Swarm intelligence is the study of systems of spatially distributed individuals that coordinate their actions in a self-organised manner and thereby exhibit complex collective behaviour. In the first part of the talk, we present our recent advances in controlling groups of robots. The platform being used is the EPFL miniature mobile robot e-puck. It is shown that some tasks can be solved by swarms of robots with severely limited abilities. For example, in order for a group of robots to spatially segregate into distinct subgroups or transport a tall object, the robots do not fundamentally require to communicate with each other in an explicit way [1,2]. Rather it is sufficient if they can discriminate between the object, the goal and the remainder of the environment. In order for a group of robots to gather in a single place , or cluster objects that are initially dispersed , it was found that the robots do not fundamentally require arithmetic computation. Such tasks can be solved by robots that use a binary sensor to trigger one of two possible actions, without the need to store information during run-time. In the second part of the talk, we present a method that is able to identify models (parameters) of individuals, for example, when part of a swarm, through observation . This method does not require any pre-defined metric to gauge the resemblance of models to observed individuals. In the third part of the talk, we outline our recent efforts towards an evolution of energy autonomous robotic organisms .
swarm robotics, minimalism, self-organized aggregation, coevolution, system identification, evolution
Segregation in swarms of e-puck robots based on the Brazil nut effect.
AAMAS 2012. pp. 163-170.
A strategy for transporting tall objects with a swarm of miniature mobile robots.
ICRA 2013. IEEE Press. pp. 863-869.
Extended version conditionally accepted in T-RO.
Self-organized aggregation without computation,
International Journal of Robotics Research, 33:1145-1161.
Clustering objects with robots that do not compute.
AAMAS 2014. pp. 421-428.
Nominated for Best Student Paper award.
See http://dl.acm.org/citation.cfm?id=2615800 & CFID=454901457 & CFTOKEN=66407710
Coevolutionary learning of swarm behaviors without metrics.
GECCO 2014. ACM Press. pp. 201-208.
Evo-bots: A Modular Robotics Platform with Efficient Energy Sharing.
IROS 2014 Workshop on Swarms and Modular Systems - From Nature to Robotics. pp. 1-4.