Modelling and Optimization of the Air Operational Manoeuvre

Proceedings of the 48h IEEE Conference on Decision and Control (CDC) held jointly with 2009 28th Chinese Control Conference, 2009

Dynamic programming has recently received significant attention as a possible technology for formulating control commands for decision makers in an extended complex enterprise that involves adversarial behavior. Enterprises of this type are typically modeled by a nonlinear discrete time dynamic system. The state is controlled by two decision makers, each with a different objective function and different hierarchy of decision making structure. To illustrate this enterprise, we derive a state space dynamic model of an extended complex military operation that involves two opposing forces engaged in a battle. The model assumes a number of fixed targets that one force is attacking and the other is defending. Due to the number of control commands, options for each force, and the steps during which the two forces could be engaged, the optimal solution for such a complicated dynamic game over all stages is computationally extremely difficult, if not impossible, to propose. As an alternative, we propose an expeditious suboptimal solution for this type of adversarial engagement. We discuss a solution approach where the decisions are decomposed hierarchically and the task allocation is separate from cooperation decisions. This decoupled solution, although suboptimal in the global sense, is useful in taking into account how fast the decisions should be in the presence of adversaries. An example scenario illustrating this military model and our solution approach is presented.

AIAA AVIATION 2022 Forum, 2022

Today, survival depends on seconds in air combats. The delay in communication of unmanned aerial vehicles with pilots in the ground station is the most important shortcoming in terms of survivability. One solution to this shortcoming is to develop autonomous operation methods for all possible types of missions that onboard computers will process the information collected by the aircraft's sensors and to take countermeasures against the threats without human input. With this regard, unmanned combat aerial vehicles (UCAVs) will take a more active role in air combat and contribute to air superiority in the future. In this study, various combat scenarios are generated and trajectory optimization solutions are obtained to perform autonomous evasive maneuvers for UCAVs against air-to-air missiles without human input. To accomplish this objective, an engagement geometry that includes details of a UCAV and a missile is introduced. This geometry is constructed by employing factors such as line-of-sight (LOS), velocity vectors, angle of attack, flight path angle, and heading angle, which expresses the relative positions of the missile and the UCAV in 3-dimensional space. The UCAV and missile are represented as point-mass models using the given geometry. Along with point-mass models, the commonly used Proportional Navigation (PN) method for missiles guidance is implemented. An energy formulation is incorporated into the model to calculate the instantaneous energy consumption of the missile. An optimization algorithm is developed so that the UCAV can automatically command the angle of attack and the bank angle to maximize the instantaneous energy consumption of the missile at every time step using the generated model. Optimal trajectories for different engagement scenarios are automatically generated by the optimization algorithm for variable initial conditions such as the missile's heading angle, altitude, and distance from the UCAV. Finally, the UCAV performed successful evasive maneuvers to evade the missile in all of its medium/long-range engagements and one of the short-range engagements which demonstrates that adaptive maneuvers suitable for real combat situations are produced for different initial condition sets.

1990

A research program investigating the use of Artificial Intelligence (AI) techniques to aid in the development of a Tactical Decision Generator (TDG) for Within Visual Range (WVR) air combat engagements is discussed. The application of AI programming and problem solving methods in the development and implementation of the Computerized Logic For Air-to-Air Warfare Simulations (CLAWS), a second generation TDG, is presented. The Knowledge-Based Systems used by CLAWS to aid in the tactical decision-making process are outlined in detail, and the results of tests to evaluate the performance of CLAWS versus a baseline TDG developed in FORTRAN to run in real-time in the Langley Differential Maneuvering Simulator (DMS), are presented. To date, these test results have shown significant performance gains with respect to the TDG baseline in one-versus-one air combat engagements, and the AI-based TDG software has proven to be much easier to modify and maintain than the baseline FORTRAN TDG programs. Alternate computing environments and programming approaches, including the use of parallel algorithms and heterogeneous computer networks are discussed, and the design and performance of a prototype concurrent TDG system are presented.

2005

Games Theory is used to model conflict scenarios where two or more players compete to achieve a predefined objective. This paper presents the development of a stochastic modeling technique to optimise the trajectory of two aircraft in an air combat situation. One aircraft will act as an evader and the other as a pursuer. The study considers pilot and aircraft performance limitations and assumes that each aircraft possesses complete knowledge of the states of the opponent. In optimisation routines, a set of the evader's potential trajectories are randomly generated and evaluated. Each trajectory is played for 100 seconds. The end result is the final distance between both players and the best trajectory is the one that gives the longest distance. This trajectory will be used in main simulation for 100 seconds of play. For the next 100 seconds, optimisation routines are called again to find a new optimised trajectory for use in the main simulation. This process is repeated until both aircraft intercept. A proof-of-concept computer program was written and is presented in this paper.

1998

Operational Research computer models must model both the relevant physical systems and the behaviour of their operators. The simulation requirements for these two components and the techniques used for developing, designing, validating and verifying them are quite different. In air combat these differences are heightened by the complexity of the physical systems and the wide variation in operator behaviour.

Guidance, Navigation and Control Conference, 1989

A research program investigating the use of Artificial Intelligence (AI) techniques to aid in the development of a Tactical Decision Generator (TDG) for Within-Visual-Range (WVR) air combat engagements is discussed. The application of AI methods for development and implementation of the TDG is presented. The history of the Adaptive Maneuvering Logic (AML) program is traced and current versions of the AML program are compared and contrasted with the TDG system. The Knowledge-Based Systems (KBS) used by the TDG to aid in the decision-making process are outlined in detail and example rules are presented. The results of tests to evaluate the performance of the TDG versus a version of AML and versus human pilots in the Langley Differential Maneuvering Simulator (DMS) are presented. To date, these results have shown significant performance gains in one-versus-one air combat engagements, and the AI-based TDG software has proven to be much easier to modify than the updated FORTRAN AML programs.

This book gives an introduction to the specifics of military flight operations. It covers the basics of aerodynamic, navigation, sensors, electronic warfare, intelligence, weopons, command and control, close air support, air interdiction, counter air, air defence, COMAO. helicopter operations and the history of airpower.

2016

Autonomous Control of UAV is a complex problem that has many parameters requiring low level robust control. In air combat there are more than one aircraft and relative geometry of both sides are also included into this complex problem. Control objective is getting to an advantageous position rather than following a constant trajectory. Long term trajectory planning is not possible since relative geometry changes instantaneous. In this paper, a solution is proposed that chooses the right movement to take advantage on the other aircraft. The solution considers the energy conversion and turn radius heuristics. Depending on the relative geometry of both sides, air combat controller decides on the movement and synthesizes the necessary control signal. An offensive and a defensive BFM scenario are designed to test the behavior of the system. The simulations demonstrated that the proposed scheme has considered the combat constraints.

This paper investigates a complex pursuit-evasion game in three dimensions with complete information applied to two aircrafts in an air combat. Both aircrafts are simulated as point masses with limitations of the flight performance. To find an optimal trajectory for the evader, populations of trajectories are randomly generated for a given time length. The optimal evader's trajectory is a trajectory that gives the best payoff. The best payoff is a trajectory that guides the evader from being intercepted, and gives the maximum separation distance at the end of the given time length. The pursuer uses a proportional navigation guidance system to guide itself to the evader. As an illustrative example, the study considers the evasion of an aircraft, which is very agile but slower, from a pursuing missile, which is faster but less agile. The aircraft maneouvres are restricted by various control and state variable inequality constraints. Several factors are studied in this paper to see their relationship to interceptability. These factors are intercept radius, turning radius and speed. For the purpose of simplifying the analysis, it is assumes both players to fly at a constant speed. This technique is able to find an optimal trajectory for the evader in order to avoid interception. The optimal trajectories exhibit several well known tactical manoeuvres such as the horizontal-S and the vertical-S, but the manoeuvres need to be performed in a timely manner for a successful evasion.

Modeling, Simulation, and Visualization of Sensory Response for Defense Applications, 1997

For a computer-generated force (CGF) system to be useful in training environments, it must be able to operate at multiple skill levels, exhibit competency at assigned missions, and comply with current doctrine. Because ofthe rapid rate cf change in Distributed Interactive Simulation (DIS) and the expanding set of performance objectives for any computergenerated force, the system must also be modifiable at reasonable cost and incorporate mechanisms for learning. Therefore, CGF applications must have adaptable decision mechanisms and behaviors and perform automated incorporation of past reasoning and experience into its decision process. The CGF must also possess multiple skill levels for classes of entities, gracefully degrade its reasoning capability in response to system stress, possess an expandable modular knowledge structure, and perform adaptive mission planning. Furthermore, correctly performing individual entity behaviors is not sufficient. Issues related to complex inter-entity behavioral interactions, such as the need to maintain formation and share information, must also be considered. The CGF must also be able to acceptably respond to unforeseen circumstances and be able to make decisions in spite ofuncertain information. Because ofthe need for increased complexity in the virtual battlespace, the CGF should exhibit complex, realistic behavior patterns within the battlespace.

IEEE Access

One of the fundamental technologies for unmanned combat aerial vehicles and combat simulators is behavior optimization, which finds a behavior that maximizes the probability of winning a battle. With the advent of military science, combat logs became available, allowing machine learning algorithms to be used for the behavior optimization. Due to implicit attributes such as the experience of an operator that are not explicitly presented in log data, existing methods for behavior optimization have limitations in performance improvement. Furthermore, specific behaviors occur with low frequency, resulting in a dataset with imbalanced and empty values. Therefore, we apply a matrix factorization (MF) method, which is one of latent factor models and known for sophisticated imputation of empty values, to the behavior optimization problem of unmanned combat aerial vehicles. A situation-behavior matrix, whose elements are ratings indicating the optimality of behaviors in situations, is defined to implement the MF based method. Experiments for performance comparison were conducted on combat logs, in which the proposed method yielded satisfactory results. INDEX TERMS Behavior optimization, unmanned vehicle, matrix factorization, reinforcement learning, situation-behavior matrix. ABBREVIATIONS AM Advantage matrix. FOV Field of view. GA Genetic algorithm. LOS Line of sight. MF Matrix factorization. nDCG Normalized discounted cumulative gain. RL Reinforcement learning. SB Situation-behavior. UV Unmanned vehicle.

1995

TAcAm-SoAR is a reactive system that uses recognition-driven problem solving to plan and generate behavior in the domain of tactical air combat simulation. Our current research efforts focus on integrating more deliberative planning and learning mechanisms into the system. This paper discusses characteristics of the domain that influence potential planning solutions, together with our approach for integrating reactive and deliberative

AVIA, 2020

Beyond Visual Range (BVR) air combat is a future trend of war tactic. In this situation, a fighter can attack the opponent before direct encounter. Its complexity arises due to the necessity to take into account the information of target’s maneuver, the specification of the missile, and the advantage of fighter position. In this paper, a simple BVR air combat system has been developed to give a fight strategy for pilot. Some important parameters are considered, such as the distance and the azimuth position of the target’s as well as the range and the energy of missile to reach the target. The information is processed to determine the fighter supremacy and the opponent’s threat factor. The result of the processing is used as an input of fuzzy logic algorithm to determine the optimal fighting strategy. The feasibility of the model and validity of the algorithm are verified by simulation under two typical situations

International Journal of Operational …, 2009

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."