Search

The problem of fault propagation which exists in the deeply integrated GNSS (Global Navigation Satellite System)/INS (Inertial Navigation System) system makes it difficult to identify faults. Once a fault occurs, system performance will be degraded due to the inability to identify and isolate the fault accurately. After analyzing the causes of fault propagation and the difficulty of fault identification, maintaining correct navigation solution is found to be the key to prevent fault propagation from occurring. In order to solve the problem, a novel robust algorithm based on convolutional neural network (CNN) is proposed. The optimal expansion factor of the robust algorithm is obtained adaptively by utilizing CNN, thus the adverse effect of fault on navigation solution can be reduced as much as possible. At last, the fault identification ability is verified by two types of experiments: artificial fault injection and outdoor occlusion. Experiment results show that the proposed robust algorithm which can successfully suppress the fault propagation is an effective solution. The accuracy of fault identification is increased by more than 20% compared with that before improvement, and the robustness of deep GNSS/INS integration is also improved.

Considering the radio-based indoor positioning system pertaining to signal degradation due to the environmental factors, and rising popularity of IP (Internet Protocol) cameras in cities, a novel fusion of inertial measurement units (IMUs) with external IP cameras to determine the positions of moving users in indoor environments is presented. This approach uses a fine-tuned Faster R-CNN (Region Convolutional Neural Network) to detect users in images captured by cameras, and acquires visual measurements including ranges and angles of users with respect to the cameras based on the proposed monocular vision relatively measuring (MVRM) method. The results are determined by integrating the positions predicted by each user’s inertial measurement unit (IMU) and visual measurements using an EKF (Extended Kalman Filter). The results experimentally show that the ranging accuracy is affected by both the detected bounding box’s by Faster R-CNN height errors and diverse measuring distances, however, the heading accuracy is solely interfered with bounding box’s horizontal biases. The indoor obstacles including stationary obstacles and a pedestrian in our tests more significantly decrease the accuracy of ranging than that of heading, and the effect of a pedestrian on the heading errors is greater than stationary obstacles on that. We implemented a positioning test for a single user and an external camera in five indoor scenarios to evaluate the performance. The robust fused IMU/MVRM solution significantly decreases the positioning errors and shows better performance in dense multipath scenarios compared with the pure MVRM solution and ultra-wideband (UWB) solution.