TY - GEN
T1 - Critic-Only Learning-Based Optimal Visual Servoing Control for Quadrotors with Safe Constraints
AU - Yi, Xinning
AU - Liu, Hao
AU - Xue, Shibei
N1 - Publisher Copyright:
© 2025 IEEE.
PY - 2025
Y1 - 2025
N2 - This paper investigates the constrained optimal visual servoing control problem for quadrotors tracking moving ground targets without direct position measurements. To ensure compliance with safe constraints, the quadrotor visual servoing model is transformed using a barrier function, and formulated as a time-varying optimal control problem for both the image feature and attitude systems. The proposed optimal control law is derived using an integral learning-based approach, and implemented through a modified critic-only neural network with time-related basis functions. Simulation results validate the effectiveness of the proposed control approach.
AB - This paper investigates the constrained optimal visual servoing control problem for quadrotors tracking moving ground targets without direct position measurements. To ensure compliance with safe constraints, the quadrotor visual servoing model is transformed using a barrier function, and formulated as a time-varying optimal control problem for both the image feature and attitude systems. The proposed optimal control law is derived using an integral learning-based approach, and implemented through a modified critic-only neural network with time-related basis functions. Simulation results validate the effectiveness of the proposed control approach.
UR - https://www.scopus.com/pages/publications/105031896122
U2 - 10.1109/CDC57313.2025.11312790
DO - 10.1109/CDC57313.2025.11312790
M3 - 会议稿件
AN - SCOPUS:105031896122
T3 - Proceedings of the IEEE Conference on Decision and Control
SP - 7777
EP - 7782
BT - 2025 IEEE 64th Conference on Decision and Control, CDC 2025
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 64th IEEE Conference on Decision and Control, CDC 2025
Y2 - 9 December 2025 through 12 December 2025
ER -