Posts

Showing posts with the label swarmintelligence

#robotics #swarmrobotics #swarmintelligence

#robotics #swarmrobotics #swarmintelligence

http://spectrum.ieee.org/automaton/robotics/robotics-software/swarms-of-robots-manage-to-not-run-into-each-other

World's Largest Swarm of Miniature Robot Submarines

World's Largest Swarm of Miniature Robot Submarines

I have first heard of CoCoRo during AWASS2013, I was in the workshop that developed one swarm strategy for the simulated robots to perform their task. I have learned NetLogo for it, quite an interesting and exciting experience.

Forty one tiny robot submarines is a lot of tiny robot submarines. It’s so many, in fact, that controlling them individually doesn’t make sense, and the only way to go is to give them levels of swarm intelligence, so that each individual robot can take care of itself while the swarm as a whole completes an objective.

The CoCoRo (Collective Cognitive Robotics) Project, sponsored by the European Commission, has been working with a heterogeneous swarm of autonomous underwater vehicles (AUVs) since 2011

#robotics   #swarmrobotics   #swarmintelligence  

Originally shared by Automaton, IEEE Spectrum's Robotics Blog
http://spectrum.ieee.org/automaton/robotics/artificial-intelligence/worlds-largest-swarm-of-miniature-robot-submarines

#robotics #drones #swarmintelligence #swarmrobotics

#robotics #drones #swarmintelligence #swarmrobotics

Originally shared by Lacerant Plainer

The SMAVNET project aims at developing swarms of flying robots that can be deployed in disaster areas to rapidly create communication networks for rescuers. Flying robots are interesting for such applications because they are fast, can easily overcome difficult terrain, and benefit from line-of-sight communication. 

To make aerial swarming a reality, robots and controllers need to be made as simple as possible. 

Designing swarm controllers is typically challenging because no obvious relationship exists between the individual robot behaviors and the emergent behavior of the entire swarm. For this reason, we turn to biology for inspiration. 

In a first approach, artificial evolution is used for its potential to automatically discover simple and unthought-of robot controllers. Good evolved controllers are then reverse-engineered so as to capture the simple and efficient solutions found through evolution in hand-designed controllers that are easy to understand and can be modeled. Resulting controllers can therefore be adapted to a variety of scenarios in a predictable manner. Furthermore, they can be extended to accommodate entirely new applications. Reverse-engineered controllers demonstrate a variety of behaviors such as exploration, synchronization, area coverage and communication relay. 

Designing swarm controllers is typically challenging because no obvious relationship exists between the individual robot behaviors and the emergent behavior of the entire swarm. For this reason, we turn to biology for inspiration. 

Full Article: http://lis.epfl.ch/smavs

Video link: Deployment of Large Aerial Swarms

#swarm   #swarmintelligence   #robots   #science   #sciencesunday   #scienceeveryday   #biology  

#robotics #swarmintelligence #swarmrobotics

#robotics #swarmintelligence #swarmrobotics

Originally shared by Lacerant Plainer

Swarm Robots

University of Colorado Boulder Assistant Professor Nikolaus Correll likes to think in multiples. If one robot can accomplish a singular task, think how much more could be accomplished if you had hundreds of them.

Correll and his computer science research team, including research associate Dustin Reishus and professional research assistant Nick Farrow, have developed a basic robotic building block, which he hopes to reproduce in large quantities to develop increasingly complex systems.

Recently the team created a swarm of 20 robots, each the size of a pingpong ball, which they call “droplets.” When the droplets swarm together, Correll said, they form a “liquid that thinks.”

To accelerate the pace of innovation, he has created a lab where students can explore and develop new applications of robotics with basic, inexpensive tools.

Similar to the fictional “nanomorphs” depicted in the “Terminator” films, large swarms of intelligent robotic devices could be used for a range of tasks. Swarms of robots could be unleashed to contain an oil spill or to self-assemble into a piece of hardware after being launched separately into space, Correll said.

Video link: http://www.colorado.edu/news/multimedia/researchers-creating-team-tiny-robots

#robotics   #robots   #science   #scienceeveryday  
http://www.colorado.edu/news/releases/2012/12/14/cu-boulder-team-develops-swarm-pingpong-ball-sized-robots

This one sounds very interesting!

This one sounds very interesting!

#robotics   #swarmrobotics   #swarmintelligence   #ants  

Originally shared by Science on Google+

Dr. Theodore (Ted) P. Pavlic, Assistant Professor of Industrial Engineering and Operations Research in the School of Computing, Informatics, and Decision Systems Engineering at Arizona State University. Ted Pavlic received his PhD in Electrical and Computer Engineering in 2010 from The Ohio State University where he learned to combine behavioral ecology and control theory to build algorithms that allow automation to make flexible decisions that are rational with respect to the current environment. Inspiration came from optimal foraging theory and cooperative breeding, and target applications ranged from military to the sustainable built environment. From 2010 to 2012, he worked as a postdoctoral scholar in Computer Science and Engineering studying cyber-physical systems of the future composed of fully autonomous and human driven cars operating in parallel in the cities of the near future. Since 2012, he has worked as a research scientist at Arizona State University in the social-insect laboratory of Stephen Pratt studying the collective decision-making processes of ants and honeybees. Not only have these studies inspired novel stochastic programming techniques for swarm robotics, but these animal models are also providing insights into the information structures that emerged at the origins of life. In August of 2015, he will join the engineering faculty of Arizona State University where he will use a variety of theoretical, computational, and empirical methods to study decision-making and organization across a wide range of artificial and natural systems. Potential graduate students interested in trans-disciplinary explorations of decision making are welcome to contact him to discuss opportunities.

Links
Personal website in desperate need of updating:
http://www.tedpavlic.com/

Current host (Stephen Pratt) laboratory for ant work: 
http://pratt.lab.asu.edu/

Collaborator (Sara Imari Walker) laboratory for info. theory work:
http://emergence.asu.edu/

Recommended Readings
Sean Wilson, Theodore P. Pavlic, Ganesh P. Kumar, Aurélie Buffin, Stephen C. Pratt, and Spring Berman. Design of ant-inspired stochastic control policies for collective transport by robotic swarms. Swarm Intelligence, 8(4):303–327, December 2014.
http://dx.doi.org/10.1007/s11721-014-0100-8

Theodore P. Pavlic, Alyssa M. Adams, Paul C. W. Davies, and Sara Imari Walker. Self-referencing cellular automata: A model of the evolution of information control in biological systems. In: Proceedings of the Fourteenth International Conference on the Synthesis and Simulation of Living Systems (ALIFE 14), pages 522–529, July 31 – August 2, 2014.
http://dx.doi.org/10.7551/978-0-262-32621-6-ch083

Theodore P. Pavlic and Stephen C. Pratt. Superorganismic behavior via human computation. In: Pietro Michelucci, editor, Handbook of Human Computation, pages 911–960. Springer, 2013.
http://dx.doi.org/10.1007/978-1-4614-8806-4_74

#robotics #swarmintelligence #swarmrobotics

#robotics #swarmintelligence #swarmrobotics

Originally shared by Singularity 2045

#Festo has 3D-printed BionicANTS to compliment their eMotionButterflies. The two robots will be on display at in Germany, at the Hannover Fair 13-17 April 2015.

You may remember Festo regarding robotic dragonfly (bionicopter) drones: http://www.engadget.com/2013/03/29/bionicopter-dragonfly-drone/

3Dprint.com (27 Mar 2015): "Just imagine 3D printed colonies of ants, commanded to work together just as their live counterparts do naturally. Not only are they highly functional, they are stunningly beautiful with intricate details and vibrant color — almost jewel-like in their aesthetics, thanks to the use of 3D MID technology on laser-sintered shaped body parts. They are also powered by electronics, and part of their beauty is actually lent due to the strategic design of the golden-hued electrical components, which cause the 3D printed ants to function in myriad ways."

#robots #robotics #3Dprinting  

Note the following S45 post from March 2013 regarding various mini dones, which you may also be interested in: https://plus.google.com/+Singularity-2045/posts/WnQxdxA4SnF

Here is the source regarding the ants: http://www.festo.com/cms/en_corp/14252.htm (https://archive.today/kmSxH).
http://3dprint.com/54023/festo-3d-printed-bionicants

I have kick started the project Robots vs.

I have kick started the project Robots vs. Animals at the Bristol Zoo. Mine was the first session! The kids had great fun, and us too.

During the session, the students investigated human-robot interaction, learning about why engineers make robots yawn, dance and gesture like humans in order to make the robots more approachable and engaging. Students saw how evolution is shortening the legs of the blue-tongued skink. This helped them understand how robots are evolving – and one day might be able to change their shape rapidly like Transformers.

#robotics    #brl   #robotsvsanimals   #uwe   #bristol   #bristolzoo   #swarmintelligence   #swarmrobotics   #robots   #animals   #biomimicry     #jessicameyer  
http://info.uwe.ac.uk/news/uwenews/news.aspx?id=2988

#robotics #swarmintelligence #swarmrobotics #robotica #inteligenciacoletiva

#robotics   #swarmintelligence   #swarmrobotics   #robotica   #inteligenciacoletiva  

Originally shared by Gehazi Bispo

Robótica de enxame: robôs unidos jamais serão vencidos
Swarm Robotics: robots united will never be defeated

Ação grupal / Grupal action

_Inspirada nas características de insetos que vivem em grupos, como as abelhas e as formigas, a chamada "robótica de enxame" trabalha com robôs pequenos e simples, que agem em conjunto para realizar tarefas complexas.-

Essas tarefas podem ser participar de um jogo de futebol de robôs, por exemplo. Mas, no futuro, também poderão consistir em coletar contaminantes químicos ou radioativos, partícula por partícula, depositando-os em local seguro.

A equipe da pesquisadora Nadia Nedjah, da Universidade do Estado do Rio de Janeiro (UERJ), está aprimorando esta tecnologia.

Para explicar seu trabalho, ele recorre ao exemplo das formigas que, embora não tenham um cérebro muito desenvolvido, não sendo individualmente muito inteligentes, nem tenham uma boa visão, conseguem realizar trabalhos complexos, como encontrar e usar o menor caminho do ninho à comida ou a construção de pontes vivas.

"Para isso, as formigas interagem entre si e com o ambiente ao redor", explica Nadia. (continua...)

(...)"Vamos continuar trabalhando no desenvolvimento da inteligência de enxame até que possamos colocá-la em prática. Tudo isso vai ajudar muito nas situações mais difíceis de nosso cotidiano", finaliza.

#Robótica #Enxame #inteligência #IA #ciência #tecnologia #Robotics #SwarmRobotics #intelligence #AI #Science #technology #sciencesunday #sciencebrazil
http://pulse.me/s/9vijO

The Symbrion EU project in the beginning. This is the project that I'm currently working on :)

The Symbrion EU project in the beginning. This is the project that I'm currently working on :)

The aim of the ‘Symbiotic Evolutionary Robot Organisms’ project, or ‘Symbrion’, is to understand the principles that govern how robots can form themselves into a single artificial organism. The technique enables them to interact collectively with the physical world, and might ultimately be applied to real-world tasks such as rescuing earthquake victims.

‘Multi-robot organisms’ are made up of large swarms of individual robots, each slightly larger than a sugar cube, which work together to form a single artificial life-form. The organisms are able to share information and energy with one another, and to manage their own hardware and software.

#robotics   #symbrion   #replicator   #uwe   #brl   #swarmintelligence   #swarmrobotics   
http://spectrum.ieee.org/automaton/robotics/robotics-software/symbrion_and_replicator_swarm_robot_projects