In Wi-Fi fingerprint positioning, what we should most care about is the distance relationship between the user and the reference points (RP). However, most of the existing weighted k-nearest neighbor (WKNN) algorithms use the Euclidean distance of received signal strengths (RSS) as distance measure for fingerprint matching, and the RSS Euclidean distance is not consistent with the position distance. To address this issue, this paper analyzes the relationship between RSS similarity and position distance, propose a novel WKNN based on signal similarity and spatial position. Firstly, we obtain the weighted Euclidean distance (WED) by balancing the size between the RSS difference and the signal propagation distance difference according to the attenuation law of the spatial signal. Then, we obtain the approximate position distance (APD) by making full use of the position distances and WEDs between RPs. Finally, the nearest RPs can be selected more accurately based on the APDs between the user and different RPs, and the position of user can be estimated by the proposed WKNN based on the APD (APD-WKNN) algorithm. In order to fully evaluate the proposed algorithm, we use three fingerprint databases for comparison experiments with eight fingerprint positioning algorithms. The results show that the proposed algorithm can significantly improve the positioning accuracy of WKNN algorithm.

The unmanned logistics and distribution urgently require a large number of unmanned ground vehicles(UGVs) under the influence of the potential spread of the Coronavirus Disease 2019 (COVID-19). The path planning of UGV relies excessively on SLAM map, and has no self-optimization and learning ability for the space containing a large number of unknown obstacles. In this paper, a new dynamic parameter-A* (DP-A*) algorithm is proposed, which is based on the A* algorithm and enables the UGV to continuously optimize the path while performing the same task repeatedly. First, the original evaluation functions of the A* algorithm are modified by Q-Learning to memory the coordinates of unknown obstacle. Then, Q-table is adopted as an auxiliary guidance for recording the characteristics of environmental changes and generating heuristic factor to overcome the shortcoming of the A* algorithm. At last, the DP-A* algorithm can realize path planning in the instantaneous changing environment, record the actual situation of obstacles encountered, and gradually optimize the path in the task that needs multiple explorations. By several simulations with different characteristics, it is shown that our algorithm outperforms Q-learning, Sarsa and A* according to the evaluation criteria such as convergence speed, memory systems consume, Optimization ability of path planning and dynamic learning ability.

Environmental noise affects people’s lives and poses challenges for urban sound classification. Traditional algorithms such as Mel frequency cepstral coefficients (MFCCs) struggle due to audio signal complexity. This study applied an attention mechanism to a deep residual network (ResNet) deep learning network to overcome the structural impact of urban noise on audio signals and improve classification accuracy. We propose a three-feature fusion ResNet + attention method (Net50_SE) to maximize information representation in environmental sound signals. This method uses residual structured convolutional neural networks (CNNs) for feature extraction in sound classification tasks. Additionally, an attention module is added to suppress environmental noise impact and focus on different feature map channels. The experimental results demonstrate the effectiveness of our method, achieving 93.2% accuracy compared with 82.87% with CNN and 84.77% with long short-term memory (LSTM). Our model provides higher accuracy and confidence in urban sound classification.

Global Satellite Navigation System (GNSS) can’t provide normal location service in the indoor environment because the signal can be blocked by buildings. The pseudolites system can supplement GNSS, especially in the indoor environments. A new indoor array pseudolites system is introduced, its multi-channel transmitter has an identical clock source. The high-precision Doppler positioning method based on Z-fixed Known Point Initialization (Z-KPI) is developed without ambiguity resolution. Some static and dynamic tests are conducted to evaluate the positioning accuracy of this new method. In the static testing, the average Doppler measurement error is 1×10-5 m/s, which lays the foundation of the high precision velocity measurement, and the average positioning error is 0.02 m in X axis, 0.004 m in Y axis, and the average velocity error is 3.28×10-5 m/s in X axis, 1.94×10-5 m/s in Y axis. In the dynamic test, the maximum positioning error is 0.39 m in X axis, 0.34 m in Y axis. Finally, the reason for adopting the Z-fixed KPI algorithm is explained by the horizontal dilution of precision (HDOP), meanwhile, the influence of the known initialization point error on indoor positioning accuracy is analyzed, when a deviation from -1.5 m to 0.9 m is added to the Z-axis of the KPI, the maximum positioning error is 0.311 m in X axis, 0.08 m in Y axis; when the horizontal deviation tolerance of the KPI is set from -0.5 m to 0.5 m, the maximum horizontal positioning error is less than 0.5 m.

A Global Satellite Navigation System (GNSS) cannot provide normal location services in an indoor environment because the signals are blocked by buildings. The Beidou satellite navigation system (BDS)/GPS indoor array pseudolite system is proposed to overcome the problems of indoor positioning with conventional pseudolite, such as time synchronization, ambiguity resolution and base stations. At the same time, an algorithm for Doppler differential positioning is proposed to improve the indoor positioning accuracy and the positioning coverage of the system, which uses the Doppler difference equation and Known Point Initialization (KPI) to determinate the velocity and position of the receiver. Experiments were conducted to verify the proposed system under different conditions; the average positioning error of the Doppler differential positioning algorithm was 7.86 mm in the kinematic test and 2.9 mm in the static test. The results show that BDS/GPS indoor array pseudolite system has the potential to make indoor positioning achieve sub-centimeter precision. Finally, the positioning error of the proposed algorithm is also analyzed, and the data tests show that the dilution of precision (DOP) and cycle- slips have a significant impact on the indoor positioning accuracy; a cycle-slip of a half-wavelength can cause positioning errors of tens of millimeters. Therefore, the Doppler-aided cycle-slip detection method (DACS) is proposed to detect cycle-slips of one cycle or greater than one, and the carrier phase double difference cycle-slip detection method (CPDD) is used to detect cycle slips of a half-wavelength.

Since the signals of the global navigation satellite system (GNSS) are blocked by buildings, accurate positioning cannot be achieved in an indoor environment. Pseudolite can simulate similar outdoor satellite signals and can be used as a stable and reliable positioning signal source in indoor environments. Therefore, it has been proposed as a good substitute and has become a research hotspot in the field of indoor positioning. There are still some problems in the pseudolite positioning field, such as: Integer ambiguity of carrier phase, initial position determination, and low signal coverage. To avoid the limitation of these factors, an indoor positioning system based on fingerprint database matching of homologous array pseudolite is proposed in this paper, which can achieve higher positioning accuracy. The realization of this positioning system mainly includes the offline phase and the online phase. In the offline phase, the carrier phase data in the indoor environment is first collected, and a fingerprint database is established. Then a variational auto-encoding (VAE) network with location information is used to learn the probability distribution characteristics of the carrier phase difference of pseudolite in the latent space to realize feature clustering. Finally, the deep neural network is constructed by using the hidden features learned to further study the mapping relationship between different carrier phases of pseudolite and different indoor locations. In the online phase, the trained model and real-time carrier phases of pseudolite are used to predict the location of the positioning terminal. In this paper, by a large number of experiments, the performance of the pseudolite positioning system is evaluated under dynamic and static conditions. The effectiveness of the algorithm is evaluated by the comparison experiments, the experimental results show that the average positioning accuracy of the positioning system in a real indoor scene is 0.39 m, and the 95% positioning error is less than 0.85 m, which outperforms the traditional fingerprint positioning algorithms.