B. Ravichandran

Classifier systems in combat : two-sided learning of maneuvers for advanced fighter aircraft

This paper reports the continuing results of a project where a genetics-based machine learning system acquires rules for novel fighter combat maneuvers through simulation. In this project, a genetics-based machine learning system was implemented to generate high angle-of-attack air combat tactics for advanced fighter aircraft. This system, which was based on a learning classifier system approach, employed a digital simulation model of one-versus-one air combat, and a genetic algorithm, to develop effective tactics for the X-31 experimental fighter aircraft. Previous efforts with this system showed that the resulting maneuvers allowed the X-31 to successfully exploit its post-stall capabilities against a conventional fighter opponent. This demonstrated the ability of the genetic learning system to discover novel tactics in a dynamic air combat environment. The results gained favorable evaluation from fighter aircraft test pilots. However, these pilots noted that the static strategy employed by the X-31s opponent was a limitation. In response to these comments, this paper reports new results with two-sided learning, where both aircraft in a one-versus-one combat scenario use genetics-based machine learning to adapt their strategies. The experiments successfully demonstrate both aircraft developing objectively interesting strategies. However, the results also point out the complexity of evaluating results from mutually adaptive players, due to the red queen effect. These complexities, and future directions of the project, are discussed in the papers conclusions.

The Fighter Aircraft LCS: A Case of Different LCS Goals and Techniques

A system employed by the authors to acquire novel fighter aircraft manoeuvres from combat simulation is more akin to the traditional LCS model than to more recent systems. Given the difficulties often experienced in LCS research on simple problems, one must ask how a relatively primitive LCS has had consistent success in the complex domain of fighter aircraft manoeuvring. This paper presents the fighter aircraft LCS, in greater detail than in previous publications. Positive results from the system are discussed. The paper then focuses on the primary reasons the fighter aircraft LCS has avoided the difficulties of the traditional LCS. The authors believe the systems success has three primary origins: differences in credit assignment, differences in action encoding, and (possibly most importantly) a difference in system goals. In the fighter aircraft system, the goal has been simply the discovery of innovative, novel tactics, rather than online control. The paper concludes by discussing the most salient features of the fighter aircraft learning system, and how those features may be profitably combined with other LCS developments.

XCS for robust automatic target recognition

A primary strength of the XCS approach is its ability to create maximally accurate general rules. In automatic target recognition (ATR) there is a need for robust performance beyond so-called standard operating conditions (SOCs, those conditions for which training data is available) to extended operating conditions (EOCs, conditions of known targets that cannot be foreseen and trained for). EOCs include things like vehicle-specific variations, environmental effects (mud, etc.), unanticipated viewing angles, and articulation of components of the target (hatches, turrets, etc.). This paper presents experiments where XCS addresses structural generalization over global and local features normally used in ATR classification. In many SOCs, these features are adequate for target recognition. Our goal with XCS is to form generalized rules that utilize these features for effective ATR in EOCs. Results show that XCS is effective in this generalization task. Conclusions and future directions for research are discussed.

The Fighter Aircraft LCS: A Real-World, Machine Innovation Application

This chapter reports the authors’ ongoing experience with a system for discovering novel fighter combat maneuvers, using a genetics-based machine learning process, and combat simulation. Despite the difficulties often experienced with LCSs, this complex, real-world application has proved very successful. In effect, the adaptive system is taking the place of a test pilot, in discovering complex maneuvers from experience. The goal of this work is distinct from that of many other studies, in that innovation, and discovery of novelty, is, in itself valuable. This makes the details of aims and techniques somewhat distinct from other LCSs.

The monitoring, detection, interpretation and response paradigm for the security of battlespace networks

Modern battlespace networks are too complex to be defended using only the traditional shielding techniques of cryptography, authentication and static firewalls. Implicit in much of the current research devoted to applying data based techniques to network security is the paradigm of monitoring, detection, interpretation and response (MDIR). Under MDIR, shielding technologies are still present, but the designer accepts the possibility of external attacks, insiders misuse, and vulnerable application software, and constantly monitors the network for detecting abnormalities. Previous work by the authors on a research testbed has shown that the COTS network management systems (NMSs) combined with anomaly detection and other statistical techniques can be successfully used for data monitoring, and for automatically detecting correlations among attacker events and target events during distributed denial of service attacks introduced by hacker toolkits. This paper examines the MDIR paradigm, and reviews these experiments within its background.

Multisensor-multitarget sensor management with target preference

Multisensor-multitarget sensor management is viewed as a problem in nonlinear control theory. This paper applies newly developed theories for sensor management based on a Bayesian control-theoretic foundation. Finite-Set-Statistics (FISST) and the Bayes recursive filter for the entire multisensor-multitarget system are used with information-theoretic objective functions in the development of the sensor management algorithms. The theoretical analysis indicate that some of these objective functions lead to potentially tractable sensor management algorithms when used in conjunction with MHC (multi-hypothesis correlator)-like algorithms. We show examples of such algorithms, and present an evaluation of their performance against multisensor-multitarget scenarios. This sensor management formulation also allows for the incorporation of target preference, and experiments demonstrating the performance of sensor management with target preference will be presented.

Developing a robust integrated learning system for the modern battlefield

This paper outlines our long-term vision for integrating robust machine learning as an approach to the modern battlefield. We will develop the architecture for an Integrated Learning System (ILS) that will enable representation tools to maximize the utility of data collected by distributed sensors. This project will suggest a system for data capture, processing, retrieval and analysis and focus on the development of semantic interoperability for ontology alignment and the ability to learn from experiences, so that performance improves as it accumulates knowledge resulting in the ability to learn new object/event classes and improve its classification accuracy. To illustrate the notion of robust learning from distinct representations of sensor data from a common source, we offer an application where a LCS addresses automatic target recognition (ATR) in extended operating conditions (EOCs). The LCS-based robust ATR system performed well, resulting in powerful ATR rules that generalize over multiple feature types, with accuracy over 99% and robustness over 80%. To illustrate the notion of ontology enabling learning, we outline preliminary experiments with a network of LCSs integrating ATR via a simple vehicle ontology.

SAR ATR using genetics based machine learning

Addressing the challenge of robust ATR, this paper describes the development and demonstration of Machine Learning for Robust ATR. The primary innovation of this work is the development of an automated way of developing heuristic inference rules that can draw on multiple models and multiple feature types to make more robust ATR decisions. The key realization is that this meta learning problem is one of structural learning; that can be conducted independently of parameter learning associated with each model and feature based technique, and more effectively draw on the strengths of all such techniques, and even information from unforeseen techniques. This is accomplished by using robust, genetics-based machine learning for the ill conditioned combinatorial problem of structural rule learning, while using statistical and mathematical techniques for parameter learning. This paper describes a learning classifier system approach (with evolutionary computation for structural learning) for robust ATR and points to a promising solution to the structural learning problem, across multiple feature types (which we will refer to as the meta-learning problem), for ATR with EOCs. This system was tested on MSTAR Public Release SAR data using nominal and extended operation conditions. These results were also compared against two baseline classifiers, a PCA based distance classifier and a MSE classifier. The systems were evaluated for accuracy (via training set classification) and robustness (via testing set classification). In both cases, the LCS based robust ATR system performed very well with accuracy over 99% and robustness over 80%.

Discovering Novel Fighter Combat Maneuvers

Publisher Summary New technologies for fighter aircrafts are being developed continuously. Often, aircraft engineers know a great deal about the aerodynamic performance of new fighter aircraft that exploit new technologies, even before a physical prototype is constructed or flown. Such aerodynamic knowledge is available from design principles, computer simulation, and wind tunnel experiments. However, knowing the aerodynamic impact of a new technology is distinct from knowing how the plane will perform in combat. The chapter mentions how evaluating the impact of new technologies on actual combat can provide vital feedback to designers, customers, and future pilots of the aircraft in question. However, due to the complex mapping discussed above, this feedback typically comes at a high price. While designers can use fundamental design principles to shape their designs, often good maneuvers lie in odd parts of the aircraft performance space, and in the creativity and innovation of the pilot. Therefore, the typical process would be to develop a new aircraft, construct a one-off prototype, and allow test pilots to experiment with the prototype, developing maneuvers in simulated combat. Clearly, the expense of such a prototype is substantial. Moreover, simulated combat with highly trained test pilots has a substantial price tag. Therefore, it would be desirable to discover the maneuver utility of new technologies, without a physical prototype.Publisher Summary New technologies for fighter aircrafts are being developed continuously. Often, aircraft engineers know a great deal about the aerodynamic performance of new fighter aircraft that exploit new technologies, even before a physical prototype is constructed or flown. Such aerodynamic knowledge is available from design principles, computer simulation, and wind tunnel experiments. However, knowing the aerodynamic impact of a new technology is distinct from knowing how the plane will perform in combat. The chapter mentions how evaluating the impact of new technologies on actual combat can provide vital feedback to designers, customers, and future pilots of the aircraft in question. However, due to the complex mapping discussed above, this feedback typically comes at a high price. While designers can use fundamental design principles to shape their designs, often good maneuvers lie in odd parts of the aircraft performance space, and in the creativity and innovation of the pilot. Therefore, the typical process would be to develop a new aircraft, construct a one-off prototype, and allow test pilots to experiment with the prototype, developing maneuvers in simulated combat. Clearly, the expense of such a prototype is substantial. Moreover, simulated combat with highly trained test pilots has a substantial price tag. Therefore, it would be desirable to discover the maneuver utility of new technologies, without a physical prototype.