Genetic programming provides a useful paradigm for developing multiagent systems in the domains where human programming alone is not sufficient to take into account all the details of possible situations. However, existing GP methods attempt to evolve collective behavior immediately from primitive actions. More realistic tasks require several emergent behaviors and a proper coordination of thes...

Genetic programming provides a useful paradigm for developing multiagent systems in the domains where human programming alone is not sufficient to take into account all the details of possible situations. However, existing GP methods attempt to evolve collective behavior immediately from primitive actions. More realistic tasks require several emergent behaviors and a proper coordination of thes...

We propose here a formal approach to study collective behaviors intended as coherent sequences of spatial configurations, adopted by agents through various corresponding structures over time. Multiple, simultaneous structures over time and their sequences are called Meta-Structures and establish sequences of spatial configurations considered as emergent on the basis of coherent criteria chosen ...

We present a supervised learning from demonstration system capable of training stateful and recurrent collective behaviors for multiple agents or robots. A model space of this kind is often high-dimensional and consequently may require a large number of samples to learn. Furthermore, the inverse problem posed by emergent macrophenomena among multiple agents presents major challenges to supervis...

Group-living animals often exhibit complex collective behaviors that emerge through the non-linear dynamics of social interactions between individuals. Previous studies have shown that it is possible to influence the collective decision-making process of groups of insects by integrating them with autonomous multi-robot systems. However, generating robot controller models for this particular tas...

Despite its importance, human collective intelligence remains enigmatic. We know what features are predictive of collective intelligence in human groups, but we do not understand the specific mechanisms that lead to the emergence of this distributed information processing ability. In contrast, there is a well-developed literature of experiments that have exposed the mechanisms of collective int...

Collective interaction occurs in many natural and artificial matters in broad scales. In a biological system, collective spatial organization of live individuals in a colony is important for their viability determination. Interactive motions between a single individual and an agglomerate are critical for whole procedure of the collective behaviors, but few has been clarified for these intermedi...

Swarm Intelligence (SI) is the property of a system whereby the collective behaviors of (unsophisticated) entities interacting locally with their environment cause coherent functional global patterns to emerge. SI provides a basis with which it is possible to explore collective (or distributed) problem solving without centralized control or the provision of a global model. To tackle the formati...

A number of theoretical models have been proposed in recent years to explain pacing strategies observed in individual competitive endurance events. These have typically related to the internal regulatory processes that inform the making of decisions relating to muscular work rate. Despite a substantial body of research which has investigated the influence of collective group dynamics on individ...

This paper analyzes the collective behaviors of swarm robots that play role in the aggregation scenario. Honeybee aggregation is an inspired behavior of young honeybees which tend to aggregate around an optimal zone. This aggregation is implemented based on variation of parameters values. In the second phase, two modifications on original honeybee aggregation namely dynamic velocity and compara...