Jun 6, 2015 | By Simon

While the robots you or I build with a 3D printer involve little more than an Arduino, some motors and some PLA, a team of roboticists from the Department of Zoology at the Austrian University of Graz illustrate just what can be achieved. They have created a swarm of 3D printed fish-like robots capable of not only learning individually, but also functioning through collective cognition, or the group-based interaction and exchange of information. The COCORO team behind this project has further announced that 2015 will be the year of the COCORO, and they will unveil a new video on YouTube of the exploits of their 41-fish swarm every week.

This fascinating project ran from 2011 up to 2014, and was led by dr. Thomas Schmickl with funding by the European research commission. As he explained on the project’s website, the COCRO is different from other swarm projects due to the complexity of the collective cognition instilled in the robots. ‘They work as a collective system of autonomous agents that can learn from past experience and their environment,’ he writes. Among the tasks these robots are capable of performing are exchanging information about the environment, exploring underwater environments, and even maintaining and harvesting resources. And just like fish themselves, they can do so collectively and individually.

‘We specialize in swarm robotics which exploits individual learning but more prominently the learning and knowledge of the group,’ the enthusiastic coordinator told reporters. ‘In this context, even individually non–learning robots can achieve collective cognition by, for example, changing the topology of the group. While this was exploited in land-based robotics several times, to our knowledge we are the first ones that exploit this in underwater autonomous robotics.’

As the team wrote on the project’s homepage, the swarm will maintain integrity under all those changing conditions and hazardous environments. ‘This will be achieved by letting the AUVs interact with each other and exchange information, resulting in a cognitive system that is aware of its environment, of local individual goals and threats and of global swarm-level goals and threats,’ they write. ‘By a combination of locally acting and globally acting self-organizing mechanisms, information from the global level flows into the local level and influences the behaviour of individual AUVs. Such a cognitive- based scheme creates a very fast reaction of the whole collective system when optimizing the global performance. As shown by natural swimming fish swarms, such mechanisms are also flexible and scalable.’

These impressive tasks are illustrated in the many videos that can be found the project’s YouTube channel. Among the videos, you can for instance see them conducting searches in pools. When one of the swarm members discovers the target, it alerts the rest through a series of LEDs they use for communications. Before long, the entire 'school’ of robotic fish swarm the target. ‘They are more a swarm-like mobile sensor-network and information-processing network,’ Schmickl explains. Other videos see them finding debris from airplanes by tracking the magnetic signals from magnets placed around the debris.

As you can imagine, this thoroughly builds on examples from nature itself. As Schmickl explained, they closely modelled their algorithms on the behavior of bees and fish, and even the communication patterns of amoebas. The robots themselves are largely made with 3D printed components for these prototype models, though as you can understand this isn’t exactly optimal for robots in very extreme environments.

The ‘Jeff’ model robot in sea water.

To illustrate the potential of these parts, field trials were staged in the Livorno Harbour in Italy, where the 3D printed swarm had to deal with waves, currents and of course salt water. This requires a bit more from the algorithms than freshwater pools only 10 feet deep. ‘The hardware was stressed and broke after some time, but several days of experimentation were possible,’ the scientist explained, adding that the swarm was successful nonetheless. ‘Of course the open ocean is demanding for strong — and also larger — hardware. So we will see larger AUVs (autonomous underwater vehicles) that today operate alone to pick up algorithms from swarm robotics and employ them in small groups to make search or monitoring efficient.’

As such, the applications are obvious; not just scientifically for its cognitive abilities, but also for rescue, reconnaissance and other missions. ‘Sunken wreckage is an option, definitely,’ Schmickl concluded. ‘We thought about wrecks, but also about airplane black boxes and waste that was thrown into the ocean.’ Check out footage of these interesting 3D printed robots below.

The ‘Lily’ model robot in a lake.

Lily in a pool.

 

 

Posted in 3D Printing Applications

 

 

Maybe you also like:


   





Leave a comment:

Your Name:

 


Subscribe us to

3ders.org Feeds 3ders.org twitter 3ders.org facebook   

About 3Ders.org

3Ders.org provides the latest news about 3D printing technology and 3D printers. We are now seven years old and have around 1.5 million unique visitors per month.

News Archive