The primary objective of this study is to incorporate the deep reinforcement learning (DRL) technique in conflict detection and resolution (CD&R) control strategies to generate an optimised trajectory for air traffic controllers as reference, in order to improve efficiency and reduce the amount of heading angle change. A DRL environment which can be applied to CD&R agent training is developed. The agent receives the current state of multiple aircrafts in a sector and generates an action to change the heading angle of an aircraft to avoid conflict. A K ‐Control Actor‐Critic algorithm is proposed to limit the number of control times and a two‐dimensional continuous action selection policy is utilised. The simulation results show the feasibility of DRL applied in CD&R and there is an obvious advantage in computational efficiency.


    Access

    Download


    Export, share and cite



    Title :

    Deep reinforcement learning based conflict detection and resolution in air traffic control


    Contributors:
    Wang, Zhuang (author) / Li, Hui (author) / Wang, Junfeng (author) / Shen, Feng (author)

    Published in:

    Publication date :

    2019-06-01


    Size :

    7 pages




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English




    Deep reinforcement learning based conflict detection and resolution in air traffic control

    Wang, Zhuang / Li, Hui / Wang, Junfeng et al. | IET | 2019

    Free access

    Deep Reinforcement Learning for Air Traffic Conflict Resolution Under Traffic Uncertainties

    Mukherjee, Anurag / Guleria, Yash / Alam, Sameer | IEEE | 2022


    Conflict resolution strategy based on deep reinforcement learning for air traffic management

    Sui, Dong / Ma, Chenyu / Dong, Jintao | BASE | 2023

    Free access