Invited Speakers / Plenary Talks
Title: Soft Aerial Robotics for Digital Infrastructure Systems
Dr. Mirko Kovac
Dr. Mirko Kovac is Director of the Aerial Robotics Laboratory, Reader in Aero-structures at Imperial College London and Royal Society Wolfson Fellow. He is also heading the newly established Materials and Technology Centre of Robotics at the Swiss Federal Laboratories for Materials Science and Technology in Zürich. His research group focusses on the development of novel, biologically inspired flying robots for distributed sensing in air and water and on autonomous robotic construction for future infrastructure systems. Dr. Kovac's particular specialisation is in robot design, soft robotics, hardware development and multi-modal robot mobility.
Before his appointment in London, he was post-doctoral researcher at Harvard University and he obtained his PhD at the Swiss Federal Institute of Technology in Lausanne (EPFL). He received his undergraduate degree in Mechanical Engineering from the Swiss Federal Institute of Technology in Zurich (ETHZ) in 2005. During his studies he was research associate with the University of California in Berkeley USA, RIETER Automotive Switzerland, the WARTSILA Diesel Technology Division in Switzerland, and CISERV in Singapore.
Since 2006, he has presented his work in >70 international proceedings and journals, has won several best paper awards and has delivered >30 keynote lectures. He also regularly acts as advisor to government, investment funds and industry on robotics opportunities.
Future infrastructure systems will evolve into complex ecosystems where autonomous aerial, aquatic and ground-based robots will coexist with people and cooperate in symbiosis. To create this human-robot ecosystem, robots will need to respond more flexibly, robustly and efficiently than they do today. They will need to be designed with the ability to move safely close to humans and in contact with infrastructure elements to perform sensing and intervention tasks. Their behaviours will need to be carefully orchestrated to integrate smoothly into the environment and in industry 4.0 workflows. Taking inspiration from natural systems, aerial robotic systems can integrate multi-functional morphology, new materials, energy-efficient locomotion principles and advanced perception abilities that will allow them to successfully operate and cooperate in these complex and dynamic environments. This talk will describe design principles and technologies for the development of biologically inspired flying robots with adaptive morphology that can perform monitoring and manufacturing tasks for infrastructure and building systems. Examples will include flying robots with perching and aerial sensor-placement abilities, aerial-aquatic drones, drones with compliant landing systems for landing on autonomous cars, drones for aerial construction and repair, and origami-based drones for safe interactions with infrastructure elements.
Title: Robot swarms and the Human-in-the-Loop
Dr. Gianni A. Di Caro
Since 2016, Gianni A. Di Caro is an Associate Teaching Professor at the Department of Computer Science of the Carnegie Mellon University. He is teaching in CMU's Qatar campus, in Doha. He has a degree in Physics, magna cum laude, from the University of Bologna, Italy (1992), and a PhD in Applied Sciences, with full honors, from the Universite' Libre de Bruxelles (ULB), in Belgium (2004). Before joining CMU he was Senior researcher at the Dalle Molle Institute for Artificial Intelligence (IDSIA), in Lugano Switzerland (2003-2016), post-doctoral Marie Curie fellow at IRIDIA/ULB in Belgium (1996-1999, 2001-2003), and EC Science and Technology in Japan fellow at the Advanced Telecommunications Research (ATR), in Japan (1999-2001). He has been the recipient of several project grants from Swiss, European, and Qatari scientific research agencies. He has co-authored more than 150 peer reviewed publications in the fields of swarm intelligence, autonomous robotics, multi-robot systems, combinatorial optimization, networking, artificial intelligence, machine learning.
The design of a robot swarm revolves around the concepts of fully distributed control, local interactions, self-organization, redundancy, and parallelism. In turn, the swarm is expected to display autonomy, adaptivity, fault-tolerance, and scalability, among others. All these properties are in principle quite appealing. Unfortunately, there's a price to pay for such a flexibility, which is usually in terms of accuracy, efficiency, and predictability performing a given task. As a result, in many scenarios of interest, swarm autonomy should be backed up by humans to perform with desired efficacy, efficiency, and guarantees. For instance, a human can exploit his/her cognitive and sensory-motor capabilities to support a safe and fast swarm navigation in harsh, unknown, or complex environments. On the other way round, a human can take profit from the presence of a robot swarm, that can provide a number of perceptual and actuation services during a mission, once properly instructed and guided for the purpose. .
Therefore, the human-in-the-loop of operations of robot swarms should be seen both as a necessity and an opportunity. The recent, and still developing, field of human-swarm interaction (HSI) addresses the challenges related to the inclusion of human agents in a swarm system, accounting for the various aspects of bidirectional communication, control, and cooperation. HSI builds on HRI, but brings a number of novel, hard challenges.
The talk will provide a general overview of the HSI field. The core challenges and the main solutions devised so far will be presented and discussed towards the actual deployment of mixed human-swarm teams in the real-world. In particular, the following aspects of HSI will be addressed: (i) modalities for communication and interaction with the swarm or with subsets of robots (e.g., gestures, speech, radio links, beacons, joypad, haptic interfaces, virtual reality) ; (ii) data structures and visualization interfaces for the representation of information about status and dynamics of the swarm; (iii) roles that the human-in-the-loop can play to affect or control swarm operations and decision-making (e.g., peer, supervisor, influencer, leader); (iv) mapping between human inputs and self-organized swarm responses; (v) scenarios suitable for mixed human-swarm teams.
Title: Human-aware decision making and navigation for service robots
Dr. Luis Merino
Luis Merino is Associate Professor of Systems Engineering and Automation and Co-Principal Investigator of the Service Robotics Laboratory at the Universidad Pablo de Olavide (UPO) in Seville, Spain. His research interests include autonomous navigation, collaborative and social robotics, robot perception, and planning under uncertainty. He has published more than 80 papers in international proceedings and journals on those topics. He also leads UPO’s team in several national and European projects funded by the EU Commission and maintains international collaborations with centres like the German Aerospace Centre (DLR) and Honda Research Institute Japan along these lines.
He holds a Ph.D. degree from the University of Seville. His thesis was awarded with the ABB Award to the Best Doctoral Dissertation on Robotics 2007 in Spain, given by the Spanish Committee of Automation (CEA, Robotics Group). He moved to UPO, where he contributed to the creation of the Systems Engineering and Automation Division and has been Vice-Dean of the School of Engineering at UPO for 5 years.
He is Associate Editor of the Image and Vision Computing Journal, as well as the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) and the IEEE International Conference on Robotics and Automation (ICRA). He is member of the Robotics and Automation Society (RAS) of IEEE, the Spanish Society on Research and Development in Robotics (SEIDROB) and the Spanish Committee on Automation (CEA-IFAC).
Service robots acting among humans require human-awareness when performing their tasks. That is, people should be considered differently from static and dynamic obstacles present in the scene for the robot to act in a pertinent way. And they have to be considered by all the robot decisional components, from high-level planning and supervision to motion planning and execution. In the talk, different techniques developed by our group for human-aware decision making and social navigation will be presented. These include techniques for human-aware motion planning, learning methods to obtain people navigation intention models and social cost functions from observations/demonstrations, and task planning considering human intentions and uncertainties. The talk will discuss the results of using these different techniques in service robots in different applications.
Title: Optimization and Learning in Robotics
Nuno Lau: University of Aveiro, Portugal
Nuno Lau is Assistant Professor at Aveiro University, Portugal. He got is Electrical Engineering Degree from Oporto University in 1993, a DEA degree in Biomedical Engineering from Claude Bernard University, Lyon, France, in 1994 and the PhD from Aveiro University in 2003. His research interests include Intelligent Robotics, Artificial Intelligence, Multi-Agent Systems and Simulation. Nuno Lau has participated, often with the coordination role, in several research projects that have been awarded international prizes.
Nuno Lau is the author of more than 150 publications in international conferences and journals, including several Best Paper awards. He Supervised 8 PhD students that concluded their degree, and is currently supervising 6 PhD students. Nuno Lau was President and Vice-President of the Portuguese Robotics Society. He is the Vice-Coordinator of the Institute of Electronics and Informatics Engineering of Aveiro, and Principal Investigator of the Intelligent Robotics and Systems group at the same research unit.
Optimization and Machine Learning techniques are now widely used in many scientific disciplines. Using Optimization and Machine Learning in Robotics is a very challenging task as robots may be expensive and fragile, and the time and effort to collect data is, in general, quite high. Considering these premises, we have developed several techniques that through the use of simulators, and adapted learning/optimization algorithms, that use the data very efficiently, make the use of Optimization and Learning in Robotics an effective option for hand-coded approaches that may achieve impressive results. These techniques have been applied to solve perception, reasoning and behavior level robotic tasks.
This talk will present some of these techniques, in different contexts, namely those related to optimization/ML based development of robotic skills, data preparation, Q-Batch update rule, multi-agent learning, adapted interfaces and mixed deep learning/heuristic classification.
Title: Perspectives on Minimalistic Robot Hand Design and a New Class of Cagnig-to-Grasping Algorithms
Elon Rimon: Israel Institute of Technology, Israel
Elon Rimon is a professor in the Department of Mechanical Engineering at the Technion – Israel Institute of Technology. He has also been a visiting associate faculty member at the California Institute of Technology. Professor Rimon was a finalist for the best paper awards at the IEEE International Conference on Robotics and Automation and the Workshop on Algorithmic Foundations of Robotics, and he was awarded best paper presentation at the Robotics Science and Systems Conference. Professor Rimon is the lead author of the new Mechanics of Robot Grasping text, published by Cambridge University Press.
Ten years of research on minimalistic robot hands resulted in novel robot hand designs and culminated with a new book, The Mechanics of Robotic Grasping by Rimon and Burdick. The perspectives gained from this intensive activity will be shared with the ROBOT'2019 participants, in a talk that consists of two related parts. Part I describes the configuration space analysis of multi-finger grasps. In so doing, we obtain the minimalistic 2-D and 3-D robot hand designs in terms of number of fingers. Surprise: the minimalistic 3-D design is the classical 3-finger Salisbary hand, with added security of using the hand's palm when object immobilization is necessary. Part II considers the notion of caging, which offers a robust object grasping methodology under huge uncertainty in the finger positions. A novel contact space approach resulted in a series of highly efficient and intuitive caging-to-grasping algorithms, specifically suited for minimalistic robot hands. Two such algorithms will be described for 3-finger robot hands grasping 2-D objects. The first algorithm computes caging grasps for formationally similar 3-finger hands. The second algorithm computes caging grasps of 2-D objects against a wall using two-finger hands, with the same computational complexity as the 3-finger algorithm. Perspectives on grasping 3-D objects against the environment will also be discussed.