A New Compensation Method of Dynamic Lever-arm Effect Error for Hypersonic Vehicles

For the Inertial Navigation System (INS) in hypersonic flight, when centroid of Measurement Unit (IMU) does not coincide with that vehicle, a lever-arm effect error will be generated, which further expand dynamic complex environment. In order to improve navigation accuracy, needs compensated. Although much research has been done on compensation effect, existing methods are almost based fixed length, can adapt changes and obtain higher accuracy environment for more perfect model is established, new method reinforcement learning (RL-DLAC) proposed. The adopts framework obtains optimal parameter estimation from continuous action space according deep deterministic policy gradient (DDPG). simulation results show proposed estimate parameters an only 0.31%, compensate accuracy.