Speakers

Title: Aerial Base Stations for Supporting Emergency Communications

Abstract: As aviation safety agencies around the world are working towards integrating unmanned aerial systems (UAS) into the national airspace, we envision numerous civilian applications of UAS in near future. One of the most useful applications of UAS in civilian domain is the restoration of communications during disaster recovery.  We are currently developing a proof of concept for UAS enabled communication and networking strategies for supporting emergency communications during disaster response. It involves creating a network consisting of several UAS nodes that can be deployed within few hours after an emergency situation arises. In this talk, we discuss the challenges involved in developing such a UAS network for a real-world application.

Bio: Kamesh Namuduri received B.Tech degree in Electronics and Communications from Osmania University, Hyderabad, India, M.Tech degree in Computer Science from University of Hyderabad, India, and Ph.D. degree in Computer Science and Engineering from the University of South Florida, Tampa, USA. Currently, he is with the Electrical Engineering Department, University of North Texas, Denton, USA. He is currently investigating communications, networking, safety, security, and privacy issues involved in deploying Unmanned Aerial Systems in real-world applications.

Title: Advantages and limitations of controlled mobility in flying robot
networks
Abstract: Recently, flying robot networks are attracting a lot of interest in the research community. Moreover, in the last decade many mobile devices have appeared in the market. Exploiting mobility in a wireless environment, instead of considering it as a kind of disturbance, is a fundamental concept that the research community is beginning to appreciate. Of course, the advantages obtainable through the use of the mobility imply the knowledge of different types of mobility and the way to include it in the management architecture of the flying robot networks. In this talk we claim that mobility and flying robot networks can be considered as two synergetic elements of the same reality. For this purpose, we sketch a macro-classification of the different objectives which can be pursued by controlled mobility. Moreover, we identify and highlight the interactions between this specific type of mobility and the layers of the control stack. Lastly, this talks reports several works where controlled mobility can be exploited practically.

Bio: I obtained my master’s degree magna cum laude in Computer Engineering with a thesis on “Improvements in Radio Resources Management in a Cellular Hierarchical System” at the Universita’ della Calabria, Italy in 2000. In 2001 I was awarded a one-year CNIT (National Inter-University Consortium for Telecommunications) grant and I also had a six month internship at Value Team (technological consulting company of the Value Partners group). In 2002 I started my doctoral studies at the Università della Calabria. I obtained my Ph.D. in 2005 with a dissertation on “New Algorithms of Mobility and Resource Management for Wireless Networks”. During my last year of doctoral studies I joined the BWN (Broadband Wireless Networking) Lab at Georgia Tech in Atlanta, GA, USA. From December 2005 until September 2010, I worked as a research fellow and a contract professor at the Titan Lab of the Department of Electronics, Computer and System Sciences, Universita’ della Calabria, Italy. From October 2010 to August 2012 I worked with the FUN (former POPS) Team at INRIA Lille – Nord Europe as a postdoctoral researcher. I’m currently an Associate Professor at the Université de Technologie de Compiègne, in the Network&Optimization group within the Heudiasyc Lab.

Title: Highly Dynamic Airborne Networking
Abstract: Highly dynamic mobile wireless networks present unique challenges to end-to-end communication, particularly caused by the time varying connectivity of high-velocity nodes combined with the unreliability of the wireless communication channel. Addressing these challenges requires the design of new protocols and mechanisms specific to this environment. Our research explores the tradeoffs in the location of functionality such as error control and location management for high-velocity multihop airborne networks and presents cross-layer optimizations between the MAC, link, network, and transport layers to enable a domain specific network architecture, which provides high reliability for telemetry applications. We have designed new transport, network, and routing protocols for this environment: TCP-friendly disruption-tolerant AeroTP, IP-compatible AeroNP, and geolocation-based AeroRP, which show significant performance improvement over the traditional TCP/IP/MANET protocol stack.

Bio: James P.G. Sterbenz is Professor of Electrical Engineering & Computer Science and a member of technical staff at the Information & Telecommunication Technology Center at The University of Kansas, is a Visiting Professor of Computing in InfoLab 21 at Lancaster University in the UK, has been a Visiting Guest Professor in the Communication Systems Group at ETH Zürich, a Visiting Scholar in the Computing Department at Hong Kong Polytechnic University, a Visiting Research Scientist at the University of Massachusetts, and is on the Advisory Board of the NorNet testbed of Simula Research Laboratory in Norway and on the board of directors of KanREN (Kansas Research and Education Network).  He has previously held senior staff and research management positions at BBN Technologies, GTE Laboratories, and IBM Research. His research interests include resilient, survivable, and disruption tolerant networking, future Internet architectures, active and programmable networks, and high-speed networking and components.  He is director of the ResiliNets Research Group, and has been PI in a number of projects including the NSF FIND and GENI programs, the EU FIRE ResumeNet project, leads the GpENI international programmable network testbed project, and has lead a US DoD project in highly-mobile ad hoc disruption-tolerant networking.  He received a DsC in computer science from Washington University in 1991.  He has been program chair for IEEE GI, GBN, and HotI; IFIP RNDM, IWSOS, PfHSN, and IWAN; and was on the editorial board of IEEE Network.  He is principal author of the book High-Speed Networking: A Systematic Approach to High-Bandwidth Low-Latency Communication.

Title: Context-Oriented Adaptation in Cyber-Physical Systems
Abstract: Cyber-physical systems (CPS) are a class of computing systems that involves a tight interaction between the real world and the machine. Example CPS are wireless sensor networks, the Internet of Things, and robot drones. The real world, however, is characterized  by multiple dimensions that are changing constantly and independently. CPS software is therefore continuously confronted with unpredictable environment dynamics and, as a result, implementations easily become  entangled and thus difficult to debug and to maintain. The problem becomes even harder against severe resource constraints. To address these issues, we conceive dedicated design and programming support based on a notion of context as an abstraction of the environmental situation the software may find itself in. We implement our approach in a tool called Grevecom, where designers can create language-independent models of adaptive CPS software, and verify the models against possible environment dynamics. Our tool also allows  designers to generate implementation templates for the target platforms. The current prototype generates ConesC sources: a context-oriented extension of an existing language for wireless sensor networks called nesC. We demonstrate that the resulting implementations  are easier to maintain and to understand, and the functionality therein is more decoupled. On the other hand, the system overhead is negligible; for example, we measure a mere 2.5% (2.25%) static memory (program memory) overhead.

Bio: Mikhail Afanasov is a PhD student at the Department of Electronics and Information (DEI) of Politecnico di Milano since November 2012, where he was accepted after receiving Masters degree in “Applied Physics and Mathematics” at Moscow Institute of Physics and Technology (2012). His research is about designing self-adaptive software for extremely resource-constrained cyber-physical systems, which he has a pleasure to conduct in tight collaboration with Carlo Ghezzi and Luca Mottola. His research interests imply, but are not limited to, software engineering, self-adaptive software, cyber-physical systems and wireless sensor networks.

Title: Horizon 2020 and other International Funding Options
Abstract: Horizon 2020, the new EU Framework Programme for Research and Innovation, has started on January 1, 2014. It connects seamlessly to the 7th EU Framework Programme for Research and unites all funding programmes of the European Commission relevant for research and innovation. Horizon 2020 addresses researchers from universities, research organisations, enterprises, international special interest organisations and other legal entities of the EU Member States and the Associated States of the Framework Programme. Institutions from third countries are principally entitled to participate. Next to this also different other Funding Mechanisms might be interesting for your research. The presentation aims at giving you an overview of running programmes and showing you ways to find your opportunity.

Bio: Karl Kerschbaum is Research Associate and Legal Counsel at EU GrantsAccess, the joint office of University and ETH Zürich for support in international and EU grants. He holds a degree in law from the University of Munich (D), and also studied in  Amsterdam (NL) and Lausanne (CH) with a focus on international relations. After his admission to the bar in Munich (D), he worked for several years as a consultant and project manager in HR and as a Contract Manager in the IT and communications industry. After his appointment at the ETH transfer office he joined EU GrantsAccess with a focus on EU Framework Programmes for Research and Innovation (FP7, Horizon 2020), Consortium Agreements and Mediation and Arbitration in international research collaborations.

Title: Vision-Controlled Micro Flying Robots
Abstract: This talk will give an overview of my group research activities on vision-based autonomous navigation of micro and nanoqaudrotors. Our quadrotors (the size of a few centimentrs) can fly all by themselves by processing fully onboard data from a single downlooking camera and an inertial measurement unit. Our research spans indoor and outdoor GPS-denied navigation, collaboration between ground and aerial platforms, and computer vision.

Bio: Davide Scaramuzza is Assistant Professor of Robotics at the University of Zurich. He is founder and director of the Robotics and Perception Group (http://rpg.ifi.uzh.ch), where he develops cutting-edge research on low-latency vision and visually-guided micro aerial vehicles. He received his PhD (2008) in Robotics and Computer Vision at ETH Zurich (with Roland Siegwart). He was Postdoc at both ETH Zurich and the University of Pennsylvania (with Vijay Kumar and Kostas Daniilidis). From 2009 to 2012, he led the European project “sFly”, which introduced the world’s first autonomous navigation of micro quadrotors in GPS-denied environments using vision as the main sensor modality. For his research contributions, he was awarded the IEEE Robotics and Automation Early Career Award (2014), a Google Research Award (2014), the KUKA Innovation Award (2014), the European Young Researcher Award (2012), and the Robotdalen Scientific Award (2009). He is coauthor of the 2nd edition of the book “Introduction to Autonomous Mobile Robots” (MIT Press).

Title: High-performance flight control in unknown and changing conditions

Abstract: Traditionally, motion planning and control algorithms for robots have been designed based on a priori knowledge about the system and its environment (including models of the robot’s dynamics and maps of the environment). This approach has enabled successful robot operations in predictable environments. However, to achieve reliable and efficient robot operations in unknown, changing, and generally uncontrolled environments, we must enable robots to acquire knowledge during operation and adapt their behavior accordingly. In my talk, I will give an overview of my group’s research activities on learning-based control for high-performance flight in unknown conditions. Our learning schemes combine ideas from control theory and machine learning, and are motivated by real-world applications of flying vehicles.

Bio: Angela Schoellig is an Assistant Professor at the University of Toronto Institute for Aerospace Studies (UTIAS). She conducts research at the interface of robotics, controls and learning. Her goal is to enhance the performance and autonomy of robots by enabling them to learn from past experiments and from each other. Angela has been working with aerial vehicles for the past six years and, more recently, applied her motion planning, control and learning algorithms to large, outdoor ground vehicles. You can watch her vehicles perform slalom races and flight dances at www.youtube.com/user/angelaschoe.
Angela received her Ph.D. from ETH Zurich (with Prof. Raffaello D’Andrea), and holds both an M.Sc. in Engineering Science and Mechanics from the Georgia Institute of Technology and a Masters degree in Engineering Cybernetics from the University of Stuttgart, Germany. Her Ph.D. was awarded the ETH Medal and the 2013 Dimitris N. Chorafas Foundation Award (as one of 35 world-wide). She was selected as the youngest member of the 2014 Science Leadership Program, which promotes outstanding scientists in Canada. In 2013 she was named one of “25 women in robotics you need to know about” by Robohub.org, a leading professional robotics online platform. She was finalist of the 2008 IEEE Fellowship in Robotics and Automation, which supports prospective leaders in this field. Her past research has been published in journals such as Autonomous Robots and the IEEE Robotics & Automation Magazine, and has received coverage worldwide in mainstream TV, print and online media. More information about her research is available at: www.schoellig.name.

Title: Design and Navigation of Flying Robots

Abstract: Robots are rapidly evolving from factory work-horses, which are physically bound to their work-cells, to increasingly complex machines capable of performing challenging tasks as search and rescuing, surveillance and industrial inspections, or autonomous transportation of goods. This requires robots to reliably operate in unstructured and unpredictable environments and various settings. This talk will focus on design and navigation aspects of aerial robots operating in complex environments. It will cover the design of an omnidirectional blimp and a solar airplane for continuous operation. Recent results of visual navigation including visual-inertial localization and mapping (SLAM) in GPS denied environments are presented and discussed. It includes a specially developed visual-inertial sensor for real-time on-board SLAM and collision avoidance. http://www.asl.ethz.ch/

Bio: Roland Siegwart (born in 1959) is a Professor for autonomous mobile robots and Vice President Research and Corporate Relations at ETH Zurich. He studied mechanical engineering at ETH, brought up a spin-off company, spent ten years as professor at EPFL and he held visiting positions at Stanford University and NASA Ames. He is and was the coordinator of multiple European projects and co-founder of half a dozen spin-off companies. He is recipient of the IEEE RAS Inaba Technical Award, IEEE Fellow and officer of the International Federation of Robotics Research (IFRR). He is in the editorial board of multiple journals in robotics and was a general chair of several conferences in robotics including IROS 2002, AIM 2007, FSR 2007 and ISRR 2009. His interests are in the design and navigation of wheeled, walking, swimming and flying robots operating in complex and highly dynamical environments.

Title: 5G and context awareness for MAV communication

Abstract: The flexibility and ubiquity of wireless communication solutions has played an important role in the explosive growth in mobile radios used in laptops, smartphones and tablets. With the evolution towards cyber physical systems and aerial communication networks, mobile systems promise unprecedented opportunities for monitoring and controlling cities and our environment. Today, we notice that this promise is only partially fulfilled, and important spectrum and flexibility bottlenecks hamper the full potential of the next generation wirelessly connected systems. As 5G research is starting, various innovative ideas are being proposed to promise the much desired versatile and spectrum-efficient systems. In this talk, an overview will be given of possible 5G directions, waveforms being proposed, how context awareness is exploited to improve spectrum use, and how all this could be relevant for MAV communication.

Bio: Sofie Pollin obtained her PhD degree at KU Leuven with honors in 2006. From 2006-2008 she continued her research on wireless communication, energy-efficient networks, cross-layer design, coexistence and cognitive radio at UC Berkeley. In November 2008 she returned to imec to become a principal scientist in the green radio team. Since 2012, she is tenure track assistant professor at the electrical engineering department at KU Leuven. Her research centers around Networked Systems that require networks that are ever more dense, heterogeneous, battery powered and spectrum constrained. Prof. Pollin is BAEF and Marie Curie fellow, and IEEE senior member.

Title: Autonomous flight of very light-weight Micro Air Vehicles

Abstract: Autonomous flight of light-weight Micro Air Vehicles (MAVs) poses a major challenge for the field of Artificial Intelligence. MAVs in the order of tens of grams are very restricted in the energy, sensors, and processing that they can take on board. Many state-of-the-art approaches to robotics and AI are either computationally too expensive at this scale, or require too much weight / energy for the required sensors. I will present the ideas and methods that allowed us to create the fully autonomous 20-gram DelFly Explorer, which features a 1-gram autopilot and a 4-gram onboard stereo vision system. The DelFly Explorer can fly completely by itself in unknown environments, taking off, keeping altitude, and avoiding obstacles with the help of vision algorithms. In the presentation I will highlight how one can achieve computational efficiency without sacrificing too much on accuracy, how to deal with little texture in the environment, and what are the current limitations and challenges ahead.

Bio: Guido de Croon is assistant professor in the Micro Air Vehicle lab of Delft University of Technology, the Netherlands. His main research focus is on the autonomy of small robotic systems. He has a background in computer vision, evolutionary robotics, and Artificial Intelligence. Since 2008, he has performed research on the autonomous flight of various Micro Air Vehicles, and has joined with the MAV-lab team in many international competitions, such as various IMAVs.

Title: Communication and Cooperation in Multi-UAV Networks

Abstract: With the recent technological advances in small-scale aerial vehicles, deployment of three-dimensional vehicular and sensor
networks for civil applications becomes increasingly probable. Especially, networks of aerial and ground robots equipped with various sensors are expected to be deployed for monitoring, surveillance, disaster management, etc. In our work, we develop a high level architecture for the design of collaborative multiple aerial robot systems that consist of vehicles with on-board sensors and embedded processing, and sensing, coordination, and communication&networking capabilities. The talk will illustrate the challenges in the design of multi-UAV systems and present potential solutions based on the lessons we have learned so far. The multi-UAV system will be treated as a network of nodes that cooperate toward a common goal such as area coverage or search and rescue, where the team behavior is enabled via communication between the UAVs. Especially, focus will be on the planning in multi-UAV systems and evaluation of networking behavior via real-world experiments.

Bio: Evsen Yanmaz received the B.S. degree in electrical and electronics engineering from Bogazici University in 2000; the M.S. degree in electrical engineering from SUNY at Buffalo in 2002; and the Ph. D. degree in electrical and computer engineering at Carnegie Mellon University in 2005. Her doctoral thesis was on dynamic load balancing in wireless networks. From 2006 to 2008, she held a Postdoctoral Fellowship in CCS Division at the LANL. Since October 2008, she has been with the Mobile Systems Group at the University of Klagenfurt and the research cluster Lakeside Labs as senior researcher. Her research interests include dynamic load balancing, resource allocation, and cooperation in wireless networks, self-organization, design of unmanned vehicle networks.

Title: Outdoor flocking and formation flight with autonomous quadrotors

Abstract: The EU ERC COLLMOT project is about the collective motion of animals and robots. We develop statistical-physical models describing the synchronized group motion of animals and build autonomous flying robots that use the control principles of these models. In this talk I present a decentralized multi-copter flock that performs stable
autonomous outdoor flight even in a noisy, windy, delayed and error-prone environment. Using this framework we successfully
implemented several fundamental collective flight tasks with up to 10 units: i) we achieved self-propelled flocking in a bounded area with self-organized object avoidance capabilities and ii) performed collective target tracking with stable formation flights (grid, rotating ring, straight line). With realistic numerical simulations we demonstrated that the local broadcast-type communication and the decentralized autonomous control method allows for the scalability of the model for much larger flocks.

Bio: GV was born in Budapest, Hungary, in 1979. He received his MSc in engineering-physics from the Technical University of Budapest, Hungary, in 2003, and his PhD in technical sciences (info-bionics) from Péter Pázmány Catholic University, Faculty of Information Technology, Hungary, in 2007. In 2007 he received Junior Prima Award in the category of informatics, science. In 2013 he received Zoltán Magyary post-doc Scholarship.
He is currently a post-doc research fellow at Eötvös University, Department of Biological Physics and at MTA-ELTE Statistical and Biological Physics Research Group, Budapest, Hungary. His main research fields are connected the collective motion and collective behavior of animals and robots and the development of ultra-small GPS/INS systems and autonomous drone flocks.

Title: The Flying Machine Arena

Abstract: The Flying Machine Arena is a portable space devoted to autonomous flight. Measuring up to 10 x 10 x 10 meters, it consists of a high-precision motion capture system, a wireless communication network, and custom software executing sophisticated algorithms for estimation and control.

Bio: Mark received his bachelors degree in mechanical engineering from the University of Pretoria in 2008, and received awards for best final year project and best aeronautical project for his final year project “UAV Autopilot Implementation: Longitudinal control”. Subsequently, with a scholarship from the Swiss government, he received a masters degree in mechanical engineering from the ETH Zurich in 2011, being awarded the Jakob Ackeret prize of the Swiss Aeronautical Association for his thesis “Quadrocopter ball juggling”. Since September 2011 he has been pursuing a doctorate at the ETH Zurich under Professor Raffaello D’Andrea.

Title: Fotokite

Abstract: The Fotokite is a flying camera, based on a quad-copter that is tethered to the operator. The introduction of a tether to a UAV provides some unique features that make aerial photography and filming accessible to everyone. More Information can be found at www.fotokite.com.

Bio: Sergei Lupashin created the Fotokite, an easy to use, accessible tethered flying camera. Recently presented at TED2014, the Fotokite enables observation and storytelling from novel aerial perspectives without the complexities of traditional UAVs. His previous work includes autonomous cars, next-generation UAVs and robotics for hazardous environments. Sergei received a PhD in Mechanical Engineering from ETH Zurich and is a TED Fellow.

Title: Supporting degraded mode of operation in swarms/fleets of unmanned (aerial) vehicles: theoretical issues and illustrative scenarios

Abstract: The technological progress has made it possible to embed various sensing and communication capabilities inside drones and it is now possible for the aircrafts to interact with each other. When considered individually, these machines raise technical issues (trajectory control, attitude, endurance, stability, etc.) but they also raise much more difficult and still to explore issues when considered in groups (communication, identity management, service discovery, re-tasking, etc.). Such groups are referred to as fleets or swarms, swarms usually involving more collaboration and closer flight.

It should also be noted that heterogeneous swarms involving different sorts of unmanned vehicles (air, ground, surface, underwater, etc.) make sense in terms of the services they can offer. There is no doubt that these will develop in the (near) future because: a (heterogeneous) swarm of unmanned vehicles is much more powerful than a single unmanned system (air –ground-sea cooperation, multi-sensors support, continuous flight, etc.); a swarm can help in many so called DDD (Dull, Dirty, Dangerous) domains, e.g. rescue or emergency disaster relief, where a single UAV cannot support all the mission.

Still, the network is the keystone of such systems, but because of mobility and external constraints, degraded mode of operation should be considered as the standard use case: there can be no assumption on the availability of communication links or computing nodes that constitute the network. In this talk, we will give an overview of the theoretical and practical issues to address so as to support this kind of configuration and illustrate them by means of real world scenarios that we are currently implementing.

Bio: Dr. Serge Chaumette is Professor in Computer Science at the University of Bordeaux, France, leader of the Muse (Mobility, Ubiquity, Security) research group at LaBRI (Bordeaux Computer Science Research Laboratory, UMR CNRS 5800). He owns a PhD in Computer Science and an Engineering Degree in Networks and Systems. He is in charge of the UAVs activities at LaBRI and a member of the steering committee of the UAV Cluster of Région Aquitaine. He is in charge of several research projects funded/run with private companies such as Thales, Gemalto, NXP, etc. and government bodies such as the DGA (French Army), or ORNL and ARL (US Army). His domain of research is on secured fleets/swarms of communicating mobile terminals (phones, robots UAVs, etc.), where degraded mode of operation is considered as the standard use case, i.e. where there can be no assumption on the availability of communication links or computing nodes that constitute the network. He works on theoretical aspects and also designs and runs real world applications.

Title: Autonomous navigation for flying robots: learning to follow trails

Abstract: Reliable autonomous navigation is still a challenge for flying robots, especially when it comes to fly in cluttered environments such as densely treed areas (e.g., a wood or a forest). However, such a capability could be effectively exploited in a number of practical applications, including search and rescue in the wilderness, automatic terrain/path mapping, environmental inspection and surveillance, transport of goods to remote locations. At this aim, instead of trying to equip the flying robot with special sensing capabilities and/or sophisticated navigation algorithms, we let the robot moving over existing trails, that, by construction, are expected to be obstacle free paths. Therefore, we focus on the problem of perceiving forest or mountain trails from a single monocular image acquired from the viewpoint of a robot traveling on the trail itself, and let the robot to be able to recognize and follow the trail. Differently from existing literature, that mainly relies on trail segmentation and the use of low-level features such as image saliency or appearance contrast,  we make use of machine learning and automatic feature extraction. More specifically, we gathered a large dataset of forest trails and used it to train a Deep Neural Network to act as a supervised trail classifier for a robot navigation system. By operating on the whole image at once, the system computes the main direction of the trail compared to the viewing direction. Qualitative and quantitative results show that our approach outperforms alternative ones, and yields an accuracy comparable to the accuracy of humans which are tested on the same task. As it will be shown through a number of videos, the system has been validated in simulation, emulation, and real-robots. The application to similar problems of practical interest and the potential benefits of using a fleet of trail-following flying robots will be also discussed.

Bio: Gianni A. Di Caro is senior researcher at the Dalle Molle Institute for Artificial Intelligence (IDSIA), in Lugano, Switzerland.  He has a degree in Physics, obtained from the University of Bologna in 1992, and a PhD in Applied Science, obtained from the Universite’ Libre de Bruxelles (ULB) in 2004. He has been awarded several individual grants, including 4 Marie Curie / TMR fellowships, and has published more than 120 peer-reviewed works focusing on adaptive routing in dynamic networks, combinatorial and network optimization, bio-inspired algorithms, parallel computing, and, more recently on distributed algorithms for coordination, navigation, sensing, and planning in swarm and multi-robot systems. According to Google Scholar, the papers he has co-authored have more than 10,250 citations in total. He is the coordinator of the FP7 project, ALMA, funded under the Ambient Assisted Living (AAL) framework, addressing the interplay of ambient intelligence and mobile robotics to support the mobility and autonomy of elder and disable people. He has been chair of EvoCOMNET (from 2007 to 2011), ANTS (2002, 2010), and BIONETICS (2012).