Keynote
Jacques Malenfant
Full Professeur in LIP6 (Computer Lab of Paris 6) and Vice-President of Pierre et Marie Curie University, Paris, France Jacques Malenfant holds a B.Sc. in computer science and mathematics and a M.Sc. in computer science from the Université Laval (Québec), as well as a Ph.D. from the Université de Montréal. He is currently full professor of computer science and vice-president for human resources at the Université Pierre et Marie Curie (Paris). Coming from a programming languages and software architectures background, he engaged in 2006 into a French initiative started by roboticists to foster collaborations between the software engineering and robotics research communities. These efforts laid the ground for the creation in 2015 of a French CNRS research network he is co-chairing which gathers the two French communities in annual conferences, called CAR and now SHARC, as well as regular workshops. He currently serves on the program committee of the IEEE Robotic Computing 2017 conference.
Title: Software Engineering meets Robotics: from common grounds to cross-fertilization
Abstract: Software engineering mainly developed during the ’80s and ’90s over the precepts of virtualization, abstraction from resources and little interest for interaction with the real world. In parallel, the real-time programming and especially the control architecture for robots research communities were developing against the challenges from resources shortage, cyber-physical programming constraints and the growing complexity of robotic software. Now, the two communities objectively rejoin, as fewer and fewer significant software today can ignore resources constraints, interactions with the physical world as well as control-theoretic issues. This talks aims at supporting this latter claim and building a common understanding between the two communities over their shared challenges and opportunities.
Javier Civera
Associate professor at the Robotics, Perception and Real-Time Group, University of Zaragoza, Spain. Javier Civera was born in Barcelona, Spain, in 1980. He received his Ph.D. degree in 2009, from the University of Zaragoza in Spain. He is currently an Associate Professor at the University of Zaragoza, where he teaches courses in computer vision, machine learning and control engineering. He has leaded or participated on more than 30 EU-funded, national and technology transfer projects related with vision and robotics. He has been funded for research visits to Imperial College (London) and ETH (Zürich). He has coauthored more than 30 publications in top conferences and journals, receiving around 2,100 references (GoogleScholar). Currently, his research interests are in the use of 3D vision, distributed architectures and learning algorithms to produce robust and real-time vision technologies for robotics, wearables and AR applications.
Title: Cloud Robotics: Outsourced Computation and Shared Data
Pieter Simoens
Assistant Professor in iMind, Ghent University, Belgium Pieter Simoens received his M.Sc. degree in Electronic Engineering (2005) and Ph.D. degree (2011) from the Ghent University, Belgium. During his Ph.D. research, he was funded by the Fund for Scientific Research Flanders (FWO-V). In 2012, he was a visiting researcher at the School of Computer Science of Carnegie Mellon University, USA. Currently, he is assistant professor affiliated with the Department of Information Technology of the Ghent University and with iMinds. He is teaching courses on Mobile Application Development and Software Engineering.
Title: Distributed intelligence at the edge for advanced robotics Abstract: Robots, traditionally stand-alone systems, are quickly moving towards “everything connected” applications, accelerated by the availability of IoT-powered resources like big data, advancements in machine learning and the deployment of distributed cloud computing infrastructure at the network edge. Open worlds and human presence requires advanced capabilities to observe, understand and interpret the surroundings and dynamically adjust a robot’s control strategy accordingly. In this talk, I will zoom in various techniques to tackle the complexity, dynamism and uncertainty in robotic operational contexts. This includes trade-offs for deep learning on resource-constrained devices, platform solutions for real-time discovery, negotation and on-the-fly allocation of additional services on the robot and the cloud, and advanced planning.
Vineet Nagrath
Researcher at Telecom Sud-Paris, University of Paris Saclay, France
Title: HTML5 Meta-Model for Cloud Robotic Software Design
Fabio Morbidi
Associate professor at the MIS laboratory, University of Picardie Jules Verne, France. Fabio Morbidi received the M.Sc. degree in computer engineering and the Ph.D. degree in robotics and automation from the University of Siena, Italy, in 2005 and 2009, respectively. He was a visiting scholar at the University of California, Santa Barbara, in 2007-2008. He held postdoctoral positions at the Northwestern University, at the University of Texas at Arlington, and at Inria Grenoble Rhône-Alpes. He has been an Associate Professor at the University of Picardy Jules Vernes, Amiens, France, since September 2014. He is a member of the Robotic Perception group of the MIS Laboratory. He was an Outstanding Reviewer for the IEEE Transactions on Robotics in 2013 and 2014, and he is currently serving as an Associate Editor for ICRA 2017. His research interests include multi-robot systems, distributed estimation and control, and robot vision.
Title: Digital Modeling of Cultural Heritage: Toward Cloud-based Robotic Solutions
Abstract: In the first part of my talk, I will present the main research activities of the four groups of the Modeling, Information & Systems (MIS) laboratory at the University of Picardy Jules Verne, France. I will then focus on the recent work of the Robotic Perception group on digital modeling of historical monuments. Special emphasis will be given, in particular, to E-cathedral (https://mis.u-picardie.fr/e- cathedrale/), an ambitious 15-year program started in 2010, which aims at creating a complete and accurate 3D model of Amiens Cathedral, one of the best examples of Gothic architecture in France. I will conclude my talk by examining the possible impact of mobile-robotics and cloud-based solutions on the data collection (via 3D laser scanners) and data processing phases of the digital modeling pipeline.