Home » IROS 2018 Workshop “Robots that learn and reason” » Invited speakers & Accepted papers

Invited speakers & Accepted papers

  • Tony Cohn, Professor of Automated Reasoning at University of Leeds, UK.
    Talk title: “Learning Rules and Grammars from Video (and Language)” (Slides)
    Short Bio: Tony Cohn is Professor of Automated Reasoning in the School of Computing, at the University of Leeds. His current research interests range from theoretical work on spatial calculi and spatial ontologies, to cognitive vision, modelling spatial information in the hippocampus, and Decision Support Systems, particularly for the built environment. He is Editor-in-Chief Spatial Cognition and Computation and was previously Editor-in-chief of the AI journal. He is the recipient of the 2015 IJCAI Donald E Walker Distinguished Service Award which honours senior scientists in AI for contributions and service to the field during their careers, as well as the 2012 AAAI Distinguished Service Award. He is a Fellow of the Royal Academy of Engineering, the Alan Turing Institute in the UK, and is also a Fellow of AAAI, AISB, EurAI (formerly ECCAI), the BCS, and the IET. He is a Distinguished Visiting Professor and High End Expert at the University of Tongji. 
  • Irina Higgins, Senior Research Scientist at DeepMind, UK
    Talk title: “Unsupervised Disentanglement Or How to Transfer Skills and Imagine Things”
    Summary: Despite the advances in modern deep learning approaches, we are still quite far from the generality, robustness and data efficiency of biological intelligence. We suggest that this gap may be narrowed by re-focusing on explicit unsupervised representation learning, rather than relying on the implicit representation learning prevalent to end-to-end deep learning approaches. In particular, we demonstrate the value of disentangled visual representations acquired in an unsupervised manner by solving a constrained optimisation problem loosely inspired by the considerations from Neuroscience. We demonstrate how such representations can be acquired in life-long learning scenarios and form the foundation for abstract compositional visual concepts. Such concepts enable imagination of meaningful and diverse samples beyond the training data distribution. We also show how such representations can enable the acquisition of reinforcement learning (RL) policies that are more robust to transfer scenarios than standard RL approaches.
    Short Bio: Irina Higgins is a Senior Research Scientist at DeepMind, where she works in the Neuroscience team. Her work aims to develop more robust, general and interpretable artificial intelligence by taking inspiration from the neurosphysiology of the brain. Before joining DeepMind, Irina was a British Psychological Society Undergraduate Award winner for her achievements as an undergraduate student in Experimental Psychology at Westminster University, followed by a PhD at the Oxford Centre for Computational Neuroscience and Artificial Intelligence, where she focused on understanding the computational principles underlying speech processing in the auditory brain. During her PhD, Irina also worked on developing poker AI, applying machine learning in the finance sector, and working on speech recognition at Google Research. 
  • Guglielmo Gemignani, Team leader at Magazino, Germany
    Talk Title: “Learning and Reasoning Approaches in Logistics” (Slides)
    Short Bio: Dr. Guglielmo Gemignani is currently a team lead at Magazino GmbH, Munich. His team is responsible for the plan execution and reasoning of the logistics robots developed at Magazino. Guglielmo received his doctoral degree in 2016 from Sapienza University of Rome, Italy, which focused on the development of a cognitive agent able to learn and intelligently interact with multiple users in a domestic environment.. Prior to that, Guglielmo obtained his MSc in physics from the university of Rome in 2012 and his BSc in Physics from the university of Pisa in 2010. 

Accepted Papers