Friday, 23 December 2011

Swarm robotics at the Science Museum

From Prof. Alan Winfield's Web Log

Swarm robotics at the Science Museum: Just spent an awesomely busy weekend at the Science Museum, demonstrating Swarm Robotics. We were here as part of the Robotville exhibition, and - on the wider stage - European Robotics Week. I say we because it was a team effort, led by my PhD student Paul O'Dowd who heroically manned the exhibit all four days, and supported also by postdoc Dr Wenguo Liu. Here is a gallery of pictures from Robotville on the science museum blog, and some more pictures here (photos by Patu Tifinger):

Although exhausting, it was at the same time uplifting. We had a crowd of very interested families and children the whole time - in fact the organisers tell me that Robotville had just short of 8000 visitors over the 4 days of the exhibition. What was really nice was that the whole exhibition was hands-on, and our sturdy e-puck robots - at pretty much eye-level for 5-year olds, attracted lots of small hands interacting with the swarm. A bit like putting your hand into an ants nest (although I doubt the kids would have been so keen on that.)

Let me explain what the robots were doing. Paul had programmed two different demonstrations, one with fixed behaviours and the other with learning.

For the fixed behaviour demo the e-puck robots were programmed with the following low-level behaviours:
  1. Short-range avoidance. If a robot gets too close to another robot or an obstacle then it turns away to avoid it.
  2. Longer-range attraction. If a robot can sense other robots nearby but gets too far from the flock, then it turns back toward the flock. And while in a flock, move slowly.
  3. If a robot loses the flock then it speeds up and wanders at random in an effort to regain the flock (i.e. another robot).
  4. While in a flock, each robot will communicate (via infra-red) its estimate of the position of an external light source to nearby robots in the flock. While communicating the robot flashes its green body LED.
  5. Also while in a flock, each robot will turn toward the 'consensus' direction of the external light source.
The net effect of these low-level behaviours is that the robots will both stay together as a swarm (or flock), and over time, move as a swarm toward the external light source. Both of these swarm-level behaviours are emergent because they result from the low-level robot-robot and robot-environment interactions. While the flocking behaviour is evident in just a few minutes, the overall swarm movement toward the external light source is less obvious. In reality even the flocking behaviour appears chaotic, with robots losing each other, and leaving the flock, or several mini-flocks forming. The reason for this is that all of the low-level behaviours make use of the e-puck robots' multi-purpose Infra-red sensors, and the environment is noisy; in other words because we don't have carefully controlled lighting there is lots of ambient IR light constantly confusing the robots.

The learning demo is a little more complex and makes use of an embedded evolutionary algorithm, actually running within the e-puck robots, so that - over time - the robots learn how to flock. This demo is based on Paul's experimental work, which I described in some detail in an earlier blog post, so I won't go into detail here. It's the robots with the yellow hats in the lower picture above. What's interesting to observe is that initially, the robots are hopeless - constantly crashing into each other or the arena walls, but noticeably over 30 minutes or so we can see the robots learn to control themselves, using information from their sensors. The weird thing here is that, every minute or so, each robot's control software is replaced by a great-great-grand child of itself. The robot's body is not evolving, but invisibly it's controller is evolving, so that later generations of controller are more capable.

The magical moment of the two days was when one young lad - maybe 12 years old, who very clearly understood everything straight away and seemed to intuit things I hadn't explained - stayed nearly an hour explaining and demonstrating to other children. Priceless.

Tuesday, 29 November 2011



Analysis by Nic Halverson

Schools of fish, flocks of birds -- even bicyclists in the Tour de France -- all use the principles of swarm behavior and drafting to conserve energy while moving in the same direction.

PHOTOS: Top 10 Fastest Electric Vehicles

Australian industrial designer, Charles Rattray, believes these concepts are the future of transportation. That's why he's designed Autonomo, a biomimicry inspired autonomous vehicle he hopes will revolutionize the auto industry by the year 2030.

Influenced heavily by swarm robotics and artificial intelligence, Rattray's omni-wheeled, self-driving Autonomos would travel in tight platoons while shifting their configurations to maintain an uninterrupted traffic flow. Microwave sensors would allow cars to travel a mere 7.8 inches apart, thus aerodynamically reducing vehicle drag and energy consumption, making tailgating actually a good thing.

Onboard computers would synthesize data from an array of sensors (radar, microwave, lidar, optical and infrared) and external feedback systems that would monitor the road 656 feet in front of and behind the vehicle or vehicle platoon. There's also hi-def cameras equipped with object recognition technologies that would help predict the path of other vehicles, cyclists, pedestrians and other hazardous objects.

Balancing these flocks of vehicles would be a centralized database controlled by intelligent algorithms that could adjust as new spatial information is fed to them.

Rattray's concept vehicle is a svelte 3.77 foot wide two-seater with bobsled-style seating. It's slim design would allow Autonomos to travel two abreast in a single lane so that existing road infrastructures would not need overhauling.

Vehicles would be charged wirelessly through electrodynamic induction or energy transfer lasers via charging pads embedded on the surface of the road.

BLOG: Speed Bumps You'll Be Happy To Drive Over

Obviously, this project aims to lasso the moon with an ambition of fantastical proportions. But as the great architect of Chicago, Daniel Burnham, once said, "Make no little plans. They have no magic to stir men's blood and probably themselves will not be realized."

[Via GizMag]

Credit: Charles Rattray

Friday, 25 November 2011

I, for one, welcome our new farming robots

I, for one, welcome our new farming robots:

One step closer to the robots taking over!

Wired’s Eric Smalley has an awesomely titled article about a Massachusetts based startup, Harvest Automation, is testing a small farming robot to work in nurseries in the horticulture industry.

The Harvest Automation robots are knee-high, wheeled machines. Each robot has a gripper for grasping pots, a deck for carrying pots, and an array of sensors to keep track of where it is and what’s around it. Teams of robots zip around nursery fields, single-mindedly spacing and grouping plants. Think Wall-E without the doe eyes and cuddly personality, or the little forest-tending ‘bots in the 1972 sci-fi classic Silent Running.

Thank you Wired!

Share and Enjoy:

Google Bookmarks

Tuesday, 4 October 2011

EPFL Researchers Demonstrate Flocking

EPFL Researchers Demonstrate Flocking: initial image from video on EPFL flocking study

The above image is taken from a video of research done by Sabine Hauert, Severin Leven, and Dario Floreano of the Laboratory of Intelligent Systems, EPFL, Lausanne, Switzerland. As part of this research, they tested the effects of turning radius and communications range on programmed flocking behavior in a group of ten aerial robots. More details are available on the Wired Science blog, and in the video.

Thursday, 15 September 2011

Incredible Collaboration of Swam Robotics

Incredible Collaboration of Swam Robotics:

In the very near future, these researchers believe robots will combine together to do all the tasks assigned to them. The Swarmanoid Project is a glorious example of a glimpse into the future which demonstrates 60 robots working together in a collaborative environment. The goal of the swarm robotic project (4 years in the making) is to use the different capabilities of each class of robot and combine them into a system to accomplish tasks.

The “Eye bots” sense the environment and provide an aerial overview. “Hand-bots” can climb vertical surfaces of walls or grab objects located in the environment. “Foot-bots” move on rough terrain and transport either robots. This distributed robotic system is inspired from the social behavior of insects where each member of the colony performs a particular task.

Popular Robotic Projects:

Monday, 15 August 2011

Swarms Of Robots Out To Steal Your Books

Swarms Of Robots Out To Steal Your Books: "

Watch out Seal Team Six, there’s a new group of special forces entering the mix – and they’re out for your literature.

Evan Ackerman over at IEEE has written an interesting blog post about the Swarmanoid project.

The swarmanoid robots consist of three types, each specializing in specific tasks: hands, feet, and eyes. When their powers combine they turn into an unstoppable machine on a mission to steal your valuables.

Share and Enjoy:

Google Bookmarks


Video: Raid of the robot swarm

Video: Raid of the robot swarm: "Thanks to our sister site, New Scientist, for highlighting this rather sinister one - a co-ordinated raid by 'eye-bots', 'foot-bots', and 'hand-bots' to grab a book from a high shelf.

They are many, and they work together. And they are getting more clever...

(The award-winning film is by Mauro Birattari and Rehan O'Grady)

Thanks to our sister site, New Scientist, for highlighting this rather sinister one - a co-ordinated raid by 'eye-bots', 'foot-bots', and 'hand-bots' to grab a book from a high shelf.

They are many, and they work together. And they are getting more clever...

(The award-winning film is by Mauro Birattari and Rehan O'Grady)

Melissae Fellet writes:
You could call it Mission Impossible: Robot Library Heist. An army of flying, rolling, and climbing robots have been taught to work together to find and snatch a book from a high shelf.

In a striking display of military-like precision, the robotic team, dubbed the 'Swarmanoid', attacks the problem with flying 'eye-bots' and rolling 'foot-bots'. A 'hand-bot' then fires a grappling hook-like device up to the ceiling and scales the bookshelf. Footage of the experiment, conducted by Marco Dorigo at the Free University of Brussels, Belgium, and colleagues, won the video competition at the Conference on Artificial Intelligence in San Francisco earlier this week.

It's a simple demonstration, but in the future Dorigo says the robots could be tasked with more difficult and important tasks. For instance, a bot team equipped like firefighters could wait in a building and spring to action when disaster strikes.
Read the full post >>


Monday, 8 August 2011

Robots listen only to the leader when building a roving quadcopter landing pad

Robots listen only to the leader when building a roving quadcopter landing pad: "

Swarm robotics is really starting to produce some interesting results. This image is from the video embedded after the break that show a group of five robots creating a landing platform for a quadrotor helicopter. The four that actually make up the platform are not in contact with each other, but instead following commands from the leader. We’re impressed by the helicopter’s ability to target and land on the moving platform. Takeoff appears to be another issue, as the platform bots stop moving until the quadcopter is airborne again.

These robots are part of a Graduate project at Georgia Tech. [Ted Macdonald] has been working along with others to implement an organizational algorithm that guides the swarm. The method requires that the robots have an overview of the location of all others in the swarm. This is done with high-speed cameras like we’ve seen in other robotic control projects. But that doesn’t discourage us. If you already have a flying robot as part of the swarm, you might as well add a few more to serve as the eyes in the sky.

[Thanks Supertroopa via Engadget]

Filed under: robots hacks


Tuesday, 5 July 2011

Voice controlled robot controlled by an Android phone

Voice controlled robot controlled by an Android phone: "

[Jeff] sent in a build of a voice controlled robot he just finished based on the Android ADK and an iRobot Create.

The robot is able to obey voice commands telling it where to go. Currently the robot responds to forward, reverse, left, right, stop, and ‘whistle while you work.’ It’s a creative use of the Android ADK with some obvious applications, but this project really shines with the write up on instructables. It’s rare that we’ve seen a project so well documented; it’s a great project for someone who wants to get their feet wet in the world of robotics.

[Jeff]‘s write up goes through the steps of hooking up the ADK board to iRobot and providing all the electronic necessities. [Jeff] graciously provided the code for his robot if anyone would like to add to his project.

The ultimate goal [Jeff] is currently working towards is something akin to a TurtleBot, while keeping the voice control of the robot. In all, a very nice project.

Saturday, 2 July 2011

RF Transceivers


Long time without news, I'm sorry!
But now i'm fully ready to begin the development of my swarm of iRobots!

Today I will talk about the cheap RF transceivers I found at sparkfun (
They are FM transceiver with configurable frequency bandwitch, SPI interface, internal FIFO (very small, but very useful). Right now I'm programming the eLua software to test them:

Here I'm using the STM32 kit to talk with two RFM12 (one on each SPI port) they will simply echo each other as a test application.
I will create soon a GITHub Repo to share the code of this post and futures ones!

Sunday, 1 May 2011

Sunday, 20 March 2011

swarm-bots pulling a child

Thursday, 10 February 2011

Monday, 3 January 2011

Review: Swarm Robotics: From Sources of Inspiration to Domains of Application

As the first reviewed article I've chosen "'Sahin, Erol - Swarm Robotics" because it is a nice overview of the technology and tries do define swarm robotics as an area of robotics with very clear boundaries and goals.

The first part of the article is about motivation for studies, highlighting the three most praised characteristics of swarm systems, that are:
  • Robustness;
  • Flexibility;
  • Scalability.
After that comes a brief explanation about the ambitions of the work, saying it not pretend to be a formal definition of the area, but a guideline for future developments. Setting a nice statement as starting point:
"Swarm robotics is the study of how large number of relatively simple physically embodied agents can be designed such that a desired collective behavior emerges from the local interactions among agents and between the agents and the environment."

Then going through some points about autonomous robots such as:

  • Large number of robots;
  • Few homogenous groups of robots;
  • Relatively incapable or inefficient robots;
  • Robots with local sensing and communication capabilities.
The following topic is about sources of inspiration for swarm robotics and collective behavior in general, most of then biological with some very informative content about bacterial mechanisms and so on.

Finally some possible applications where swarms are highly recommended:

  • Tasks that cover a region;
  • Tasks that are too dangerous;
  • Tasks that scale-up or scale-down in time;
  • Tasks that require redundancy.
Ref: The article site at Springer Link (it can be downloaded under certain universities proxys)