TY - GEN
T1 - Mission Planning for Active GEO Debris Removal with Orbital Refueling via QL-ACO
AU - Guo, Zheng
AU - Wang, Haibo
AU - Li, Chuanjiang
AU - Ran, Guangtao
N1 - Publisher Copyright:
© 2026 IEEE.
PY - 2026
Y1 - 2026
N2 - The increasing amount of space debris severely threatens the safety of orbital operations, making highly efficient mission planning for active debris removal (ADR) critically important, especially in the geostationary orbit (GEO). To solve the GEO debris removal mission planning problem, a Q-learning-enhanced ant colony optimization (QL-ACO) algorithm is proposed. Firstly, a mathematical model for the space debris removal mission planning is established, and the specific cleanup procedures and orbital maneuver strategies are proposed. Then, to enhance the solving capability of the ant colony algorithm for the ADR mission planning problem, an initial pheromone distribution mechanism based on Q-learning exploration is presented. Finally, a simulation scenario for GEO debris removal is established. The results demonstrate that the proposed method effectively enhances the search efficiency and stability of the mission planning.
AB - The increasing amount of space debris severely threatens the safety of orbital operations, making highly efficient mission planning for active debris removal (ADR) critically important, especially in the geostationary orbit (GEO). To solve the GEO debris removal mission planning problem, a Q-learning-enhanced ant colony optimization (QL-ACO) algorithm is proposed. Firstly, a mathematical model for the space debris removal mission planning is established, and the specific cleanup procedures and orbital maneuver strategies are proposed. Then, to enhance the solving capability of the ant colony algorithm for the ADR mission planning problem, an initial pheromone distribution mechanism based on Q-learning exploration is presented. Finally, a simulation scenario for GEO debris removal is established. The results demonstrate that the proposed method effectively enhances the search efficiency and stability of the mission planning.
KW - Ant Colony Optimization
KW - Geostationary Earth Orbit
KW - Q-Learning
KW - fuel station
KW - mission planning
KW - space debris removal
UR - https://www.scopus.com/pages/publications/105044985270
U2 - 10.1109/CSIS-IAC70275.2026.11585108
DO - 10.1109/CSIS-IAC70275.2026.11585108
M3 - 会议稿件
AN - SCOPUS:105044985270
T3 - 2026 International Annual Conference on Complex Systems and Intelligent Science, CSIS-IAC 2026
SP - 108
EP - 113
BT - 2026 International Annual Conference on Complex Systems and Intelligent Science, CSIS-IAC 2026
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2026 International Annual Conference on Complex Systems and Intelligent Science, CSIS-IAC 2026
Y2 - 15 May 2026 through 17 May 2026
ER -