Wolfram Burgard

Title: Deep Learning for Robot Navigation and Perception

Abstract: Autonomous robots are faced with a series of learning problems to optimize their behavior. In this presentation I will describe recent approaches developed in my group based on deep learning architectures for different perception problems including object recognition and segmentation and using RGB(-D) images. In addition, I will present a terrain classification approach that utilizes sound and vision. Furthermore, I will present an approach applying deep network architectures for transferring navigation tasks between environments. For all approaches I will describe extensive experiments quantifying in which way they extend the state of the art.

Biography: Wolfram Burgard is a professor for computer science at the University of Freiburg and head of the research lab for Autonomous Intelligent Systems. His areas of interest lie in artificial intelligence and mobile robots. His research mainly focuses on the development of robust and adaptive techniques for state estimation and control. Over the past years Wolfram Burgard and his group have developed a series of innovative probabilistic techniques for robot navigation and control. They cover different aspects such as localization, map-building, SLAM, path-planning, exploration, and several other aspects. Wolfram Burgard coauthored two books and more than 300 scientific papers. In 2009, Wolfram Burgard received the Gottfried Wilhelm Leibniz Prize, the most prestigious German research award. In 2010, Wolfram Burgard received an Advanced Grant of the European Research Council. Since 2012, Wolfram Burgard is the coordinator of the Cluster of Excellence BrainLinks-BrainTools funded by the German Research Foundation. Wolfram Burgard is Fellow of the ECCAI, the AAAI, and the IEEE.

Jorge M. Pacheco

Title: Evolutionary Game Theory of Cooperation: From Cells to Societies

Abstract: The evolution of cooperation stands as one of the main inter-disciplinary challenges of the XXIst century. In this realm, evolutionary game theory provides an adequate and common mathematical basis to address this problem across disciplines. Here I will review some of the main applications of evolutionary game theory to a wide variety of problems that humans face at present, all involving the dynamical interplay between conflict and cooperation. Starting from our increasing understanding of the ecology of cancer, I will also review recent advances in our understanding of how microbes use quorum sensing to communicate with each-other, how adaptive networks allow populations to cooperate globally, and how bottom-up approaches pave the way for overcoming the global governance challenge posed by Climate Change.

Biography: Jorge M. Pacheco (Oporto, 1958) is currently Professor of Mathematics at the Mathematics & Applications Department of the University of Minho (Portugal) and also a member of the Centre of Molecular and Environmental Biology at the same University. His background is in Theoretical Physics, with a degree from the University of Coimbra (Portugal) and a PhD degree from the Niels Bohr Institute, in Copenhagen (Denmark). He is active in a variety of research topics, ranging from many-body physics to the mathematical description of evolutionary processes such as human cancer, evolution of cooperation, urban development, global governance & complexity and complex networks.

Massimiliano Giacomin

Title: Handling heterogeneous disagreements through abstract argumentation

Abstract: Agents disagree in many situations and in many ways on their beliefs, preferences and goals, both interacting with other agents and during their individual reasoning activity. Abstract argumentation frameworks are a formal model to handle disagreement which is represented as a conflict relation between a set of arguments. While arguments intuitively represent reasons to support the acceptance of their conclusions, this model is specifically devoted to conflict management, as it abstracts away the structure of arguments and focuses on a binary relation of attack between them. To solve the conflict and identify justified arguments, various argumentation semantics have been devised reflecting different intuitions and featuring different degrees of skepticism. In traditional argumentation frameworks a single argumentation semantics is applied at a global level, under the assumption that the involved conflicts are essentially homogeneous. In this talk, I will argue that disagreements are in general heterogeneous and thus should be treated in different ways according both to their nature and to the specific agents features. For instance, in the case of epistemic reasoning, i.e. when agents reason over their beliefs, conflicts between arguments arise mainly from uncertainty and incompleteness of information, whereas in the case of practical reasoning, i.e. when agents reason about what to do, distinct goals may conflict since they cannot all be fulfilled due resource limitations. Furthermore, different agents have in general individual interests and preferences, and their reasoning may be characterized by different features (e.g. credulous vs. skeptical). According to these considerations, a general model of abstract argumentation will be discussed, able to handle heterogeneous disagreements by means of multiple argumentation semantics at a local level. The model builds on some recent work on the characterization of argumentation semantics and on the partition of an argumentation framework into interacting sub-frameworks.

Biography: Massimiliano Giacomin is an Associate Professor of Computer Science at the University of Brescia (Italy). He received a M.S. in Electronic Engineering from the University of Padova (Italy) and a Ph.D. degree in Information Engineering from the University of Brescia. He is a co-author of more than 100 papers in the research areas of knowledge representation, knowledge-based systems and automated reasoning, focusing in particular on argumentation theory, fuzzy constraints and temporal reasoning. In 2006, he has awarded the “Marco Somalvico” Artificial Intelligence prize by the Italian Association for Artificial Intelligence (AI*IA) as an outstanding Italian young researcher in the AI field. He is currently a member of the Editorial Board of the journal “Argument and Computation”.