December 13th: The Return of the Light
The Third Örebro Winter School on "Artificial Intelligence and Robotics"

Lectures and Teachers

AI and Robotics at Örebro University: a 18-year retrospective (Monday)

The Center for Applied Autonomous Sensor Systems (AASS) at the Host University for this School has been active in the integration of AI and Robotics since its foundation, back in 1998. These introductory talks will outline some of challenges of this integration, and how we at AASS have addressed these challenges during the life of the Center. These talks are meant to set the scene for the rest of the school, showing in a constructive way some of the difficulties in integrating AI and Robotics, and some of the added value of this integration.

Teachers

Amy Loutfi, Alessandro Saffiotti, Achim Lilienthal (AASS)

Contact: http://www.vernon.eu

 

Cognitive Robotics: A Tutorial (Monday)

Cognitive Robotics is an emerging discipline that draws on robotics, artificial intelligence, and cognitive science. It often exploits models based on biological cognition. The goal of this tutorial is to provide an introduction to the foundations of cognitive robotics, to review the essential elements of cognition, and to provide a summary of the capabilities industrial developers and users seek in a cognitive robot. The tutorial will walk through the various paradigms of cognitive science cognitivist, emergent, and hybrid and their encapsulation in cognitive architectures. It will consider the role of autonomy and role of embodiment in the realization of these architectures in physical cognitive robots. One of the goals of the tutorial is to highlight the different agendas of cognitive science and cognitive robotics, while at the same time acknowledging that their respective research programmes are mutually instructive.

Prerequisites: Students are expected to have gone thru their reading assignments prior to the event at Örebro.

Teacher

Photo David Vernon is a Professor of Informatics at the University of Skövde, Sweden. He works on two projects funded by the European Commission: ROCKeu2, a coordination action focusing on the deployment of cognitive systems in industry, and DREAM, a project that aims to deliver the next generation robot-enhanced therapy (RET) for children with autism spectrum disorder (ASD). In the past, he coordinated two research networks (www.eucognition.org and www.ecvision.org) and he was a member of the team that created the iCub, an open-source cognitive humanoid robot. He was the chair of the sixth European Conference on Computer Vision (ECCV) in 2000. He is a Senior Member of the IEEE, a Chartered Engineer of the Institution of Engineers of Ireland, and a past Fellow of Trinity College Dublin. He is co-chair of the IEEE Robotics and Automation Technical Committee for Cognitive Robotics, survey & review editor of Cognitive Systems Research, and associate editor of the IEEE Transactions on Cognitive and Developmental Systems.

Contact: http://www.vernon.eu

 

3D Semantic Perception - From Point Clouds to Semantic Maps (Tuesday)

Any symbolic representation that a robot can use to plan and reason about the world must eventually be based on raw sensor data. In this full day tutorial we will present methods to generate symbolic information about a robot's environment from 3D point cloud data. During the tutorial we will discuss and implement an exemplary processing pipeline to detect furniture instances in raw point cloud data. The first part of the tutorial deals with the simultaneous acquisition and registration of 3D point cloud data into a common coordinate system (SLAM problem). Surface reconstruction methods will then be used to triangulate the point clouds into triangle meshes that can be segmented in to planar patches. These patches are then classified into furniture instances using semantic background knowledge modeled in an OWL-DL ontology and SWRL rules. The latter part of this tutorial will focus on active perception, i.e., providing the robot with the ability to actively seek new information about its environment. The aim of this full-day course is to give students a glimpse into a variety of techniques along a sensor data processing and mapping pipeline, from the registration of 3D point clouds up to semantic mapping and active perception.

This tutorial consists of four 90 minute sessions with the following topics:

Each session will consist of an introductory talk to the topic, followed by hands-on exercises and practical demonstrations as well as a discussion of the current state of the art in the respective research fields of the single sessions.

Prerequisites

Students are expected to have gone through their pre-school assignments (installation and reading) prior to the School. Basic programming skills in C++ are required.

Teachers

Photo Joachim Hertzberg is a full professor for computer science at Osnabrück University since 2004, heading the Knowledge-Based Systems group; since 2011, he is also head of the Osnabrück branch of DFKI's Robotics Innovation Center. His areas of research are AI and Mobile Robotics, with contributions to action planning, plan-based robot control, sensor data interpretation, semantic mapping, reasoning about action, constraint-based reasoning, and applications of these. In his research fields, he has been the PI in various national and European projects. At Osnabrück University, he served as the Dean of the School of Mathematics and Computer Science. Awards for his work include the EurAi (formerly ECCAI) fellowship received in 2014.

Photo Martin Günther is a researcher at DFKI, the German Research Center for Artificial Intelligence. He earned his Diploma in Computer Science from Technical University Dresden, Germany, in 2008. From 2009 until 2015 he worked as a research associate at the Knowledge-Based Systems group at Osnabrück University, Germany, where he worked among other things on the FP7 project RACE. His research interests are 3D perception, semantic mapping, context-aware object anchoring, active perception and the general question of how to achieve goal-directed action in an autonomous robot.

Photo Dr. Thomas Wiemann is a researcher at the Knowledge Based Systems Research group at Osnabrück University. Focus of his research is 3D sensor data processing and interpretation with emphasis on generating semantic scene interpretations from point cloud data for semantic mapping and robot localization. He has given several tutorials on these topics on a number of international conferences like ICRA, ICAR and IAS. He is the main maintainer of the open source Las Vegas Surface Reconstruction toolkit for surface reconstruction from unorganized point cloud data.

Contact

http://www.inf.uos.de/hertzberg

 

Constraint-Based Reasoning for Robots (Wednesday)

In 1966, SRI International developed Shakey, the first AI-driven robot. Shakey exemplifies a major contribution of AI to Robotics, namely the model-centered approach, whereby robot behavior stems from reasoning in a model of the world which can be changed to suit different environments, physical capabilities, and tasks. But what are the meaningful aspects of the world that should be represented in a model? Clearly, these depend on the particular application context at hand. As robots become more flexible and usable, we wish to "program" them through increasingly sophisticated models - whereas Shakey's model consisted of a purely propositional abstraction of the world (a STRIPS propositional action theory), today's applications may call for temporal, spatial, resource, geometric, and other forms of knowledge.

This lecture focuses on constraint-based models for multi-robot planning and coordination. We will explore the use of temporal and spatial constraints as a means to specify and regulate the behavior of a fleet of Turtlebots. The lecture will build upon the techniques for active perception presented in the "3D Semantic Perception" tutorial given on the first day of the school. We will employ the so-called Meta-CSP approach to plan and coordinate multiple robots in the task of cooperatively exploring a target volume in the environment. Spatial reasoning will be employed to regulate the areas each robot is dispatched to explore, while hybrid spatio-temporal reasoning will be used to ensure that robots do not interfere with each others' observations (avoiding collisions, deadlocks, and occlusions by other robots). The course will be centered around practical exercises involving robots (simulated through Gazebo and real robots in an arena located in the classroom).

Prerequisites

Students are expected to have gone through the (light) reading assignments on Constraint-Based Reasoning provided prior to the tutorial. It is also expected that students have installed ROS on their laptop, as these tools will be used extensively during the tutorial. The exercises will require basic knowledge of programming in Java

Teachers

Photo Federico Pecora (PhD in Computer Science from University of Rome "La Sapienza" 2007) is Associate Professor at the Center for Applied Autonomous Sensor Systems (AASS) at Örebro University, Sweden. His interests lie at the intersection of Artificial Intelligence and Robotics, with a focus constraint reasoning algorithms, planning, scheduling, meta-CSP techniques for integrated reasoning, constraint-based planning and scheduling for robotic systems, and context recognition. He has primarily applied these techniques in two broad application areas: service robots/sensor systems for use in domestic environments; and decision support tools for industrial scenarios with large autonomous vehicles.

Photo Masoumeh Mansouri is a postdoctoral researcher in the Cognitive Robotic Systems Lab at the Center for Applied Autonomous Sensor Systems (AASS, Örebro University, Sweden). Her main research interest is to employ artificial intelligence techniques in autonomous mobile robotics, with a particular focus on the use of hybrid knowledge representation and reasoning and meta constraint-based reasoning. She earned her master degree in Robotics and Intelligent Systems at Örebro University in 2011, with a master's thesis on constraint based activity recognition with uncertainty. She finished her Ph.D studies in 2016, during which she investigated a meta-CSP approach for hybrid reasoning in robotics. Her overall passion is to work towards the realization of fully AI-driven integrated robotic systems.

Contact

http://aass.oru.se/~fpa

 

Robots and Humans (Thursday)

The lecture will provide some general background to the field of human robot interaction from the point of view of social robotics. The main topics that are addressed in this research area will be initially surveyed. Then, as communication in natural language plays a key role in the social interaction with robot, the talk will focus on it. In particular, we will address the technical and scientific challenges that research is currently facing in human robot interaction through spoken language. In addition, we will present a tool for spoken command understanding that we have recently made available to the research community. Finally, we will present some of the challenges and possible approaches to dialogue management.

Prerequisites: Students are expected to have gone thru their reading assignments prior to the event at Örebro.

Teachers

Photo Daniele Nardi is full Professor (since 2000) at Sapienza Univ. Roma, Faculty of Ingegneria dell'Informazione, Informatica, Statistica, Dept. Computer, Control and Management Engineering "A. Ruberti". He is currently coordinator of the PhD program in Computer Engineering at Sapienza and responsible for the Master curriculum in Artificial Intelligence and Robotics. 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 speech; The scientific and technical achievements are deployed in manifold application domains: Ambient Intelligence and robots to support elderly people, Disaster Response robots to explore and gather information from the environment, Soccer Player robots for RoboCup competitions. Daniele Nardi is ECCAI Fellow, and was President of RoboCup Federation (2011-2014).

Photo Andrea Vanzo is a PhD student (2014-now) at the Department of Computer, Control and Management Engineering "Antonio Ruberti" of Sapienza University of Rome. He works within the Ro.Co.Co. group, under the supervision of Prof. Daniele Nardi, addressing manifold problems in the context of Human-Robot Interaction in Natural Language. He earned both the BSc and MSc in Computer Science at University of Rome Tor Vergata, Italy, in 2010 and 2014, respectively, under the supervision of Prof. Roberto Basili. He is currently active on research topics such as Spoken Language Understanding and Dialogue Modeling within the Robotics field.

Contact: http://www.dis.uniroma1.it/~nardi/

 

Benchmarking and Evaluation of Intelligent Robotic Systems (Thursday)

Problem benchmarks are used in experimental science as a reference against which results of experiments using distinct approaches to solve the problem are compared and evaluated in relative terms. In Robotics, just formulating a general performance assessment problem is difficult per se, as robotic systems are composed of very diverse subsystems (e.g., localization, human-robot interaction). Thus, performance evaluation and benchmarking are tightly intertwined problems in Robotics. Robot competitions have been proposed in the last decades as means of benchmarking the solution of a research challenge posed by the specific competition, assuming that the competition results are, by themselves, a means for performance assessment of the integrated system. In this talk we will survey and propose methods and metrics for performance evaluation of robot systems through competitions, as well as benchmarking methods that use the data logged during the competitions to infer conclusions on the impact of robot system components on the actual overall task performance.

The lecture will be divided in two parts:

Prerequisites: Students are expected to have gone thru their reading assignments prior to the event at Örebro.

Teachers

Photo Pedro U. Lima got his Licenciatura (5 year degree, 1984) and MSc (1989) in Electrical and Computer Engineering from Instituto Superior Técnico (IST), and the Ph.D. (1994) in Electrical Engineering at RPI, NY, USA. Currently, he is a Professor at IST, Universidade de Lisboa, and a researcher of the Institute for Systems and Robotics, where he is the coordinator of the Intelligent Robots and Systems group. He is the co-author of two books, and Associate Editor of the Elsevier Journal Robotics and Autonomous Systems. His research interests lie in the areas of discrete event models of robot tasks and planning under uncertainty, with applications to networked robot systems and interaction with humans.
Pedro U. Lima is a Trustee of the RoboCup Federation (2003-2012, 2016-), and was the General Chair of RoboCup2004, held in Lisbon. He was President and founding member of the Portuguese Robotics Society, was National Delegate to EU and ESA Space Robotics programs and was awarded a 6-month Chair of Excellence at the Universidad Carlos III de Madrid, Spain in 2010. He was also the Coordinator of the FP7 Coordination Action RoCKIn, and currently in charge of the Indoor Competitions f the European Robotics League. He has also been very active in the promotion of Science and Technology to the society, through the organization of Robotics events in Portugal, including the Portuguese Robotics Open since 2001.

Photo Fabien Lagriffoul got his PhD degree in Computer Science in January 2016. He is currently a Postdoc at Örebro University. His research interests are both AI and Robotics, with focus on problems which require to combine high-level (task planning, scheduling) with low-level (geometric reasoning, motion planning) reasoning techniques.

Contact: http://users.isr.tecnico.ulisboa.pt/~pal

 

Robot Control Architectures (Friday)

Architecture is the fundamental organization of a system embodied in its components, their relationships to each other and to the environment and the principles guiding its design and evolution. The design of the software architecture of a robot control application is challenging for two main reasons.

  1. A robot control application is an embedded software system equipped with a rich set of software functionalities, typically deployed on a distributed computing infrastructure with stringent resource constraints, for interacting purposefully and in real-time with an open-ended environment through sensors and actuators.
  2. A robot control application should be flexible enough to accommodate easily frequently changing requirements: more advanced tasks in highly dynamic environments, in collaboration with unskilled users, and in compliance with changing regulations.
Software architecture design is a multidimensional decision-making process and different software models are needed to describe the system from multiple perspectives, such as structure, behavior, and nonfunctional properties.

The aim of the lecture is to illustrate best practice modeling techniques, processes, and tools for developing robot control architectures and to discuss with the audience issues, challenges, and promising research directions in control architectures for autonomous robots.

Prerequisites: Students are expected to have gone thru their reading assignments prior to the event at Örebro.

Teacher

Photo Prof. Davide Brugali graduated in Electronic Engineering at Politecnico di Milano in 1994; he received the PhD in Computer Science from Politecnico di Torino in 1998. From 2001 until 2011 he has been Assistant Professor at University of Bergamo. Since 2011 he is Associate Professor at the Department of Engineering of the University of Bergamo, where he leads the Software for Experimental Robotics Laboratory (SERL). He has been visiting researcher at the CMU Robotics Institute between year 1997 and 1998 and visiting professor at NASA Jet Propulsion Laboratory in year 2006. Since 2000 he is Co-Chair of the IEEE RAS Technical Committee on "Software Engineering for Robotics and Automation". Since 2009 he is Editor-in-Chief of the Journal of Software Engineering for Robotics. His main research interests are in the field of software development and reuse for autonomous robots. Recent achievements include the development of modeling tools for the design and configuration of software product lines for autonomous robots.

Contact: http://robotics.unibg.it/people/brugali.html/

 

From Blue Skies to Believable Applications: 12 Years of Robotics and AI in the EU (Friday)

In this talk I'll give a personal (and thus highly biased/selective!) view of AI and robotics projects in Europe. This will mainly cover three large integrated projects (CoSy, CogX and STRANDS), whilst attempting to identify the trends and pressures which shaped the development of our field from the early 2000s until now.

Teacher

Photo Dr Nick Hawes is a Reader in Autonomous Intelligent Robotics in the School of Computer Science at the University of Birmingham. His research applies techniques from artificial intelligence to allow robots to perform useful tasks for, or with, humans in everyday environments (from moving goods in warehouses to supporting nursing staff in a care home). He is particularly interested in how robots can understand the world around them and how it changes over time (e.g. where objects usually appear, how people move through buildings etc.), and how robots can exploit this knowledge to perform tasks more efficiently and intelligently.

Contact: http://nickhaw.es

 

AI and Robotics from an Industrial Perspective (Friday)

  • Abstract will come ...
  • Teacher

    Photo Dr-Ing Georg von Wichert, with Siemens since 1998, currently heads the Research Group Robotics, Autonomous Systems and Control within Siemens Corporate Technology, Munich, Germany. Georg von Wichert holds a PhD in Robotics and Control Engineering from Technische Universität Darmstadt, Germany. He contributed to and managed projects with applications among others in advanced robotics, driver assistance systems, autonomous driving, human-machine interaction, and sensor data and information fusion. Georg von Wichert is a Rudolf Diesel Fellow of the Institute for Advanced Study at Technische Universität München, where he also gives lectures on Advanced Robot Perception. Georg von Wichert actively serves the European research community as a evaluator and reviewer for FP7 and H2020 projects.

     

    What's there to fear about AI? (Friday)

    Artificial Intelligence (AI) is back in the zeitgeist. The Chief Economist of the Bank of England predicted AI will destroy 50% of jobs in the UK. In 2015, thousands of AI researchers signed an Open Letter to the UN predicting that AI could transform warfare and lead to an arms race of "killer robots". And Stephen Hawking and others have predicted that AI could end humanity itself. What should you make of all these predictions? What should we do to ensure a safe and prosperous future for all?

    Teacher

    Photo Toby Walsh is a leading expert in artificial intelligence (AI). He was named by the Australian newspaper as a "rock star" of the digital revolution, and included in the inaugural Knowledge Nation 100, the list of the 100 most important digital innovators in Australia. Professor Walsh's research focuses on how computers can interact with humans to optimise decision-making for the common good. He is also a passionate advocate for limits to ensure AI is used to improve, not take, lives. In 2015, Professor Walsh was one of the people behind an open letter calling for a ban on autonomous weapons or "killer robots" that was signed by thousands of AI researchers and high profile scientists, entrepreneurs and intellectuals, including Stephen Hawking, Noam Chomsky, Apple co-founder Steve Wozniak, and Tesla founder Elon Musk. He was subsequently invited by Human Rights Watch to talk at the United Nations in both New York and Geneva. Professor Walsh is a Fellow of the Australia Academy of Science and of the Association for the Advancement of Artificial Intelligence, and was recently awarded the 2016 NSW Premier's Prize for Excellence in Engineering and Information and Communications Technologies.

    Contact: http://www.cse.unsw.edu.au/~tw

     

    [ School Home ]

    ------------------
    Website hosted by AASS
    Last updated on December 10, 2016