Brent E. Eskridge

Large-scale coordination in nature relies on the effective flow of information through a group. Understanding this flow is essential to implementing similar behaviors in artificial groups such as teams of robots, especially if communication is limited to an individual’s closest neighbors as in nature. While observational studies of the spatial posi...

Large scale coordination without dominant, consistent leadership is frequent in nature. How individuals emerge from within the group as leaders, however transitory this position may be, has become an increasingly common question asked. This question is further complicated by the fact that in many of these aggregations, differences between individua...

Optimizing group success is challenging for multi-robot systems, especially for large systems such as robot swarms where even simple individual interaction rules can lead to complex group behavior. Studies of natural systems have shown that heterogeneous groups can outperform homogeneous groups, especially when individual differences lead to role o...

Many animals form large aggregations that have no apparent consistent leader, yet are capable of highly coordinated movements. At any given time, it seems like an individual can emerge as a leader only to be replaced by another. Although individuals within a group are largely considered equal, even individuals in a homogeneous group are different....

Aggregation, whether it be in natural or artificial systems, provides numerous benefits to both the individual and the group. However, aggregation has costs and frequently involves inter-individual conflict. Although conflicts in natural systems is understood to be at times beneficial, as well as detrimental, conflict in artificial systems, such as...

In natural systems, many animals organize into groups without a designated leader and still perform complex collective behaviors. Although individuals in the group may be considered equal, all the individuals differ in the traits each of them possess. Of particular interest is the idea of an individual's personality as it often plays a role in dete...

It is commonly observed that aggregation in nature provides significant benefits to the group members. However, to reach a consensus individual preferences are frequently lost. Conflict is generally avoided because of the negative influence it could have on the success of collective movements. However, it could be used to balance consensus costs wi...

Adapting to a changing and uncertain environment is vital for the long-term success of individuals, whether they are biological or artificial. While learning can be powerful in the adaptation process, a lack of understanding exists in the factors that promote or inhibit its evolution. Nurturing is widely thought to be a contributing factor, if not...

Nurturing behaviors comprise a fundamental class of actions that can occur between individuals. They are vital components of the behavioral repertoires of numerous biological organisms and are objects of study in numerous disciplines. In this call to the community, we consider what nurturing means for biological and artificial systems, how robot-to...

In many real-world tasks, the ability to use a group of autonomous agents provides significant benefits over a single agent. However, these benefits come at the cost of greater complexity, particularly in the areas of cooperation and coordination. While many approaches address this problem, of particular interest is the use of leaders that emerge t...

In many real-world tasks, the ability to use a group of autonomous agents provides significant benefits over a single agent. However, these benefits come at the cost of greater complexity, particularly in the areas of cooperation and coordination. While many approaches address this problem, of particular interest is the use of leaders that emerge t...

The choice of training data used in evolution can have a significant impact on the generalized performance of the evolved solutions. Historically, if the training set was not representative of the problem's overall state space, the evolved solutions could not practically be applied to the overall problem. However, generative systems and indirect en...

We propose an extended version of adaptive fuzzy behavior hierarchies, termed Multiple Composite Levels (MCL), that allows for the proper modulation of composite behaviors over multiple levels of a behavior hierarchy, and demonstrate its effectiveness for a hybrid learning/reactive control system. Controllers using adaptive fuzzy behavior hierarchi...

A method for identifying values for a genetic algorithm's probability of crossover, mutation rate, and selection pressure that promote the evolution of better results in fewer generations has recently been proposed. This approach, termed the Triple Parameter Hypothesis, uses schema theory to derive these values. However, in initial experimental tes...

The most significant result of these experiments is that, in the problem domains used in this chapter, the abstraction of an agent's action space provided more tangible benefits in the development of agent controllers than abstraction of an agent's state space. In a direct comparison, controllers that used significant action abstraction and no stat...

We propose that abstracting the actions of a behavior coordination mechanism promotes the faster development and higher fitness of an effective controller for complex, composite tasks. Various techniques are well suited for the development of controllers for individual simple tasks. However, as individual tasks are combined into complex, composite...

In evolutionary computation, experimental results are commonly analyzed using an algorithmic performance metric called best-so-far. While best-so-far can be a useful metric, its use is particularly susceptible to three pitfalls: a failure to establish a baseline for comparison, a failure to perform significance testing, and an insufficient sample s...

Previous research has used behavior hierarchies to address the problem of coordinating large numbers of behaviors. However, behavior hierarchies scale poorly since they require the state information of low-level behaviors. Abstracting this state information into priorities has recently been introduced to resolve this problem. In this work, we evalu...

The combination of fuzzy control and behavior hierarchies allows for the construction of more complex behavior-based robot control agents than does either technique alone. However, current implementations are limited in their complexity since high-level behaviors still use low-level sensor information. We propose a technique for abstracting this lo...

In problem domains such as robotic control, where the evaluation of an individual significantly dominates the rest of the evolutionary process with respect to time, the viability of an evolutionary approach can be called into question. In an effort to minimise the number of evaluations by maximising the learning that takes place during an evaluatio...

For some problem domains, the evaluation of individuals is significantly more expensive than the other steps in the evolutionary process. Minimizing these evaluations is vital if we want to make genetic programming a viable strategy. In order to minimize the required evaluations, we need to maximize the amount learned from each evaluation. To accom...

For problems where the evaluation of an individual is the dominant factor in the total computation time of the evolutionary process, minimizing the number of evaluations becomes critical. This paper introduces a new crossover operator for genetic programming, memetic crossover, that reduces the number of evaluations required to find an ideal soluti...

The calculation of the primordial hydrogen and helium abundances in the big-bang cosmology is presented in an oversimplified model accessible to university physics students who have had no physics beyond an elementary modern physics course.

Multi-agent systems offer capabilities that single agent systems cannot. Chief among these capabilities are robustness, scalability, modularity, and the ability to distribute the agents throughout their environment. Along with these capabilities, however, comes the challenge of coordination the agents so they are able to achieve their goals effecti...

In problem domains where the evaluation of the individual signifi-cantly dominates the rest of the evolutionary process with respect to time, such as robotic control, the viability of an evolutionary approach can be called into question. In an effort to minimize the total num-ber of evaluations by maximizing the amount of learning that takes place...