Autonomous operation of civil aviation is a new mode of future Air Traffic Management (ATM), where the onboard pilot is the central decision-maker supported by precise situation awareness, reliable decision-making support, and an advanced ATM system. The promotion of autonomous operations in civil aviation aims to overcome the limitations of airspace capacity and efficiency, reduce the workload of air traffic controllers, and enhance the merit of the flight. This paper systematically defines the concept and characteristics of the autonomous operation mode. Based on the current development of China's civil aviation industry and global trends in ATM reforms, it outlines the key technologies needed to implement autonomous operations, such as situational awareness, decision-making support, and safety interval maintenance. Furthermore, we propose the necessary infrastructure for both onboard and ground-based systems, and a development plan for promoting autonomous operation, considering the existing ATM system. Finally, to meet the future high-density and high-volume aviation transport demands, comprehensive and systematic reforms in ATM systems of civil aviation is imperative. With continuous innovations in air traffic operation systems, advanced intelligent algorithms for decision-making support, and communication capabilities, autonomous operations are expected to become a platform for deploying and integrating multiple advanced technologies, ultimately leading to a significant breakthrough in air traffic capabilities in China and around the world.

Unmanned Aerial Vehicle (UAV) stands as a burgeoning electric transportation carrier, holding substantial promise for the logistics sector. A reinforcement learning framework Centralized - S Proximal Policy Optimization (C-SPPO) based on centralized decision process and considering policy entropy (S) is proposed. The proposed framework aims to plan the best scheduling scheme with the objective of minimizing both the timeout of order requests and the flight impact of UAVs that may lead to conflicts. In this framework, the intents of matching act are generated through the observations of UAV agents, and the ultimate conflict-free matching results are output under the guidance of a centralized decision maker. Concurrently, a pre-activation operation is introduced to further enhance the cooperation among UAV agents. Simulation experiments based on real-world data from New York City are conducted. The results indicate that the proposed C-SPPO outperforms the baseline algorithms in the Average Delay Time (ADT), the Maximum Delay Time (MDT), the Order Delay Rate (ODR), the Average Flight Distance (AFD), and the Flight Impact Ratio (FIR). Furthermore, the framework demonstrates scalability to scenarios of different sizes without requiring additional training.

Adverse weather during aircraft operation generates more complex scenarios for tactical trajectory planning, which requires superior real-time performance and conflict-free reliability of solving methods. Multi-aircraft real-time 4D trajectory planning under adverse weather is an essential problem in Air Traffic Control (ATC) and it is challenging for the existing methods to be applied effectively. A framework of Double Deep Q-value Network under the Critic guidance with heuristic Pairing (DDQNC-P) is proposed to solve this problem. An Agent for two aircraft synergetic trajectory planning is trained by the Deep Reinforcement Learning (DRL) model of DDQNC, which completes two aircraft 4D trajectory planning tasks preliminarily under dynamic weather conditions. Then a heuristic pairing algorithm is designed to convert the multi-aircraft synergetic trajectory planning into multi-time pairwise synergetic trajectory planning, making the multi-aircraft trajectory planning problem processable for the trained Agent. This framework compresses the input dimensions of the DRL model while improving its generalization ability significantly. Substantial simulations with various aircraft numbers, weather conditions, and airspace structures were conducted for performance verification and comparison. The success rate of conflict-free trajectory resolution reached 96.56% with an average calculation time of 0.41 s for 350 4D trajectory points per aircraft, finally confirming its applicability to make real-time decision-making support for controllers in real-world ATC systems.