A Robust Visual-Aided Inertial Navigation Algorithm for Pedestrians

Real-time and robust state estimation for pedestrians is a challenging problem under the satellite denial environment. The zero-velocity-aided foot-mounted inertial navigation system, with the shortcomings of unobservable heading, error accumulation, and poorly adaptable parameters, is a conventional method to estimate the pose relative to a known origin. Visual and inertial fusion is a popular technology for state estimation over the past decades, but it cannot make full use of the movement characteristics of pedestrians. In this paper, we propose a novel visual-aided inertial navigation algorithm for pedestrians, which improves the robustness in the dynamic environment and for multi-motion pedestrians. The algorithm proposed combines the zero-velocity-aided INS with visual odometry to obtain more accurate pose estimation in various environments. And then, the parameters of INS have adjusted adaptively via taking errors between fusion estimation and INS outputs as observers in the factor graphs. We evaluate the performance of our system with real-world experiments. Results are compared with other algorithms to show that the absolute trajectory accuracy in the algorithm proposed has been greatly improved, especially in the dynamic scene and multi-motions trials.

Advance prediction method for rock mass stability of tunnel boring based on deep neural network of time series

Geological layers excavated using tunnel boring machines are buried deeply and sampled difficultly, and the geological behavior exhibits high diversity and complexity. Excavating in uncertain geology conditions bears the risks of excessive damage to the equipment and facing geologic hazards. Many scholars have used various signals to predict the advance geology conditions, but accurate prediction of these conditions in real-time and without effecting operations has not been realized yet. In this article, based on a large amount of corresponding data, an advance prediction model of the rock mass category (RMC) is formulated. First, the problem is divided into two parts, which are modeled separately to reduce the complexity of design and training. Then, the two models are combined in a pre-trained model, which is retrained to as the final prediction model to avoid the problem of error accumulation. The final model can predict the advance RMC in real-time and without affecting operations. The accuracy of the prediction model reaches 99% at an advance time of 60 min. The advance RMC can be used to guide the selection of support modes and control parameters without additional detection equipment and excavation down-time.

A Novel Self-Positioning Based on Feature Map Creation and Laser Location Method for RBPF-SLAM

Aiming at the high computational complexity of the traditional Rao-Blackwellized Particle Filtering (RBPF) method for simultaneous localization and Mapping (SLAM), an optimization method of RBPF-SLAM system is proposed, which is based on lidar and least square line segment feature extraction as well as raster, reliability mapping continuity. Validation test results show that less storage in constructing a map with this method is occupied, and the computational complexity is significantly reduced. The effect of noise data on feature data extraction results is effectively avoided. It also solves the problem of error accumulation caused by noninteger grid size movement of unmanned vehicle in time update stage based on Markov positioning scheme. The improved RBPF-SLAM method can enable the unmanned vehicle to construct raster map in real time, and the efficiency and accuracy of map construction are significantly improved.

Research on Fusion Predictive Control Method of Size and Roundness in Online Grinding

In order to solve the problem that the error evaluation delay and the size and roundness of workpiece can not meet the processing requirements at the same time in online measurement. First this paper proposes an online fusion control method for the size and roundness error of workpiece, which can not only improve the processing efficiency, but also improve the consistency of workpiece quality. Then, the Long Short-Term Memory(LSTM) is used to predict the workpiece information of online measurement, and the error is calibrated according to the predicted value. The LSTM is used to predict the workpiece information in real time, and the process parameters are adjusted in time when the prediction value is out of the theoretical boundary to avoid error accumulation. Finallyr the online grinding measurement experiment based on the LSTM is designed and carried out, and the relationship between the dimension of input tensor and the prediction accuracy is analyzed through the experimental results. The results show that the LSTM can accurately predict the grinding size sequence and roundness sequence, and has good universality. The small batch machining is carried out according to the experimental results. Statistical analysis shows that the grinding accuracy is significantly improved by using the fusion prediction and calibration method.

Mine MIMO Depth Receiver: An Intelligent Receiving Model Based on Densely Connected Convolutional Networks

Multiple-input multiple-output (MIMO) systems suffer from high BER in the mining environment. In this paper, the mine MIMO depth receiver model is proposed. The model uses densely connected convolutional networks for feature extraction and constructs multiple binary classifiers to recover the original information. Compared with conventional MIMO receivers, the model has no error accumulation caused by processes such as decoding and demodulation. The experimental results show that the model has better performance than conventional decoding methods under different modulation codes and variations in the number of transmitting terminals. Furthermore, we demonstrate that the model can still achieve effective decoding and recover the original information with some data loss at the receiver.

Feature of statistical data processing by computer mathematics systems tools

Processes of error accumulation were analysed during arithmetic operations on statistical data obtained in the course of research on oscillations in cross-field electron vacuum devices. The features of statistical data processing obtained as a result of experimental research were investigated using the most widespread computer mathematical packages. The features of statistical data processing were investigated by processing a sample of 80 values of the magnetron generation frequency using popular mathematical packages Excel, Maple, Matlab and MathCad and comparing the results obtained with calculations using theoretical formulas. Calculation results for all packages give the same results for mean, variance and standard deviation. As for the coefficients of skewness and kurtosis, most of the results do not coincide. Analysis of the calculation results showed that the difference in the obtained values ​​of the skewness and kurtosis is due to different definitions of these indicators in mathematical packages Excel, Maple, Matlab and MathCad. It is proved that in Microsoft Excel we cannot correctly construct a histogram without using additional operations, because the interval limits are calculated with errors. It leads to an incorrect determination of the number of elements into these intervals. To build correctly a histogram using the Excel package, it is necessary to calculate the interval limits in advance. It is concluded that before using computer mathematical packages for processing statistical data, it is necessary to analyze first by what formulas the required parameters are calculated and take appropriate measures to eliminate possible discrepancies with the parameters calculated using theoretical formulas.