Ultra-wideband technology has good anti-interference capabilities and development prospects in indoor positioning. Since ultra-wideband will be affected by random errors in indoor positioning, to exploit the advantages of the Kalman filter (KF) and the long short-term memory (LSTM) network, this paper proposes a long short-term memory neural network algorithm fused with the Kalman filter (KF–LSTM) to improve UWB positioning. First, the ultra-wideband data is processed through KF to weaken the noise in the data, and then the data is fed into the LSTM network for training, and the capability of the LSTM network to process time series features is employed to obtain more accurate label positions. Finally, simulation and measurement results show that the KF–LSTM algorithm achieves 71.31%, 37.28%, and 49.31% higher average positioning accuracy than the back propagation (BP) network, (back propagation network fused with the Kalman filter (KF-BP), and LSTM network algorithms, respectively, and the KF–LSTM algorithm performs more stably. Meanwhile, the more noise the data contains, the more obvious the stability contrast between the four algorithms.

Aiming at the problems of Non-Line-of-Sight (NLOS) observation errors and inaccurate kinematic model in ultra-wideband (UWB) systems, this paper proposed an improved robust adaptive cubature Kalman filter (IRACKF). Robust and adaptive filtering can weaken the influence of observed outliers and kinematic model errors on filtering, respectively. However, their application conditions are different, and improper use may reduce positioning accuracy. Therefore, this paper designed a sliding window recognition scheme based on polynomial fitting, which can process the observation data in real-time to identify error types. Simulation and experimental results indicate that compared to the robust CKF, adaptive CKF, and robust adaptive CKF, the IRACKF algorithm reduces the position error by 38.0%, 45.1%, and 25.3%, respectively. The proposed IRACKF algorithm significantly improves the positioning accuracy and stability of the UWB system.

The Ultra-Wideband (UWB) indoor positioning method is widely used in areas where no satellite signals are available. However, during the measurement process of UWB, the collected data contain random errors. To alleviate the effect of random errors on positioning accuracy, an improved adaptive sparrow search algorithm (IASSA) based on the sparrow search algorithm (SSA) is proposed in this paper by introducing three strategies, namely, the two-step weighted least squares algorithm, adaptive adjustment of search boundary, and producer–scrounger quantity adaptive adjustment. The simulation and field test results indicate that the IASSA algorithm achieves significantly higher localization accuracy than previous methods. Meanwhile, the IASSA algorithm requires fewer iterations, which overcomes the problem of the long computation time of the swarm intelligence optimization algorithm. Therefore, the IASSA algorithm has advantages in indoor positioning accuracy and robustness performance.

When robots perform localization in indoor low-light environments, factors such as weak and uneven lighting can degrade image quality. This degradation results in a reduced number of feature extractions by the visual odometry front end and may even cause tracking loss, thereby impacting the algorithm’s positioning accuracy. To enhance the localization accuracy of mobile robots in indoor low-light environments, this paper proposes a visual inertial odometry method (L-MSCKF) based on the multi-state constraint Kalman filter. Addressing the challenges of low-light conditions, we integrated Inertial Measurement Unit (IMU) data with stereo vision odometry. The algorithm includes an image enhancement module and a gyroscope zero-bias correction mechanism to facilitate feature matching in stereo vision odometry. We conducted tests on the EuRoC dataset and compared our method with other similar algorithms, thereby validating the effectiveness and accuracy of L-MSCKF.

Ultra-Wideband (UWB) technology is widely used in indoor positioning due to its high accuracy and strong resistance to interference. However, practical UWB positioning systems still encounter challenges such as random errors and asymmetric base station topology, which significantly affect positioning accuracy. To address these issues, this paper proposes an Adaptive Vector Projection Iteration algorithm based on the Least Squares method (LS-AVPI). Firstly, the Sparrow Search Algorithm (SSA) is employed to identify optimal parameters, with the fitness function based on an error suppression model established through vector projection angles and iterative concepts. The optimal parameters obtained from the SSA are then used to train a Convolutional Neural Network (CNN) for accurate prediction of unknown data. Finally, the predicted parameters are input into the error suppression model to solve for the final position. Experimental results demonstrate that the LS-AVPI algorithm significantly outperforms the constrained weighted, the iterative, the standard, and the two-step weighted least squares methods, with accuracy improvements of 57.3%, 62.7%, 65.7%, and 54.8%, respectively. This study not only effectively improves UWB positioning accuracy but also provides a new technical approach for achieving high-precision positioning in complex environments, offering significant theoretical and practical value.

Amidst the backdrop of the profound synergy between navigation and visual perception, there is an urgent demand for accurate real-time vehicle positioning in urban environments. However, the existing global navigation satellite system (GNSS) algorithms based on Kalman filters fall short of precision. In response, we introduce an elastic filtering algorithm with visual perception for vehicle GNSS navigation and positioning. Firstly, the visual perception system captures real-time environmental data around the vehicle. It utilizes the interframe differential optical flow method and vehicle state switching characteristics to assess the current driving status. Secondly, we design an elastic filtering model specifically for various vehicle states. This model enhances the precision of Kalman filter-based GNSS navigation. In urban driving, vehicles often experience frequent stationary parking. To address this, we incorporate a zero-speed constraint to further refine vehicle location data when the vehicle is stationary. This constraint matches the data with the appropriate elastic filtering model. Ultimately, we conduct simulation and real-world vehicle navigation experiments to confirm the validity and rationality of our proposed algorithm. Compared with the conventional algorithm and the existing interactive multi-model algorithm, the proposed algorithm significantly improves the navigation and positioning accuracy of vehicle GNSS in urban environments. Compared to the commonly used constant acceleration (CA) and Constant Velocity (CV) models, there has been a significant improvement in positioning accuracy. Furthermore, when benchmarked against the more advanced interactive multi-model (IMM) model, the method proposed in this paper has enhanced the positioning accuracy enhancements in three dimensions: 21.8%, 20.9%, and 31.3%, respectively.