University of Pennsylvania

https://www.upenn.edu/


MBZIRC

Mohamed Bin Zayed

International Robotics Challenge

We competed and won in the prestigious Mohamed Bin Zayed International Robotics Challenge (MBZIRC) held during 16-18 March 2017 at the Yas Marina Circuit in Abu Dhabi, UAE. The team led by Dr. Martin Saska of the Multi-robot Systems (MRS) group at the Faculty of Electrical Engineering, accompanied by a representative of the American University of Pennsylvania and the British University of Lincoln, won first place in the discipline of cooperative collection of objects using a group of autonomous helicopters (Challenge 3) and took silver position in the category of autonomous landing on a moving vehicle (Challenge 1). This success earned the team the possibility to participate in the Grand Challenge competition, in which they have won the bronze medal together with colleagues from the Italian University of Padua.


The Multi-robot Systems (MRS) group has participated in the Mohamed Bin Zayed International Robotics Challenge . The Robotics Challenge is organized by Khalifa University in Abu Dhabi and took place in February 2017. Team of Czech Technical University in Prague , University of Pennsylvania and University of Lincoln , where members of MRS group play key roles and which is led by Martin Saska , has been selected for gaining sponsorship from the Khalifa University out of 143 applicants from the most prestigious universities in the world.

We  competed with the worldwide best universities in the field of Micro Aerial Vehicles (MAV) in two Challenges. The aim of Challenge 1 is to autonomously localize a moving vehicle in the arena by a single MAV and then land on a landing platform carried by the vehicle. In the second challenge, where our team also competed (Challenge 3 in the challenge description movie), a group of three MAVs has to search the arena for various static and moving color objects, then pick them and move them to dedicated area.

During the competition, MRS members strongly cooperate with researches from Departments of Cybernetics and Computer Science and Engineering associated in Center for Robotics and Autonomous Systems , and mainly with researchers from University of Pennsylvania and University of Lincoln. In particular, the computer vision techniques needed for the Challenges 1 and 3 will be investigated by researchers from Center for Machine Perception of Department of Cybernetics and from University of Lincoln. The MAV stabilization, control, and the active manipulation with objects in Challenge 3 was handled within a tight cooperation of members of our group and researchers from the team of Vijay Kumar from GRASP laboratory at University of Pennsylvania. The planning and coordination of the MAV team was tackled by researches of MRS group together with Agent Technology Center of dept. of Computer Science and Engineering at CTU.

 

For more information, visit http://mrs.felk.cvut.cz/mbzirc.


Team:

CTU Martin Saska (Team Leader), Tomáš Báča, Vojtěch Spurný, Robert Pěnička, Vojtěch Vonásek, Petr Štěpán, Tomáš Svoboda, Karel Zimmerman, Jan Faigl
UPENN Vijay Kumar, Giuseppe Loianno, Justin Thomas, Dinesh Thakur
Lincoln Tomáš Krajník

COLOS - Control and Localization for Swarms of Low-cost Autonomous Robots

The aim of the proposed project is to develop a control framework that enables to settle boundness of cooperative localization of particles in robotic swarms. The motivation of such an effort is to improve standard cooperative navigation and localization approaches based on swapping obtained information between robots via communication. Utilization of these methods is limited in scenarios, where a large robotic teams needs to be utilized. Extensive deployment of robots in a small area decreases communication bandwidth or even disenable transmission of messages between the robots at all. Here, we can find an inspiration in nature: individuals in big school of fish, clusters of insect or flocks of birds cannot directly communicate with neighbors due to surrounding noise and their relative localization is realized through observation of neighbors. Our idea is to transfer similar concepts to localization in robotics, mainly in applications of autonomous low-cost helicopters (small quad-rotor helicopters equipped with simple panoramatic cameras). The challenging problem in such a task is, how to keep localization precision above a given threshold which is a key property. This requirement leads to necessity of particles movement stability analysis. Such a theoretical framework should provide control boundness that results from limits of movement given by requirements of localization (e.g. each particle should perceive a minimal amount of neighbors), environment (e.g. helicopters should keep sufficient distance from obstacles and neighbors) and application (the complete swarm should follow a mission plan).

The proposed project COLOS aims to integrate principles and theoretical background of helicopters control and swarm behavior with methodology and theory describing existing approaches for cooperative localization of heterogenous teams of mobile robots and a single helicopter. The Czech (Czech technical University in Prague) partner is continuously developing a framework that is focused on main principles how to increase the localization precision leading to reliable navigational techniques. Within the project, their approach and developed theory will be used as a core of arising system for localization of swarms. The US partner (Department of Mechanical Engineering and Applied Mechanics, University of Pennsylvania) is one of leading bodies in area of control of cooperating quad-rotor helicopters. Within the project, their experience with control of cooperating UAVs and knowledge of stability analysis will be utilized to develop a robust system applicable in scenarios of swarm robotics that cannot be realized with existing methods.

More information at http://mrs.felk.cvut.cz/projects/colos.


Tangible PSO for odor source localization

PSO searching process modified for an odor source localization with swarms of unmanned helicopters. The entire UAV group is represented by the PSO swarm with fitness function corresponding to a virtual concentration of a simulated smoke plume. Each PSO rule is decomposed to independent motion primitives of separate helicopters. UAVs are subsequently moved into new positions required by the PSO process. In each subsequent movement, a quadrocopter approaches into the new location, while the remaining robots keep constant pose and only their Yaw angle is changed to track the moving UAV and to realize the required relative localization. The advantage of such an approach is the possibility to keep the global position of the swarm during the mission.


Team:

CTU Libor Přeučil (PI, Intelligent and Mobile Robotics group), Martin Saska (technical/research project leader), Jan Chudoba (Intelligent and Mobile Robotics group), Jan Faigl (Agent Technology Center), Tomas Baca, Zdenek Kasl, Vojtech Vonasek
UPENN Vijay Kumar, Justin Thomas, Matthew Turpin, Giuseppe Loianno

Publications

Journal articles:

  1. M Saska, T Baca, J Thomas, J Chudoba, L Preucil, T Krajnik, J Faigl, G Loianno and V Kumar. System for deployment of groups of unmanned micro aerial vehicles in GPS-denied environments using onboard visual relative localization. Autonomous Robots 41(4):919–944, 2017. PDF BibTeX

    @article{SaskaAURO16,
    	author = "Saska, M. and Baca, T. and Thomas, J. and Chudoba, J. and Preucil, L. and Krajnik, T. and Faigl, J. and Loianno, G. and Kumar, V.",
    	title = "{System for deployment of groups of unmanned micro aerial vehicles in GPS-denied environments using onboard visual relative localization}",
    	journal = "Autonomous Robots",
    	year = 2017,
    	volume = 41,
    	number = 4,
    	pages = "919--944",
    	pdf = "data/papers/AURO2016.pdf"
    }
    
  2. G Loianno, V Spurny, T Baca, J Thomas, D Thakur, T Krajnik, A Zhou, A Cho, M Saska and V Kumar. Localization, Grasping, and Transportation of Magnetic Objects by a team of MAVs in Challenging Desert like Environments. IEEE Robotics and Automation Letters, 2018. PDF BibTeX

    @article{ral2018Loianno,
    	author = "G. Loianno and V. Spurny and T. Baca and J. Thomas and D. Thakur and T. Krajnik and A. Zhou and A. Cho and M. Saska and V. Kumar",
    	journal = "IEEE Robotics and Automation Letters",
    	title = "Localization, Grasping, and Transportation of Magnetic Objects by a team of MAVs in Challenging Desert like Environments",
    	year = 2018,
    	pdf = "data/papers/ral2018Loianno.pdf"
    }
    
  3. M Saska, V Vonásek, J Chudoba, J Thomas, G Loianno and V Kumar. Swarm Distribution and Deployment for Cooperative Surveillance by Micro-Aerial Vehicles. Journal of Intelligent & Robotic Systems. 84(1):469–492, 2016. PDF BibTeX

    @article{SaskaJINT2016,
    	author = "Saska, M. and Von{\'a}sek, V. and Chudoba, J. and Thomas, J. and Loianno, G. and Kumar, V.",
    	title = "Swarm Distribution and Deployment for Cooperative Surveillance by Micro-Aerial Vehicles",
    	journal = "Journal of Intelligent \& Robotic Systems.",
    	volume = 84,
    	number = 1,
    	pages = "469--492",
    	year = 2016,
    	pdf = "data/papers/SaskaJINT2016.pdf"
    }
    

WoS conference papers:

  1. M Saska, J Chudoba, L Preucil, J Thomas, G Loianno, A Tresnak, V Vonasek and V Kumar. Autonomous Deployment of Swarms of Micro-Aerial Vehicles in Cooperative Surveillance. In International Conference on Unmanned Aircraft Systems (ICUAS). 2014. PDF BibTeX

    @inproceedings{Saska14:221385,
    	author = "Saska, M. and Chudoba, J. and Preucil, L. and Thomas, J. and Loianno, G. and Tresnak, A. and Vonasek, V. and Kumar, V.",
    	title = "{Autonomous Deployment of Swarms of Micro-Aerial Vehicles in Cooperative Surveillance}",
    	booktitle = "{International Conference on Unmanned Aircraft Systems (ICUAS)}",
    	year = 2014,
    	pdf = "data/papers/icuas2014-joined.pdf"
    }