A.bstract-The goal of this paper is to consider, formulate, and solve prediction problems encount... more A.bstract-The goal of this paper is to consider, formulate, and solve prediction problems encountered in tactical air combat. The problem involves prediction and identification of continuous-trajectory air combat maneuvers where only partial/incomplete information is given. This problem is solved using a qualitative representation of the maneuvers and their implementation as a neural network. We have broken our central dynamical problem down into several smaller subproblems ("eigencm-ves"), which describe the states of a continuous-trajectory dynamic system. We find tiust the resulting sequences of vectors uniquely express the time evolution of interacting dynamic objects. This method has been used to describe the forms of relationships between accelerations and velocities (not the values themselves.) All possible modes of a system can be identified while offering a complete parametrization of all possible tactical maneuvers. Additional inforraation can be used to establish which of the several alternative behaviors will actually take place. These sequences serve as the symbolic input to the artificial neural network we have provided. We found that due to high correlation of input data, a single hidden layer could not satisfactorily distinguish (with at least 55-85% accuracy) simple one-on-one maneuvers, such as the Turn-In, from more complex two-on-one maneuvers; for this reason, two hidden layers were incorporated. For each layer, many different architectures and learning rules were tested; the network described here gives the best results (55-95% accuracy for partial information). Thus, we found that the neural network implementation provided a high-speed, fault-tolerant, and robust computational cell for the identification of tactical maneuvers and suggestions for a best countermaneuver. We note that, for the sake of completeness, we include considerable background material about neural networks also. 1. INTRODUCTION Picture an autonomous missile with built-in logic to identify and predict the motion of a designated airborne target. Or, alternatively, imagine a combat pilot engaged in tactical maneuvers against one or two enemy aircraft, who has a decision-aiding display which offers advantageous offensive and/or defensive countermaneuvers. We have implemented a multi-layer artificial neu-ral network (ANN), designed to identify countermaneuvers for several well-known and relevant tactical air combat maneuvers (TACM). These include the Turning-In, the Lead Turn, and the Flat/Rolling Scissors maneuvers, all one-on-one; two-on-one maneuvers include the Bracket and the Hook-and-Drag. The graphic depiction of all these maneuvers is displayed in Figure 1. A graphic representation of the Cunningham-Toon dogfight (10 May 1972) is also reprinted in Figure 2. Our approach provides an innovative methodology for TACM identification/prediction as well as the suggestion of countermaneuvers through in-loop utilization of ANNs, when faced with partial or incomplete information. The TACM problem had previously been tackled via veloc-ity/trajectory estimation, Kalman filtering, and various composite measures for threat/lethality. This module has the ability to 1) help an autonomous missile home in on a designated target aircraft engaged in tactical maneuvers, as well as 2) serve as an on-board decision-aiding device for the pilot, increasing his "situational awareness."
A.bstract-The goal of this paper is to consider, formulate, and solve prediction problems encount... more A.bstract-The goal of this paper is to consider, formulate, and solve prediction problems encountered in tactical air combat. The problem involves prediction and identification of continuous-trajectory air combat maneuvers where only partial/incomplete information is given. This problem is solved using a qualitative representation of the maneuvers and their implementation as a neural network. We have broken our central dynamical problem down into several smaller subproblems ("eigencm-ves"), which describe the states of a continuous-trajectory dynamic system. We find tiust the resulting sequences of vectors uniquely express the time evolution of interacting dynamic objects. This method has been used to describe the forms of relationships between accelerations and velocities (not the values themselves.) All possible modes of a system can be identified while offering a complete parametrization of all possible tactical maneuvers. Additional inforraation can be used to establish which of the several alternative behaviors will actually take place. These sequences serve as the symbolic input to the artificial neural network we have provided. We found that due to high correlation of input data, a single hidden layer could not satisfactorily distinguish (with at least 55-85% accuracy) simple one-on-one maneuvers, such as the Turn-In, from more complex two-on-one maneuvers; for this reason, two hidden layers were incorporated. For each layer, many different architectures and learning rules were tested; the network described here gives the best results (55-95% accuracy for partial information). Thus, we found that the neural network implementation provided a high-speed, fault-tolerant, and robust computational cell for the identification of tactical maneuvers and suggestions for a best countermaneuver. We note that, for the sake of completeness, we include considerable background material about neural networks also. 1. INTRODUCTION Picture an autonomous missile with built-in logic to identify and predict the motion of a designated airborne target. Or, alternatively, imagine a combat pilot engaged in tactical maneuvers against one or two enemy aircraft, who has a decision-aiding display which offers advantageous offensive and/or defensive countermaneuvers. We have implemented a multi-layer artificial neu-ral network (ANN), designed to identify countermaneuvers for several well-known and relevant tactical air combat maneuvers (TACM). These include the Turning-In, the Lead Turn, and the Flat/Rolling Scissors maneuvers, all one-on-one; two-on-one maneuvers include the Bracket and the Hook-and-Drag. The graphic depiction of all these maneuvers is displayed in Figure 1. A graphic representation of the Cunningham-Toon dogfight (10 May 1972) is also reprinted in Figure 2. Our approach provides an innovative methodology for TACM identification/prediction as well as the suggestion of countermaneuvers through in-loop utilization of ANNs, when faced with partial or incomplete information. The TACM problem had previously been tackled via veloc-ity/trajectory estimation, Kalman filtering, and various composite measures for threat/lethality. This module has the ability to 1) help an autonomous missile home in on a designated target aircraft engaged in tactical maneuvers, as well as 2) serve as an on-board decision-aiding device for the pilot, increasing his "situational awareness."
Uploads
Papers by saif ullah