A spacecraft attitude maneuvering path planning method based on PIO-improved reinforcement learning

Abstract

<p indent="0mm">Aiming at the problem of spacecraft attitude maneuver planning under multiple mandatory pointing constraints and prohibited pointing constraints, based on pigeon-inspired optimization (PIO), we proposed an improved policy gradient reinforcement learning (RL) algorithm (PIOPGRL). First, we establish an angle-based attitude constraint model, and then, we establish the reward function of RL based on the model. Then, the fitness function is used to replace the policy evaluation function, so PIOPGRL is integrated with RL. The PIOPGRL algorithm uses the PIO algorithm to solve the policy gradient, significantly reduces the amount of calculation and accelerating the convergence speed. The simulation results show that the spacecraft attitude maneuvering path planning method based on PIO-improved RL (PIOPGRL) has better planning results and lower cost of maneuver than the classical PGRL algorithm, which can solve the problem of spacecraft attitude maneuver planning under multiple pointing constraints perfectly.