Research on unmanned combat aerial vehicle robust maneuvering decision under incomplete target information

Abstract

This article investigates the problem of designing a novel maneuvering decision-making method for the unmanned combat aerial vehicle. The design objective is to promote the real-time ability of decision-making method and solve the problem of uncertainty caused by incomplete target information. On the basis of statistics theory, a robust maneuvering decision method with self-adaptive target intention prediction is proposed. The robustness design is embedded in the membership function of the situation parameters. The reachable set theory and adaptive adjustment mechanism of the target state weight are used in the target intention prediction to promote the real-time ability. Simulations are conducted under the condition that the enemy aircraft perform both non-maneuvering and combat maneuvering. The results verify the good properties of the decision-making method, which can extend the survival time of the unmanned combat aerial vehicle when the enemy aircraft attacks, and short the taking position and attack time of the unmanned combat aerial vehicle when the enemy aircraft evades.

Maneuver Decision-Making of Deep Learning for UCAV Thorough Azimuth Angles

“…The maneuver libraries of both sides are equal. The decisionmaking method of the enemy fighter is identical to the method in [12], which can be summarized as selecting the maneuver with the maximum situation function value in the next stage at each decision-making time-step.…”

“…However, ADP limited aircraft within the horizontal plane, and only three maneuvers were used. Wang et al [12] proposed a robust maneuvering decision method. They improved the membership function of situation evaluation during the decision process on the basis of the MIN-MAX decision method to make the situation function have a certain insensitivity to changes in the air combat situation.…”

“…The reason these overloads are set to a maximum is that maximum overloads ensure maneuverability. Finally, one on one air combat under different conditions is simulated with enemy fighters using the decision-making model in [12].…”

Effectiveness of Autonomous Decision Making for Unmanned Combat Aerial Vehicles in Dogfight Engagements

“…In [7], it was shown that it is possible to guide a UCAV in close-range combat using the virtual pursuit point, effectively replacing a list of standard maneuvers (as in [2]) with a single guidance law, thus allowing real-time simulation for simplified UCAV flight dynamics. Unlike in [7], the work in [8] did not use a guidance law but employed the basic maneuver library of [2], albeit extending the number of elemental maneuvers from seven to eleven to account for increased maneuvering capabilities of UCAVs when compared to manned aircraft.…”

“…However, the game associated with DF engagements is not simple so that the corresponding game tree is large and thus it is computationally expensive to evaluate all possible states [10]. As pioneered in [2], and followed in [8] among others, it is often necessary to obtain quickly an approximate solution of the DF game rather than bear the prohibitive cost of finding the exact solution.…”