This PDF file contains the front matter associated with SPIE Proceedings Volume 6563, including the Title Page, Copyright information, Table of Contents, Introduction (if any), and the Conference Committee listing.

"Understanding" the behavior of a biological system typically means formulating a sensible model, postulating a feedback law (incorporating biologically plausible sensory measurements), and experimentally verifying that the model and feedback law are consistent with nature. This approach is illustrated well in the work of K. Ghose, T. K. Horiuchi, P. S. Krishnaprasad, and C. F. Moss (and colleagues) on insect pursuit by echolocating bats. In work of F. Zhang, E. W. Justh, and P. S. Krishnaprasad, similar modeling principles and feedback laws have also been shown to play an important role in biologically-inspired formation-control and obstacle-avoidance laws. Building on this earlier work, we seek to identify a bio-inspired framework for cooperative swarming, in which the apparently complicated trajectories of individuals are explained by feedback laws which take a relatively simple form. The objectives of such swarming (e.g., for teams of unmanned vehicles) could include rendezvous, target capture (or destruction), and cooperative sensing.

This work investigates the efforts behind defining a classification system for multi-agent search and tracking problems, specifically those based on relatively small numbers of agents. The pack behavior search and tracking classification (PBSTC) we define as mappings to animal pack behaviors that regularly perform activities similar to search and tracking problems, categorizing small multi-agent problems based on these activities. From this, we use evolutionary computation to evolve goal priorities for a team of cooperating agents. Our goal priorities are trained to generate candidate parameter solutions for a search and tracking problem in an emitter/sensor scenario. We identify and isolate several classifiers from the evolved solutions and how they reflect on the agent control systems's ability in the simulation to solve a task subset of the search and tracking problem. We also isolate the types of goal vector parameters that contribute to these classified behaviors, and categorize the limitations from those parameters in these scenarios.

The role of an airborne electronic attack (AEA) system-of-systems (SoS) is to increase survivability of friendly aircraft by jamming hostile air defense radars. AEA systems are scarce, high-demand assets and have limited resources with which to engage a large number of radars. Given the limited resources, it is a significant challenge to plan their employment to achieve the desired results. Plans require specifying locations of jammers, as well as the mix of wide- and narrow-band jamming assignments delivered against particular radars. Further, the environment is uncertain as to the locations and emissions behaviors of radars. Therefore, we require plans that are not only capable, but also robust to the variability of the environment. In this paper, we use a multi-objective genetic algorithm to develop capable and robust AEA SoS mission plans. The algorithm seeks to determine the Pareto-front of three objectives - maximize the operational objectives achieved by friendly aircraft, minimize the threat to friendly aircraft, and minimize the expenditure of AEA assets. The results show that this algorithm is able to provide planners with the quantitative information necessary to intelligently construct capable and robust mission plans for an AEA SoS.

There is considerable interest in developing teams of autonomous, unmanned vehicles that can function in hostile environments without endangering human lives. However, heterogeneous teams, teams of units with specialized roles and/or specialized capabilities, have received relatively little attention. Specialized roles and capabilities can significantly increase team effectiveness and efficiency. Unfortunately, developing effective cooperation mechanisms is much more difficult in heterogeneous teams. Units with specialized roles or capabilities require specialized software that take into account the role and capabilities of both itself and its neighbors. Evolutionary algorithms, algorithms modeled on the principles of natural selection, have a proven track record in generating successful teams for a wide variety of problem domains. Using classification problems as a prototype, we have shown that typical evolutionary algorithms either generate highly effective teams members that cooperate poorly or poorly performing individuals that cooperate well. To overcome these weaknesses we have developed a novel class of evolutionary algorithms. In this paper we apply these algorithms to the problem of controlling simulated, heterogeneous teams of "scouts" and "investigators". Our test problem requires producing a map of an area and to further investigate "areas of interest". We compare several evolutionary algorithms for their ability to generate individually effective members and high levels of cooperation.

Assignment problems are a common area of research in operational research and computer science. Military applications include military personnel assignment, combat radio frequency assignment, and weapon target assignment. In general, assignment problems can be found in a wide array of areas, from modular placement to resource scheduling. Many of these problems are very similar to one another. This paper models and compares some of the assignment problems in literature. These similar problems are then generalized into a generalized multi-objective problem, the constrained assignment problem. Using a multi-objective genetic algorithm, we solve an example of a constrained assignment problem called the airman assignment problem. Results show that good solutions along the interior portion of the Pareto front are found in earlier generations and later generations produce more exterior points.

This paper describes a novel capability for modeling known idea propagation transformations and predicting responses to new ideas from geopolitical groups. Ideas are captured using semantic words that are text based and bear cognitive definitions. We demonstrate a unique algorithm for converting these into analytical predictive equations. Using the illustrative idea of "proposing a gasoline price increase of $1 per gallon from $2" and its changing perceived impact throughout 5 demographic groups, we identify 13 cost of living Diplomatic, Information, Military, and Economic (DIME) features common across all 5 demographic groups. This enables the modeling and monitoring of Political, Military, Economic, Social, Information, and Infrastructure (PMESII) effects of each group to this idea and how their "perception" of this proposal changes. Our algorithm and results are summarized in this paper.

This paper describes a novel capability for modeling and predicting community responses to events (specifically military operations) related to demographics. Demographics in the form of words and/or numbers are used. As an example, State of Alabama annual demographic data for retail sales, auto registration, wholesale trade, shopping goods, and population were used; from which we determined a ranked estimate of the sensitivity of the demographic parameters on the cultural group response. Our algorithm and results are summarized in this paper.

In this paper, we propose a rule-based search method for multiple mobile distributed agents to cooperatively search an area for mobile target detection. The collective goals of the agents are (1) to maximize the coverage of a search area without explicit coordination among the members of the group, (2) to achieve suffcient minimum coverage of a search area in as little time as possible, and (3) to decrease the predictability of the search pattern of each agent. We assume that the search space contains multiple mobile targets and each agent is equipped with a non-gimbaled visual sensor and a range-limited radio frequency sensor. We envision the proposed search method to be applicable to cooperative mobile robots, Unmanned Aerial Vehicles (UAVs), and Unmanned Underwater Vehicles (UUVs). The search rules used by each agent characterize a decentralized search algorithm where the mobility decision of an agent at each time increment is independently made as a function of the direction of the previous motion of the agent, the known locations of other agents, the distance of the agent from the boundaries of the search area, and the agent's knowledge of the area already covered by the group. Weights and parameters of the proposed decentralized search algorithm are tuned to particular scenarios and goals using a genetic algorithm. We demonstrate the effectiveness of the proposed search method in multiple scenarios with varying numbers of agents. Furthermore, we use the results of the tuning processes for different scenarios to draw conclusions on the role each weight and parameter plays during the execution of a mission.

This paper uses a behavioral hierarchy approach to reduce the mission solution space and make the mission design easier. A UAV behavioral hierarchy is suggested, which is derived from three levels of behaviors: basic, individual and group. The individual UAV behavior is a combination of basic, lower level swarming behaviors with priorities. Mission design can be simplified by picking the right combination of individual swarming behaviors, which will emerge the needed group behaviors. Genetic Algorithm is used in both lower-level basic behavior design and mission design.

The paper discusses evolution of consciousness driven by the knowledge instinct, a fundamental mechanism of the mind which determines its higher cognitive functions. Dynamic logic mathematically describes the knowledge instinct. It overcomes past mathematical difficulties encountered in modeling intelligence and relates it to mechanisms of concepts, emotions, instincts, consciousness and unconscious. The two main aspects of the knowledge instinct are differentiation and synthesis. Differentiation is driven by dynamic logic and proceeds from vague and unconscious states to more crisp and conscious states, from less knowledge to more knowledge at each hierarchical level of the mind. Synthesis is driven by dynamic logic operating in a hierarchical organization of the mind; it strives to achieve unity and meaning of knowledge: every concept finds its deeper and more general meaning at a higher level. These mechanisms are in complex relationship of symbiosis and opposition, which leads to complex dynamics of evolution of consciousness and cultures. Modeling this dynamics in a population leads to predictions for the evolution of consciousness, and cultures. Cultural predictive models can be compared to experimental data and used for improvement of human conditions. We discuss existing evidence and future research directions.

In this paper, we discuss the mathematics, electronic hardware, and network software aspects of the HYper-Distributed Robotic Autonomy (HYDRA) bio-inspired large neural network, proposed in a previous paper.

Simple genetic algorithm optimizations often utilize fixed-length chromosomes containing a predefined set of parameters to be optimized. While such algorithms have successfully created electrically small narrow-band and large wide-band military antennas, they require the antenna designer to have a fairly concrete antenna representation prior to exercising the genetic algorithm. In this research we investigate the use of genetic programming (GP) techniques to "program" the design of simple thin-wire antennas. Genetic programming techniques offer the potential to create random, multi-arm, multi-dimension antennas from variable length, tree-like chromosomes. We present a new genetic programming paradigm for creating multi-branched, thin-wire, genetic antennas and describe how GP commands are represented and decoded into physical antenna structures. We present preliminary results obtained from this algorithm showing evolutions along Pareto fronts representing antenna electrical size, VSWR, and antenna quality factor (Q).

This paper describes the application of biologically-inspired algorithms and concepts to the design of wideband antenna arrays. In particular, we address two specific design problems. The first involves the design of a constrained-feed network for a Rotman-lens beamformer. We implemented two evolutionary optimization (EO) approaches, namely a simple genetic algorithm (SGA) and a competent genetic algorithm. We conducted simulations based on experimental data, which effectively demonstrate that the competent GA outperforms the SGA (i.e., finds a better design solution) as the objective function becomes less specific and more "general." The second design problem involves the implementation of polyomino-shaped subarrays for sidelobe suppression of large, wideband planar arrays. We use a modified screen-saver code to generate random polyomino tilings. A separate code assigns array values to each element of the tiling (i.e., amplitude, phase, time delay, etc.) and computes the corresponding far-field radiation pattern. In order to conduct a statistical analysis of pattern characteristics vs. tiling geometry, we needed a way to measure the "similarity" between two arbitrary tilings to ensure that our sampling of the tiling space was somewhat uniformly distributed. We ultimately borrowed a concept from neural network theory, which we refer to as the "dot-product metric," to effectively categorize tilings based on their degree of similarity.

Military imaging systems often require the transmission of copious amounts of data in noisy or bandwidth-limited situations. High rates of lossy image compression may be achieved through the use of quantization at the expense of resulting image quality. We employ genetic algorithms (GAs) to evolve military-grade transforms capable of improving reconstruction of satellite reconnaissance images under conditions subject to high quantization error. The resulting transforms outperform existing wavelet transforms at a given compression ratio allowing transmission of data at a lower bandwidth. Because GAs are notoriously difficult to tune, the selection of appropriate variation operators is critical when designing GAs for military-grade algorithm development. We test several state-of-the-art real-coded crossover and mutation operators to develop an evolutionary system capable of producing transforms providing robust performance over a set of fifty satellite images of military interest. With appropriate operators, evolved filters consistently provide an average mean squared error (MSE) reduction greater than 17% over the original wavelet transform. By improving image quality, evolved transforms increase the amount of intelligence that may be obtained reconstructed images.

A culturally diverse group of people are now participating in military multinational coalition operations (e.g., combined air operations center, training exercises such as Red Flag at Nellis AFB, NATO AWACS), as well as in extreme environments. Human biases and routines, capabilities, and limitations strongly influence overall system performance; whether during operations or simulations using models of humans. Many missions and environments challenge human capabilities (e.g., combat stress, waiting, fatigue from long duty hours or tour of duty). This paper presents a team selection algorithm based on an evolutionary algorithm. The main difference between this and the standard EA is that a new form of objective function is used that incorporates the beliefs and uncertainties of the data. Preliminary results show that this selection algorithm will be very beneficial for very large data sets with multiple constraints and uncertainties. This algorithm will be utilized in a military unit selection tool.

We present a mathematical model of interacting neuron- like units that we call Recurrent Feedback Neuronal Networks (RFNN). Our model is closer to biological neural networks than current approaches (e.g. Layered Neural Networks, Perceptron, etc.). Classification and reasoning in RFNN are accomplished by an iterative algorithm, and learning changes only structure (weights are fixed in RFNN). Thus it emphasizes network structure over edge weights. RFNNs are more flexible and scalable than previous approaches. In particular, integration of a new node can affect the outcome of existing nodes without modifying their prior structure. RFNN can produce informative responses to partial inputs or when the networks are extended to other tasks. It also enables recognition of complex entities (e.g. images) from parts. This new model is promising for future contributions to integrated human-level intelligent applications due to its flexibility, dynamics and structural similarity to natural neuronal networks.