Human motion tracking could be viewed as a multi-target tracking problem towards numerous body joints. Inertial-measurement-unit-based human motion tracking technique stands out and has been widely used in body are network applications. However, it has been facing the tough problem of accumulative errors and drift. In this paper, we propose a multi-sensor hybrid method to solve this problem. Firstly, an inertial-measurement-unit and time-of-arrival fusion-based method is proposed to compensate the drift and accumulative errors caused by inertial sensors. Secondly, Cramér–Rao lower bound is derived in detail with consideration of both spatial and temporal related factors. Simulation results show that the proposed method in this paper has both spatial and temporal advantages, compared with traditional sole inertial or time-of-arrival-based tracking methods. Furthermore, proposed method is verified in 3D practical application scenarios. Compared with state-of-the-art algorithms, proposed fusion method shows better consistency and higher tracking accuracy, especially when moving direction changes. The proposed fusion method and comprehensive fundamental limits analysis conducted in this paper can provide a theoretical basis for further system design and algorithm analysis. Without the requirements of external anchors, the proposed method has good stability and high tracking accuracy, thus it is more suitable for wearable motion tracking applications.

Underground metal target detection technology has been widely applied in industrial production, resource exploration, and engineering construction, etc. However, due to the influence of non-negligible noise and high dimensionality in collected data, achieving efficient and accurate underground target classification remains a grand challenge for further applications of underground metal target detection on portable devices with limited computing capability and energy supply. This study aimed to seek out robust and efficient data-based strategies to classify the underground metal targets of different shapes and materials based on electromagnetic induction detection. We investigated thirty-three classification strategies based on eleven dimensionality reduction methods, namely, the least absolute shrinkage and selection operator (LASSO), genetic algorithm-support vector machine (GA-SVM), Pearson correlation coefficient (PCC), mutual information (MI), maximal relevance minimal redundancy Pearson correlation (mRMRP), maximal relevance minimal redundancy mutual information (mRMRMI), statistical features (SF), principal component analysis (PCA), kernel principal component analysis (KPCA), locally linear embedding (LLE), and stacked denoising autoencoder (SDAE), and three machine learning models, namely, artificial neural network (ANN), linear support vector machine (L-SVM), and Gaussian Naïve Bayes (GNB). Several parameters, including classification accuracy, the number of features after dimensionality, the feature type importance, and the time consumption were considered to evaluate the data-based classification strategies. Among the classification strategies investigated and considering the above evaluation parameters, the artificial neural network (ANN) classifier assisted with the kernel principal component analysis (KPCA) feature extraction method yielded the best performance in the material-based classification (accuracy:0.99) and the shape-based classification (accuracy:0.99). The locally linear embedding (LLE) improved the robustness of machine learning classifiers and efficiency of the artificial neural network in the material-based classification (improvement of average accuracy:0.17, reduction of classification time cost:14%) and shape-based classification (improvement of average accuracy:0.16, reduction of classification time cost:22%). Our comparative investigation provides a robust and efficient data-based strategy for underground metal target classification, which is significant for applications of underground metal target detection on portable devices with limited computing capability and energy supply. The cross-combination strategy of dimensionality reduction methods and machine learning models provides a way to find the optimal machine learning model for underground target detection.

In complex and unknown environments, achieving precise localization and real-time mapping stands as a critical requirement for agent navigation and scene comprehension. However, conventional localization methods, which rely on single sensors such as Inertial Measurement Units (IMUs) or Ultra-wideband (UWB) sensors, often face challenges in maintaining high precision within these intricate settings. Consequently, the task of achieving accurate self-localization and constructing topological maps becomes increasingly daunting. To tackle this challenge, we introduce a collaborative localization and mapping approach that harnesses data from both IMU and UWB sensors. We employ factor graphs as the representation model, treating observations, states, and constraints as factors within the graph. The IMU provides vital attitude and acceleration information, while the UWB sensor contributes valuable distance observations. Through the maximization of posterior probability, we estimate the agent’s position and create the map. Our comprehensive evaluations conducted in physical environments conclusively demonstrate the effectiveness of our method in achieving accurate localization and mapping.

Ultra-Wideband (UWB) technology has great potential for the cooperation and navigation among near ground mobile robots in GPS-denied environments. In this paper, an efficient two-segment UWB radio channel model is proposed with considering the multi-path condition in very near-ground environments and different surface roughness. We conducted field measurements to collect channel information, with both transmitter and receiver antennas placed at different heights above the ground: 0cm-20cm. Signal frequency was chosen at 4.3GHz with bandwidth of 1GHz. Three ground coverings were tested in common scenarios: brick, grass and robber fields. The proposed model has enhanced accuracy achieved by careful assessment of dominant propagation mechanisms in each segment, such as diffraction loss due to obstruction of the first Fresnel zone and higher-order waves produced by ground roughness. It is realized that antenna height and distance are the most influential geometric parameters to affect the path loss model. Once the antenna height is known, there exists a breakpoint distance in UWB propagation, which separates two segmentation using the different path-loss mechanism. Different surface types can cause different signal attenuation. Monte Carlo simulations are used to investigate the effects of antenna height, distance, ground surface type on mobile robots swarm communication to find out the antenna height is also a dominant factor on connectivity and the average number of neighbors. Within a certain range, the higher the antenna height and the closer the communication distance, the better the communication performance will usually be. Cramér-Rao lower bound(CRLB) of path loss estimator based on the proposed model is derived to show the relationship between CRLB with height and distance.

In modern navigation and positioning systems, accurate location information is crucial for ensuring system performance and user experience. Particularly, in scenarios involving the use of multiple agents such as robots and drones for rescue operations in unknown complex environments, accurate localization is fundamental for subsequent actions. However, traditional filtering-based localization algorithms may exhibit suboptimal performance and are sensitive to initial estimates and system noise. To address these issues, this paper proposes a multi-agent collaborative localization algorithm based on reinforcement learning compensation filtering to tackle localization problems in complex environments and improve the robustness and accuracy. Specifically, this paper introduces a value decomposition-based reinforcement learning network for filtering compensation to reduce overall localization error and address the credit allocation problem in multi-agent reinforcement learning. The main contributions of this paper are as follows: Firstly, a local localization estimation method based on reinforcement learning compensation Extended Kalman Filter (EKF) is proposed, which further corrects the results of the EKF algorithm and eliminates initial estimation errors. Secondly, a global collaborative localization estimation algorithm (MARL_CF) based on credit allocation in multi-agent reinforcement learning is proposed, which maximizes the reduction of overall localization error through information sharing and global optimization. Finally, the effectiveness of the proposed algorithms is validated through both numerical simulation and physical experiments. The results demonstrate that the proposed MARL_CF significantly improve the accuracy and robustness of localization in complex environments.

Cooperative localization is essential for many Internet of Things (IoT)-related applications in harsh environments. Generally, the inertial navigation system is self-contained and adopted as the basis of a cooperative tracking system, but it still faces the problem of accumulated errors and cannot provide long-term, high-precision positioning. The particle filter (PF) is widely used to fuse multiple information to inhibit accumulative errors. However, particle degradation and impoverishment remain unsolved. This article proposed an IMU/time-of-arrival (TOA) fusion-based tracking method, namely, uncertainty-constrained belief propagation (UCBP). We address particle degradation and impoverishment by introducing uncertainty-constrained optimization into belief propagation (BP). An uncertainty-constrained resampling (UCR) method is applied to quantify the uncertainty in cooperative systems. Hierarchical resampling is realized to solve the particle impoverishment issue. Meanwhile, particle degradation is resolved through constrained resampling while ensuring the diversity of particles. Furthermore, we illustrated the factor graph (FG) structure of UCBP to mitigate the accumulation of errors through message fusion over the graph. Compared with the state-of-the-art methods, our proposed UCBP algorithm has better precision and robustness without introducing much time overhead.