On the evolution of self-organised role-allocation and role-switching behaviour in swarm robotics: a case study

Abstract

In spite of its significance for the adaptability of autonomous robotic swarms, the dynamic allocation and re-distribution of robots to tasks (i.e., role-allocation and role-switching behaviour) is still a design challenge in swarm robotics. This study investigates a simulated foraging scenario in which the variability of the environmental conditions requires that robots switch between two roles (i.e., foraging and nestpatrolling). To the best of our knowledge, this is the first simulation study that demonstrates that role-allocation and role-switching behaviour can be evolved using dynamic neural network controllers for robots with minimal communication capabilities. Initial analyses of the best evolved teams shed light on some of the characteristics and robustness of the strategies used by these teams to repeatedly face this task.

Evolution of Communication-Based Collaborative Behavior in Homogeneous Robots

“…We maintain that this high robustness depends on the presence of a communication channel that is used to allocate the roles. If, as in previous works (Baldassarre et al, 2003;Quinn et al, 2003;Tuci et al, 2013) role allocation depends only on robots behaviour, it will tend to be situated, that is dependent on the context. This means that as the context changes, for example because the groups contains a different number of robots, then the behaviour will tend to stop functioning.…”

“…A few previous works have been devoted to the evolution of role differentiation in groups of robots (Baldassarre et al, 2003;Quinn et al, 2003;Tuci et al, 2013). Baldassarre et al (2003) evolved a group of robots for the ability to collectively navigate toward a light target.…”

“…Finally, Tuci et al (2013) evolved a group of homogeneous robots for their ability to perform two behaviours: some robots had to remain and patrol the 'nest', while other robots had to leave the nest and go foraging in a food area. Furthermore, the role allocation strategy depended on the context: in one context the number of robot patrolling the nest had to be higher than the number of robots foraging, while in a second context the opposite holded.…”

Augmenting Scalable Communication-Based Role Allocation for a Three-Role Task

“…Research on evolutionary collective robotics [2] [17] [20] for homogeneous robots suggest that role differentiation, which is fundamental for cooperation in natural and artificial systems, is triggered by differences in local physical interactions. In [2], a group of four robots was evolved to collectively navigate toward a light.…”

“…If any robot is removed, the remaining robots cease motion. In [20], a group of five robots was evolved to guard a nest and forage simultaneously. The environment had two variations that required different behaviors to maximize fitness: (i) most robots stayed in the nest while others foraged; or (ii) fewer robots stayed in the nest while others foraged.…”