About

The 2019 IEEE RAS Summer School on Multi-Robot Systems follows the great success of the last 2016 IEEE RAS Summer School on Multi-Robot Systems (https://www.comp.nus.edu.sg/~lowkh/mrsss.html#go ). This time the IEEE Summer School on Multi-Robot Systems will be held at the campus of Czech Technical University located at the heart of historical city Prague. The Summer School aims to promote the newest achievements in the multi-robot systems research to students, academic researchers, and industrial practitioners to enable putting systems of cooperating robots into practise. The content of the Summer School will be focused but not limited to systems of cooperating aerial vehicles as this domain is growing recently and promises a high potential for improving quality of our life in near future. The topics addressed by well recognised experts in the field of Multi-Robot Systems are composed to provide the participants necessary knowledge for understanding the available theory and for realisation real-world experiments with a fleet of autonomous micro aerial vehicles in the last day of the Summer School. The event is jointly organised by the Czech Technical University (CTU) in Prague , which is one of the biggest and oldest technical universities in Europe and the top-ranked technical university in the Czech Republic, and the IEEE RAS Technical Committee on Multi-Robot Systems.

Our lecturers

Learning to coordinate

Multi-robot teams present opportunities for achieving complex tasks that are challenging or even infeasible for single robots to achieve. However, the trade off is that specifying individual control policies for each robot becomes increasingly difficult as the task complexity rises and tightness of the coordination increases. One solution is to pursue a multiagent learning approach in which individual robots adapt their control policies via concurrent learning. Of course, these learning methods also experience their share of challenges and in this lecture we will discuss those that are unique to multiagent learning; namely, the structural credit assignment problem and agent noise. Bio:
Jen Jen Chung is a Senior Researcher in the Autonomous Systems Lab at ETH Zürich. Her current research interests include learning for multi-robot coordination and risk-aware planning for applications such as robot navigation through human crowds. This builds on her past work at Oregon State University and the Australian Centre for Field Robotics, which focused on the development of information-based exploration strategies to characterise the exploration-exploitation trade-off within resource-constrained learning missions. She received her Ph.D. (2014) and B.E. (2010) from the University of Sydney. website: http://jenjenchung.github.io/anthropomorphic/

Politecnico di Milano
Francesco Amigoni PDF of the lecture Record of the lecture

Coordinated Path Planning for Information Gathering Multirobot Systems

In the last decades, scientific and technological advances in autonomous mobile robotics have shown that teams of cooperative robots can provide a valid alternative to the employment of humans in carrying out repetitive, difficult, and hazardous tasks. This is especially true for information gathering tasks, including exploration, search and rescue, monitoring, inspection, and patrolling. This lecture will discuss algorithmic aspects involved in planning coordinated paths for multiple robots performing information gathering tasks. The presentation will start from the simplest scenarios in which the environment is fully known and the robots can always communicate with each other, will move towards more challenging settings in which the environment is initially unknown and the communication is restricted, and will finally discuss situations in which some adversaries try to oppose the tasks of the team of robots. Bio:
Francesco Amigoni got the MSc degree in Computer Engineering from the Politecnico di Milano in 1996 and the PhD degree in Computer Engineering and Automatica from the Politecnico di Milano in 2000. From December 1999 to September 2000 he has been a visiting scholar at the Computer Science Department of the Stanford University (USA). From February 2002 to April 2007 he has been an assistant professor and from May 2007 he is an associate professor at the Dipartimento di Elettronica, Informazione e Bioingegneria of the Politecnico di Milano. His main research interests include: agents and multiagent systems, autonomous mobile robotics, and the philosophical aspects of artificial intelligence and robotics.

Czech Technical University
Jan Faigl PDF of the lecture Record of the lecture

Curvature-Constrained Multi-Goal Trajectory Planning with Team of Unmanned Aerial Vehicles (link to pdf)

Unmanned aerial vehicles (UAVs) can be utilized not only for flights to a single destination, but they can be utilized to efficiently visit a set of locations to perform the requested operation. Examples of such deployments are surveillance missions where the vehicles can monitor areas of interests, but also in other data collection missions. Finding the best way how to visit a set of locations is a hard combinatorial problem which becomes even more challenging when the trajectories have to respect the motion constraints of aerial vehicles. In the talk, I will present recent advancements in multi-goal trajectory planning for curvature-constrained vehicles. The talk will be focused on fundamental approaches for mission planning considered as variants of the traveling salesperson problem and recently established orienteering problems with the Dubins vehicle model of the aerial vehicles. It will be shown how the existing approaches can be generalized to 3D planning but most importantly how the solution quality can be determined and utilized in finding solutions very close to optimal solutions. Moreover, recent results on diminishing the gap to the optimal solution in the generalized problem with non-zero sensing range will be presented. In addition to the traditional approaches based on the Dubins vehicle model, I will show planning techniques suitable for multi-rotor UAVs which are not limited by the minimum required forward velocity and minimum turning radius as the Dubins vehicle, but rather by the maximal speed and acceleration. Bio:
Jan Faigl is an associate professor of computer science at the Department of Computer Science, Faculty of Electrical Engineering (FEE), Czech Technical University in Prague (CTU), Czechia. He received the Ph.D. degree in artificial intelligence and biocybernetics and the Ing. degree in cybernetics from CTU in 2010 and 2003, respectively. In 2013 and 2014, he was a Fulbright Visiting Scholar with the University of Southern California, Los Angeles, CA, USA. In 2011, he was visiting scholar at the University of Pennsylvania, Philadelphia, PA, USA. Since 2013, he is leading the Computational Robotics Laboratory (http://comrob.fel.cvut.cz) within the Artificial Intelligence Center (http://aic.fel.cvut.cz). He is also co-founder of the Center for Robotics and Autonomous Systems (http://robotics.fel.cvut.cz) with more than 40 researchers cooperating in robotics. Since 2018, he is acting as the board member of the Research Center for Informatics. Dr. Faigl had been awarded the Antonin Svoboda Award from the Czech Society for Cybernetics and Informatics in 2011. He received best poster awards at IJCNN 2017, WSOM'16, and WSOM'14 and be the finalist of the paper awards at RSS'18 and IROS'16. In 2017, he was a member of the winning team of Challenge No. 3 in the Mohamed Bin Zayed International Robotics Challenge (MBZIRC), Abu Dhabi, UAE (http://mrs.felk.cvut.cz/projects/mbzirc). He is acting as a program committee member for IJCNN, AAMAS, AAAI, MESAS, IJCAI, SMC, RSS events and he serves as reviewer for Adaptive Behavior, Applied Mathematics and Computation, Applied Soft Computing, Artificial Intelligence Review, Autonomous Robots, Computer Communications, IEEE Intelligent Systems, IEEE Transactions on Cybernetics, IEEE Transactions on Neural Networks and Learning Systems, IEEE Transactions on Robotics, International Journal of Robotics Research, Journal of Field Robotics, Journal of Intelligent and Robotic Systems, Neurocomputing, Robotics and Autonomous Systems. He has been a guest editor of Autonomous Robots for the special issue on Online Decision Making in Multi-Robot Coordination, and he organized workshops on the same topic with the conjunction of RSS 2016, Ann, Arbor, MI, USA, and IEEE/RSJ IROS 2015, Hamburg, Germany. He is an associate editor of IEEE Transactions on Automation Science and Engineering. Since 2014, he is organizing student conference on Planning in Artificial intelligence and Robotics (PAIR) - http://robotics.fel.cvut.cz/pair. His current research interests include unsupervised learning, self-organizing systems, autonomous navigation, aerial systems, path and motion planning techniques, robotic learning and locomotion control of multi-legged walking robots.

University of Cambridge
Amanda Prorok PDF of the lecture Record of the lecture

Control and coordination (link to pdf)

My lectures will start by motivating the general field of multi-robot systems; I will elaborate on centralized vs decentralized architectures, and will show examples of MRS in real-world applications. I will then follow up with three core topics: (1) collective movement, in which I will cover basic concepts of formations and flocking, (2) task assignment, in which I will cover discrete and continuous approaches, and (3) navigation and planning, in which I will cover some core principles and a few key algorithms.
Bio:
Amanda Prorok is an Assistant Professor at the Department of Computer Science and Technology, University of Cambridge, UK. Previously, she was a Postdoctoral Researcher in the General Robotics, Automation, Sensing and Perception (GRASP) Laboratory at the University of Pennsylvania, USA, where she worked on networked robotic systems. She completed her PhD at EPFL, Switzerland, where she addressed the topic of localization with ultra-wideband sensing for robotic networks. Her dissertation was awarded the Asea Brown Boveri (ABB) award for the best thesis at EPFL in the fields of Computer Sciences, Automatics and Telecommunications. Further awards include Best Paper Award at DARS 2018, Finalist for Best Multi-Robot Systems Paper at ICRA 2017, Best Paper at BICT 2015, and MIT Rising Stars 2015.

Centro Universitario de la Defensa de Zaragoza
Alejandro Mosteo PDF of the lecture Record of the lecture

Multi-hop communications in large and challenging scenarios.

Multi-robot teams often require explicit communications, commonly carried out using wireless protocols. Deployments in scenarios without infrastructure furthermore require specific strategies for communications among robots and with remote operators by means of mobile ad hoc networks. Among the many challenges that appear in this context, this lecture will address the problem of maintaining a connected communications graph, with particular discussion of the special signal propagation characteristics in typical underground environments like tunnels and sewer galleries. Bio:
Alejandro R. Mosteo has been a professor at Centro Universitario de la Defensa, Zaragoza, Spain, since 2011. He received the Ph.D. in 2010 from the Universidad de Zaragoza, Spain. He has been a postgraduate researcher at Laboratoire d’Analyse et d’Architecture des Systèmes (LAAS), Toulouse, France. He is a member of the Robotics, Perception, and Real-Time group at Universidad de Zaragoza. He is affiliated to the Ada-Spain and Ada-Europe societies for the promotion of the Ada language. His research interests include multi-robot cooperation, decentralized algorithms, autonomous vehicles, and high-integrity software.

Eötvös Loránd University
Gábor Vásárhelyi PDF of the lecture Record of the lecture

Bio-inspired collective behavior of autonomous outdoor drone swarms(link to pdf)

While individual drones have gone through a tremendous development in the last years towards autonomy and intelligent behavior, functional drone swarms are still very limited in number, due to the new levels of complexity a multi-agent system brings into the picture. The straightforward approach to multi-drone systems builds on the mindset of high individual intelligence and tries to increase the number of drones gradually. Contrarily, we investigate large natural multi-agent systems and create statistical physical models optimized for the minimally required intelligence to perform a given task collectively. With this methodology, the typical bottlenecks of multi-agent systems are in the focus and thus there are less unexpected dynamical issues emerging when system size is increased. With our self-organized, distributed approach, we were able to recreate most of the basic building blocks of collective behavior both in simulation and on actual outdoor swarms of dozens of quadcopters: synchronized collective motion in free or confined spaces, collective object avoidance, self-organized formation flights, collective search, chase and escape scenarios and coordinated autonomous drone traffic. In this talk I will give an introduction to our modeling concept and show our various results and applications performed by our autonomous drone fleet. Bio:
Gábor Vásárhelyi 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, Hungary, in 2007. Since 2009 he is with Eötvös University, Department of Biological Physics as leader of the Robotic Lab at Tamas Vicsek’s Research Group on collective motion. He is currently a senior research fellow at MTA-ELTE Statistical and Biological Physics Research Group and CEO of CollMot Robotics Ltd., a spin-off dedicated to multi-drone services. His research fields are connected to the collective motion and collective behavior of animals and robots (drones). Awards: Junior Prima Award, category of informatics (2007), Magyary Postdoctoral Grant (2013), Bolyai János Research Scholarship (2015). Further information: www.hal.elte.hu/~vasarhelyi

Multi-Robot Control for Cooperative Transportation and Manipulation

Part 1: Modeling
— kinematic models
— dynamic models
— actuation, sensing, and communication models

Part 2: Control methods
— kinematic control
— force and interaction control
— hybrid control
— distributed control

Part 3: Identification and Estimation Methods
— identification of the load parameters
— estimation of the load state

Part 4: Real use cases
— ground mobile manipulators
— cooperative aerial transportation and manipulation with cables
— MAGMaS: multiple aerial-ground manipulator systems
Bio:
Antonio Franchi is a Tenured Researcher of CNRS, the French National Centre for Scientific Research, one of the world's leading research institutions (http://www.cnrs.fr/en/cnrs). He is based at LAAS-CNRS (RIS team) in Toulouse, France, since 2014. From 2010 to 2013 he was a Research Scientist and then a Senior Research Scientist at the Max Planck Institute for Biological Cybernetics in Germany, and the scientific leader of the group ‘Autonomous Robotics and Human-Machine Systems’. He received the HDR (French Professorial Habilitation) from the National Polytechnic Institute of Toulouse, the Ph.D. degree in Control and System Theory and master degree in Electronic Engineering from the Sapienza University of Rome, Italy. He was a visiting scholar at the University of California at Santa Barbara. His main research interests in robotics are motion control, estimation, hardware design, and human-machine systems. His main areas of expertise are aerial robotics and multi-robot systems. He published about 130 articles in international journals, conferences, and books, and in 2010 he was awarded with the ‘IEEE RAS ICYA Best Paper Award’ for one of his works on Multi-robot Exploration. He is a IEEE Senior Member and Associate Editor of the IEEE Transactions on Robotics. He has been Associate Editor of the IEEE Robotics & Automation Magazine (2013 to 2016), IEEE ICRA (2014 to 2019), IEEE/RSJ IROS (2014 to 2019) and the IEEE Aerospace and Electronic Systems Magazine (2015). He is currently coordinator of the ANR MuRoPhen project (2018-2021), the CNRS PI of the AEROARMS EU H2020 project (2015-2019), coordinator of the MBZIRC 2020 LAAS team project (2018-2020), and co-coordinator of the FlyCrane Occitanie Pre-Maturation project (2019-2020). He has also a prominent role in the ANR Flying Co-Worker project (2019-2022) and the PRO-ACT EU H2020 project (2019-2021). In the past, he also participated to the ARCAS EU FP7 (2014-2010) project. He is a co-chair of the IEEE RAS Technical Committee on Multi-Robot systems (400+ members), which he co-founded in 2014, and was the recipient of the IEEE RAS most active TC Award 2018. He co-funded and was the program co-chair of the IEEE-sponsored biannual International Symposium on Multi-robot and Multi-agent Systems (MRS 2017 in Los Angeles, MRS 2019 in New Brunswick).

Carnegie Mellon University
Gianni Di Caro PDF of the lecture Record of the lecture

Human-swarm interaction and cooperation

A robot swarm features a relatively large number of locally interacting robots giving raise to a fully distributed and decentralized system. By design, a robot swarm is expected to display autonomy and self-organization, that in turn should result in robustness and adaptivity. All these properties make robot swarms quite appealing. On the downside, individual robots may be not extremely sophisticated, and the swarm itself may be not extremely accurate and efficient performing its tasks. Therefore, in spite of the claimed autonomy, the presence of humans in the loop of swarm operations can be beneficial, if not necessary. For instance, a human can exploit her/his cognitive and sensory-motor capabilities to support and guide the swarm in harsh, unknown, or complex environments. The lecture will consider the integration of the human in the loop and will focus on human-swarm interaction, providing an overview of the core challenges in this relatively novel field of research. The main results and solutions existing in the literature will be reviewed along application scenarios of interest. In particular, the following aspects will be addressed:
(i) modalities (e.g., gestures, speech, radio links, beacons, haptic interfaces) for communication and interaction with subsets of robots;
(ii) representation and gathering of information about status and dynamics of the swarm;
(iii) roles that the human can play in the loop of swarm operations and decision-making (e.g., peer, supervisor, influencer, leader), and ways to operate the control in practice;
(iv) mission examples with mixed human-swarm teams, involving the issue of sharing navigation and action spaces.
Bio:
Since 2016, Gianni A. Di Caro is 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.

Multi Robot Systems CTU
Martin Saska PDF of the lecture Record of the lecture

Research of groups of aerial robots at CTU in Prague

Deployment of large teams of Micro Aerial Vehicles (MAVs) in real-world (outdoor and indoor) environments without precise external localisation or motion capture systems is very challenging. I will present the latest results of our endeavor towards fully autonomous compact flocks of MAVs with onboard artificial intelligence, which was achieved by the Multi-robot Systems group at the Czech Technical University in Prague together with Vijay Kumar Lab at the University of Pennsylvania. Stabilization, control, and motion planning techniques for steering swarms and formations of unmanned MAVs will be discussed in the talk. We shall focus on biologically inspired techniques that integrate swarming abilities of individual particles with a Model Predictive Control (MPC) methodology respecting the fast dynamics of unmanned quadrotors. Besides the basic principles of formation flying and swarm stabilization, examples of real-world applications of the introduced methods will be shown in complex indoor and outdoor experiments. First, we show how we use MAVs for indoor documentation of large historical objects (cathedrals) by formations of cooperating MAVs, where one MAV carries a camera and its neighbors carry light sources with the possibility to set a relative angle between the camera axis and the lights as required. Second, we demonstrate cooperative manipulation of large objects by a pair of MAVs developed for the international MBZIRC competition. Last, we present the fully autonomous flying robot Eagle.one hunting for unauthorized drones.

Multi Robot Systems CTU
Tomáš Báča PDF of the lecture Record of the lecture

Introduction to the Unmanned Aerial Platform in the MRS Lab

Tomáš Báča is one of the core members of the MRS group. His lecture will cover the structure of the MRS UAV platform and the seminar task for the summer school. Tomáš works on sensor-driven planning with drones using MPC control. He is persuading his Ph.D. in radiation localization using a swarm of UAVs.

University of Lübeck
Heiko Hamann PDF of the lecture Record of the lecture

Swarm Robotics and Collective Decision-Making

Swarm robotics is the application of swarm intelligence to robotics. We study methods to design large-scale robot systems for scenarios, such as collective motion and collective construction. By collective decision-making we implement autonomy on the swarm-level. Challenges are to balance speed and accuracy of the decision-making process and to ensure robustness.
Bio:
Heiko Hamann received his doctorate in engineering from the University of Karlsruhe, Germany in 2008. He did his postdoctoral training in swarm robotics, modular robotics, and evolutionary robotics at the Zoology department of the University of Graz, Austria. He was assistant professor of swarm robotics at the University of Paderborn, Germany from 2013 until 2017. Since 2017 he is professor for service robotics at the University of Lübeck, Germany. His main research interests are swarm intelligence, swarm robotics, bio-hybrid systems, evolutionary robotics, applications of evolutionary computation in software engineering, and modeling of complex systems.

Program

29.7. - Monday

Keynote speakers - Amanda Prorok, Vásárhelyi Gábor
  • 8:00-8:45 -

    Registration

  • 9:00-9:30 -

    Martin Saska - welcome and organisation details

  • 9:30-10:15 -

    Amanda Prorok - Collective movement (Introduction to Multi-Robot Systems, Centralized vs decentralized architectures, formations, flocking)

  • 10:15-10:30 -

    Coffee break

  • 10:30-12:00 -

    Amanda Prorok - Task assignment and Multi-robot navigation and path planning

  • 12:00-13:00 -

    Lunch

  • 13:00-14:20 -

    Martin Saska - Research of groups of aerial robots at CTU in Prague

  • 14:30-16:00 -

    Gábor Vásárhelyi - Bio-inspired collective behavior of autonomous outdoor drone swarms

  • 16:00-16:15 -

    Coffee break

  • 16:15-17:00 -

    Short presentations of students

  • 17:00-18:15 -

    Tomáš Báča - introduction into MRS system in ROS

  • 18:15-19:30 -

    Practical in groups: (A-H)

  • 19:30 - 21:00 -

    Social program: Welcome drink - in university campus

30.7. - Tuesday

Keynote speakers - Francesco Amigoni, Jan Faigl
  • 8:00-8:45-

    Registration (for later coming)

  • 9:00-10:30-

    Francesco Amigoni - Coordinated Path Planning for Information Gathering Multirobot Systems I

  • 10:30-10:45 -

    Coffee break

  • 10:45-12:15 -

    Jan Faigl - Curvature-Constrained Multi-Goal Trajectory Planning with Team of Unmanned Aerial Vehicles

  • 12:15-13:15 -

    Lunch

  • 13:15-14:15 -

    Group 1 - Francesco Amigoni - Coordinated Path Planning for Information Gathering Multirobot Systems II
    Group 2 - Practical seminar: MRS system in ROS for MTSP outdoor experiments

  • 14:15-15:15 -

    Group 1 - lab tour
    Group 2 - Practical seminar: MRS system in ROS for MTSP outdoor experiments

  • 15:15-15:30 -

    Coffee break

  • 15:30-17:00 -

    Short presentations of students

  • 17:15-18:15 -

    Group 1 - Practical seminar: MRS system in ROS for MTSP outdoor experiments
    Group 2 - Francesco Amigoni - Coordinated Path Planning for Information Gathering Multirobot Systems II

  • 18:15-19:15 -

    Group 1 - Practical seminar: MRS system in ROS for MTSP outdoor experiments
    Group 2 - lab tour

31.7. - Wednesday

Keynote speakers - Antonio Franchi, Heiko Hamann
  • 8:00-8:45 -

    Registration (for later coming)

  • 9:00-10:30 -

    Antonio Franchi- Multi-Robot Control for Cooperative Transportation and Manipulation I

  • 10:30-10:45 -

    Coffee break

  • 10:45-12:15 -

    Antonio Franchi - Multi-Robot Control for Cooperative Transportation and Manipulation II

  • 12:15-13:15 -

    Lunch

  • 13:15-14:15 -

    Heiko Hamann - Decentralised decision making and swarm robotics I

  • 14:15-15:45 -

    Short presentations of students

  • 15:45-16:00 -

    Coffee break

  • 16:00-17:00 -

    Heiko Hamann - Decentralised decision making and swarm robotics II

  • 17:00 - 18:30 -

    Short presentations of students

  • 19:30 - 22:00 -

    Banquet

1.8. - Thursday

Keynote speakers - Gianni A. Di Caro, Alejandro R. Mosteo, Jen Jen Chung
  • 8:00-8:45 -

    Registration (for later coming)

  • 9:00-10:30 -

    Gianni A. Di Caro - Human-swarm interaction and cooperation

  • 10:30-10:45 -

    Coffee break

  • 10:45-12:15 -

    Group 1: Alejandro R. Mosteo, Multi-hop communications in large and challenging scenarios.
    Group 2: Practical in PC lab (simulations in Gazebo)

  • 12:15-13:15 -

    Lunch

  • 13:15-14:50 -

    Jen Jen Chung - Learning to coordinate

  • 15:00-16:30 -

    Group 1: Practical in PC lab (simulations in Gazebo)
    Group 2: Alejandro R. Mosteo, Multi-hop communications in large and challenging scenarios

  • 16:30-16:45 -

    Coffee break

  • 16:45-17:45 -

    Briefing on the experimental part & organisation details & safety instructions

  • 18:30 - 21:30 -

    Guided tour in Prague's Old Town

2.8. - Friday

  • 9:00-13:00 -

    Outdoor experiments

  • 13:00-14:00 -

    Outdoor lunch

  • 14:00 - 18:00 -

    Outdoor experiments

  • 18:00-20:00 -

    Farewell drink

  • 20:00 -

    Party in Prague's pubs (not organised event)

Registration fees

Accommodation

Important dates

Applications are closed, check out the 2020 summer school page