In this paper, we study the impact of selection methods in the context of on-line on-board distributed evolutionary algorithms. We propose a variant of the mEDEA algorithm in which we add a selection operator, and we apply it in a task-driven scenario. We evaluate four selection methods that induce different intensity of selection pressure in a multi-robot navigation with obstacle avoidance task and a collective foraging task. Experiments show that a small intensity of selection pressure is sufficient to rapidly obtain good performances on the tasks at hand. We introduce different measures to compare the selection methods, and show that the higher the selection pressure, the better the performances obtained, especially for the more challenging food foraging task.

In this paper, we study how a swarm of robots adapts over time to solve a collaborative task using a distributed Embodied Evolutionary approach, where each robot runs an evolutionary algorithm and they locally exchange genomes and fitness values. Particularly, we study a collaborative foraging task, where the robots are rewarded for collecting food items that are too heavy to be collected individually and need at least two robots to be collected. Further, the robots also need to display a signal matching the color of the item with an additional effector. Our experiments show that the distributed algorithm is able to evolve swarm behavior to collect items cooperatively. The experiments also reveal that effective cooperation is evolved due mostly to the ability of robots to jointly reach food items, while learning to display the right color that matches the item is done suboptimally. However, a closer analysis shows that, without a mechanism to avoid neglecting any kind of item, robots collect all of them, which means that there is some degree of learning to choose the right value for the color effector depending on the situation.

We propose a novel innovation marking method for NeuroEvolution of Augmenting Topologies in Embodied Evolutionary Robotics. This method does not rely on a centralized clock, which makes it well suited for the decentralized nature of EE where no central evolutionary process governs the adaptation of a team of robots exchanging messages locally.This method is inspired from event dating algorithms, based on logical clocks, that are used in distributed systems, where clock synchronization is not possible. We compare our method to odNEAT, an algorithm in which agents use local time clocks as innovation numbers, on two multi-robot learning tasks: navigation and item collection. Our experiments showed that the proposed method performs as well as odNEAT, with the added benefit that it does not rely on synchronization of clocks and is not affected by time drifts.

Biology is a rich source of inspiration in designing digital artifacts capable of autonomous, cooperative and distributed behaviors. Particularly, conceptual links can be established between (1) communication networks and (2) colonies of bacteria that communicate using chemical molecules. The goal of this paper is to propose a computational multiagent model of an interspecies bacterial communication system, termed quorum sensing, and analyze its self-sustainability and its self-maintaining ability to cooperatively form artificial wireless networks. Specifically, we propose a bottom-up agent-based approach combined with Ordinary Differential Equations, which abstract the intracellular dynamics, such as a proposed metabolism model that serves as a basis underlying self-sustainable networks. Results show that artificial bacterial cells have regeneration abilities in the light of random cell death and selected area for cell death, and a metabolism allowing them to exploit their own produced energy to cooperate at the population level to exhibit near-optimal self-organizing light-producing behaviors. The resulting artificial networks display several beneficial properties and could be used for the emergence of resistant wireless network topologies without the use of overhead messages. Povzetek: Analizirano je komuniciranje med bakterijami, na osnovi katerih so razvite agentne metode za bolj odporna brezžična omrežja.