and currently member of the euRobotics Topic Group on “Experiment Replication, Benchmarking, Challenges and Competitions”. He has been the Coordinator of the European project RAWSEEDS (2006-2009,http://www.rawseeds.org) a Specific Support Action in the FP6 for the development of a benchmarking toolkit for multi-sensor SLAM algorithms. He has been the National Scientific Coordinator (Principal Investigator) of the ROAMFREE project (2009-2013, http://roamfree.dei.polimi.it) for the development of method for the robust estimation of robot odometry by sensor fusion funded by the Italian Ministry for the University and the Research (MIUR) under the PRIN 2009 program. He has been the Principal Investigator for Politecnico di Milano (Partner) of the FP7 project RoCKIn (2013-2015, http://www.rockinrobotchallenge.eu/) for the design and execution of two international competitions for the benchmarking of autonomous robots in the home environment (RoCKIn@Home) and at work (RoCKIn@Work). He is currently the Principal Investigator for Politecnico di Milano in the H2020 RockEU2 (2016-2018) Coordinated Action within the workpackages devoted to the development of the European Robotics League and the establishment of distributed benchmarking competitions in Europe.

Abstract

Building a benchmark might turn out to be more complex that expected! Some time ago, the RAWSEEDS project consortium, faced the setup of a benchmarking toolkit for Simultaneous Localization and Mapping (SLAM). In my talk I would like to share with you that experience, the challenges we faced, the solution we found, and the lessons we learned in doing that. RAWSEEDS was my first experience in robot benchmarking and after that experience I decided to investigate alternative ways for evaluating robot system performance including the use of robot competitions ...if there will be time I will tell you something about this as well ;-)

Wednesday 21/06/2017

Keynote talk

AttachmentSize
PDF icon CHIST-ERA_Rawseeds.pdf4.34 MB
Object recognition and manipulation by robots: data sharing and experiment reproducibility (ORMR)