Evolving collective behaviours in simulated kilobots
MetadataShow full item record
This item's downloads: 215 (view details)
Cited 0 times in Scopus (view citations)
Holland, Jane, Griffith, Josephine , & O'Riordan, Colm (2018). Evolving collective behaviours in simulated kilobots. Paper presented at the 33rd Annual ACM Symposium on Applied Computing (SAC), Pau, France, 09-13 April.
The field of Evolutionary Robotics has multiple common tasks and widely used benchmark activities such as navigation, obstacle avoidance, and phototaxis. We present an evolutionary approach to learning behaviours that demonstrate emergent collective phototaxis in a swarm of simulated robots. Our approach demonstrates that evolutionary computation can be used to evolve the emergent, self-organising behaviours of clustering and phototaxis in a population of simulated robots where the robots possess limited capabilities. In addition to demonstrating the feasibility of the approach, we show that the evolved behaviours are also robust to noise and flexible in changing environments.