Edinburgh Napier University

  Swarm robotics is a special case within the general field of robotics. The distributed nature makes it more resilient with no single point of failure. Considering the application in remote locations, the swarm needs to adapt autonomously to a priori unknown environmental conditions. A special branch of evolutionary robotics achieves online adaptation during runtime through embedding the evolutionary algorithm in the robot. A well studied algorithm to do that is mEDEA, minimal Environment-driven Distributed Evolutionary Adaptation, which has been shown to be able to maintain the swarm's integrity in an abruptly changing environment. It’s completely decentralised nature and the lack of an explicit fitness function leaves only the environment to provide the driving force for the evolutionary process.

This thesis investigates several aspects of environment-driven adaptation in simulated evolutionary swarm robotics. It is centred around a specific algorithm for distributed embodied evolution called mEDEA.
Firstly, mEDEA is extended with an explicit relative fitness measure while still maintaining the distributed nature of the algorithm. Two ways of using the relative fitness are investigated: influencing the spreading of genomes and performing an explicit genome selection. Both methods lead to an improvement in the swarm’s ability to maintain energy over longer periods.
Secondly, a communication energy model is derived and introduced into the simulator to investigate the influence of accounting for the costs of communication in the distributed evolutionary algorithm where communication is a key component.
Thirdly, a method is introduced that relates environmental conditions to a measure of the swarm’s behaviour in a 3-dimensional map to study the environment’s influence on the emergence of behaviours at the individual and swarm level. Interesting regions for further experimentation are identified in which algorithm specific characteristics
show effect and can be explored.
Finally, a novel individual learning method is developed and used to investigate how the most effective balance between evolutionary and lifetime-adaptation mechanisms is influenced by aspects of the environment a swarm operates in. The results show a clear link between the effectiveness of different adaptation mechanisms and environmental conditions, specifically the rate of change and the availability of learning opportunities.