Abstract: Purpose Most existing path planning methods for Carrier-based aircraft overlook the practical spatial constraints during their transfer process and struggle to adapt to the highly dynamic deck environment. To address these limitations, this paper proposes a dynamic path planning algorithm for Carrier-based aircraft that comprehensively considers positional and motion constraints as well as target heading angles. Method Initially, the geometric modeling of the Carrier-based aircraft's shape is conducted using the polygon method. Based on parameters such as the transfer speed and heading angle of the Carrier-based aircraft, a kinematics model is then proposed. Subsequently, the path planning problem for the Carrier-based aircraft is modeled as a Markov Decision Process (MDP). The action space and state space are determined according to the aircraft's motion characteristics. A reward function is designed, taking into account various factors such as position, orientation, safety, and efficiency. A Carrier-based aircraft path planning algorithm based on deep reinforcement learning is then proposed. Finally, simulation experiments are conducted to validate the effectiveness of the proposed algorithm. Results The results demonstrate that the proposed algorithm reduces the scheduling time by an average of 9.2% and the target heading angle error by an average of 98.7% compared to traditional algorithms. Conclusion The proposed method effectively enhances the transfer efficiency of Carrier-based aircraft, providing valuable insights for decision-making in the coordination and movement of Carrier-based aircraft on aircraft carrier decks.