GNSS拒止时基于并行CNN-BiLSTM回归和残差补偿的UAV导航误差校正方法

全球导航卫星系统(GNSS)拒止时,GNSS/惯性导航系统(INS)组合导航系统的性能严重下降,导致无人机集群导航误差快速发散.目前,利用神经网络预测位置与速度代替GNSS导航信息可校正无人机INS误差,但该方法仍存在定位误差较高且在轨迹突变时预测精度急剧下降的问题.因此,提出了一种基于卷积-双向长短时记忆网络联合残差补偿的位置与速度预测方法,用于提高位置与速度预测精度.首先,针对GNSS拒止后GNSS/INS组合导航系统定位误差较高的问题,提出卷积神经网络(CNN)与双向长短时记忆网络(BiLSTM)的融合模型,该模型可建立惯性测量单元(IMU)动力学测量数据与GNSS导航信息之间的关系,实现较准确的位置和速度预测.其次,针对轨迹突变时预测效果急剧下降的问题,提出并行CNNBiLSTM回归架构,在预测位置与速度的同时,挖掘IMU动力学测量数据、预测值与预测残差之间的关系,预测并补偿预测残差,增强模型在轨迹突变时的预测精度.仿真结果表明,所提模型在预测准确性、有效性和稳定性方面都优于CNN-LSTM、LSTM网络模型.

大学生职业规划教学与实践体系创新

大学生职业规划教学与实践是一个复杂而系统性的工作,尤其是针对不同专业类别、不同性格的学生来说很难做到面面俱全。文章首先探讨各高校大学生(特别是民办高校大学生)职业规划教学与实践中目标确立及实施过程所存在种种问题,进而通过专业理论和技术解析当前大学生职业性格、目标和职业生涯忧虑等方面,最后,改造和优化传统大学生职业规划教学与实践模式,合理构建全新的双向大学生职业规划教学与实践体系。

Bidirectional transfer of quantum information for unknown photons via cross-Kerr nonlinearity and photon-number-resolving measurement

We propose an arbitrary controlled-unitary （CU） gate and a bidirectional transfer scheme of quantum information （BTQI） for unknown photons. The proposed CU gate utilizes quantum non-demolition photon-number-resolving measure- ment based on the weak cross-Kerr nonlinearities （XKNLs） and two quantum bus beams; the proposed CU gate consists of consecutive operations of a controlled-path gate and a gathering-path gate. It is almost deterministic and is feasible with current technology when a strong amplitude of the coherent state and weak XKNLs are employed. Compared with the existing optical multi-qubit or controlled gates, which utilize XKNLs and homodyne detectors, the proposed CU gate can increase experimental realization feasibility and enhance robustness against decoherence. According to the CU gate, we present a BTQI scheme in which the two unknown states of photons between two parties （Alice and Bob） are mutually swapped by transferring only a single photon. Consequently, by using the proposed CU gate, it is possible to experimentally implement the BTQI scheme with a certain probability of success.