A Deep Reinforcement Learning Approach for UAS Conflict-Avoidance Maneuvers with Flight-Path Recapture

This paper presents a deep reinforcement learning approach for generating conflict-avoidance maneuvers that aim to maintain well-clear separation from an intruder aircraft while enabling subsequent recapture of the planned flight path. The proposed method is applicable to automated Detect-and-Avoid functions in lost-link scenarios as well as in autonomous flight. Pairwise encounters are used to train the neural-network policy. The performance of the trained policy is compared with that of a conventional heuristic path-stretch algorithm. Results show that the two approaches achieve comparable performance, with only minor differences in separation and efficiency metrics. In addition, the trained neural networks identify an emergent maneuver strategy that is not available to the heuristic method unless explicitly encoded.